Prostate Cancer Classification Using 3D Deep Learning and Ultrasound Video Clips: A Multicenter Study

Wenjie Lou¹Peizhe Chen²Chengyi Wu³Qinghua Liu⁴Lingyan Zhou^5,6Maoliang Zhang⁷Jing Tu¹Zhengbiao Hu¹Cheng Lv⁸Jie Yang¹Xiaoyang Qi¹Xingbo Sun¹Yanhong Du¹Xueping Liu⁴Yuwang Zhou⁴Liu Yuanzhen^5,6Chen Chen^5,6,9Zhengping Wang¹Jincao Yao^10,11,12,5,6Kai Wang^1*

• ¹Affliiated Dongyang Hospital of Wenzhou Medical University, Dongyang, China
• ²College of Optical Science and Engineering, Zhejiang University, Hangzhou, Zhejiang Province, China
• ³School of Medicine, Zhejiang University, Hangzhou, China
• ⁴Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou, China
• ⁵Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou, China
• ⁶Hangzhou Institute of Medicine(HIM), Chianese Academy of Sciences, Hangzhou, China
• ⁷Dongyang Hospital of Wenzhou Medical University, Dongyang, China
• ⁸Yiwu Tianxiang Medical Oriental Hospital, Yiwu, China
• ⁹Taizhou Cancer Hospital, Taizhou, Zhejiang Province, China
• ¹⁰Department of Diagnostic Key Laboratory of Head & Neck Cancer Translational Research of Zhejiang Province, Hangzhou, China
• ¹¹Zhejiang Provincial Research Center for Cancer Intelligent Diagnosis and Molecular Technology, Hangzhou, China
• ¹²Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence, Taizhou, China

Objective: This study aimed to evaluate the effectiveness of deep-learning models using transrectal ultrasound (TRUS) video clips in predicting prostate cancer.: We manually segmented TRUS video clips from consecutive men who underwent examination with EsaoteMyLab™ Class C ultrasonic diagnostic machines between January 2021 and October 2022. The deep learning-inflated 3D ConvNet (I3D) model was internally validated using split-sample validation on the development set through cross-validation. The final performance was evaluated on two external test sets using geographic validation. We compared the results obtained from a ResNet 50 model, four ML models, and the diagnosis provided by five senior sonologists. Results: A total of 815 men (median age: 71 years; IQR: 67-77 years) were included. The development set comprised 552 men (median age: 71 years; IQR: 67-77 years), the internal test set included 93 men (median age: 71 years; IQR: 67-77 years), external test set 1 consisted of 96 men (median age: 70 years; IQR: 65-77 years), and external test set 2 had 74 men (median age: 72 years; IQR: 68-78 years). The I3D model achieved diagnostic classification AUCs greater than 0.86 in the internal test set as well as in the independent external test sets 1 and 2. Moreover, it demonstrated greater consistency in sensitivity, specificity, and accuracy compared to pathological diagnosis (kappa > 0.62, p < 0.05). It exhibited a statistically significant superior ability to classify and predict prostate cancer when compared to other AI models, and the diagnoses provided by sonologists (p<0.05).The I3D model, utilizing TRUS prostate video clips, proved to be valuable for classifying and predicting prostate cancer.