Breast Cancer Induced Bone Osteolysis Prediction Using Temporal Variational Autoencoders

作     者：Wei Xiong Neil Yeung Shubo Wang Haofu Liao Liyun Wang Jiebo Luo 

作者机构：Department of Computer ScienceUniversity of RochesterRochesterUSA Department of Mechanical EngineeringUniversity of DelawareUSA Amazon Web ServicesUSA 

出 版 物：《Biomedical Engineering Frontiers》 (生物医学工程前沿（英文）)

年 卷 期：2022年第3卷第1期

页      面：116-125页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

基　　金：supported by the National Institutes of Health (R01AR054385 to L.Wang) supported by the National Science Foundation (1704337 to J.Luo) 

主　　题：Breast prediction utilize 

摘      要：Objective and Impact *** adopt a deep learning model for bone osteolysis prediction on computed tomography(CT)images of murine breast cancer bone *** the bone CT scans at previous time steps,the model incorporates the bone-cancer interactions learned from the sequential images and generates future CT *** ability of predicting the development of bone lesions in cancer-invading bones can assist in assessing the risk of impending fractures and choosing proper treatments in breast cancer bone *** cancer often metastasizes to bone,causes osteolytic lesions,and results in skeletal-related events(SREs)including severe pain and even fatal *** current imaging techniques can detect macroscopic bone lesions,predicting the occurrence and progression of bone lesions remains a *** adopt a temporal variational autoencoder(T-VAE)model that utilizes a combination of variational autoencoders and long short-term memory networks to predict bone lesion emergence on our micro-CT dataset containing sequential images of murine *** the CT scans of murine tibiae at early weeks,our model can learn the distribution of their future states from *** test our model against other deep learning-based prediction models on the bone lesion progression prediction *** model produces much more accurate predictions than existing models under various evaluation *** develop a deep learning framework that can accurately predict and visualize the progression of osteolytic bone *** will assist in planning and evaluating treatment strategies to prevent SREs in breast cancer patients.