{"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/bayesian-quicknat-model-uncertainty-in-deep","title":"Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Control","arxiv_id":"1811.09800","date":"2018-11-24","proceeding":null,"authors":["Abhijit Guha Roy","Sailesh Conjeti","Nassir Navab","Christian Wachinger"],"abstract":"We introduce Bayesian QuickNAT for the automated quality control of\nwhole-brain segmentation on MRI T1 scans. Next to the Bayesian fully\nconvolutional neural network, we also present inherent measures of segmentation\nuncertainty that allow for quality control per brain structure. For estimating\nmodel uncertainty, we follow a Bayesian approach, wherein, Monte Carlo (MC)\nsamples from the posterior distribution are generated by keeping the dropout\nlayers active at test time. Entropy over the MC samples provides a voxel-wise\nmodel uncertainty map, whereas expectation over the MC predictions provides the\nfinal segmentation. Next to voxel-wise uncertainty, we introduce four metrics\nto quantify structure-wise uncertainty in segmentation for quality control. We\nreport experiments on four out-of-sample datasets comprising of diverse age\nrange, pathology and imaging artifacts. The proposed structure-wise uncertainty\nmetrics are highly correlated with the Dice score estimated with manual\nannotation and therefore present an inherent measure of segmentation quality.\nIn particular, the intersection over union over all the MC samples is a\nsuitable proxy for the Dice score. In addition to quality control at\nscan-level, we propose to incorporate the structure-wise uncertainty as a\nmeasure of confidence to do reliable group analysis on large data repositories.\nWe envisage that the introduced uncertainty metrics would help assess the\nfidelity of automated deep learning based segmentation methods for large-scale\npopulation studies, as they enable automated quality control and group analyses\nin processing large data repositories.","url_abs":"http://arxiv.org/abs/1811.09800v1","url_pdf":"http://arxiv.org/pdf/1811.09800v1.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":"bayesian-quicknat-model-uncertainty-in-deep","repo_url":"https://github.com/abhi4ssj/BayesianQuickNAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"bayesian-quicknat-model-uncertainty-in-deep","repo_url":"https://github.com/ai-med/quickNAT_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"brain-segmentation","task_name":"Brain Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.09800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09800"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abhi4ssj/BayesianQuickNAT","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ai-med/quickNAT_pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e9f2847240975534","entry":"compute_volume","repo":"ai-med/quickNAT_pytorch","repo_kind":"listed","path":"utils/evaluator.py","file_url":"https://github.com/ai-med/quickNAT_pytorch/blob/HEAD/utils/evaluator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9f2847240975534"}},{"code_sha256_prefix":"d3624fbc165839bb","entry":"dice_confusion_matrix","repo":"ai-med/quickNAT_pytorch","repo_kind":"listed","path":"utils/evaluator.py","file_url":"https://github.com/ai-med/quickNAT_pytorch/blob/HEAD/utils/evaluator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3624fbc165839bb"}},{"code_sha256_prefix":"bb8fee5ba734e976","entry":"dice_score_perclass","repo":"ai-med/quickNAT_pytorch","repo_kind":"listed","path":"utils/evaluator.py","file_url":"https://github.com/ai-med/quickNAT_pytorch/blob/HEAD/utils/evaluator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb8fee5ba734e976"}},{"code_sha256_prefix":"fcf754503b98adc9","entry":"estimate_weights_mfb","repo":"ai-med/quickNAT_pytorch","repo_kind":"listed","path":"utils/preprocessor.py","file_url":"https://github.com/ai-med/quickNAT_pytorch/blob/HEAD/utils/preprocessor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcf754503b98adc9"}},{"code_sha256_prefix":"4addd964b92585ee","entry":"get_imdb_dataset","repo":"ai-med/quickNAT_pytorch","repo_kind":"listed","path":"utils/data_utils.py","file_url":"https://github.com/ai-med/quickNAT_pytorch/blob/HEAD/utils/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4addd964b92585ee"}},{"code_sha256_prefix":"f419700d7ae296ee","entry":"remap_labels","repo":"ai-med/quickNAT_pytorch","repo_kind":"listed","path":"utils/preprocessor.py","file_url":"https://github.com/ai-med/quickNAT_pytorch/blob/HEAD/utils/preprocessor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f419700d7ae296ee"}},{"code_sha256_prefix":"fa1041b0fb86f73e","entry":"rotate_orientation","repo":"ai-med/quickNAT_pytorch","repo_kind":"listed","path":"utils/preprocessor.py","file_url":"https://github.com/ai-med/quickNAT_pytorch/blob/HEAD/utils/preprocessor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa1041b0fb86f73e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}