The wide applications of X-ray computed tomography (CT) bring low dose CT (LDCT) into a clinical prerequisite. But reducing radiation exposure in CT often leads to significantly increased noise and artifacts, which might lower the judgement accuracy of radiologists. In this paper, we put forward a domain progressive 3D residual convolution network (DP-ResNet) for LDCT imaging procedure which contains sinogram domain network (SD-net), filtered back projection (FBP) and image domain network (ID-net) three stages. Though both based on the residual network structure, the SD-net and ID-net provide complementary effect on improving the final LDCT quality. Experimental results with both simulated and real projection data show that this domain progressive deep learning network achieves significantly improved performance by combing the network processing in the two domains.

Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this paper, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments.

Cardiovascular disease is a major global public health problem, and intelligent diagnostic approaches play an increasingly important role in the analysis of electrocardiograms (ECGs). Convenient wearable ECG devices enable the detection of transient arrhythmias and improve patient health by making it possible to seek intervention during continuous monitoring. We collected 658,486 wearable 12-lead ECGs, among which 164,538 were annotated, and the remaining 493,948 were without diagnostic. We present four data augmentation operations and a self-supervised learning classification framework that can recognize 60 ECG diagnostic terms. Our model achieves an average area under the receiver-operating characteristic curve (AUROC) and average F1 score on the offline test of 0.975 and 0.575. The average sensitivity, specificity and F1-score during the 2-month online test are 0.736, 0.954 and 0.468, respectively. This approach offers real-time intelligent diagnosis, and detects abnormal segments in long-term ECG monitoring in the clinical setting for further diagnosis by cardiologists.

Accurate and automatic segmentation of individual tooth is critical for computer-aided analysis towards clinical decision support and treatment planning. Three-dimensional reconstruction of individual tooth after the segmentation also plays an important role in simulation in digital orthodontics. However, it is difficult to automatically segment individual tooth in cone beam computed tomography (CBCT) images due to the blurring boundaries of neighboring teeth and the similar intensities between teeth and mandible bone. In this work, we propose the use of a multi-task 3D fully convolutional network (FCN) and marker-controlled watershed transform (MWT) to segment individual tooth. The multi-task FCN learns to simultaneously predict the probability of tooth region and the probability of tooth surface. Through the combination of the tooth probability gradient map and the surface probability map as the input image, MWT is used to automatically separate and segment individual tooth. Twenty-five dental CBCT scans are used in the study. The average Dice similarity coefficient, Jaccard index, and relative volume difference are 0.936 (±0.012), 0.881 (±0.019), and 0.072 (±0.027), respectively, and the average symmetric surface distance is 0.363 (±0.145) mm for our method. The experimental results demonstrate that the multi-task 3D FCN combined with MWT can segment individual tooth of various types in dental CBCT images.

In low dose computed tomography (LDCT) imaging, the data inconsistency of measured noisy projections can significantly deteriorate reconstruction images. To deal with this problem, we propose here a new sinogram restoration approach, the sinogram- discriminative feature representation (S-DFR) method. Different from other sinogram restoration methods, the proposed method works through a 3-D representation-based feature decomposition of the projected attenuation component and the noise component using a well-designed composite dictionary containing atoms with discriminative features. This method can be easily implemented with good robustness in parameter setting. Its comparison to other competing methods through experiments on simulated and real data demonstrated that the S-DFR method offers a sound alternative in LDCT.

Background: Ultrasonic flow ratio (UFR) is a novel method for fast computation of fractional flow reserve (FFR) from intravascular ultrasound images. The objective of this study is to evaluate the diagnostic performance of UFR using wire-based FFR as the reference. Methods: Post hoc computation of UFR was performed in consecutive patients with both intravascular ultrasound and FFR measurement in a core lab while the analysts were blinded to FFR. Results: A total of 167 paired comparisons between UFR and FFR from 94 patients were obtained. Median FFR was 0.80 (interquartile range, 0.68–0.89) and 50.3% had a FFR≤0.80. Median UFR was 0.81 (interquartile range, 0.69–0.91), and UFR showed strong correlation with FFR ( r =0.87; P <0.001). The area under the curve was higher for UFR than intravascular ultrasound-derived minimal lumen area (0.97 versus 0.89, P <0.001). The diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, and negative likelihood ratio for UFR to identify FFR≤0.80 was 92% (95% CI, 87–96), 91% (95% CI, 82–96), 96% (95% CI, 90–99), 96% (95% CI, 89–99), 91% (95% CI, 93–96), 25.0 (95% CI, 8.2–76.2), and 0.10 (95% CI, 0.05–0.20), respectively. The agreement between UFR and FFR was independent of lesion locations ( P =0.48), prior myocardial infarction ( P =0.29), and imaging catheters ( P =0.22). Intraobserver and interobserver variability of UFR analysis was 0.00±0.03 and 0.01±0.03, respectively. Median UFR analysis time was 102 (interquartile range, 87–122) seconds. Conclusions: UFR had a strong correlation and good agreement with FFR. The fast computational time and excellent analysis reproducibility of UFR bears the potential of a wider adoption of integration of coronary imaging and physiology in the catheterization laboratory.