Why CAD Failed in Mammography.

111 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Human-Centered Evaluation of a Deep Learning System Deployed in Clinics for the Detection of Diabetic Retinopathy (2020, background): “Even systems with widespread adoption, such as CAD in Mammography, have been shown to require a radiologist to do more work, not less, [18] and generally do not improve a radiologist’s diagnostic accuracy [12, 26].”
"Hello AI": Uncovering the Onboarding Needs of Medical Practitioners for Human-AI Collaborative Decision-Making (2019, background): “Despite the high-performing nature of these algorithms, prior work has shown that CDSSes can be difficult to successfully integrate into practice, citing a lack of HCI consideration as one of the primary reasons for failure [41, 44, 55, 76, 78].”
Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making (2019, background): “and trust: experts may resist using a system if it does not provide relevant information or capture the nuances of human thinking [23, 27, 45].”