Richard Ha1, Peter Chang2, Jenika Karcich3, Simukayi Mutasa3, Eduardo Pascual Van Sant4, Michael Z Liu5, Sachin Jambawalikar5. 1. Research and Education, Breast Imaging Section, Department of Radiology, Columbia University Medical Center, 622 West 168th Street, PB-1-301, New York, NY 10032. Electronic address: rh2616@columbia.edu. 2. UC San Francisco Medical Center, Department of Radiology, 505 Parnassus Avenue, San Francisco, CA 94143. 3. Department of Radiology, Columbia University Medical Center, New York, New York 10032. 4. Columbia University College of Physicians and Surgeons, New York, New York 10032. 5. Department of Medical Physics, Columbia University Medical Center, New York, New York 10032-3784.
Abstract
RATIONALE AND OBJECTIVES: We propose a novel convolutional neural network derived pixel-wise breast cancer risk model using mammographic dataset. MATERIALS AND METHODS: An institutional review board approved retrospective case-control study of 1474 mammographic images was performed in average risk women. First, 210 patients with new incidence of breast cancer were identified. Mammograms from these patients prior to developing breast cancer were identified and made up the case group [420 bilateral craniocaudal mammograms]. The control group consisted of 527 patients without breast cancer from the same time period. Prior mammograms from these patients made up the control group [1054 bilateral craniocaudal mammograms]. A convolutional neural network (CNN) architecture was designed for pixel-wise breast cancer risk prediction. Briefly, each mammogram was normalized as a map of z-scores and resized to an input image size of 256 × 256. Then a contracting and expanding fully convolutional CNN architecture was composed entirely of 3 × 3 convolutions, a total of four strided convolutions instead of pooling layers, and symmetric residual connections. L2 regularization and augmentation methods were implemented to prevent overfitting. Cases were separated into training (80%) and test sets (20%). A 5-fold cross validation was performed. Software code was written in Python using the TensorFlow module on a Linux workstation with NVIDIA GTX 1070 Pascal GPU. RESULTS: The average age of patients between the case and the control groups was not statistically different [case: 57.4years (SD, 10.4) and control: 58.2years (SD, 10.9), p = 0.33]. Breast Density (BD) was significantly higher in the case group [2.39 (SD, 0.7)] than the control group [1.98 (SD, 0.75), p < 0.0001]. On multivariate logistic regression analysis, both CNN pixel-wise mammographic risk model and BD were significant independent predictors of breast cancer risk (p < 0.0001). The CNN risk model showed greater predictive potential [OR = 4.42 (95% CI, 3.4-5.7] compared to BD [OR = 1.67 (95% CI, 1.4-1.9). The CNN risk model achieved an overall accuracy of 72% (95%CI, 69.8-74.4) in predicting patients in the case group. CONCLUSION: Novel pixel-wise mammographic breast evaluation using a CNN architecture can stratify breast cancer risk, independent of the BD. Larger dataset will likely improve our model.
RATIONALE AND OBJECTIVES: We propose a novel convolutional neural network derived pixel-wise breast cancer risk model using mammographic dataset. MATERIALS AND METHODS: An institutional review board approved retrospective case-control study of 1474 mammographic images was performed in average risk women. First, 210 patients with new incidence of breast cancer were identified. Mammograms from these patients prior to developing breast cancer were identified and made up the case group [420 bilateral craniocaudal mammograms]. The control group consisted of 527 patients without breast cancer from the same time period. Prior mammograms from these patients made up the control group [1054 bilateral craniocaudal mammograms]. A convolutional neural network (CNN) architecture was designed for pixel-wise breast cancer risk prediction. Briefly, each mammogram was normalized as a map of z-scores and resized to an input image size of 256 × 256. Then a contracting and expanding fully convolutional CNN architecture was composed entirely of 3 × 3 convolutions, a total of four strided convolutions instead of pooling layers, and symmetric residual connections. L2 regularization and augmentation methods were implemented to prevent overfitting. Cases were separated into training (80%) and test sets (20%). A 5-fold cross validation was performed. Software code was written in Python using the TensorFlow module on a Linux workstation with NVIDIA GTX 1070 Pascal GPU. RESULTS: The average age of patients between the case and the control groups was not statistically different [case: 57.4years (SD, 10.4) and control: 58.2years (SD, 10.9), p = 0.33]. Breast Density (BD) was significantly higher in the case group [2.39 (SD, 0.7)] than the control group [1.98 (SD, 0.75), p < 0.0001]. On multivariate logistic regression analysis, both CNN pixel-wise mammographic risk model and BD were significant independent predictors of breast cancer risk (p < 0.0001). The CNN risk model showed greater predictive potential [OR = 4.42 (95% CI, 3.4-5.7] compared to BD [OR = 1.67 (95% CI, 1.4-1.9). The CNN risk model achieved an overall accuracy of 72% (95%CI, 69.8-74.4) in predicting patients in the case group. CONCLUSION: Novel pixel-wise mammographic breast evaluation using a CNN architecture can stratify breast cancer risk, independent of the BD. Larger dataset will likely improve our model.
Authors: E A Ooms; H M Zonderland; M J C Eijkemans; M Kriege; B Mahdavian Delavary; C W Burger; A C Ansink Journal: Breast Date: 2007-12 Impact factor: 4.380
Authors: Kala Visvanathan; Patricia Hurley; Elissa Bantug; Powel Brown; Nananda F Col; Jack Cuzick; Nancy E Davidson; Andrea Decensi; Carol Fabian; Leslie Ford; Judy Garber; Maria Katapodi; Barnett Kramer; Monica Morrow; Barbara Parker; Carolyn Runowicz; Victor G Vogel; James L Wade; Scott M Lippman Journal: J Clin Oncol Date: 2013-07-08 Impact factor: 44.544
Authors: N F Boyd; J W Byng; R A Jong; E K Fishell; L E Little; A B Miller; G A Lockwood; D L Tritchler; M J Yaffe Journal: J Natl Cancer Inst Date: 1995-05-03 Impact factor: 13.506
Authors: Julia E McGuinness; Vicky Ro; Simukayi Mutasa; Samuel Pan; Jianhua Hu; Meghna S Trivedi; Melissa K Accordino; Kevin Kalinsky; Dawn L Hershman; Richard S Ha; Katherine D Crew Journal: Breast Cancer Res Treat Date: 2022-05-16 Impact factor: 4.872
Authors: Frederik Abel; Anna Landsmann; Patryk Hejduk; Carlotta Ruppert; Karol Borkowski; Alexander Ciritsis; Cristina Rossi; Andreas Boss Journal: Diagnostics (Basel) Date: 2022-05-29
Authors: Haley Manley; Simukayi Mutasa; Peter Chang; Elise Desperito; Katherine Crew; Richard Ha Journal: Clin Breast Cancer Date: 2020-11-17 Impact factor: 3.225