{"id":2807,"date":"2021-08-28T10:59:42","date_gmt":"2021-08-28T15:59:42","guid":{"rendered":"https:\/\/my.vanderbilt.edu\/masi\/?p=2807"},"modified":"2021-08-30T10:46:40","modified_gmt":"2021-08-30T15:46:40","slug":"missing-imputation-lung","status":"publish","type":"post","link":"https:\/\/my.vanderbilt.edu\/masi\/2021\/08\/missing-imputation-lung\/","title":{"rendered":"Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective"},"content":{"rendered":"<p>Riqiang Gao, Yucheng Tang, Kaiwen Xu, Ho Hin Lee, Steve Deppen, Kim Sandler, Pierre Massion, Thomas A. Lasko, Yuankai Huo, Bennett A. Landman,\u00a0Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective, MICCAI, 2021.<\/p>\n<p>Full text:\u00a0https:\/\/arxiv.org\/abs\/2107.11882<\/p>\n<h2>Abstract<\/h2>\n<p>Data from multi-modality provide complementary information in clinical prediction, but missing data in clinical cohorts limits the number of subjects in multi-modal learning context. Multi-modal missing imputation is challenging with existing methods when 1) the missing data span across heterogeneous modalities (e.g., image vs. non-image); or 2) one modality is largely missing. In this paper, we address the imputation of missing data by modeling the joint distribution of multi-modal data. Motivated by partial bidirectional generative adversarial net (PBiGAN), we propose a new Conditional PBiGAN (C-PBiGAN) method that imputes one modality combining the conditional knowledge from another modality. Specifically, C-PBiGAN introduces a conditional latent space in a missing imputation framework that jointly encodes the available multi-modal data, along with a class regularization loss on imputed data to recover discriminative information. To our knowledge, it is the first generative adversarial model that addresses multi-modal missing imputation by modeling the joint distribution of image and non-image data. We validate our model with both the national lung screening trial (NLST) dataset and an external clinical validation cohort. The proposed C-PBiGAN achieves significant improvements in lung cancer risk estimation compared with representative imputation methods (e.g., AUC values increase in both NLST (+2.9%) and in-house dataset (+4.3%) compared with PBiGAN, p<span id=\"MathJax-Element-1-Frame\" class=\"MathJax\"><span id=\"MathJax-Span-1\" class=\"math\"><span id=\"MathJax-Span-2\" class=\"mrow\"><span id=\"MathJax-Span-3\" class=\"mo\">&lt;<\/span><\/span><\/span><\/span>0.05).<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-2809\" src=\"https:\/\/my.vanderbilt.edu\/masi\/wp-content\/uploads\/sites\/2304\n2661\/2021\/08\/Figure1-e1630166305705.png\" alt=\"Figure1\" width=\"810\" height=\"326\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Riqiang Gao, Yucheng Tang, Kaiwen Xu, Ho Hin Lee, Steve Deppen, Kim Sandler, Pierre Massion, Thomas A. Lasko, Yuankai Huo, Bennett A. Landman,\u00a0Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective, MICCAI, 2021. Full text:\u00a0https:\/\/arxiv.org\/abs\/2107.11882 Abstract Data from multi-modality provide complementary information in clinical prediction, but missing data in clinical cohorts limits&#8230;<\/p>\n","protected":false},"author":7645,"featured_media":2809,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[144,147,180],"tags":[],"class_list":["post-2807","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-longitudinal","category-lung-screening-ct","category-missing-data"],"_links":{"self":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/2807","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/users\/7645"}],"replies":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/comments?post=2807"}],"version-history":[{"count":1,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/2807\/revisions"}],"predecessor-version":[{"id":2810,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/2807\/revisions\/2810"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/media\/2809"}],"wp:attachment":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/media?parent=2807"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/categories?post=2807"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/tags?post=2807"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}