Adding double reading with arbitration to mammography screening improves cancer detection.
Double reading with arbitration of mammograms reduces recall and increases cancer detection compared with single reading, according to a study published in the journal Radiology.
Researchers from the United Kingdom performed a retrospective analysis of 805,206 women who had undergone screening and diagnostic test at 33 breast screening centers. The centers used double reading of digital mammograms, with arbitration if there were discrepant interpretations.
The researchers used information on reader decisions, with results of follow-up tests, to explore the effect of the second reader.
The results showed the first reader recalled 4.76 percent of women (38,295 of 805,206 women, while two readers recalled 6.19 percent of women in total (49,857 of 805,206 women. However, arbitration of discordant readings reduced the recall rate to 4.08 percent.
A total of 627 cancers of 7,055 cancers detected were found by the second reader only. These additional cancers were more likely to be ductal carcinoma in situ (30.5 percent [183 of 600] vs 22 percent [1,344 of 6,114]). Additional invasive cancers were smaller (mean size, 14.2 versus 16.7 mm), had fewer involved nodes, and were likely to be lower grade.
The researchers concluded that double reading with arbitration reduces recall and increases cancer detection compared with single reading, and those detected only by the second reader were smaller, of lower grade, and had less nodal involvement.
New Study Examines Short-Term Consistency of Large Language Models in Radiology
November 22nd 2024While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
FDA Clears Updated AI Platform for Digital Breast Tomosynthesis
November 12th 2024Employing advanced deep learning convolutional neural networks, ProFound Detection Version 4.0 reportedly offers a 50 percent improvement in detecting cancer in dense breasts in comparison to the previous version of the software.