基于级联卷积神经网络的前列腺磁共振图像分类

针对深度学习训练成本高,以及基于磁共振图像的前列腺癌临床诊断需要大量医学常识且极为耗时的问题,本文提出了一种基于级联卷积神经网络（Convolutional Neural Network,CNN）和磁共振图像的前列腺癌（Prostate Cancer,PCa）自动分类诊断方法,该网络以Faster-RCNN作为前网络,对前列腺区域进行提取分割,用于排除前列腺附近组织器官的干扰;以基于ResNet改进的网络结构CNN40_bottleneck作为后网络,用于对前列腺区域病变进行分类.后网络由瓶颈结构串联组成,其中使用批量标准化（Batch Normalization,BN）、全局平均池化（Global Average Pooling,GAP）进行优化.实验结果证明,本文方法对前列腺癌诊断结果较好,而且缩减了训练时间和参数量,有效降低了训练成本.     

Investigating the Role of Obesity in Prostate Cancer and Identifying Biomarkers for Drug Discovery: Systems Biology and Deep Learning Approaches

Prostate cancer (PCa) is the second most frequently diagnosed cancer for men and is viewed as the fifth leading cause of death worldwide. The body mass index (BMI) is taken as a vital criterion to elucidate the association between obesity and PCa. In this study, systematic methods are employed to investigate how obesity influences the noncutaneous malignancies of PCa. By comparing the core signaling pathways of lean and obese patients with PCa, we are able to investigate the relationships between obesity and pathogenic mechanisms and identify significant biomarkers as drug targets for drug discovery. Regarding drug design specifications, we take drug–target interaction, drug regulation ability, and drug toxicity into account. One deep neural network (DNN)-based drug–target interaction (DTI) model is trained in advance for predicting drug candidates based on the identified biomarkers. In terms of the application of the DNN-based DTI model and the consideration of drug design specifications, we suggest two potential multiple-molecule drugs to prevent PCa (covering lean and obese PCa) and obesity-specific PCa, respectively. The proposed multiple-molecule drugs (apigenin, digoxin, and orlistat) not only help to prevent PCa, suppressing malignant metastasis, but also result in lower production of fatty acids and cholesterol, especially for obesity-specific PCa.     

Analysis of Pros and Cons in Using [68Ga]Ga-PSMA-11 and [18F]PSMA-1007: Production,Costs, and PET/CT Applications in Patients with Prostate Cancer

The aim of this work is to compare [⁶⁸Ga]Ga-PSMA-11 and [¹⁸F]PSMA-1007 PET/CT as imaging agents in patients with prostate cancer (PCa). Comparisons were made by evaluating times and costs of the radiolabeling process, imaging features including pharmacokinetics, and impact on patient management. The analysis of advantages and drawbacks of both radioligands might help to make a better choice based on firm data. For [⁶⁸Ga]Ga-PSMA-11, the radiochemical yield (RCY) using a low starting activity (L, average activity of 596.55 ± 37.97 MBq) was of 80.98 ± 0.05%, while using a high one (H, average activity of 1436.27 ± 68.68 MBq), the RCY was 71.48 ± 0.04%. Thus, increased starting activities of [⁶⁸Ga]-chloride negatively influenced the RCY. A similar scenario occurred for [¹⁸F]PSMA-1007. The rate of detection of PCa lesions by Positron Emission Tomography/Computed Tomography (PET/CT) was similar for both radioligands, while their distribution in normal organs significantly differed. Furthermore, similar patterns of biodistribution were found among [¹⁸F]PSMA-1007, [⁶⁸Ga]Ga-PSMA-11, and [¹⁷⁷Lu]Lu-PSMA-617, the most used agent for RLT. Moreover, the analysis of economical aspects for each single batch of production corrected for the number of allowed PET/CT examinations suggested major advantages of [¹⁸F]PSMA-1007 compared with [⁶⁸Ga]Ga-PSMA-11. Data from this study should support the proper choice in the selection of the PSMA PET radioligand to use on the basis of the cases to study.