Daiju Ueda1, Akira Yamamoto2, Tsutomu Takashima3, Naoyoshi Onoda3, Satoru Noda3, Shinichiro Kashiwagi3, Tamami Morisaki3, Shinichi Tsutsumi4, Takashi Honjo2, Akitoshi Shimazaki2, Takuya Goto2, Yukio Miki2. 1. Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka City University, 1-4-3 Asahi-machi, Abeno-ku, Osaka, 545-8585, Japan. ai.labo.ocu@gmail.com. 2. Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka City University, 1-4-3 Asahi-machi, Abeno-ku, Osaka, 545-8585, Japan. 3. Department of Breast and Endocrine Surgery, Graduate School of Medicine, Osaka City University, 1-4-3 Asahi-machi, Abeno-ku, Osaka, 545-8585, Japan. 4. Department of Radiology, Osaka Prefectural Hospital Organization Osaka Habikino Hospital, 3-7-1 Habikino, Habikino city, Osaka, 583-8588, Japan.
Abstract
PURPOSE: To demonstrate how artificial intelligence (AI) can expand radiologists' capacity, we visualized the features of invasive ductal carcinomas (IDCs) that our algorithm, developed and validated for basic pathological classification on mammograms, had focused on. MATERIALS AND METHODS: IDC datasets were built using mammograms from patients diagnosed with IDCs from January 2006 to December 2017. The developing dataset was used to train and validate a VGG-16 deep learning (DL) network. The true positives (TPs) and accuracy of the algorithm were externally evaluated using the test dataset. A visualization technique was applied to the algorithm to determine which malignant findings on mammograms were revealed. RESULTS: The datasets were split into a developing dataset (988 images) and a test dataset (131 images). The proposed algorithm diagnosed 62 TPs with an accuracy of 0.61-0.70. The visualization of features on the mammograms revealed that the tubule forming, solid, and scirrhous types of IDCs exhibited visible features on the surroundings, corners of the masses, and architectural distortions, respectively. CONCLUSION: We successfully showed that features isolated by a DL-based algorithm trained to classify IDCs were indeed those known to be associated with each pathology. Thus, using AI can expand the capacity of radiologists through the discovery of previously unknown findings.
PURPOSE: To demonstrate how artificial intelligence (AI) can expand radiologists' capacity, we visualized the features of invasive ductal carcinomas (IDCs) that our algorithm, developed and validated for basic pathological classification on mammograms, had focused on. MATERIALS AND METHODS: IDC datasets were built using mammograms from patients diagnosed with IDCs from January 2006 to December 2017. The developing dataset was used to train and validate a VGG-16 deep learning (DL) network. The true positives (TPs) and accuracy of the algorithm were externally evaluated using the test dataset. A visualization technique was applied to the algorithm to determine which malignant findings on mammograms were revealed. RESULTS: The datasets were split into a developing dataset (988 images) and a test dataset (131 images). The proposed algorithm diagnosed 62 TPs with an accuracy of 0.61-0.70. The visualization of features on the mammograms revealed that the tubule forming, solid, and scirrhous types of IDCs exhibited visible features on the surroundings, corners of the masses, and architectural distortions, respectively. CONCLUSION: We successfully showed that features isolated by a DL-based algorithm trained to classify IDCs were indeed those known to be associated with each pathology. Thus, using AI can expand the capacity of radiologists through the discovery of previously unknown findings.
Authors: David Silver; Aja Huang; Chris J Maddison; Arthur Guez; Laurent Sifre; George van den Driessche; Julian Schrittwieser; Ioannis Antonoglou; Veda Panneershelvam; Marc Lanctot; Sander Dieleman; Dominik Grewe; John Nham; Nal Kalchbrenner; Ilya Sutskever; Timothy Lillicrap; Madeleine Leach; Koray Kavukcuoglu; Thore Graepel; Demis Hassabis Journal: Nature Date: 2016-01-28 Impact factor: 49.962