{"id":2201,"date":"2026-11-17T07:40:24","date_gmt":"2026-11-17T07:40:24","guid":{"rendered":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/?p=2201"},"modified":"2026-11-17T07:40:28","modified_gmt":"2026-11-17T07:40:28","slug":"biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation","status":"publish","type":"post","link":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/","title":{"rendered":"How can deep-learning-based biomedical image segmentation support the micro-CT analysis of bone?"},"content":{"rendered":"<h2 style=\"font-size: 100%\"><strong><span class=\"TextRun SCXW230073389 BCX0\" lang=\"EN-US\" xml:lang=\"EN-US\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW230073389 BCX0\">The i<\/span><span class=\"NormalTextRun SCXW230073389 BCX0\">mportance of <\/span><span class=\"NormalTextRun SCXW230073389 BCX0\">biomedical image segmentation<\/span><\/span><\/strong><\/h2>\n\n\n<p class=\"wp-block-paragraph\">Researchers studying whole bones utilize volumetric imaging techniques such as micro-computed tomography (micro-CT) to understand the complex 3D structures underlying bone morphology. Biomedical image segmentation is often an essential part of this analysis, helping to reveal the finer details of bone composition. The process of manually segmenting thousands of micro-CT slices can, however, slow the path from imaging to biological insights. To address this challenge, Professor Andrew Lee of Midwestern University has recently developed BONe, a set of deep-learning tools that run within Thermo Scientific Amira and Avizo Software, which support bone segmentation at scale. In this workflow, Amira-Avizo Software brings model-based segmentation together with 3D visualization and 2D inspection to streamline data processing while the researcher subsequently applies their anatomical expertise to check and refine results.&nbsp;<\/p>\n\n\n\n<div class=\"wp-block-columns are-vertically-aligned-center is-layout-flex wp-container-core-columns-is-layout-8f761849 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-vertically-aligned-center is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"has-text-align-center wp-block-paragraph\">\u201cI wanted to reduce segmentation as a major workflow bottleneck while prioritizing usability, scalability, and reproducibility.\u201d&nbsp;<\/p>\n\n\n\n<p class=\"has-text-align-center wp-block-paragraph\">\u2014 Professor Andrew Lee, Midwestern University&nbsp;<\/p>\n<\/blockquote>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-vertically-aligned-center is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\n<figure class=\"wp-block-image size-medium is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"300\" height=\"300\" src=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2-300x300.jpg\" alt=\"Professor Andrew Lee, Midwestern University\" class=\"wp-image-2210\" style=\"width:199px;height:auto\" srcset=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2-300x300-1.jpg 300w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2-150x150.jpg 150w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2-768x768.jpg 768w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2-80x80.jpg 80w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2-400x400.jpg 400w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2-600x600.jpg 600w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-headshot-1024x1024-2.jpg 1024w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/figure>\n<\/div>\n<\/div>\n\n\n<h2 style=\"font-size: 100%\"><strong><span class=\"NormalTextRun SCXW82208970 BCX0\">Why does whole-<\/span><span class=\"NormalTextRun SCXW82208970 BCX0\">bone <\/span><span class=\"NormalTextRun SCXW82208970 BCX0\">segmentation become a bottleneck?<\/span><\/strong><\/h2>\n\n\n<p class=\"wp-block-paragraph\">Professor Lee\u2019s research explores how diet and exercise affect the robusticity of mouse limb bones. By analyzing whole bones rather than a single cross section, his lab can examine the intricate geometrical variations that occur along each bone. Before such biological measurements could begin, thousands of image slices needed accurate segmentation.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For example, one of their studies, highlighted in this blog, included 74 bones collected over 20 scans. Manual segmentation of such data can serve as an excellent reference, but can be time consuming, and is dependent on the expertise of the person doing the work. Automatic thresholding is a common, alternate approach that can quickly segment datasets based on image contrast, but it can miss thin trabeculae, confuse background with internal spaces, and respond inconsistently to artifacts or changes in brightness. Across many specimens, the shortcomings and challenges of these two methods can make segmentation a limiting step in the micro-CT analysis of bone.&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"450\" src=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/comparison-of-automatic-thresholding-1024x450-1.jpg\" alt=\"Comparison of automatic thresholding and a deep-learning based approach for biomedical image segmentation.\" class=\"wp-image-2205\" srcset=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/comparison-of-automatic-thresholding-1024x450-1.jpg 1024w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/comparison-of-automatic-thresholding-1024x450-1-767x337.jpg 767w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/comparison-of-automatic-thresholding-1024x450-1-300x132.jpg 300w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\"><em><strong>Comparison of automated segmentation approaches.<\/strong> A representative raw image slice (left) is segmented using both automatic thresholding (middle) and a deep-learning model (right). Yellow arrows highlight areas where the segmentation results differ, illustrating improved delineation of the target structure by the deep-learning approach.&nbsp;<\/em><\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Deep-learning-based image analysis is a comparatively new method that can readily meet the challenges posed by traditional manual segmentation and automatic thresholding. Instead of relying on one intensity cutoff, the model learns from a set of reference segmentations, using image features and surrounding spatial patterns to distinguish bone, medullary spaces, and background.&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"450\" src=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/deep-learning-model-1024x450-1.jpg\" alt=\"Deep learning model applied to biomedical image segmentation.\" class=\"wp-image-2206\" srcset=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/deep-learning-model-1024x450-1.jpg 1024w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/deep-learning-model-1024x450-1-300x132.jpg 300w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/deep-learning-model-1024x450-1-767x337.jpg 767w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\"><em><strong>Deep-learning-based image segmentation workflow.<\/strong> A representative raw scan (left) is processed by a deep-learning model (middle) to generate a segmented image (right). The resulting segmentation distinguishes the two regions of interest, shown in green and blue.<\/em><\/figcaption><\/figure>\n\n\n<h2 style=\"font-size: 100%\"><strong><span class=\"NormalTextRun SCXW204359223 BCX0\">How does <\/span><span class=\"NormalTextRun SpellingErrorV2Themed SCXW204359223 BCX0\">BONe<\/span> <span class=\"NormalTextRun SCXW204359223 BCX0\">work within Amira-Avizo Software?<\/span><\/strong><\/h2>\n<p><span data-contrast=\"auto\">The BONe deep-learning tools developed by Professor Lee support three parts of the segmentation process:<\/span><span data-ccp-props=\"{&quot;335551550&quot;:6,&quot;335551620&quot;:6}\">\u00a0<\/span><\/p>\n<ul>\n<li><b><span data-contrast=\"auto\">BONe DLFit<\/span><\/b><span data-contrast=\"auto\"> trains or fine-tunes a model<\/span><span data-ccp-props=\"{}\">\u00a0<\/span><\/li>\n<li><b><span data-contrast=\"auto\">BONe DLPred<\/span><\/b><span data-contrast=\"auto\"> applies a trained model to new scans<\/span><span data-ccp-props=\"{}\">\u00a0<\/span><\/li>\n<li><b><span data-contrast=\"auto\">BONe IOU<\/span><\/b><span data-contrast=\"auto\"> compares a predicted segmentation with a reference mask<\/span><span data-ccp-props=\"{}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">These modules are available within Amira 3D and Avizo 3D Software, as well as in standalone versions that feature a similar interface. The models can also be moved between the different software implementations.<\/span><span data-ccp-props=\"{&quot;335551550&quot;:6,&quot;335551620&quot;:6}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">BONe brings model-based segmentation into the Amira-Avizo Software workflow. Typically, a researcher will use BONe DLPred to apply a compatible pretrained model to a scan in the project (e.g., BP-2D-03a, which is trained to distinguish bone and medullary pores in micro-CT scans of mammalian bone). The resulting multiclass segmentation is returned to the project for 2D inspection, 3D visualization, and, where needed, manual refinement. If the scan differs substantially from the model\u2019s training data, the researcher can fine-tune the model with BONe DLFit and evaluate it against reference masks with BONe IoU.<\/span><span data-ccp-props=\"{&quot;335551550&quot;:6,&quot;335551620&quot;:6}\">\u00a0<\/span><\/p>\n<h2 style=\"font-size: 100%\"><strong><span class=\"NormalTextRun SCXW23008781 BCX0\">What should researchers check after <\/span><span class=\"NormalTextRun SCXW23008781 BCX0\">deep-learning-based image segmentation<\/span><span class=\"NormalTextRun SCXW23008781 BCX0\">?<\/span><\/strong><\/h2>\n\n\n<p class=\"wp-block-paragraph\">While a 3D, deep-learning-based segmentation may look convincing, it still needs to be reviewed by the researcher performing the analysis. In the example shown here, the model appropriately identified bones and medullary spaces, but the results also included small background artifacts and areas where segmentation extended from the medullary spaces into the background. These areas may need to be cleaned manually, depending on the pervasiveness of these errors.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Professor Lee recommends quality-control review for every segmentation, especially when a scan differs from the data used to train the model. Visualization and inspection tools in Amira-Avizo Software support this review as part of the same workflow as prediction.&nbsp;<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"has-text-align-center wp-block-paragraph\">\u201cBONe does not remove the need for anatomical expertise, it just redirects the expertise from tracing every slice to training, evaluating, and refining a scalable segmentation workflow.\u201d&nbsp;<\/p>\n\n\n\n<p class=\"has-text-align-center wp-block-paragraph\">\u2014 Professor Andrew Lee, Midwestern University&nbsp;<\/p>\n<\/blockquote>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n<h2 style=\"font-size: 100%\"><strong><span class=\"NormalTextRun SCXW13160619 BCX0\">When should researchers fine-tune a pretrained <\/span><span class=\"NormalTextRun SCXW13160619 BCX0\">segmentation <\/span><span class=\"NormalTextRun SCXW13160619 BCX0\">model?<\/span><\/strong><\/h2>\n\n\n<p class=\"wp-block-paragraph\">Direct inference is a practical starting point when new scans resemble the anatomy and imaging conditions represented by the model\u2019s training data. Researchers can load the pretrained model, run BONe DLPred, and inspect the result.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">If scans differ in resolution, contrast, anatomy, or artifact profile, the initial performance of the segmentation may need to be improved. In such cases, Professor Lee recommends using a representative set of reference segmentations to fine-tune the pretrained model with BONe DLFit. The resulting task-specific model can then be applied with BONe DLPred; BONe IOU can also quantify overlap when reference masks are available. The benefit of this approach is that researchers can adapt an existing model rather than train a new one from scratch.&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1024\" src=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1.jpg\" alt=\"Flowchart comparing two deep-learning-based biomedical image segmentation approaches.\" class=\"wp-image-2207\" srcset=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1.jpg 1024w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1-150x150.jpg 150w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1-300x300-1.jpg 300w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1-768x768.jpg 768w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1-80x80.jpg 80w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1-600x600.jpg 600w, https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/flowchart-1024x576-1-400x400.jpg 400w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n<h2 style=\"font-size: 100%\"><strong><span class=\"TextRun SCXW264435175 BCX0\" lang=\"EN-US\" xml:lang=\"EN-US\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW264435175 BCX0\">How should researchers evaluate model performance?<\/span><\/span><\/strong><\/h2>\n\n\n<p class=\"wp-block-paragraph\">A segmentation model\u2019s practical value depends not only on benchmark performance but also on how well its training data represent the scans it will encounter. For the examples shown in this blog, the training data included multiple skeletal elements and variation in voxel size, noise, specimen tilt, brightness, beam hardening, as well as drill holes and broken surfaces. The fitting process added further variation through rotations, flips, and cropping, as well as changes in brightness and contrast.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">In five-fold cross-validation, the resulting revised BP-2D-03a model achieved a mean intersection over union (IoU) of approximately 91%. However, mean performance varied from about 85% to 97% across folds, with some lower results associated with unusual or out-of-domain scans. These results show why a benchmark score alone cannot establish how a model will perform on every new dataset. Researchers should assess performance on scans that reflect their specific anatomy and imaging conditions, reviewing the predictions before they are used for downstream measurements.&nbsp;<\/p>\n\n\n<h2 style=\"font-size: 100%\"><strong><span class=\"TextRun SCXW153910905 BCX0\" lang=\"EN-US\" xml:lang=\"EN-US\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW153910905 BCX0\">A more scalable image-analysis workflow<\/span><\/span><\/strong><\/h2>\n\n\n<p class=\"wp-block-paragraph\">Professor Lee\u2019s work shows how Amira-Avizo Software can support deep-learning-based segmentation workflows that include prediction, visualization, inspection, and refinement. BONe DLPred can take on repetitive segmentation across large scans, and researchers can subsequently use Amira-Avizo Software to review the results and decide whether manual cleanup or model fine-tuning is needed.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For labs facing a growing volume of micro-CT data, this approach serves as a practical way to ease the burden of segmentation and analysis; instead of spending time tracing every slice, teams can focus on understanding what the images reveal. With deep-learning-based segmentation, researchers can test a pretrained model on representative scans, review its output in 2D and 3D, and adapt it further to meet the specific needs of their data.&nbsp;&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-video aligncenter\"><video height=\"1080\" style=\"aspect-ratio: 1920 \/ 1080;\" width=\"1920\" controls src=\"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/lee-2026-imaging-webinar-1920x1080-1.mp4\"><\/video><figcaption class=\"wp-element-caption\"><em><strong>BONe DLPred in Amira-Avizo Software.<\/strong> In this demonstration, Professor Lee applies BONe DLPred to a micro-CT scan, adjusts prediction settings, and reviews the resulting segmentation in both 2D and 3D. The importance of quality control is also highlighted; even a strong prediction can contain artifacts that need inspection and, where appropriate, cleanup.<\/em><\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/www.thermofisher.com\/fr\/fr\/home\/events\/image-analysis-workflows.html\" target=\"_blank\" rel=\"noopener\"><strong>Watch the full webinar on-demand to learn more about BONe DLPred and how Amira Software supports deep-learning-based segmentation &gt;<\/strong><\/a> <strong><\/strong>&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"http:\/\/thermofisher.com\/amira\" target=\"_blank\" rel=\"noopener\"><strong>Explore more features and capabilities of Amira Software at thermofisher.com\/amira &gt;<\/strong><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The importance of biomedical image segmentation Researchers studying whole bones utilize volumetric imaging techniques such as micro-computed tomography (micro-CT) to understand the complex 3D structures underlying bone morphology. Biomedical image segmentation is often an essential part of this analysis, helping to reveal the finer details of bone composition. The process of manually segmenting thousands of<\/p>\n","protected":false},"author":1809,"featured_media":2203,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_kad_blocks_custom_css":"","_kad_blocks_head_custom_js":"","_kad_blocks_body_custom_js":"","_kad_blocks_footer_custom_js":"","_monsterinsights_skip_tracking":false,"_genesis_hide_title":false,"_genesis_hide_breadcrumbs":false,"_genesis_hide_singular_image":false,"_genesis_hide_footer_widgets":false,"_genesis_custom_body_class":"","_genesis_custom_post_class":"","_genesis_layout":"","_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_post_was_ever_published":false},"categories":[322,185],"tags":[],"division":[360],"class_list":["post-2201","post","type-post","status-publish","format-standard","has-post-thumbnail","category-amira-software","category-software","division-msd","entry"],"_selected_authors":[],"_selected_reviewers":[],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v27.8 (Yoast SEO v27.8) - https:\/\/yoast.com\/product\/yoast-seo-premium-wordpress\/ -->\n<title>Micro CT Analysis Bone | Biomedical Image Segmentation | Bone Segmentation | Thermo Fisher Scientific<\/title>\n<meta name=\"description\" content=\"Learn how deep learning image analysis in Amira Software supports biomedical image segmentation for micro CT analysis of bone.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How can deep-learning-based biomedical image segmentation support the micro-CT analysis of bone?\" \/>\n<meta property=\"og:description\" content=\"Learn how deep learning image analysis in Amira Software supports biomedical image segmentation for micro CT analysis of bone.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/\" \/>\n<meta property=\"og:site_name\" content=\"Life in Atomic Resolution\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/thermofisher\" \/>\n<meta property=\"article:published_time\" content=\"2026-11-17T07:40:24+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-11-17T07:40:28+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1080\" \/>\n\t<meta property=\"og:image:height\" content=\"1080\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Swarnim Rawat\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@thermofisher\" \/>\n<meta name=\"twitter:site\" content=\"@thermofisher\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Swarnim Rawat\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/\"},\"author\":{\"name\":\"Swarnim Rawat\",\"@id\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/#\\\/schema\\\/person\\\/69f922bec6e68102286c598737517b9c\"},\"headline\":\"How can deep-learning-based biomedical image segmentation support the micro-CT analysis of bone?\",\"datePublished\":\"2026-11-17T07:40:24+00:00\",\"dateModified\":\"2026-11-17T07:40:28+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/\"},\"wordCount\":1308,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/wp-content\\\/uploads\\\/sites\\\/22\\\/2026\\\/11\\\/social-1080x1080-1.jpg\",\"articleSection\":[\"Amira Software\",\"Software\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/\",\"url\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/\",\"name\":\"Micro CT Analysis Bone | Biomedical Image Segmentation | Bone Segmentation | Thermo Fisher Scientific\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/wp-content\\\/uploads\\\/sites\\\/22\\\/2026\\\/11\\\/social-1080x1080-1.jpg\",\"datePublished\":\"2026-11-17T07:40:24+00:00\",\"dateModified\":\"2026-11-17T07:40:28+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/#\\\/schema\\\/person\\\/69f922bec6e68102286c598737517b9c\"},\"description\":\"Learn how deep learning image analysis in Amira Software supports biomedical image segmentation for micro CT analysis of bone.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#primaryimage\",\"url\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/wp-content\\\/uploads\\\/sites\\\/22\\\/2026\\\/11\\\/social-1080x1080-1.jpg\",\"contentUrl\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/wp-content\\\/uploads\\\/sites\\\/22\\\/2026\\\/11\\\/social-1080x1080-1.jpg\",\"width\":1080,\"height\":1080,\"caption\":\"Biomedical image segmentation\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.thermofisher.com\\\/blog\\\/atomic-resolution\\\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How can deep-learning-based biomedical image segmentation support the micro-CT analysis of bone?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/#website\",\"url\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/\",\"name\":\"Life in Atomic Resolution\",\"description\":\"Electron and cryo-electron microscopy stories and solutions about the advancement of cellular and structural biology\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/atomic-resolution\\\/#\\\/schema\\\/person\\\/69f922bec6e68102286c598737517b9c\",\"name\":\"Swarnim Rawat\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f02bed90065ce2b327ace32b6aa4a9252da3c8b1091d0ca100c642490c42ec8f?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f02bed90065ce2b327ace32b6aa4a9252da3c8b1091d0ca100c642490c42ec8f?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f02bed90065ce2b327ace32b6aa4a9252da3c8b1091d0ca100c642490c42ec8f?s=96&d=mm&r=g\",\"caption\":\"Swarnim Rawat\"},\"url\":\"https:\\\/\\\/admin.acceleratingscience.com\\\/author\\\/swarnim-rawatthermofisher-com\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Micro CT Analysis Bone | Biomedical Image Segmentation | Bone Segmentation | Thermo Fisher Scientific","description":"Learn how deep learning image analysis in Amira Software supports biomedical image segmentation for micro CT analysis of bone.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/","og_locale":"en_US","og_type":"article","og_title":"How can deep-learning-based biomedical image segmentation support the micro-CT analysis of bone?","og_description":"Learn how deep learning image analysis in Amira Software supports biomedical image segmentation for micro CT analysis of bone.","og_url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/","og_site_name":"Life in Atomic Resolution","article_publisher":"https:\/\/www.facebook.com\/thermofisher","article_published_time":"2026-11-17T07:40:24+00:00","article_modified_time":"2026-11-17T07:40:28+00:00","og_image":[{"width":1080,"height":1080,"url":"http:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1.jpg","type":"image\/jpeg"}],"author":"Swarnim Rawat","twitter_card":"summary_large_image","twitter_creator":"@thermofisher","twitter_site":"@thermofisher","twitter_misc":{"Written by":"Swarnim Rawat","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#article","isPartOf":{"@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/"},"author":{"name":"Swarnim Rawat","@id":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/#\/schema\/person\/69f922bec6e68102286c598737517b9c"},"headline":"How can deep-learning-based biomedical image segmentation support the micro-CT analysis of bone?","datePublished":"2026-11-17T07:40:24+00:00","dateModified":"2026-11-17T07:40:28+00:00","mainEntityOfPage":{"@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/"},"wordCount":1308,"commentCount":0,"image":{"@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#primaryimage"},"thumbnailUrl":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1.jpg","articleSection":["Amira Software","Software"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/","url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/","name":"Micro CT Analysis Bone | Biomedical Image Segmentation | Bone Segmentation | Thermo Fisher Scientific","isPartOf":{"@id":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#primaryimage"},"image":{"@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#primaryimage"},"thumbnailUrl":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1.jpg","datePublished":"2026-11-17T07:40:24+00:00","dateModified":"2026-11-17T07:40:28+00:00","author":{"@id":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/#\/schema\/person\/69f922bec6e68102286c598737517b9c"},"description":"Learn how deep learning image analysis in Amira Software supports biomedical image segmentation for micro CT analysis of bone.","breadcrumb":{"@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#primaryimage","url":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1.jpg","contentUrl":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1.jpg","width":1080,"height":1080,"caption":"Biomedical image segmentation"},{"@type":"BreadcrumbList","@id":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/biomedical-image-segmentation-supports-micro-ct-analysis-bone-segmentation\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/"},{"@type":"ListItem","position":2,"name":"How can deep-learning-based biomedical image segmentation support the micro-CT analysis of bone?"}]},{"@type":"WebSite","@id":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/#website","url":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/","name":"Life in Atomic Resolution","description":"Electron and cryo-electron microscopy stories and solutions about the advancement of cellular and structural biology","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/#\/schema\/person\/69f922bec6e68102286c598737517b9c","name":"Swarnim Rawat","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/f02bed90065ce2b327ace32b6aa4a9252da3c8b1091d0ca100c642490c42ec8f?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/f02bed90065ce2b327ace32b6aa4a9252da3c8b1091d0ca100c642490c42ec8f?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/f02bed90065ce2b327ace32b6aa4a9252da3c8b1091d0ca100c642490c42ec8f?s=96&d=mm&r=g","caption":"Swarnim Rawat"},"url":"https:\/\/admin.acceleratingscience.com\/author\/swarnim-rawatthermofisher-com\/"}]}},"taxonomy_info":{"category":[{"value":322,"label":"Amira Software"},{"value":185,"label":"Software"}],"division":[{"value":360,"label":"MSD"}]},"featured_image_src_large":["https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1-1024x1024.jpg",760,760,true],"author_info":{"display_name":"Swarnim Rawat","author_link":"https:\/\/admin.acceleratingscience.com\/author\/swarnim-rawatthermofisher-com\/"},"comment_info":0,"category_info":[{"term_id":322,"name":"Amira Software","slug":"amira-software","term_group":0,"term_taxonomy_id":322,"taxonomy":"category","description":"","parent":24,"count":12,"filter":"raw","meta":[],"cat_ID":322,"category_count":12,"category_description":"","cat_name":"Amira Software","category_nicename":"amira-software","category_parent":24},{"term_id":185,"name":"Software","slug":"software","term_group":0,"term_taxonomy_id":185,"taxonomy":"category","description":"","parent":0,"count":17,"filter":"raw","meta":[],"cat_ID":185,"category_count":17,"category_description":"","cat_name":"Software","category_nicename":"software","category_parent":0}],"tag_info":false,"jetpack-related-posts":[{"id":2071,"url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/facilitating-soft-tissue-analysis-unraveling-complex-microct-imaging-data-with-amira-software\/","url_meta":{"origin":2201,"position":0},"title":"Facilitating Soft Tissue Analysis \u2013 Unraveling Complex MicroCT Imaging Data with Amira Software","author":"Vinay S","date":"August 27, 2026","format":false,"excerpt":"Key takeaways Micro-computed X-ray tomography (microCT) can be used for high-resolution, 3D visualization of a range of biological samples, including soft tissues, but transforming this data into scientific insights requires the processing of increasingly large, complex datasets. Thermo Scientific Amira Software is a powerful data processing tool that can simplify\u2026","rel":"","context":"In &quot;Amira Software&quot;","block_context":{"text":"Amira Software","link":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/cryo-electron-microscopy-cryo-em\/amira-software\/"},"img":{"alt_text":"Facilitating Soft Tissue Analysis \u2013 Unraveling Complex MicroCT Imaging Data with Amira Software","src":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/08\/blog-soft-tissue-micro-ct-research-header-1920x450-1.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/08\/blog-soft-tissue-micro-ct-research-header-1920x450-1.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/08\/blog-soft-tissue-micro-ct-research-header-1920x450-1.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/08\/blog-soft-tissue-micro-ct-research-header-1920x450-1.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/08\/blog-soft-tissue-micro-ct-research-header-1920x450-1.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/08\/blog-soft-tissue-micro-ct-research-header-1920x450-1.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":2016,"url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/how-artificial-intelligence-ai-improves-image-analysis-workflows-in-life-sciences\/","url_meta":{"origin":2201,"position":1},"title":"How artificial intelligence (AI) improves image analysis workflows in life sciences","author":"Vinay S","date":"June 2, 2026","format":false,"excerpt":"Image acquisition is not the end of the story\u2014it is the starting point. Once images are captured, researchers typically move into preprocessing to improve quality, then they perform visualization, segmentation, and quantitative analysis to extract meaningful measurements. The goal is simple: turn images into understanding. In practice, however, image analysis\u2026","rel":"","context":"In &quot;Amira Software&quot;","block_context":{"text":"Amira Software","link":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/cryo-electron-microscopy-cryo-em\/amira-software\/"},"img":{"alt_text":"How artificial intelligence (AI) improves image analysis workflows in life sciences","src":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/06\/amira-ai-tools-blog-header-1920x450-1.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/06\/amira-ai-tools-blog-header-1920x450-1.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/06\/amira-ai-tools-blog-header-1920x450-1.png?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/06\/amira-ai-tools-blog-header-1920x450-1.png?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/06\/amira-ai-tools-blog-header-1920x450-1.png?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/06\/amira-ai-tools-blog-header-1920x450-1.png?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":2143,"url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/microscopy-image-analysis-with-amira-software-ai-in-cell-biology\/","url_meta":{"origin":2201,"position":2},"title":"Four ways AI is making microscopy image analysis easier for cell biologists","author":"Alejandra Sanchez-Erostegui","date":"October 14, 2026","format":false,"excerpt":"Key takeaways Modern microscopes are capable of generating large volumes of high-resolution data, which is highly valuable for cell biology research, but also makes it increasingly more laborious and difficult to extract meaningful scientific information from the whole dataset.\u00a0 Artificial intelligence is well positioned to support this work by streamlining\u2026","rel":"","context":"In &quot;Amira Software&quot;","block_context":{"text":"Amira Software","link":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/cryo-electron-microscopy-cryo-em\/amira-software\/"},"img":{"alt_text":"Four ways AI is making microscopy image analysis easier for cell biologists.","src":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/fault-localization-root-cause-ai-packaging-header-1920x450-1.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/fault-localization-root-cause-ai-packaging-header-1920x450-1.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/fault-localization-root-cause-ai-packaging-header-1920x450-1.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/fault-localization-root-cause-ai-packaging-header-1920x450-1.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/fault-localization-root-cause-ai-packaging-header-1920x450-1.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/fault-localization-root-cause-ai-packaging-header-1920x450-1.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":1953,"url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/3d-tissue-histology-light-sheet-microscopy-for-nondestructive-microglia-structure-analysis\/","url_meta":{"origin":2201,"position":3},"title":"3D Tissue Histology with Light-Sheet Microscopy Enables Nondestructive Analysis of Microglia","author":"Vinay S","date":"January 21, 2026","format":false,"excerpt":"3D tissue analysis offers critical benefits for neuroscience research The imaging and analysis of tissues is vital across a number of biological fields, particularly neuroscience, where the accurate characterization of neural tissue plays an important role in our understanding of the nervous system. Historically, these samples were imaged as thin\u2026","rel":"","context":"In &quot;Amira Software&quot;","block_context":{"text":"Amira Software","link":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/cryo-electron-microscopy-cryo-em\/amira-software\/"},"img":{"alt_text":"3D Tissue Histology with Light-Sheet Microscopy Enables Nondestructive Analysis of Microglia","src":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/01\/neuroscience-blog-header-1920x450-1.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/01\/neuroscience-blog-header-1920x450-1.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/01\/neuroscience-blog-header-1920x450-1.png?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/01\/neuroscience-blog-header-1920x450-1.png?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/01\/neuroscience-blog-header-1920x450-1.png?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/01\/neuroscience-blog-header-1920x450-1.png?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":2117,"url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/advances-in-cryo-electron-tomography-expand-the-capabilities-of-quantitative-cell-biology\/","url_meta":{"origin":2201,"position":4},"title":"Advances in cryo-electron tomography expand the capabilities of quantitative cell biology","author":"Vinay S","date":"September 29, 2026","format":false,"excerpt":"Key takeaways Cryo-electron tomography has largely been seen as a qualitative method because cryo-ET data segmentation has been a highly intensive, manual process. Recent advances in deep-learning-based segmentation have expanded the capabilities of cryo-electron tomography, supporting quantitative analysis of cellular structures. A recent webinar by Professor Danielle Grotjahn highlights how\u2026","rel":"","context":"In &quot;Cryo EM Techniques&quot;","block_context":{"text":"Cryo EM Techniques","link":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/cryo-electron-microscopy-cryo-em\/cryo-em-techniques\/"},"img":{"alt_text":"Advances in cryo-electron tomography expand the capabilities of quantitative cell biology.","src":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/09\/blog-cryo-em-series-header-1920x450-1.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/09\/blog-cryo-em-series-header-1920x450-1.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/09\/blog-cryo-em-series-header-1920x450-1.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/09\/blog-cryo-em-series-header-1920x450-1.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/09\/blog-cryo-em-series-header-1920x450-1.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/09\/blog-cryo-em-series-header-1920x450-1.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":2172,"url":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/what-is-subtomogram-averaging\/","url_meta":{"origin":2201,"position":5},"title":"What is Subtomogram Averaging?","author":"Swarnim Rawat","date":"October 19, 2026","format":false,"excerpt":"Turning crowded cryo-ET data into structural insight with subtomogram averaging Cryo-electron tomography (cryo-ET) is capable of capturing detailed, three-dimensional views of vitrified biological samples, supporting a broad range of life sciences research. Subtomogram averaging helps refine that crowded data for clearer structural insight by finding repeated particles, extracting them as\u2026","rel":"","context":"In &quot;Cancer Research&quot;","block_context":{"text":"Cancer Research","link":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/cryo-electron-microscopy-cryo-em\/amira-software\/cancer-research\/"},"img":{"alt_text":"Social Cryo EM","src":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/social.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/social.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/social.png?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/10\/social.png?resize=700%2C400&ssl=1 2x"},"classes":[]}],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"https:\/\/admin.acceleratingscience.com\/atomic-resolution\/wp-content\/uploads\/sites\/22\/2026\/11\/social-1080x1080-1.jpg","_links":{"self":[{"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/posts\/2201","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/users\/1809"}],"replies":[{"embeddable":true,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/comments?post=2201"}],"version-history":[{"count":4,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/posts\/2201\/revisions"}],"predecessor-version":[{"id":2228,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/posts\/2201\/revisions\/2228"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/media\/2203"}],"wp:attachment":[{"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/media?parent=2201"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/categories?post=2201"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/tags?post=2201"},{"taxonomy":"division","embeddable":true,"href":"https:\/\/www.thermofisher.com\/blog\/atomic-resolution\/wp-json\/wp\/v2\/division?post=2201"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}