Improved Cancer Detection Using Artificial Intelligence: a Retrospective Evaluation of Missed Cancers on Mammography

Abstract

To determine whether cmAssist™, an artificial intelligence-based computer-aided detection (AI-CAD) algorithm, can be used to improve radiologists’ sensitivity in breast cancer screening and detection. A blinded retrospective study was performed with a panel of seven radiologists using a cancer-enriched data set from 122 patients that included 90 false-negative mammograms obtained up to 5.8 years prior to diagnosis and 32 BIRADS 1 and 2 patients with a 2-year follow-up of negative diagnosis. The mammograms were performed between February 7, 2008 (earliest) and January 8, 2016 (latest), and were all originally interpreted as negative in conjunction with R2 ImageChecker CAD, version 10.0. In this study, the readers analyzed the 122 studies before and after review of cmAssist™, an AI-CAD software for mammography. The statistical significance of our findings was evaluated using Student’s t test and bootstrap statistical analysis. There was a substantial and significant improvement in radiologist accuracy with use of cmAssist, as demonstrated in the 7.2% increase in the area-under-the-curve (AUC) of the receiver operating characteristic (ROC) curve with two-sided p value < 0.01 for the reader group. All radiologists showed a significant improvement in their cancer detection rate (CDR) with the use of cmAssist (two-sided p value = 0.030, confidence interval = 95%). The readers detected between 25 and 71% (mean 51%) of the early cancers without assistance. With cmAssist, the overall reader CDR was 41 to 76% (mean 62%). The percentage increase in CDR for the reader panel was significant, ranging from 6 to 64% (mean 27%) with the use of cmAssist. There was less than 1% increase in the readers’ false-positive recalls with use of cmAssist. With the use of cmAssist TM, there was a substantial and statistically significant improvement in radiologists’ accuracy and sensitivity for detection of cancers that were originally missed. The percentage increase in CDR for the radiologists in the reader panel ranged from 6 to 64% (mean 27%) with the use of cmAssist, with negligible increase in false-positive recalls. Electronic supplementary material The online version of this article (10.1007/s10278-019-00192-5) contains supplementary material, which is available to authorized users.

Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review

“…A large amount of data can then be fed into artificial intelligence (AI) systems (using computers to mimic human cognitive functions) and machine learning methods (using computer algorithms to perform clinical tasks without the need for explicit instructions). AI and machine learning can then help with diagnosis [ 9 , 10 ], treatment [ 11 , 12 ], and resource management [ 13 , 14 ] in the ICU. Given the dynamic nature of critically ill patients, one machine learning method called reinforcement learning (RL) is particularly suitable for ICU settings.…”

Artificial Intelligence: Is It Armageddon for Breast Radiologists?

“…However, mammograms are complex, and the high numbers (1.79 million mammograms done in 2017-18 under the National Health Service [NHS] Breast Screening Program) of exams per reader can result in inaccurate diagnosis [1,5]. The incorrect diagnosis led to double reading of mammograms in the UK and Europe [6]. When using double reading, sensitivity of mammography is increased by 5%-15% when compared with single reading [6].…”

“…The incorrect diagnosis led to double reading of mammograms in the UK and Europe [ 6 ]. When using double reading, sensitivity of mammography is increased by 5%-15% when compared with single reading [ 6 ]. Computer-aided detection (CAD) systems introduced because radiologists missed about 25% of visible cancers on mammograms due to interpretation errors [ 7 ].…”

A novel solution based on scale invariant feature transform descriptors and deep learning for the detection of suspicious regions in mammogram images

“…Reading mammograms is a time-demanding and tiring job; about 30% of cancers are missed on mammograms (false negatives), but recent tests and studies showed that computer-aided diagnosis (CAD) software for mammography allows for increase in radiologist sensitivity. [ 2 3 ] The risk of dying from breast cancer has dropped by >20%, according to International Agency for Research on Cancer scientific papers, in areas where screening mammograms programs have been conducted, and by as much as 40% among women who undergo screening mammograms regularly. [ 4 ] The objective of CAD systems is to draw radiologist attention to possible abnormalities in mammography, reducing the number of false positives and false negatives; according to latest scientific studies, computer-aided detection of breast cancer can improve the detection rate from 4.7% to 19.5% compared to radiologists.…”