{"entity":{"id":"radiology-ai-screening","kind":"technology","name":"AI in radiology","aka":[],"tldr":"Software that reads scans alongside radiologists, catching cancers earlier and predicting who is at risk.","summary":"Hundreds of FDA-cleared radiology AI devices exist; oncology use cases include mammography reading (Transpara, Lunit INSIGHT, MASAI trial in Sweden showed 29% more cancers detected with 44% less workload), lung nodule detection and malignancy scoring (Sybil, Optellum), prostate MRI, and risk models (Mirai). Foundation models linking images with text are emerging.","status":"established","asOf":"2026-09-04","wikipedia":"https://en.wikipedia.org/wiki/Artificial_intelligence_in_healthcare","links":[{"label":"Wikipedia","url":"https://en.wikipedia.org/wiki/Artificial_intelligence_in_healthcare"}],"tags":[],"related":["ai-oncology-clinic","radiogenomics","tumour-doubling-time"],"cancers":[],"sections":["imaging","ai-computation"],"technologies":["mammography","ct","mri"],"targets":[],"drugs":[],"companies":["kheiron-medical-technologies","nucleo-research","therapixel","vara","volpara-health"],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":["ai-compute-platforms"],"notes":[],"principle":"Deep convolutional and transformer networks trained on labelled imaging; increasingly self-supervised on large unlabelled corpora.","strengths":["Scales expert reading","Reduces workload and inter-reader variability"],"limitations":["Dataset shift across scanners and populations","Regulatory lag for adaptive models"]},"route":"/technologies/radiology-ai-screening/","neighbours":{"roadmap":[{"id":"ai-oncology-roadmap","kind":"roadmap","name":"AI in oncology roadmap: pattern readers → foundation models → agents in the workflow","route":"/roadmaps/ai-oncology-roadmap/"},{"id":"ai-oncology-clinic","kind":"roadmap","name":"AI in the oncology clinic: from narrow cleared tools to multimodal decision support","route":"/roadmaps/ai-oncology-clinic/"},{"id":"early-detection-roadmap","kind":"roadmap","name":"Early detection roadmap: organ screening → blood tests for many cancers","route":"/roadmaps/early-detection-roadmap/"},{"id":"molecular-imaging-roadmap","kind":"roadmap","name":"Molecular imaging roadmap: FDG → PSMA → FAP → antigen and immune PET","route":"/roadmaps/molecular-imaging-roadmap/"}],"technology":[{"id":"ai-compute-platforms","kind":"technology","name":"AI compute and model platforms for oncology","route":"/technologies/ai-compute-platforms/"},{"id":"aidoc-care","kind":"technology","name":"Aidoc CARE (clinical radiology foundation model)","route":"/technologies/aidoc-care/"},{"id":"breast-mri-coils-abbreviated-mri","kind":"technology","name":"Breast MRI coils and abbreviated breast MRI","route":"/technologies/breast-mri-coils-abbreviated-mri/"},{"id":"colposcopes-digital-cervical-screening","kind":"technology","name":"Colposcopes and digital cervical screening devices (DYSIS, EVA System, AVE)","route":"/technologies/colposcopes-digital-cervical-screening/"},{"id":"contrast-enhanced-mammography","kind":"technology","name":"Contrast-enhanced mammography","route":"/technologies/contrast-enhanced-mammography/"},{"id":"ct","kind":"technology","name":"CT (computed tomography)","route":"/technologies/ct/"},{"id":"ct-body-composition-sarcopenia","kind":"technology","name":"CT body composition and sarcopenia measurement","route":"/technologies/ct-body-composition-sarcopenia/"},{"id":"ct-fm","kind":"technology","name":"CT-FM (whole-body CT foundation model)","route":"/technologies/ct-fm/"},{"id":"medical-imaging-scanner-manufacturing","kind":"technology","name":"CT, MRI and PET scanner manufacturing","route":"/technologies/medical-imaging-scanner-manufacturing/"},{"id":"dermoscopy-ai","kind":"technology","name":"Dermoscopy, total-body photography & AI skin analysis","route":"/technologies/dermoscopy-ai/"},{"id":"federated-learning-medical-ai","kind":"technology","name":"Federated learning and privacy-preserving AI","route":"/technologies/federated-learning-medical-ai/"},{"id":"hand-held-ultrasound","kind":"technology","name":"Hand-held and point-of-care ultrasound","route":"/technologies/hand-held-ultrasound/"},{"id":"low-dose-ct-screening","kind":"technology","name":"Low-dose CT lung screening","route":"/technologies/low-dose-ct-screening/"},{"id":"mammography","kind":"technology","name":"Mammography & tomosynthesis","route":"/technologies/mammography/"},{"id":"medsam","kind":"technology","name":"MedSAM / SAM-Med3D (segment anything for medicine)","route":"/technologies/medsam/"},{"id":"merlin-ct","kind":"technology","name":"Merlin (Stanford abdominal CT vision-language model)","route":"/technologies/merlin-ct/"},{"id":"mirai","kind":"technology","name":"Mirai (MIT breast cancer risk from mammograms)","route":"/technologies/mirai/"},{"id":"mri","kind":"technology","name":"MRI","route":"/technologies/mri/"},{"id":"mp-mri","kind":"technology","name":"Multiparametric prostate MRI (PI-RADS)","route":"/technologies/mp-mri/"},{"id":"nhs-targeted-lung-health-check","kind":"technology","name":"NHS Targeted Lung Health Check (lung cancer screening programme)","route":"/technologies/nhs-targeted-lung-health-check/"},{"id":"pathology-foundation-model","kind":"technology","name":"Pathology & radiology foundation models","route":"/technologies/pathology-foundation-model/"},{"id":"quantitative-imaging-biomarkers","kind":"technology","name":"Quantitative imaging biomarkers (RECIST, PERCIST, SUV, ADC)","route":"/technologies/quantitative-imaging-biomarkers/"},{"id":"radfm","kind":"technology","name":"RadFM (generalist radiology foundation model)","route":"/technologies/radfm/"},{"id":"radiogenomics","kind":"technology","name":"Radiogenomics: predicting radiation sensitivity from genes","route":"/technologies/radiogenomics/"},{"id":"sybil","kind":"technology","name":"Sybil (MIT/MGH lung cancer risk from CT)","route":"/technologies/sybil/"},{"id":"tumour-doubling-time","kind":"technology","name":"Tumour volume doubling time","route":"/technologies/tumour-doubling-time/"}],"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"},{"id":"imaging","kind":"section","name":"Imaging","route":"/fronts/imaging/"}],"company":[{"id":"aidoc","kind":"company","name":"Aidoc","route":"/companies/aidoc/"},{"id":"google-health","kind":"company","name":"Google (Health, DeepMind, Verily)","route":"/companies/google-health/"},{"id":"icad","kind":"company","name":"iCAD (RadNet)","route":"/companies/icad/"},{"id":"isono-health","kind":"company","name":"iSono Health","route":"/companies/isono-health/"},{"id":"kheiron-medical-technologies","kind":"company","name":"Kheiron Medical Technologies","route":"/companies/kheiron-medical-technologies/"},{"id":"lunit","kind":"company","name":"Lunit","route":"/companies/lunit/"},{"id":"nucleo-research","kind":"company","name":"Nucleo","route":"/companies/nucleo-research/"},{"id":"optellum","kind":"company","name":"Optellum","route":"/companies/optellum/"},{"id":"screenpoint-medical","kind":"company","name":"ScreenPoint Medical","route":"/companies/screenpoint-medical/"},{"id":"therapixel","kind":"company","name":"Therapixel","route":"/companies/therapixel/"},{"id":"vara","kind":"company","name":"Vara","route":"/companies/vara/"},{"id":"volpara-health","kind":"company","name":"Volpara Health","route":"/companies/volpara-health/"}],"cancer":[{"id":"ductal-carcinoma-in-situ","kind":"cancer","name":"Ductal carcinoma in situ (DCIS)","route":"/cancers/ductal-carcinoma-in-situ/"},{"id":"breast-hr-positive","kind":"cancer","name":"HR-positive / HER2-negative breast cancer","route":"/cancers/breast-hr-positive/"},{"id":"nsclc","kind":"cancer","name":"Non-small-cell lung cancer","route":"/cancers/nsclc/"}],"term":[{"id":"body-composition","kind":"term","name":"Body composition (lean mass, fat mass, visceral fat)","route":"/terms/body-composition/"},{"id":"early-detection-term","kind":"term","name":"Early detection","route":"/terms/early-detection-term/"},{"id":"lung-rads","kind":"term","name":"Lung-RADS and nodule reporting","route":"/terms/lung-rads/"},{"id":"oncology-workforce","kind":"term","name":"Oncology workforce","route":"/terms/oncology-workforce/"},{"id":"pulmonary-nodule","kind":"term","name":"Pulmonary nodule","route":"/terms/pulmonary-nodule/"},{"id":"radiology-imaging-modality","kind":"term","name":"Radiology imaging as a data modality (CT, MRI, TCIA)","route":"/terms/radiology-imaging-modality/"},{"id":"screening","kind":"term","name":"Screening","route":"/terms/screening/"}],"person":[{"id":"constance-lehman","kind":"person","name":"Constance D. Lehman","route":"/people/constance-lehman/"},{"id":"denise-aberle","kind":"person","name":"Denise R. Aberle","route":"/people/denise-aberle/"},{"id":"kristina-lang","kind":"person","name":"Kristina Lång","route":"/people/kristina-lang/"},{"id":"laura-esserman","kind":"person","name":"Laura J. Esserman","route":"/people/laura-esserman/"},{"id":"lecia-sequist","kind":"person","name":"Lecia V. Sequist","route":"/people/lecia-sequist/"},{"id":"mark-schiffman","kind":"person","name":"Mark Schiffman","route":"/people/mark-schiffman/"},{"id":"per-hall","kind":"person","name":"Per Hall","route":"/people/per-hall/"},{"id":"regina-barzilay","kind":"person","name":"Regina Barzilay","route":"/people/regina-barzilay/"},{"id":"li-weimin","kind":"person","name":"Weimin Li","route":"/people/li-weimin/"}],"bottleneck":[{"id":"b-ai-validation","kind":"bottleneck","name":"AI that is built but not validated or deployed","route":"/bottlenecks/b-ai-validation/"},{"id":"b-workforce","kind":"bottleneck","name":"Not enough oncologists, nurses, pathologists, physicists","route":"/bottlenecks/b-workforce/"},{"id":"b-early-detection","kind":"bottleneck","name":"The hardest cancers are found late","route":"/bottlenecks/b-early-detection/"}],"idea":[{"id":"idea-data-prospective-ai-trials-fund","kind":"idea","name":"A dedicated fund for randomised trials of cancer AI with patient outcomes","route":"/ideas/idea-data-prospective-ai-trials-fund/"},{"id":"idea-fund-prevention-moonshot","kind":"idea","name":"A delivery-science moonshot for prevention we already own","route":"/ideas/idea-fund-prevention-moonshot/"},{"id":"idea-fund-federated-learning-consortium","kind":"idea","name":"A federated learning consortium of cancer centres that jointly own the models","route":"/ideas/idea-fund-federated-learning-consortium/"},{"id":"idea-prev-ldct-ai-negative-triage","kind":"idea","name":"AI clears the normal lung screening scans so radiologists read only the suspicious ones","route":"/ideas/idea-prev-ldct-ai-negative-triage/"},{"id":"idea-prev-lung-nodule-ai-discharge","kind":"idea","name":"AI malignancy scores to end repeat scans and biopsies for benign lung nodules","route":"/ideas/idea-prev-lung-nodule-ai-discharge/"},{"id":"idea-prev-pancreas-ai-prediagnostic-ct","kind":"idea","name":"AI that spots pancreatic cancer on scans taken a year before diagnosis","route":"/ideas/idea-prev-pancreas-ai-prediagnostic-ct/"},{"id":"idea-tr1-ai-central-imaging-reads","kind":"idea","name":"AI-assisted central imaging reads to cut endpoint cost and variability","route":"/ideas/idea-tr1-ai-central-imaging-reads/"},{"id":"idea-moon-continuous-ai-validation-registry","kind":"idea","name":"Continuous prospective validation for every oncology AI tool after deployment","route":"/ideas/idea-moon-continuous-ai-validation-registry/"},{"id":"idea-bio2-lean-mass-dosing","kind":"idea","name":"Dose chemotherapy by muscle mass, not body surface area","route":"/ideas/idea-bio2-lean-mass-dosing/"},{"id":"idea-prev-opportunistic-ct-ai-registry","kind":"idea","name":"Every routine CT scan checked by AI for early cancer signs, with a tracked follow-up pathway","route":"/ideas/idea-prev-opportunistic-ct-ai-registry/"},{"id":"idea-data-federated-learning-imaging","kind":"idea","name":"Federated training of pathology and radiology models across hospitals","route":"/ideas/idea-data-federated-learning-imaging/"},{"id":"idea-moon-indolence-classifiers-with-screening","kind":"idea","name":"Molecular indolence classifiers bundled with every screening programme","route":"/ideas/idea-moon-indolence-classifiers-with-screening/"},{"id":"idea-bio2-ai-sarcopenia-from-ct","kind":"idea","name":"Read muscle loss automatically from scans patients already have","route":"/ideas/idea-bio2-ai-sarcopenia-from-ct/"},{"id":"idea-data-ai-screening-endpoints","kind":"idea","name":"Require stage-shift or interval-cancer endpoints for AI in cancer screening","route":"/ideas/idea-data-ai-screening-endpoints/"},{"id":"idea-prev-mammography-ai-stepped-wedge","kind":"idea","name":"Roll out AI-supported mammography nationally as a stepped-wedge trial","route":"/ideas/idea-prev-mammography-ai-stepped-wedge/"},{"id":"idea-data-sequestered-prospective-benchmarks","kind":"idea","name":"Sequestered, prospectively collected benchmark datasets that no one can train on","route":"/ideas/idea-data-sequestered-prospective-benchmarks/"},{"id":"idea-prev-ai-mammogram-risk-intervals","kind":"idea","name":"Set each woman's mammogram interval from her last mammogram, using AI risk","route":"/ideas/idea-prev-ai-mammogram-risk-intervals/"},{"id":"idea-fund-social-impact-bonds-prevention","kind":"idea","name":"Social impact bonds for cancer prevention, repaid from avoided treatment costs","route":"/ideas/idea-fund-social-impact-bonds-prevention/"},{"id":"idea-fund-rt-planning-ai-capacity","kind":"idea","name":"Validate and reimburse AI contouring and planning to expand radiotherapy capacity","route":"/ideas/idea-fund-rt-planning-ai-capacity/"}],"paper":[{"id":"paper-screentrustcad-dembrower-lancet-digit-health-2023","kind":"paper","name":"Artificial intelligence for breast cancer detection in screening mammography in Sweden: a prospective, population-based, paired-reader, non-inferiority study (ScreenTrustCAD)","route":"/key-papers/paper-screentrustcad-dembrower-lancet-digit-health-2023/"},{"id":"paper-masai-lancet-oncol-2023","kind":"paper","name":"MASAI: AI-supported mammography screening finds more cancers with half the radiologist workload","route":"/key-papers/paper-masai-lancet-oncol-2023/"},{"id":"paper-nelson-nejm-2020","kind":"paper","name":"NELSON: volume-based CT screening reduces lung cancer deaths with fewer false alarms","route":"/key-papers/paper-nelson-nejm-2020/"}],"institution":[{"id":"iaslc","kind":"institution","name":"International Association for the Study of Lung Cancer","route":"/institutions/iaslc/"},{"id":"mhra","kind":"institution","name":"Medicines and Healthcare products Regulatory Agency","route":"/institutions/mhra/"}],"collection":[{"id":"tcia","kind":"collection","name":"The Cancer Imaging Archive (TCIA)","route":"/collections/tcia/"}],"drug":[{"id":"lunit-insight-mmg","kind":"drug","name":"Lunit INSIGHT MMG","route":"/drugs/lunit-insight-mmg/"},{"id":"kheiron-mia","kind":"drug","name":"Mia (Mammography Intelligent Assessment)","route":"/drugs/kheiron-mia/"},{"id":"optellum-virtual-nodule-clinic","kind":"drug","name":"Optellum Virtual Nodule Clinic","route":"/drugs/optellum-virtual-nodule-clinic/"},{"id":"icad-profound-ai","kind":"drug","name":"ProFound AI (iCAD)","route":"/drugs/icad-profound-ai/"},{"id":"transpara","kind":"drug","name":"Transpara","route":"/drugs/transpara/"}],"trial":[{"id":"masai","kind":"trial","name":"MASAI (Mammography Screening with Artificial Intelligence)","route":"/trials/masai/"},{"id":"screentrustcad","kind":"trial","name":"ScreenTrustCAD","route":"/trials/screentrustcad/"}]}}