Influence of computer-aided detection on performance of screening mammography.

By J. Fenton, S. Taplin, P. Carney, L. Abraham, E. Sickles, C. D'Orsi, E. Berns, G. Cutter, R. Hendrick, W. Barlow and 1 more. New England Journal of Medicine, 2007

602 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Oncology, Pulmonary and Respiratory Medicine

View Paper: https://www.semanticscholar.org/paper/32f2930072e0db7cf1ef0ea821c304767d4be845

How researchers see this paper

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

In Artificial Intelligence

In Pulmonary and Respiratory Medicine

Citations in the corpus

Deep Learning to Improve Breast Cancer Detection on Screening Mammography (2017, background): “Unfortunately, data suggests that commercial CAD systems have not led to significant improvement in performance [5–7] and progress has stagnated in the past decade.”
Computer-Aided Detection and Diagnosis of Breast Cancer With Mammography: Recent Advances (2009, unknown): “and others showing no improvement [152].”
Overview of artificial intelligence in medicine (2019, unknown): “In addition, the false‐positive diagnoses may distract the radiologist resulting in unnecessary work‐ups.[7,8] As suggested by a study,[6] AI could provide substantial aid in radiology by not only labeling abnormal exams but also by identifying quick negative exams in computed tomographies, X‐rays, ”
Deep Learning in Medical Imaging: General Overview (2017, background): “In particular, CAD systems were found to generate more false positives than human readers, which led to a greater assessment time and additional biopsies (2).”
A review of automatic mass detection and segmentation in mammographic images (2010, background): “These are only two examples of a still open debate in the medical imaging field (Gur et al., 2004; Nishikawa and Kallergi, 2006; Fenton et al., 2007).”
Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration (2018, background): “However, even the effectiveness of that has been controversial with some studies supporting the benefits(23) and others questioning the utility.(24) Importantly, most clinical CAD systems are based on traditional computer vision techniques and do not utilize deep learning.”
Detection of Breast Cancer with Mammography: Effect of an Artificial Intelligence Support System. (2019, background): “Although some studies indicated that single reading plus CAD could be an alternative to double reading (8–11), few, if any, have identified the actual benefit of using single reading plus CAD versus single reading alone (ie, the actual benefit on radiologists’ performance in screening) (12).”
The Automated Learning of Deep Features for Breast Mass Classification from Mammograms (2016, unknown): “, masses and micro-calcifications) [2].”
Deep Learning and Structured Prediction for the Segmentation of Mass in Mammograms (2015, background): “Despite the development of mass segmentation systems for mammograms, they are still not widely used in clinical practice because they can reduce the accuracy of radiologists [4].”
Computer-Aided Diagnosis in the Era of Deep Learning (2020, background): “Fenton et al. 60 observed a 30% increase in the recall rate and 4.5% gain in cancer detection sensitivity, although they found in a follow-up study 61 that the increase in recall rate decreased to 6% after some time post CAD implementation but the gain in sensitivity also decreased to 1.8%.”
Overconfidence as a cause of diagnostic error in medicine. (2008, methodology): “In the area of computer-assisted mammography interpretation, a randomized trial showed no difference in cancer detection but an increase in false-positives with the use of the software compared with unaided interpretation by radiologists.(195) It is certainly possible that technical improvements hav”
Stand-Alone Artificial Intelligence for Breast Cancer Detection in Mammography: Comparison With 101 Radiologists. (2019, background): “Unfortunately, no studies to date have found that traditional computer-aided detection systems directly improve screening performance or cost-effectiveness, mainly because of a low specificity (13,14).”