Yoko Satoh1,2, Tomoki Imokawa3, Tomoyuki Fujioka4, Mio Mori3, Emi Yamaga3, Kanae Takahashi3, Keiko Takahashi3, Takahiro Kawase3, Kazunori Kubota5, Ukihide Tateishi3, Hiroshi Onishi2. 1. Yamanashi PET Imaging Clinic, Chuo City, Yamanashi Prefecture, Japan. 2. Department of Radiology, University of Yamanashi, Chuo City, Yamanashi Prefecture, Japan. 3. Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan. 4. Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan. fjokmrad@tmd.ac.jp. 5. Department of Radiology, Dokkyo Medical University Saitama Medical Center, Koshigaya City, Saitama Prefecture, Japan.
Abstract
OBJECTIVE: This study aimed to investigate and determine the best deep learning (DL) model to predict breast cancer (BC) with dedicated breast positron emission tomography (dbPET) images. METHODS: Of the 1598 women who underwent dbPET examination between April 2015 and August 2020, a total of 618 breasts on 309 examinations for 284 women who were diagnosed with BC or non-BC were analyzed in this retrospective study. The Xception-based DL model was trained to predict BC or non-BC using dbPET images from 458 breasts of 109 BCs and 349 non-BCs, which consisted of mediallateral and craniocaudal maximum intensity projection images, respectively. It was tested using dbPET images from 160 breasts of 43 BC and 117 non-BC. Two expert radiologists and two radiology residents also interpreted them. Sensitivity, specificity, and area under the receiver operating characteristic curves (AUCs) were calculated. RESULTS: Our DL model had a sensitivity and specificity of 93% and 93%, respectively, while radiologists had a sensitivity and specificity of 77-89% and 79-100%, respectively. Diagnostic performance of our model (AUC = 0.937) tended to be superior to that of residents (AUC = 0.876 and 0.868, p = 0.073 and 0.073), although not significantly different. Moreover, no significant differences were found between the model and experts (AUC = 0.983 and 0.941, p = 0.095 and 0.907). CONCLUSIONS: Our DL model could be applied to dbPET and achieve the same diagnostic ability as that of experts.
OBJECTIVE: This study aimed to investigate and determine the best deep learning (DL) model to predict breast cancer (BC) with dedicated breast positron emission tomography (dbPET) images. METHODS: Of the 1598 women who underwent dbPET examination between April 2015 and August 2020, a total of 618 breasts on 309 examinations for 284 women who were diagnosed with BC or non-BC were analyzed in this retrospective study. The Xception-based DL model was trained to predict BC or non-BC using dbPET images from 458 breasts of 109 BCs and 349 non-BCs, which consisted of mediallateral and craniocaudal maximum intensity projection images, respectively. It was tested using dbPET images from 160 breasts of 43 BC and 117 non-BC. Two expert radiologists and two radiology residents also interpreted them. Sensitivity, specificity, and area under the receiver operating characteristic curves (AUCs) were calculated. RESULTS: Our DL model had a sensitivity and specificity of 93% and 93%, respectively, while radiologists had a sensitivity and specificity of 77-89% and 79-100%, respectively. Diagnostic performance of our model (AUC = 0.937) tended to be superior to that of residents (AUC = 0.876 and 0.868, p = 0.073 and 0.073), although not significantly different. Moreover, no significant differences were found between the model and experts (AUC = 0.983 and 0.941, p = 0.095 and 0.907). CONCLUSIONS: Our DL model could be applied to dbPET and achieve the same diagnostic ability as that of experts.