Skeletal bone age assessment is a common clinical practice to investigate endocrinology, genetic and growth disorders of children. However, clinical interpretation and bone age analyses are time-consuming, labor intensive and often subject to inter-observer variability. This advocates the need of fully automated method for bone age assessment. We propose a regression convolutional neural network (CNN) to automatically assess the pediatric bone age from hand radiograph. Our network is specifically trained to place more attention to those bone age related regions in the X-ray images. Specifically, we first adopt the attention module to process all images and generate the coarse/fine attention maps as inputs for the regression network. Then, the regression CNN follows the supervision of the dynamic attention loss during training, thus it can estimate the bone age of the hard (or “outlier”) images more accurately. The experimental results show that our method achieves an average discrepancy of 5.2-5.3 months between clinical and automatic bone age evaluations on two large datasets. In conclusion, we propose a fully automated deep learning solution to process X-ray images of the hand for bone age assessment, with the accuracy comparable to human experts but with much better efficiency.

In order to systematically evaluate the damage degree in Jinping deep tunnels during excavation, an improved SPH algorithm with good Lagrangian characteristics is introduced. By modifying the derivative of the traditional SPH kernel functions, the brittle failure processes of particles are realized. The ‘Fissure Searching Generating Method’ (FSGM) has also been used to determine the establishment of joints and the tunnel excavation parts. Based on the Jinping tunnel engineering practices, numerical models are set up, and the damage degrees of the tunnel excavation under different buried depths, joint distances, positions and inclination angles are numerically simulated, and compared with the engineering site pictures to verify the rationality. (1) Typical “V” shaped shear failure zones are observed when no joints exist in the model, and the damage degree increases with the increasing tunnel buried depth. (2) The increase of joint-tunnel distance causes the damage degree to decrease, and the failure modes between the tunnel and the joint transform from tensile to shear failure. (3) The stability of the tunnel is less affected when the joint appears in the vault, north and south arch shoulder, but the tunnel is prone to becoming unstable when the joint appears in the north and south walls. (4) Steep and gentle dips of the joints greatly influence the excavation stability of the tunnel, while the excavation damage range becomes the smallest when the joint inclination angle is 45°. (5) The improved method can be well applied to predict and evaluate surrounding rock damage in Jinping tunnels.

Semantic segmentation is essentially important to biomedical image analysis. Many recent works mainly focus on integrating the Fully Convolutional Network (FCN) architecture with sophisticated convolution implementation and deep supervision. Such complex networks need large training datasets, a requirement which is challenging for medical image analysis. In this paper, we propose to decompose the single segmentation task into three subsequent sub-tasks, including (1) pixel-wise image semantic segmentation, (2) prediction of the instance class labels of the objects within the image, and (3) classification of the scene the image belonging to. While these three sub-tasks are trained to optimize their individual loss functions at different perceptual levels, we propose to allow their interaction within the task-task context ensemble. Moreover, we propose a novel sync-regularization to penalize the deviation between the outputs of the pixel-wise semantic segmentation and the instance class prediction tasks. These effective regularizations help FCN utilize context information comprehensively and attain accurate segmentation, even though the number of images for training may be limited in many biomedical applications. We have successfully applied our framework to three diverse 2D/3D medical image datasets, including Robotic Scene Segmentation Challenge 18 (ROBOT18), Brain Tumor Segmentation Challenge 18 (BRATS18), and Retinal Fundus Glaucoma Challenge (REFUGE18). We have achieved outperformed or comparable performance in all the three challenges. Our code, typical data and trained models are available at https://github.com/xuhuaren/TDSNet .

Purpose: To explore the value of the pre-treatment MRI radiomic features in individualized prediction of the therapeutic response of carbon ion radiotherapy (CIRT) for prostate cancer patients. Patients and methods: Twenty-three patients with localized prostate cancer treated by CIRT were enrolled for analysis. Prostate tumors were manually delineated on T2-weighted (T2w) images and apparent diffusion coefficient (ADC) maps acquired before CIRT. Abundant radiomic features were extracted from the delineations, which were randomly deformed to account for delineation uncertainty. The robust features were selected and then compared between patient groups of different CIRT responses. Support vector machine (SVM) was subsequently applied to demonstrate the role of the radiomic features to predict individualized CIRT response in the way of artificial intelligence. Results: Radiomic features from ADC had significantly higher intra-correlation coefficient (ICC) (0.71±0.28) than T2w features (0.60±0.31) (p<0.01), indicating higher robustness of ADC features against delineation uncertainty. More features were excellently robust in ADC (58.2% of all the radiomic feature candidates, compared to 41.3% in T2w). By combining the excellently robust radiomic features of T2w and ADC, SVM achieved high performance to predict individualized therapeutic response of CIRT, ie, area-under-curve (AUC) = 0.88. Conclusion: Radiomic features extracted from T2w and ADC images displayed great robustness to quantify the tumor characteristics of prostate cancer and high accuracy to predict the individualized therapeutic response of CIRT. After further validation, the selected radiomic features may become potential imaging biomarkers in the management of prostate cancer through CIRT.