{"architecture":{"family":"Not disclosed. Checked on 2026-09-06: the vendor page (deephealth.com/kheiron-medical-technologies) describes the product only as built with 'deep learning and data science' and gives no network type, backbone, parameter count or training-data description.","input":"Screening mammography.","output":"Reader decision support in breast screening programmes (recall / no-recall support).","params":"not disclosed by the manufacturer"},"article":null,"cancer_slugs":["invasive-breast-carcinoma"],"category":"screening","confidence":"medium","datasets":[],"developer":"Kheiron Medical Technologies (now part of DeepHealth / RadNet)","evaluation":[{"benchmark":"GEMINI \u2014 prospective evaluation in NHS Grampian screening service, 10,889 women (mammograms read 27.02\u201305.10.2023)","external":true,"metric":"cancer detection rate / recall rate / reader workload","source":"https://doi.org/10.1038/s43018-026-01126-1","value":"Primary AI workflow: cancer detection +10.4% (1 additional cancer per 1,000 screened), recall rate maintained (0.8% reduction), reader workload reduced by up to 31%. Where AI recommended recall but standard double reading did not, additional human review identified 11 extra cancers. Alternative simulated workflows reached workload savings of up to 36%. All participants received routine care; the AI did not act alone."}],"hf":null,"kind":"product","license":"proprietary","limitations":"- Closed model; evidence is from deployment studies rather than open benchmarks.\n- Results depend on the screening programme's double-reading design.","links":{"demo":null,"docs":null,"doi":null,"github":null,"huggingface":null,"paper":null,"pmid":null},"modalities":["mammography"],"name":"Mia","notable_uses":"In a prospective NHS Grampian evaluation in Scotland covering 10,889 women, the AI-supported workflow helped detect 12% more cancers than routine practice \u2014 mostly invasive, high-grade tumours \u2014 with no increase in unnecessary recalls; modelling suggested a workload reduction of up to 30%.","openness":"closed","regulatory":{"details_en":"The manufacturer's page states that Mia (Mammography Intelligent Assessment) received CE marking in Europe in 2019; no FDA clearance or UKCA marking is stated there. Kheiron Medical Technologies became part of DeepHealth (a wholly owned subsidiary of RadNet) in 2024. Verified 2026-09-06: the owner's page refers to Mia in the past tense (\"Kheiron was known for its pioneering product\"), so current commercial availability and the scope of the certificate should be confirmed with the vendor before any clinical use.","details_pl":"Strona producenta podaje, ze Mia (Mammography Intelligent Assessment) uzyskala znak CE w Europie w 2019 r.; nie wymienia dopuszczenia FDA ani znaku UKCA. W 2024 r. Kheiron Medical Technologies wszedl w sklad DeepHealth (spolka zalezna RadNet). Zweryfikowano 6.09.2026: strona wlasciciela pisze o Mii w czasie przeszlym (\"Kheiron was known for its pioneering product\"), dlatego biezaca dostepnosc handlowa i zakres certyfikatu nalezy potwierdzic u dostawcy przed jakimkolwiek zastosowaniem klinicznym.","intended_use_en":"Decision support in screening mammography (reader support in breast screening programmes).","intended_use_pl":"Wsparcie decyzji w mammografii przesiewowej (wsparcie odczytu w programach przesiewowych piersi).","source_url":"https://deephealth.com/kheiron-medical-technologies/","status":"ce-marked"},"regulatory_status":"ce-marked","release_date":null,"run_snippet":"","settings":["screening"],"slug":"mia","sources":[{"label":"GEMINI study \u2014 Prospective evaluation of artificial intelligence integration into breast cancer screening in multiple workflow settings, Nature Cancer 2026;7(3):484-493","url":"https://doi.org/10.1038/s43018-026-01126-1"},{"label":"University of Aberdeen \u2014 GEMINI study announcement (2024; superseded figures)","url":"https://www.abdn.ac.uk/news/22964/"},{"label":"DeepHealth \u2014 Kheiron Medical Technologies (manufacturer page)","url":"https://deephealth.com/kheiron-medical-technologies/"}],"summary":"Commercial AI reader for screening mammography, evaluated as an additional reader in the UK's double-reading pathway; the GEMINI prospective study in Aberdeen reported extra cancers found when Mia flagged cases the readers had cleared.","tasks":["screening","detection"],"training":{"summary_en":"Not disclosed by the manufacturer. Checked on 2026-09-06: kheironmed.com now redirects (HTTP 301) to deephealth.com/kheiron-medical-technologies/, which states that Kheiron Medical Technologies became part of DeepHealth (a wholly owned subsidiary of RadNet) in 2024. That page names no training dataset, no number of mammograms or patients, no source institutions and no architecture; it covers company history, CE marking (2019) and clinical deployments instead.","summary_pl":"Nieujawnione przez producenta. Sprawdzone 6.09.2026: adres kheironmed.com przekierowuje juz (HTTP 301) na deephealth.com/kheiron-medical-technologies/, gdzie podano, ze Kheiron Medical Technologies wszedl w 2024 r. w sklad DeepHealth (spolki w calosci zaleznej od RadNet). Ta strona nie wymienia zbioru treningowego, liczby mammogramow ani pacjentek, osrodkow zrodlowych czy architektury; opisuje historie firmy, znak CE (2019) i wdrozenia kliniczne."},"updated_at":"2026-09-07T15:01:52.838620","url":"/ai-oncology/models/mia","usage":{},"verified_at":"2026-09-07T15:01:52.837241","verified_by":"Occe3C","version":null,"what_it_does":"Mia is an AI system that supports the reading of mammograms in breast cancer screening programmes, acting as an additional reader alongside radiologists. It highlights examinations and findings that may warrant further review."}