A Semiautonomous Deep Learning System to Reduce False Positives in Screening Mammography.

Purpose To evaluate the ability of a semiautonomous artificial intelligence (AI) model to identify screening mammograms not suspicious for breast cancer and reduce the number of false-positive examinations. Materials and Methods The deep learning algorithm was trained using 123 248 two-dimensional digital mammograms (6161 cancers) and a retrospective study was performed on three nonoverlapping datasets of 14 831 screening mammography examinations (1026 cancers) from two U.S. institutions and one U.K. institution (2008-2017). The stand-alone performance of humans and AI was compared. Human plus AI performance was simulated to examine reductions in the cancer detection rate, number of examinations, false-positive callbacks, and benign biopsies. Metrics were adjusted to mimic the natural distribution of a screening population, and bootstrapped CIs and P values were calculated. Results Retrospective evaluation on all datasets showed minimal changes to the cancer detection rate with use of the AI device (noninferiority margin of 0.25 cancers per 1000 examinations: U.S. dataset 1, P = .02; U.S. dataset 2, P < .001; U.K. dataset, P < .001). On U.S. dataset 1 (11 592 mammograms; 101 cancers; 3810 female patients; mean age, 57.3 years ± 10.0 [SD]), the device reduced screening examinations requiring radiologist interpretation by 41.6% (95% CI: 40.6%, 42.4%; P < .001), diagnostic examinations callbacks by 31.1% (95% CI: 28.7%, 33.4%; P < .001), and benign needle biopsies by 7.4% (95% CI: 4.1%, 12.4%; P < .001). U.S. dataset 2 (1362 mammograms; 330 cancers; 1293 female patients; mean age, 55.4 years ± 10.5) was reduced by 19.5% (95% CI: 16.9%, 22.1%; P < .001), 11.9% (95% CI: 8.6%, 15.7%; P < .001), and 6.5% (95% CI: 0.0%, 19.0%; P = .08), respectively. The U.K. dataset (1877 mammograms; 595 cancers; 1491 female patients; mean age, 63.5 years ± 7.1) was reduced by 36.8% (95% CI: 34.4%, 39.7%; P < .001), 17.1% (95% CI: 5.9%, 30.1%: P < .001), and 5.9% (95% CI: 2.9%, 11.5%; P < .001), respectively. Conclusion This work demonstrates the potential of a semiautonomous breast cancer screening system to reduce false positives, unnecessary procedures, patient anxiety, and medical expenses. Keywords: Artificial Intelligence, Semiautonomous Deep Learning, Breast Cancer, Screening Mammography Supplemental material is available for this article. Published under a CC BY 4.0 license.

Mitochondrial Haplotype Alters Mammary Cancer Tumorigenicity and Metastasis in an Oncogenic Driver-Dependent Manner.

Using a novel mouse model, a mitochondrial-nuclear exchange model termed MNX, we tested the hypothesis that inherited mitochondrial haplotypes alter primary tumor latency and metastatic efficiency. Male FVB/N-Tg(MMTVneu)202Mul/J (Her2) transgenic mice were bred to female MNX mice having FVB/NJ nuclear DNA with either FVB/NJ, C57BL/6J, or BALB/cJ mtDNA. Pups receiving the C57BL/6J or BALB/cJ mitochondrial genome (i.e., females crossed with Her2 males) showed significantly (P < 0.001) longer tumor latency (262 vs. 293 vs. 225 days), fewer pulmonary metastases (5 vs. 7 vs. 15), and differences in size of lung metastases (1.2 vs. 1.4 vs. 1.0 mm diameter) compared with FVB/NJ mtDNA. Although polyoma virus middle T-driven tumors showed altered primary and metastatic profiles in previous studies, depending upon nuclear and mtDNA haplotype, the magnitude and direction of changes were not the same in the HER2-driven mammary carcinomas. Collectively, these results establish mitochondrial polymorphisms as quantitative trait loci in mammary carcinogenesis, and they implicate distinct interactions between tumor drivers and mitochondria as critical modifiers of tumorigenicity and metastasis. Cancer Res; 77(24); 6941-9. ©2017 AACR.