Richard Ha1, Simukayi Mutasa2, Eduardo Pascual Van Sant2, Jenika Karcich2, Christine Chin3, Michael Z Liu4, Sachin Jambawalikar4. 1. 1 Breast Imaging Section, Department of Radiology, Columbia University Medical Center, 622 W 168th St, PB-1-301, New York, NY 10032. 2. 2 Department of Radiology, Columbia University Medical Center, New York, NY. 3. 3 Division of Radiation Oncology, Columbia University Medical Center, New York, NY. 4. 4 Department of Medical Physics, Columbia University Medical Center, New York, NY.
Abstract
OBJECTIVE: The purpose of this study was to test the hypothesis that convolutional neural networks can be used to predict which patients with pure atypical ductal hyperplasia (ADH) may be safely monitored rather than undergo surgery. MATERIALS AND METHODS: A total of 298 unique images from 149 patients were used for our convolutional neural network algorithm. A total of 134 images from 67 patients with ADH that had been diagnosed by stereotactic-guided biopsy of calcifications but had not been upgraded to ductal carcinoma in situ or invasive cancer at the time of surgical excision. A total of 164 images from 82 patients with mammographic calcifications indicated that ductal carcinoma in situ was the final diagnosis. Two standard mammographic magnification views of the calcifications (a craniocaudal view and a mediolateral or lateromedial view) were used for analysis. Calcifications were segmented using an open-source software platform and images were resized to fit a bounding box of 128 × 128 pixels. A topology with 15 hidden layers was used to implement the convolutional neural network. The network architecture contained five residual layers and dropout of 0.25 after each convolution. Patients were randomly separated into a training-and-validation set (80% of patients) and a test set (20% of patients). Code was implemented using open-source software on a workstation with an open-source operating system and a graphics card. RESULTS: The AUC value was 0.86 (95% CI, ± 0.03) for the test set. Aggregate sensitivity and specificity were 84.6% (95% CI, ± 4.0%) and 88.2% (95% CI, ± 3.0%), respectively. Diagnostic accuracy was 86.7% (95% CI, ± 2.9). CONCLUSION: It is feasible to apply convolutional neural networks to distinguish pure atypical ductal hyperplasia from ductal carcinoma in situ with the use of mammographic images. A larger dataset will likely result in further improvement of our prediction model.
OBJECTIVE: The purpose of this study was to test the hypothesis that convolutional neural networks can be used to predict which patients with pure atypical ductal hyperplasia (ADH) may be safely monitored rather than undergo surgery. MATERIALS AND METHODS: A total of 298 unique images from 149 patients were used for our convolutional neural network algorithm. A total of 134 images from 67 patients with ADH that had been diagnosed by stereotactic-guided biopsy of calcifications but had not been upgraded to ductal carcinoma in situ or invasive cancer at the time of surgical excision. A total of 164 images from 82 patients with mammographic calcifications indicated that ductal carcinoma in situ was the final diagnosis. Two standard mammographic magnification views of the calcifications (a craniocaudal view and a mediolateral or lateromedial view) were used for analysis. Calcifications were segmented using an open-source software platform and images were resized to fit a bounding box of 128 × 128 pixels. A topology with 15 hidden layers was used to implement the convolutional neural network. The network architecture contained five residual layers and dropout of 0.25 after each convolution. Patients were randomly separated into a training-and-validation set (80% of patients) and a test set (20% of patients). Code was implemented using open-source software on a workstation with an open-source operating system and a graphics card. RESULTS: The AUC value was 0.86 (95% CI, ± 0.03) for the test set. Aggregate sensitivity and specificity were 84.6% (95% CI, ± 4.0%) and 88.2% (95% CI, ± 3.0%), respectively. Diagnostic accuracy was 86.7% (95% CI, ± 2.9). CONCLUSION: It is feasible to apply convolutional neural networks to distinguish pure atypical ductal hyperplasia from ductal carcinoma in situ with the use of mammographic images. A larger dataset will likely result in further improvement of our prediction model.
Entities:
Keywords:
atypical ductal hyperplasia; breast cancer; convolutional neural network; ductal carcinoma in situ; prediction
Authors: Christopher V Nguyen; Constance T Albarracin; Gary J Whitman; Adriana Lopez; Nour Sneige Journal: Ann Surg Oncol Date: 2010-10-23 Impact factor: 5.344
Authors: Eunyoung Ko; Wonshik Han; Jong Won Lee; Jihyoung Cho; Eun-Kyu Kim; So-Youn Jung; Mee Joo Kang; Woo Kyung Moon; In Ae Park; Sung-Won Kim; Ku Sang Kim; Eun Sook Lee; Kyu Hong Min; Seok Won Kim; Dong-Young Noh Journal: Breast Cancer Res Treat Date: 2007-12-04 Impact factor: 4.872
Authors: Richard Ha; Peter Chang; Eralda Mema; Simukayi Mutasa; Jenika Karcich; Ralph T Wynn; Michael Z Liu; Sachin Jambawalikar Journal: J Digit Imaging Date: 2019-02 Impact factor: 4.056
Authors: Simukayi Mutasa; Peter Chang; John Nemer; Eduardo Pascual Van Sant; Mary Sun; Alison McIlvride; Maham Siddique; Richard Ha Journal: Clin Breast Cancer Date: 2020-06-07 Impact factor: 3.225
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
Authors: Roberto Lo Gullo; Kerri Vincenti; Carolina Rossi Saccarelli; Peter Gibbs; Michael J Fox; Isaac Daimiel; Danny F Martinez; Maxine S Jochelson; Elizabeth A Morris; Jeffrey S Reiner; Katja Pinker Journal: Breast Cancer Res Treat Date: 2021-01-20 Impact factor: 4.872