MedImaging

Download Mobile App
Recent News Radiography MRI Ultrasound Nuclear Medicine General/Advanced Imaging Imaging IT Industry News

Stand-Alone AI Technology Reduces Radiologists’ Screening Mammography Workloads by 90%

By MedImaging International staff writers
Posted on 20 Dec 2021
Print article
Illustration
Illustration

The use of artificial intelligence (AI) as a stand-alone reader for digital mammography (DM) or digital breast tomosynthesis (DBT) breast screening could ease radiologists’ workload while maintaining quality, according to new research.

Researchers from the Hospital Universitario Reina Sofía (Cordova, Spain) conducted a study to retrospectively evaluate the stand-alone performance of an AI system as an independent reader of DM and DBT screening examinations. Consecutive screening-paired and independently read DM and DBT images were collected and an AI system computed a cancer risk score (range, 1–100) for the DM and DBT examinations independently. AI stand-alone performance was measured using the area under the receiver operating characteristic curve (AUC) and sensitivity and recall rate at different operating points selected to have non-inferior sensitivity compared with the human readings (non-inferiority margin, 5%). The recall rate of AI and the human readings were compared using a McNemar test.

A total of 15 999 DM and DBT examinations (113 breast cancers, including 98 screen-detected and 15 interval cancers) from 15 998 women were evaluated. AI achieved an AUC of 0.93 (95% CI: 0.89, 0.96) for DM and 0.94 (95% CI: 0.91, 0.97) for DBT. For DM, AI achieved non-inferior sensitivity as a single (58.4%; 66 of 113; 95% CI: 49.2, 67.1) or double (67.3%; 76 of 113; 95% CI: 58.2, 75.2) reader, with a reduction in recall rate (P < .001) of up to 2% (95% CI: −2.4, −1.6). For DBT, AI achieved non-inferior sensitivity as a single (77%; 87 of 113; 95% CI: 68.4, 83.8) or double (81.4%; 92 of 113; 95% CI: 73.3, 87.5) reader, but with a higher recall rate (P < .001) of up to 12.3% (95% CI: 11.7, 12.9).

The researchers concluded that AI could replace radiologists’ readings in breast screening, achieving a non-inferior sensitivity, with a lower recall rate for DM but a higher recall rate for DBM.

Related Links:
Hospital Universitario Reina Sofía 

Gold Member
Solid State Kv/Dose Multi-Sensor
AGMS-DM+
New
Color Doppler Ultrasound System
KC20
New
Ultrasound System
Voluson Signature 18
Ultrasound System
Acclarix AX9

Print article

Channels

Ultrasound

view channel
Image: CAM figures of testing images (Photo courtesy of SPJ; DOI:10.34133/research.0319)

Diagnostic System Automatically Analyzes TTE Images to Identify Congenital Heart Disease

Congenital heart disease (CHD) is one of the most prevalent congenital anomalies worldwide, presenting substantial health and financial challenges for affected patients. Early detection and treatment of... Read more

Nuclear Medicine

view channel
Image: Researchers have identified a new imaging biomarker for tumor responses to ICB therapy (Photo courtesy of 123RF)

New PET Biomarker Predicts Success of Immune Checkpoint Blockade Therapy

Immunotherapies, such as immune checkpoint blockade (ICB), have shown promising clinical results in treating melanoma, non-small cell lung cancer, and other tumor types. However, the effectiveness of these... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more