{"id":11131,"date":"2026-02-09T16:46:27","date_gmt":"2026-02-09T21:46:27","guid":{"rendered":"https:\/\/portfolios.cs.earlham.edu\/?page_id=11131"},"modified":"2026-05-15T17:40:21","modified_gmt":"2026-05-15T21:40:21","slug":"sora-owada","status":"publish","type":"page","link":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/","title":{"rendered":"Sora Owada"},"content":{"rendered":"\n

<\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n

Unsupervised Anomaly Detection in 3D Brain MR<\/strong><\/p>\n\n\n\n

Comparison Analysis between AutoEncoder vs Denoising Diffusion Probabilistic Model<\/strong><\/p>\n<\/div><\/div>\n<\/div>\n\n\n\n

Sora Owada
Computer Science Department at Earlham College
sowada23@earlham.edu<\/p>\n\n\n\n

<\/div>\n\n\n\n

Abstract<\/strong><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
\n
\n

Unsupervised anomaly detection (UAD) in brain MRI aims to learn the distribution of healthy anatomy from unlabelled scans and flag deviations as potential lesions. This avoids the need for voxel-wise annotations and can, in principle, detect a wide range of pathologies, making it attractive for screening and quality-assurance roles in neuroimaging. However, existing UAD work spans many model families\u2014reconstruction-based autoencoders and VAEs, feature-distance and one-class methods, generative models, and hybrids\u2014while using inconsistent evaluation protocols, datasets, and thresholding rules. This makes it difficult to compare results fairly or understand how different methods actually trade off sensitivity and false positives in realistic settings. In this project, I will build a minimal but rigorous UAD benchmarking setup focused on clarity and reproducibility rather than architectural novelty. Concretely, I will (1) select one healthy MRI dataset and one public lesion dataset, (2) perform basic but standardized preprocessing and patient-level train\/validation\/test splits with no leakage, (3) implement two simple UAD baselines\u2014a reconstruction-based autoencoder\/VAE and a Pseudo-Healthy Generative Models trained only on healthy data\u2014and (4) reports voxel-level ROC\u2013AUC and Dice, plus scan-level ROC\u2013AUC. Thresholds will be chosen using a held-out healthy validation set to control false positives, rather than tuned directly on lesion labels.<\/p>\n<\/div>\n<\/div>\n<\/div><\/div>\n<\/div><\/div>\n\n\n\n

<\/div>\n\n\n\n

Graphical Abstract<\/strong><\/p>\n\n\n\n

<\/div>\n\n\n
\n
\"\"<\/figure>\n<\/div>\n\n\n
<\/div>\n\n\n\n

Data Architecture Diagram<\/strong><\/p>\n\n\n\n

<\/div>\n\n\n
\n
\"\"<\/figure>\n<\/div>\n\n\n

<\/p>\n\n\n\n

<\/p>\n\n\n\n

Paper: https:\/\/drive.google.com\/file\/d\/1eRQbrZ8IgQUWk3uYyMjNZx_vRGRSbwzZ\/view?usp=sharing<\/a><\/p>\n\n\n\n

Youtube Video: https:\/\/youtu.be\/ylK_w1lnIUo<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Unsupervised Anomaly Detection in 3D Brain MR Comparison Analysis between AutoEncoder vs Denoising Diffusion Probabilistic Model Sora OwadaComputer Science Department at Earlham Collegesowada23@earlham.edu Abstract Unsupervised anomaly detection (UAD) in brain MRI aims to learn the distribution of healthy anatomy from … Read More<\/a><\/p>\n","protected":false},"author":168,"featured_media":0,"parent":8534,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-11131","page","type-page","status-publish","hentry"],"yoast_head":"\nSora Owada - CS\/DS Student Portfolios<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Sora Owada - CS\/DS Student Portfolios\" \/>\n<meta property=\"og:description\" content=\"Unsupervised Anomaly Detection in 3D Brain MR Comparison Analysis between AutoEncoder vs Denoising Diffusion Probabilistic Model Sora OwadaComputer Science Department at Earlham Collegesowada23@earlham.edu Abstract Unsupervised anomaly detection (UAD) in brain MRI aims to learn the distribution of healthy anatomy from … Read More\" \/>\n<meta property=\"og:url\" content=\"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/\" \/>\n<meta property=\"og:site_name\" content=\"CS\/DS Student Portfolios\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-15T21:40:21+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/portfolios.cs.earlham.edu\/wp-content\/uploads\/2026\/03\/CleanShot-2026-03-22-at-17.09.42@2x.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1574\" \/>\n\t<meta property=\"og:image:height\" content=\"652\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/\",\"url\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/\",\"name\":\"Sora Owada - CS\\\/DS Student Portfolios\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/wp-content\\\/uploads\\\/2026\\\/03\\\/CleanShot-2026-03-22-at-17.09.42@2x-1024x424.png\",\"datePublished\":\"2026-02-09T21:46:27+00:00\",\"dateModified\":\"2026-05-15T21:40:21+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/#primaryimage\",\"url\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/wp-content\\\/uploads\\\/2026\\\/03\\\/CleanShot-2026-03-22-at-17.09.42@2x.png\",\"contentUrl\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/wp-content\\\/uploads\\\/2026\\\/03\\\/CleanShot-2026-03-22-at-17.09.42@2x.png\",\"width\":1574,\"height\":652},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/sora-owada\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Students\",\"item\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"2024\",\"item\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"CS488\",\"item\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/index.php\\\/students\\\/2024-2\\\/cs488\\\/\"},{\"@type\":\"ListItem\",\"position\":5,\"name\":\"Sora Owada\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/#website\",\"url\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/\",\"name\":\"CS\\\/DS Student Portfolios\",\"description\":\"AI and ML, Image Classification, Arduino\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/portfolios.cs.earlham.edu\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Sora Owada - CS\/DS Student Portfolios","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:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/","og_locale":"en_US","og_type":"article","og_title":"Sora Owada - CS\/DS Student Portfolios","og_description":"Unsupervised Anomaly Detection in 3D Brain MR Comparison Analysis between AutoEncoder vs Denoising Diffusion Probabilistic Model Sora OwadaComputer Science Department at Earlham Collegesowada23@earlham.edu Abstract Unsupervised anomaly detection (UAD) in brain MRI aims to learn the distribution of healthy anatomy from … Read More","og_url":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/","og_site_name":"CS\/DS Student Portfolios","article_modified_time":"2026-05-15T21:40:21+00:00","og_image":[{"width":1574,"height":652,"url":"https:\/\/portfolios.cs.earlham.edu\/wp-content\/uploads\/2026\/03\/CleanShot-2026-03-22-at-17.09.42@2x.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/","url":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/","name":"Sora Owada - CS\/DS Student Portfolios","isPartOf":{"@id":"https:\/\/portfolios.cs.earlham.edu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/#primaryimage"},"image":{"@id":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/#primaryimage"},"thumbnailUrl":"https:\/\/portfolios.cs.earlham.edu\/wp-content\/uploads\/2026\/03\/CleanShot-2026-03-22-at-17.09.42@2x-1024x424.png","datePublished":"2026-02-09T21:46:27+00:00","dateModified":"2026-05-15T21:40:21+00:00","breadcrumb":{"@id":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/#primaryimage","url":"https:\/\/portfolios.cs.earlham.edu\/wp-content\/uploads\/2026\/03\/CleanShot-2026-03-22-at-17.09.42@2x.png","contentUrl":"https:\/\/portfolios.cs.earlham.edu\/wp-content\/uploads\/2026\/03\/CleanShot-2026-03-22-at-17.09.42@2x.png","width":1574,"height":652},{"@type":"BreadcrumbList","@id":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/sora-owada\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/portfolios.cs.earlham.edu\/"},{"@type":"ListItem","position":2,"name":"Students","item":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/"},{"@type":"ListItem","position":3,"name":"2024","item":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/"},{"@type":"ListItem","position":4,"name":"CS488","item":"https:\/\/portfolios.cs.earlham.edu\/index.php\/students\/2024-2\/cs488\/"},{"@type":"ListItem","position":5,"name":"Sora Owada"}]},{"@type":"WebSite","@id":"https:\/\/portfolios.cs.earlham.edu\/#website","url":"https:\/\/portfolios.cs.earlham.edu\/","name":"CS\/DS Student Portfolios","description":"AI and ML, Image Classification, Arduino","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/portfolios.cs.earlham.edu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"Sora Owada","author_link":"https:\/\/portfolios.cs.earlham.edu\/index.php\/author\/sowada23\/"},"rttpg_comment":0,"rttpg_category":null,"rttpg_excerpt":"Unsupervised Anomaly Detection in 3D Brain MR Comparison Analysis between AutoEncoder vs Denoising Diffusion Probabilistic Model Sora OwadaComputer Science Department at Earlham Collegesowada23@earlham.edu Abstract Unsupervised anomaly detection (UAD) in brain MRI aims to learn the distribution of healthy anatomy from … Read More","_links":{"self":[{"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/pages\/11131","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/users\/168"}],"replies":[{"embeddable":true,"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/comments?post=11131"}],"version-history":[{"count":39,"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/pages\/11131\/revisions"}],"predecessor-version":[{"id":11588,"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/pages\/11131\/revisions\/11588"}],"up":[{"embeddable":true,"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/pages\/8534"}],"wp:attachment":[{"href":"https:\/\/portfolios.cs.earlham.edu\/index.php\/wp-json\/wp\/v2\/media?parent=11131"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}