{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/visual-explanations-from-deep-3d","title":"Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification","arxiv_id":"1803.02544","date":"2018-03-07","proceeding":null,"authors":["Chengliang Yang","Anand Rangarajan","Sanjay Ranka"],"abstract":"We develop three efficient approaches for generating visual explanations from\n3D convolutional neural networks (3D-CNNs) for Alzheimer's disease\nclassification. One approach conducts sensitivity analysis on hierarchical 3D\nimage segmentation, and the other two visualize network activations on a\nspatial map. Visual checks and a quantitative localization benchmark indicate\nthat all approaches identify important brain parts for Alzheimer's disease\ndiagnosis. Comparative analysis show that the sensitivity analysis based\napproach has difficulty handling loosely distributed cerebral cortex, and\napproaches based on visualization of activations are constrained by the\nresolution of the convolutional layer. The complementarity of these methods\nimproves the understanding of 3D-CNNs in Alzheimer's disease classification\nfrom different perspectives.","url_abs":"http://arxiv.org/abs/1803.02544v3","url_pdf":"http://arxiv.org/pdf/1803.02544v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"visual-explanations-from-deep-3d","repo_url":"https://github.com/west-gates/3DCNN-Vis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.02544","atlas_url":"https://app.syntology.ai/?focus=1803.02544","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}