• AI
  • Molecular Imaging
  • CT
  • X-Ray
  • Ultrasound
  • MRI
  • Facility Management
  • Mammography

Study Looks at Capability of AI for Detecting Overlooked Liver Metastases on CECT


An emerging artificial intelligence (AI) software reportedly detected liver metastases in 53.7 percent of cases involving missed findings by radiologists.

Artificial intelligence (AI) diagnosed liver metastases overlooked by radiologists on abdominal computed tomography (CT) in more than half of the cases, according to newly published research.

For the study, published recently in the European Journal of Radiology, researchers assessed the sensitivity of an emerging AI software (Care Advisor for Liver, co-developed by IBM Watson Health and Guerbet) in 135 patients with liver metastases for all liver lesion types, liver metastases and liver metastases overlooked by radiologists on contrast-enhanced CT (CECT).

The researchers found that the AI software concurred with radiologist findings in 92.7 percent of cases involving detected liver metastases and detected liver metastases in 53.7 percent of cases in which liver metastases were overlooked by radiologists. The AI software had an 0.48 average of false positives per patient, according to the study.

“Although this software version does not classify the detected lesions, our results have indicated its potential in reducing the number of overlooked liver metastases and providing reference information to the investigating radiologists,” wrote Yuji Nakamoto, M.D., Ph.D., a professor in the Department of Diagnostic Imaging and Nuclear Medicine at the Kyoto University Graduate School of Medicine in Japan, and colleagues.

Study Looks at Capability of AI for Detecting Overlooked Liver Metastases on CECT

Images courtesy of the European Journal of Radiology.

Overall, the study authors noted that the AI software demonstrated per-lesion sensitivity rates of 70.1 percent for all liver lesions, 70.8 percent for liver metastases and 55 percent for liver metastases overlooked by radiologists.

(Editor’s note: For related content, see “Current Perspectives on the BCLC Staging System for Hepatocellular Carcinoma” and “Could Photon Counting CT Supplant MRI for Imaging Assessment of Hepatic Steatosis?”)

Nakamoto and colleagues pointed out that the AI software failed to detect 16 percent of liver metastases diagnosed by radiologists and specifically noted a failure to diagnose liver metastases that contacted large hepatic veins.

“This leads us to believe that lesions surrounded by the liver parenchyma may be easier for the (AI) software to detect than those that are not,” suggested Nakamoto and colleagues. “Therefore, the software would not replace the radiologists. Instead, the software should be used in conjunction with the radiologists’ clinical interpretation.”

The study authors noted that the Care Advisor for Liver AI software is currently pending review by the Food and Drug Administration (FDA).

Beyond the inherent limitations of a single-center retrospective study, the researchers acknowledged a possible patient selection bias with the small heterogeneous cohort. Noting that all of the reviewed cases involved liver metastases and that the AI software does not classify benign/malignant lesions, the study authors did not assess specificity and accuracy rates of the AI modality.

Related Videos
Can Fiber Optic RealShape (FORS) Technology Provide a Viable Alternative to X-Rays for Aortic Procedures?
Does Initial CCTA Provide the Best Assessment of Stable Chest Pain?
Nina Kottler, MD, MS
The Executive Order on AI: Promising Development for Radiology or ‘HIPAA for AI’?
Practical Insights on CT and MRI Neuroimaging and Reporting for Stroke Patients
Related Content
© 2024 MJH Life Sciences

All rights reserved.