Cancers, Vol. 15, Pages 1922: Predicting Breast Cancer Events in Ductal Carcinoma In Situ (DCIS) Using Generative Adversarial Network Augmented Deep Learning Model

Cancers, Vol. 15, Pages 1922: Predicting Breast Cancer Events in Ductal Carcinoma In Situ (DCIS) Using Generative Adversarial Network Augmented Deep Learning Model Cancers doi: 10.3390/cancers15071922 Authors: Soumya Ghose Sanghee Cho Fiona Ginty Elizabeth McDonough Cynthia Davis Zhanpan Zhang Jhimli Mitra Adrian L. Harris Aye Aye Thike Puay Hoon Tan Yesim Gökmen-Polar Sunil S. Badve Standard clinicopathological parameters (age, growth pattern, tumor size, margin status, and grade) have been shown to have limited value in predicting recurrence in ductal carcinoma in situ (DCIS) patients. Early and accurate recurrence prediction would facilitate a more aggressive treatment policy for high-risk patients (mastectomy or adjuvant radiation therapy), and simultaneously reduce over-treatment of low-risk patients. Generative adversarial networks (GAN) are a class of DL models in which two adversarial neural networks, generator and discriminator, compete with each other to generate high quality images. In this work, we have developed a deep learning (DL) classification network that predicts breast cancer events (BCEs) in DCIS patients using hematoxylin and eosin (H & E) images. The DL classification model was trained on 67 patients using image patches from the actual DCIS cores and GAN generated image patches to predict breast cancer events (BCEs). The hold-out validation dataset (n = 66) had an AUC of 0.82. Bayesian analysis further confirme...
Source: Cancers - Category: Cancer & Oncology Authors: Tags: Article Source Type: research