Malignancy Detection on Mammography Using Dual Deep Convolutional Neural Networks and Genetically Discovered False Color Input Enhancement
- 815 Downloads
Breast cancer is the most prevalent malignancy in the US and the third highest cause of cancer-related mortality worldwide. Regular mammography screening has been attributed with doubling the rate of early cancer detection over the past three decades, yet estimates of mammographic accuracy in the hands of experienced radiologists remain suboptimal with sensitivity ranging from 62 to 87% and specificity from 75 to 91%. Advances in machine learning (ML) in recent years have demonstrated capabilities of image analysis which often surpass those of human observers. Here we present two novel techniques to address inherent challenges in the application of ML to the domain of mammography. We describe the use of genetic search of image enhancement methods, leading us to the use of a novel form of false color enhancement through contrast limited adaptive histogram equalization (CLAHE), as a method to optimize mammographic feature representation. We also utilize dual deep convolutional neural networks at different scales, for classification of full mammogram images and derivative patches combined with a random forest gating network as a novel architectural solution capable of discerning malignancy with a specificity of 0.91 and a specificity of 0.80. To our knowledge, this represents the first automatic stand-alone mammography malignancy detection algorithm with sensitivity and specificity performance similar to that of expert radiologists.
KeywordsDeep learning Machine learning Convolutional neural networks Mammography
Compliance with Ethical Standards
Conflicts of Interest
Philip Teare, Eyal Toledano, and Eldad Elnekave are employees of Zebra Medical Vision.
Oshra Benzaquen has no conflicts of interest to disclose.
- 1.American Cancer Society: Cancer Facts & Figures 2015. Cancer Facts Fig 2015:1–9, 2015Google Scholar
- 8.Kerlikowske K, Hubbard RA, Miglioretti DL, Geller BM, Yankaskas BC, Lehman CD, Taplin SH, Sickles EA: Comparative effectiveness of digital versus film-screen mammography in community practice in the United States: A cohort study. Ann. Intern. Med. 155(8):493–502, 2011CrossRefPubMedPubMedCentralGoogle Scholar
- 12.M Heath, K Bowyer, D Kopans, R Moore, P Kegelmeyer (2001) “The digital database for screening mammography,” Proc. Fifth Int. Work. Digit. Mammogr., pp. 212–218Google Scholar
- 14.J Arevalo, FA González, R Ramos-Pollán, JL Oliveira, MA Guevara Lopez (2015) “Representation learning for mammography mass lesion classification with convolutional neural networks,” Computer Methods and Programs in BiomedicineGoogle Scholar
- 15.Ho, Tin Kam (1995). Random Decision Forests (PDF). Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, 14–16 August 1995Google Scholar
- 16.J Deng, W Dong, R Socher, L-J Li, K Li, L Fei-Fei (2009) “ImageNet: A large-scale hierarchical image database,” in 2009 I.E. Conference on Computer Vision and Pattern Recognition, pp. 248–255Google Scholar
- 17.Rafferty EA, Park JM, Philpotts LE, Poplack SP, Sumkin JH, Halpern EF, Niklason LT: Assessing radiologist performance using combined digital mammography and breast tomosynthesis compared with digital mammography alone: results of a multicenter, multireader trial. Radiology 266(1):104–113, 2013CrossRefPubMedPubMedCentralGoogle Scholar
- 18.Skaane P, Bandos AI, Gullien R, Eben EB, Ekseth U, Haakenaasen U, Izadi M, Jebsen IN, Jahr G, Krager M, Niklason LT, Hofvind S, Gur D: Comparison of digital mammography alone and digital mammography plus tomosynthesis in a population-based screening program. Radiology 267(1):47–56, 2013CrossRefPubMedGoogle Scholar
- 19.Lee CI, Cevik M, Alagoz O, Sprague BL, Tosteson ANA, Miglioretti DL, Kerlikowske K, Stout NK, Jarvik JG, Ramsey SD, Lehman CD: Comparative effectiveness of combined digital mammography and tomosynthesis screening for women with dense breasts. Radiology 274(3):772–780, 2015CrossRefPubMedGoogle Scholar
- 20.Berg WA, Blume JD, Cormack JB, Mendelson EB, Lehrer D, Böhm-Vélez M, Pisano ED, Jong RA, Evans WP, Morton MJ, Mahoney MC, Larsen LH, Barr RG, Farria DM, Marques HS, Boparai K, ACRIN 6666 Investigators: Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer. JAMA 299(18):2151–2163, 2008CrossRefPubMedPubMedCentralGoogle Scholar
- 22.CK Kuhl, K Strobel, H Bieling, C Leutner, HH Schild, S Schrading (2017) “Supplemental Breast MR Imaging Screening of Women with Average Risk of Breast Cancer,” Radiology, p. 161444Google Scholar