Background: Convolutional neural networks (CNNs) have been extensively applied to two-dimensional (2D) medical image segmentation, yielding excellent performance. However, their application to three-dimensional (3D) nodule segmentation remains a challenge.Methods: In this study, we propose a multi-view secondary input residual (MV-SIR) convolutional neural network model for 3D lung nodule segmentation using the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset of chest computed tomography (CT) images. Lung nodule cubes are prepared from the sample CT images. Further, from the axial, coronal, and sagittal perspectives, multi-view patches are generated with randomly selected voxels in the lung nodule cubes as centers. Our model consists of six submodels, which enable learning of 3D lung nodules sliced into three views of features; each submodel extracts voxel heterogeneity and shape heterogeneity features. We convert the segmentation of 3D lung nodules into voxel classification by inputting the multi-view patches into the model and determine whether the voxel points belong to the nodule. The structure of the secondary input residual submodel comprises a residual block followed by a secondary input module. We integrate the six submodels to classify whether voxel points belong to nodules, and then reconstruct the segmentation image.Results: The results of tests conducted using our model and comparison with other existing CNN models indicate that the MV-SIR model achieves excellent results in the 3D segmentation of pulmonary nodules, with a Dice coefficient of 0.926 and an average surface distance of 0.072.Conclusion: our MV-SIR model can accurately perform 3D segmentation of lung nodules with the same segmentation accuracy as the U-net model.

Background: Bone was the most common site of metastasis in prostate cancer(PCa) patients and was correlated with poor prognosis and increasing economicalburden. Studies were limited on the prognostic prediction for metastatic PCapatients with the assistance of neural network. Methods: Four convolutional neural network (CNN) models were developed andevaluated to predict overall survival (OS) of PCa patients with bone metastasis.All the CNN models were first trained with 64 samples and evaluated with 10samples, two models used only bone scan images and two models used both bonescan images and clinical parameters (CPs). Predictions of the best models werecompared with those of two urology surgeons on 20 test samples. Results: Our best models could predict OS of PCa patients with bone metastasiswith AUC = 0.8022 by using only bone scan images and AUC = 0.8132 by usingboth bone scan image and CPs on 20 test samples. When the sensitivities(specificities) set equal to average level of urology surgeons, their specificities(sensitivities) were 0%(7.2%) and 30.77%(7.7%) higher, which showedsignificant advantages of CNN models. Conclusion: The CNN models were suitable to predict OS in PCa patients withbone metastasis using bone scan images and CPs. Our models showed betterperformance in terms of accuracy and stability than urology surgeons. Keywords: Bone Metastasis; Bone Scan; Convolutional Neural Network;Prostate Cancer; Overall Survival