{"id":4415,"date":"2026-04-21T09:32:12","date_gmt":"2026-04-21T09:32:12","guid":{"rendered":"https:\/\/www.oferreiter.com\/?p=4415"},"modified":"2026-04-21T09:33:03","modified_gmt":"2026-04-21T09:33:03","slug":"beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis","status":"publish","type":"post","link":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/","title":{"rendered":"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis"},"content":{"rendered":"
\n
\n
\n
\"BrowZine<\/a><\/div>\n<\/div>\n
\n
\n
Ofer Reiter<\/a>\u00a0<\/span>1<\/a>\u00a0<\/span>2<\/a><\/sup>,\u00a0<\/span><\/span>Cristian Navarrete-Dechent<\/a>\u00a0<\/span>3<\/a><\/sup>,\u00a0<\/span><\/span>Mor Atlas<\/a>\u00a0<\/span>4<\/a><\/sup>,\u00a0<\/span><\/span>Nir Nathansohn<\/a>\u00a0<\/span>5<\/a><\/sup>,\u00a0<\/span><\/span>Yaron Ben Mordehai<\/a>\u00a0<\/span>6<\/a><\/sup>,\u00a0<\/span><\/span>Tomer Mimouni<\/a>\u00a0<\/span>2<\/a><\/sup>,\u00a0<\/span><\/span>Romi Gleicher<\/a>\u00a0<\/span>7<\/a><\/sup>,\u00a0<\/span><\/span>Mahdi Awwad<\/a>\u00a0<\/span>8<\/a><\/sup>,\u00a0<\/span><\/span>Itay Cohen<\/a>\u00a0<\/span>9<\/a><\/sup>,\u00a0<\/span><\/span>Ziad Khamaysi<\/a>\u00a0<\/span>7<\/a>\u00a0<\/span>10<\/a><\/sup>,\u00a0<\/span><\/span>Jonathan Shapiro<\/a>\u00a0<\/span>6<\/a><\/sup><\/span><\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/header>\n
\n

Abstract<\/h2>\n
\n

Background:\u00a0<\/strong>Artificial intelligence (AI) algorithms have advanced and recently shown high accuracy in diagnosing skin cancer from dermoscopic images. This study compared the diagnostic performance of the large language model ChatGPT-4 with that of specialized convolutional neural network (CNN)-based models in analyzing melanocytic lesions.<\/p>\n

Patients and methods:\u00a0<\/strong>A cross-sectional comparative study was conducted using 117 dermoscopic images. The performance of ChatGPT-4 was assessed under two conditions: diagnosing lesions directly without annotations and diagnosing after annotating dermoscopic features. Results were compared with CNN-based models (YPSONO and ResNet) and human expert evaluations. The confusion matrices of all the models were calculated in addition to the diagnostic accuracy, sensitivity, specificity, and interobserver agreement (Cohen’s Kappa).<\/p>\n

Results:\u00a0<\/strong>ChatGPT-4 achieved 92 % sensitivity, 89 % specificity, and an accuracy of 89.7 % in direct diagnosis. When annotations were required, sensitivity and specificity dropped to 68 % and 64 %, respectively. Agreement with experts on dermoscopic patterns was minimal (Cohen’s Kappa = 0.13). ChatGPT-4 outperformed CNN models in direct diagnosis but exhibited notable limitations in describing dermoscopic features.<\/p>\n

Conclusions:\u00a0<\/strong>ChatGPT-4 demonstrated promising potential for accurate melanoma versus nevus classification without annotations, surpassing CNN-based models. However, its limited ability to describe dermoscopic features accurately highlights the need for further research and training.<\/p>\n<\/div>\n

Keywords:\u00a0<\/strong>Annotations; GPT; artificial intelligence; dermoscopy; diagnostic accuracy; interobserver agreement; melanoma; nevus.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Ofer Reiter\u00a01\u00a02,\u00a0Cristian Navarrete-Dechent\u00a03,\u00a0Mor Atlas\u00a04,\u00a0Nir Nathansohn\u00a05,\u00a0Yaron Ben Mordehai\u00a06,\u00a0Tomer Mimouni\u00a02,\u00a0Romi Gleicher\u00a07,\u00a0Mahdi Awwad\u00a08,\u00a0Itay Cohen\u00a09,\u00a0Ziad Khamaysi\u00a07\u00a010,\u00a0Jonathan Shapiro\u00a06 Abstract Background:\u00a0Artificial intelligence (AI) algorithms have advanced and recently shown high accuracy in diagnosing skin cancer from dermoscopic images. This study compared the diagnostic performance of the large language model ChatGPT-4 with that of specialized convolutional neural network (CNN)-based models in analyzing […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-4415","post","type-post","status-publish","format-standard","hentry","category-published-research"],"yoast_head":"\nBeyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis - \u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8<\/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:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis - \u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8\" \/>\n<meta property=\"og:description\" content=\"Ofer Reiter\u00a01\u00a02,\u00a0Cristian Navarrete-Dechent\u00a03,\u00a0Mor Atlas\u00a04,\u00a0Nir Nathansohn\u00a05,\u00a0Yaron Ben Mordehai\u00a06,\u00a0Tomer Mimouni\u00a02,\u00a0Romi Gleicher\u00a07,\u00a0Mahdi Awwad\u00a08,\u00a0Itay Cohen\u00a09,\u00a0Ziad Khamaysi\u00a07\u00a010,\u00a0Jonathan Shapiro\u00a06 Abstract Background:\u00a0Artificial intelligence (AI) algorithms have advanced and recently shown high accuracy in diagnosing skin cancer from dermoscopic images. This study compared the diagnostic performance of the large language model ChatGPT-4 with that of specialized convolutional neural network (CNN)-based models in analyzing […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/\" \/>\n<meta property=\"og:site_name\" content=\"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8\" \/>\n<meta property=\"article:published_time\" content=\"2026-04-21T09:32:12+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-21T09:33:03+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png\" \/>\n<meta name=\"author\" content=\"ofer-r\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"ofer-r\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/\"},\"author\":{\"name\":\"ofer-r\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/#\/schema\/person\/29e63728a19c29c75570d11d7116e8f1\"},\"headline\":\"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis\",\"datePublished\":\"2026-04-21T09:32:12+00:00\",\"dateModified\":\"2026-04-21T09:33:03+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/\"},\"wordCount\":245,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png\",\"articleSection\":[\"Published Research\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/\",\"url\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/\",\"name\":\"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis - \u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8\",\"isPartOf\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png\",\"datePublished\":\"2026-04-21T09:32:12+00:00\",\"dateModified\":\"2026-04-21T09:33:03+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage\",\"url\":\"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png\",\"contentUrl\":\"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u05d3\u05e3 \u05d4\u05d1\u05d9\u05ea\",\"item\":\"https:\/\/www.oferreiter.com\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/#website\",\"url\":\"https:\/\/www.oferreiter.com\/en\/\",\"name\":\"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8\",\"description\":\"\u05d0\u05d1\u05d7\u05d5\u05df \u05d5\u05d8\u05d9\u05e4\u05d5\u05dc \u05de\u05d5\u05e7\u05d3\u05dd \u05d1\u05e1\u05e8\u05d8\u05df \u05d4\u05e2\u05d5\u05e8\",\"publisher\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.oferreiter.com\/en\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/#organization\",\"name\":\"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8\",\"url\":\"https:\/\/www.oferreiter.com\/en\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.oferreiter.com\/wp-content\/uploads\/2023\/03\/cropped-ofer-logo-1.png\",\"contentUrl\":\"https:\/\/www.oferreiter.com\/wp-content\/uploads\/2023\/03\/cropped-ofer-logo-1.png\",\"width\":300,\"height\":57,\"caption\":\"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8\"},\"image\":{\"@id\":\"https:\/\/www.oferreiter.com\/en\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/#\/schema\/person\/29e63728a19c29c75570d11d7116e8f1\",\"name\":\"ofer-r\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.oferreiter.com\/en\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/8a67cd8b359905848a05d6707760d379f070f07d6bcd98845823446f50ed78ec?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/8a67cd8b359905848a05d6707760d379f070f07d6bcd98845823446f50ed78ec?s=96&d=mm&r=g\",\"caption\":\"ofer-r\"},\"url\":\"https:\/\/www.oferreiter.com\/en\/author\/ofer-r\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis - \u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8","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.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/","og_locale":"en_US","og_type":"article","og_title":"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis - \u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8","og_description":"Ofer Reiter\u00a01\u00a02,\u00a0Cristian Navarrete-Dechent\u00a03,\u00a0Mor Atlas\u00a04,\u00a0Nir Nathansohn\u00a05,\u00a0Yaron Ben Mordehai\u00a06,\u00a0Tomer Mimouni\u00a02,\u00a0Romi Gleicher\u00a07,\u00a0Mahdi Awwad\u00a08,\u00a0Itay Cohen\u00a09,\u00a0Ziad Khamaysi\u00a07\u00a010,\u00a0Jonathan Shapiro\u00a06 Abstract Background:\u00a0Artificial intelligence (AI) algorithms have advanced and recently shown high accuracy in diagnosing skin cancer from dermoscopic images. This study compared the diagnostic performance of the large language model ChatGPT-4 with that of specialized convolutional neural network (CNN)-based models in analyzing […]","og_url":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/","og_site_name":"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8","article_published_time":"2026-04-21T09:32:12+00:00","article_modified_time":"2026-04-21T09:33:03+00:00","og_image":[{"url":"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png","type":"","width":"","height":""}],"author":"ofer-r","twitter_card":"summary_large_image","twitter_misc":{"Written by":"ofer-r","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#article","isPartOf":{"@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/"},"author":{"name":"ofer-r","@id":"https:\/\/www.oferreiter.com\/en\/#\/schema\/person\/29e63728a19c29c75570d11d7116e8f1"},"headline":"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis","datePublished":"2026-04-21T09:32:12+00:00","dateModified":"2026-04-21T09:33:03+00:00","mainEntityOfPage":{"@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/"},"wordCount":245,"commentCount":0,"publisher":{"@id":"https:\/\/www.oferreiter.com\/en\/#organization"},"image":{"@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage"},"thumbnailUrl":"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png","articleSection":["Published Research"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/","url":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/","name":"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis - \u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8","isPartOf":{"@id":"https:\/\/www.oferreiter.com\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage"},"image":{"@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage"},"thumbnailUrl":"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png","datePublished":"2026-04-21T09:32:12+00:00","dateModified":"2026-04-21T09:33:03+00:00","breadcrumb":{"@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#primaryimage","url":"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png","contentUrl":"https:\/\/assets.thirdiron.com\/images\/covers\/1610-0379.png"},{"@type":"BreadcrumbList","@id":"https:\/\/www.oferreiter.com\/en\/beyond-black-box-ai-comparing-chatgpt-4-interpretability-and-accuracy-to-cnns-in-melanocytic-lesions-diagnosis\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u05d3\u05e3 \u05d4\u05d1\u05d9\u05ea","item":"https:\/\/www.oferreiter.com\/en\/"},{"@type":"ListItem","position":2,"name":"Beyond black-box AI: Comparing ChatGPT-4 interpretability and accuracy to CNNs in melanocytic lesions diagnosis"}]},{"@type":"WebSite","@id":"https:\/\/www.oferreiter.com\/en\/#website","url":"https:\/\/www.oferreiter.com\/en\/","name":"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8","description":"\u05d0\u05d1\u05d7\u05d5\u05df \u05d5\u05d8\u05d9\u05e4\u05d5\u05dc \u05de\u05d5\u05e7\u05d3\u05dd \u05d1\u05e1\u05e8\u05d8\u05df \u05d4\u05e2\u05d5\u05e8","publisher":{"@id":"https:\/\/www.oferreiter.com\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.oferreiter.com\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.oferreiter.com\/en\/#organization","name":"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8","url":"https:\/\/www.oferreiter.com\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.oferreiter.com\/en\/#\/schema\/logo\/image\/","url":"https:\/\/www.oferreiter.com\/wp-content\/uploads\/2023\/03\/cropped-ofer-logo-1.png","contentUrl":"https:\/\/www.oferreiter.com\/wp-content\/uploads\/2023\/03\/cropped-ofer-logo-1.png","width":300,"height":57,"caption":"\u05d3"\u05e8 \u05e2\u05d5\u05e4\u05e8 \u05e8\u05d9\u05d9\u05d8\u05e8 \u05d0\u05d2\u05e8"},"image":{"@id":"https:\/\/www.oferreiter.com\/en\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/www.oferreiter.com\/en\/#\/schema\/person\/29e63728a19c29c75570d11d7116e8f1","name":"ofer-r","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.oferreiter.com\/en\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/8a67cd8b359905848a05d6707760d379f070f07d6bcd98845823446f50ed78ec?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/8a67cd8b359905848a05d6707760d379f070f07d6bcd98845823446f50ed78ec?s=96&d=mm&r=g","caption":"ofer-r"},"url":"https:\/\/www.oferreiter.com\/en\/author\/ofer-r\/"}]}},"_links":{"self":[{"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/posts\/4415","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/comments?post=4415"}],"version-history":[{"count":0,"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/posts\/4415\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/media?parent=4415"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/categories?post=4415"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.oferreiter.com\/en\/wp-json\/wp\/v2\/tags?post=4415"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}