Project AURIONAI Use-Cases Research & Innovation
Healthcare

Chest X-Ray and TB Screening

CNN computer-aided detection for chest X-ray and TB screening; WHO recommended CAD for TB screening on 22 Mar 2021.

Named Models

Where this comes from
Models the research names for this use case. Research, with sources on each model record.

Who Runs It

production, 3contract signed, 1pilot, 2research, 1
Kemenkes (Ministry of Health)Kementerian Kesehatan (Kemenkes), national TB programmeCountry: IndonesiaAI-assisted portable chest X-ray for TB screening in pesantren and dense settlements; about 10,000 X-ray units to puskesmas in stages (vendor not named)Vendor: not statedproductionDate13 Aug 2026About 200,000 people screened with portable X-ray AI to 2025 (Deputy Minister, 9 June 2026); national kick-off 13 August 2026. Distinct from kemenkes-tbscreen-ai and the Harrison.ai and Qure.ai pilots unless the vendor turns out to be one of themEvidence: government statementConfidence: mediumSource: kemkes.go.id, keslan.kemkes.go.id, health.detik.com, m.antaranews.com
Qure.ai customers (not itemised)Country: globalqXRVendor: Qure.aiproductionDate–105+ countries, 5,500+ sites (vendor claim); which ASEAN countries not statedEvidence: company statementConfidence: lowSource: qure.ai
Apollo Hospitals with Google HealthCountry: IndiaGoogle screening models for TB and breast cancerVendor: GoogleproductionDate–Scaling to 3 million screeningsEvidence: company statementConfidence: lowSource: cloud.google.com
EMC HealthcareEMC HealthcareCountry: IndonesiaHarrison.ai chest X-ray solutionVendor: Harrison.aicontract signedDate–Partners to deploy, per search titles onlyEvidence: company statementConfidence: lowSource: harrison.ai
Kemenkes (Ministry of Health)Kemenkes; RS Fatmawati; RSPONCountry: IndonesiaQure.ai (qXR named on vendor site; product name not stated in article)Vendor: Qure.aipilotDate27 Feb 2025Pilot at two hospitals with central reporting and teleradiology; expansion if successful; no outcome publishedEvidence: government statementConfidence: mediumSource: metrotvnews.com, koran-jakarta.com, id.wikipedia.org, rspon.co.id
Kemenkes (Ministry of Health)Kemenkes; RSUP Dr. M. Djamil PadangCountry: IndonesiaHarrison.ai products (names not stated)Vendor: Harrison.aipilotDate9 Jul 2024MoU; clinical trials for TB screening on chest X-ray; no outcome publishedEvidence: government statementConfidence: mediumSource: kemkes.go.id, disway.id, id.wikipedia.org
Kemenkes (Ministry of Health)Kemenkes TB programme with UGM, University of Melbourne, SAPDA, YPKMPCountry: IndonesiaTBScreen.AIVendor: UGM and University of Melbourne (KONEKSI-funded)researchDate3 Aug 2026Sensitivity 83.16% reported; online version operable, offline plannedEvidence: government statementConfidence: mediumSource: antaranews.com
Where this comes from
Documented uses by named organisations. The evidence column says who made the claim.

Candidate Models

UltralyticsYOLO26lUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsUltralyticsYOLO26mUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsUltralyticsYOLO26nUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsUltralyticsYOLO26sUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsUltralyticsYOLO26xUltralytics, visionReleasedJan 2026open weightshas scoreslast 18 monthsRoboflowRF-DETR 2XLRoboflow, visionReleasedNov 2025runs on edgehas scoreslast 18 monthsRoboflowRF-DETR MRoboflow, visionReleasedNov 2025runs on edgehas scoreslast 18 monthsRoboflowRF-DETR NRoboflow, visionReleasedNov 2025runs on edgehas scoreslast 18 monthsRoboflowRF-DETR SRoboflow, visionReleasedNov 2025runs on edgehas scoreslast 18 monthsMetaSAM 3Meta, visionReleasedNov 2025open weightshas scoreslast 18 months

Showing 10 of 656. All models of this class

Where this comes from
Derived, not researched: models in the directory whose class matches a class this use case uses, excluding family records and models shut down or deprecated. Ranked by how many fit facts they meet, then by release date. Each fit fact is read from the model record.

Sources

  1. Qure AI | AI assistance for Accelerated Healthcare qure.ai https://www.qure.ai/
  2. WHO consolidated guidelines on tuberculosis: module 2: screening: systematic screening for tuberculosis disease who.int https://www.who.int/publications/i/item/9789240022676
  3. Kemenkes Manfaatkan Kecerdasan Buatan untuk Deteksi Tuberkulosis metrotvnews.com https://www.metrotvnews.com/read/K5nC7m81-kemenkes-manfaatkan-kecerdasan-buatan-untuk-deteksi-tuberkulosis
  4. Kemenkes: Teknologi TBScreen.AI mampu tingkatkan efisiensi skrining TB antaranews.com https://www.antaranews.com/berita/5678115/kemenkes-teknologi-tbscreenai-mampu-tingkatkan-efisiensi-skrining-tb

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Chest X-Ray and TB Screening", https://aurion.semai.id/usecases/hc-chest-xray-tb-screening/, records of October 2026.