[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-tool-narrows-pathologist-disagreement-on-tumor-counts":10,"sections":40},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},9559,"ai-tool-narrows-pathologist-disagreement-on-tumor-counts","AI Tool Narrows Pathologist Disagreement on Tumor Counts","A multi-center trial found AI assistance raised pathologist agreement (ICC 0.59 to 0.95) and cut assessment time nearly in half.","Counting cancer cells by eye is getting a second opinion from AI.\n\nResearchers built MitPro, a tool that points pathologists toward the busiest-looking patches of a tumor slide and flags likely dividing cells, called mitotic figures, while leaving the final count to the human reader. Thirteen pathologists across three countries read 385 whole-slide images spanning seven tumor types, each scoring every slide twice - once unaided, once with AI help - with a two-week gap between reads. Agreement between pathologists, measured by intraclass correlation coefficient, rose from 0.589 to 0.949. Median read time per slide dropped from about 286 seconds to about 128 seconds.\n\nMitotic count feeds directly into tumor grading, which shapes treatment decisions, so two pathologists landing on different grades for the same slide isn't an academic quibble. An ICC of 0.589 means readers were frequently out of step before any AI involvement; 0.949 puts them in close agreement. The AI also nudged counts slightly higher overall, which the researchers attribute to catching mitotic figures humans missed rather than AI overcounting.\n\nThat's a reproducibility and speed study, not a clinical outcomes trial - it says nothing yet about whether tighter agreement among pathologists changes what oncologists actually prescribe.","[\"ai\",\"pathology\",\"medical-ai\",\"diagnostics\"]","2026-10-02T04:00:00.000Z","2026-10-03T00:36:40.022Z","2026-10-03T00:36:45.595Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The dek's claim that AI 'nearly tripled agreement between doctors' misstates the data — ICC rose from 0.589 to 0.949, roughly a 1.6x increase, not a tripling, so rephrase the dek (and check the headline's 'in half' framing) to state the actual ICC figures rather than an inflated multiple.","resolved","ai",[30,32,33,34],"pathology","medical-ai","diagnostics",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.01813",0,{"sections":41},[42,45,49,53,58,62,66,71,76,81,86,91,96,101],{"name":43,"slug":30,"count":44,"latest_published_at":18},"AI",5896,{"name":46,"slug":47,"count":48,"latest_published_at":18},"Security","security",837,{"name":50,"slug":51,"count":52,"latest_published_at":18},"Policy","policy",438,{"name":54,"slug":55,"count":56,"latest_published_at":57},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":18},"Hardware","hardware",199,{"name":63,"slug":64,"count":65,"latest_published_at":18},"Science","science",171,{"name":67,"slug":68,"count":69,"latest_published_at":70},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]