Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study

Abstract

Purpose: To study the feasibility of automatically identifying normal digital mammography (DM) exams with artificial intelligence (AI) to reduce the breast cancer screening reading workload.

Methods and materials: A total of 2652 DM exams (653 cancer) and interpretations by 101 radiologists were gathered from nine previously performed multi-reader multi-case receiver operating characteristic (MRMC ROC) studies. An AI system was used to obtain a score between 1 and 10 for each exam, representing the likelihood of cancer present. Using all AI scores between 1 and 9 as possible thresholds, the exams were divided into groups of low- and high likelihood of cancer present. It was assumed that, under the pre-selection scenario, only the high-likelihood group would be read by radiologists, while all low-likelihood exams would be reported as normal. The area under the reader-averaged ROC curve (AUC) was calculated for the original evaluations and for the pre-selection scenarios and compared using a non-inferiority hypothesis.

Results: Setting the low/high-likelihood threshold at an AI score of 5 (high likelihood > 5) results in a trade-off of approximately halving (- 47%) the workload to be read by radiologists while excluding 7% of true-positive exams. Using an AI score of 2 as threshold yields a workload reduction of 17% while only excluding 1% of true-positive exams. Pre-selection did not change the average AUC of radiologists (inferior 95% CI > - 0.05) for any threshold except at the extreme AI score of 9.

Conclusion: It is possible to automatically pre-select exams using AI to significantly reduce the breast cancer screening reading workload.

Key points: • There is potential to use artificial intelligence to automatically reduce the breast cancer screening reading workload by excluding exams with a low likelihood of cancer. • The exclusion of exams with the lowest likelihood of cancer in screening might not change radiologists' breast cancer detection performance. • When excluding exams with the lowest likelihood of cancer, the decrease in true-positive recalls would be balanced by a simultaneous reduction in false-positive recalls.

Keywords: Artificial intelligence; Breast cancer; Deep learning; Mammography; Screening.

Fig. 1

Distribution of normal (a), cancer (b), and benign exams (c) as a function of AI score, representing the likelihood of cancer present (1–10, 10 means high likelihood of cancer present). The contribution of each dataset to the overall percentage of exams is shown

Fig. 2

An example of the nine exams in our study that contained cancer but were assigned an AI score of 1 or 2, the lowest cancer-present likelihood categories. None of the 6 radiologists recalled this exam during the original MRMC study (read without priors), suggesting that the cancer visibility with mammography is poor in these exams (and in fact, the cancer may have been detected by other means)

Fig. 3

Proportion (%) of exams that would be excluded from the final sample to be evaluated by the radiologists, using all possible AI scores as thresholds values for pre-selection for reading

Fig. 4

ROC curves (a) and change (b) in AUC values of the average of radiologists in the original population, as well as in all possible pre-selected populations (using all possible AI scores as threshold values for pre-selection for reading; if the case is not pre-selected, the radiologist score is converted to the lowest possible cancer suspicion score for the MRMC study). 95% confidence intervals are Bonferroni-corrected