Automated Screening of COVID-19 from chest CT is of emergency and importance during the outbreak of SARS-CoV-2 worldwide in 2020. However, accurate screening of COVID-19 is still a massive challenge due to the spatial complexity of 3D volumes, the labeling difficulty of infection areas, and the slight discrepancy between COVID-19 and other viral pneumonia in chest CT. While a few pioneering works have made significant progress, they are either demanding manual annotations of infection areas or lack of interpretability. In this paper, we report our attempt towards achieving highly accurate and interpretable screening of COVID-19 from chest CT with weak labels. We propose an attention-based deep 3D multiple instance learning (AD3D-MIL) where a patient-level label is assigned to a 3D chest CT that is viewed as a bag of instances. AD3D-MIL can semantically generate deep 3D instances following the possible infection area. AD3D-MIL further applies an attention-based pooling approach to 3D instances to provide insight into each instance's contribution to the bag label. AD3D-MIL finally learns Bernoulli distributions of the bag-level labels for more accessible learning. We collected 460 chest CT examples: 230 CT examples from 79 patients with COVID-19, 100 CT examples from 100 patients with common pneumonia, and 130 CT examples from 130 people without pneumonia. A series of empirical studies show that our algorithm achieves an overall accuracy of 97.9%, AUC of 99.0%, and Cohen kappa score of 95.7%. These advantages endow our algorithm as an efficient assisted tool in the screening of COVID-19.

Breast cancer has been one of the main diseases that threatens women's life. Early detection and diagnosis of breast cancer play an important role in reducing mortality of breast cancer. In this paper, we propose a selective ensemble method integrated with the KNN, SVM, and Naive Bayes to diagnose the breast cancer combining ultrasound images with mammography images. Our experimental results have shown that the selective classification method with an accuracy of 88.73% and sensitivity of 97.06% is efficient for breast cancer diagnosis. And indicator R presents a new way to choose the base classifier for ensemble learning.

Multi-spectral imaging (MSI) is a novel non-invasive tool for visualizing the entire span of the eye, from the internal limiting membrane to the choroid. However, spatial misalignments can be frequently observed in sequential MSI images because the eye saccade movement is usually faster than the MSI image acquisition speed. Therefore, registering MSI images is necessary for computer-based analysis of retinal degeneration via MSI. In this paper, we propose an early deep learning framework for achieving an accurate registration of MSI images in a group-wise fashion. The framework contains three parts: a template construction based on principal component analysis, a deformation field calculation, and a spatial transformation. The framework is uniquely capable of resolving two key challenges, i.e., the ''multimodal'' characteristics in MSI images for the acquisition with different spectra and the requirement of joint registration of the sequential images. Our experimental results demonstrate the superior performance of our framework compared to several representative state-of-the-art techniques in both speed and accuracy. INDEX TERMS Multi-spectral images, group-wise registration, deep learning, mono/multi-modal images.

Simple Linear Iterative Clustering (SLIC) algorithm is increasingly applied to different kinds of image processing because of its excellent perceptually meaningful characteristics. In order to better meet the needs of medical image processing and provide technical reference for SLIC on the application of medical image segmentation, two indicators of boundary accuracy and superpixel uniformity are introduced with other indicators to systematically analyze the performance of SLIC algorithm, compared with Normalized cuts and Turbopixels algorithm. The extensive experimental results show that SLIC is faster and less sensitive to the image type and the setting superpixel number than other similar algorithms such as Turbopixels and Normalized cuts algorithms. And it also has a great benefit to the boundary recall, the robustness of fuzzy boundary, the setting superpixel size and the segmentation performance on medical image segmentation.

3D spinal structures segmentation is crucial to reduce the time-consumption issue and provide quantitative parameters for disease treatment and surgical operation. However, the most related studies of spinal structures segmentation are based on 2D or 3D single structure segmentation. Due to the high complexity of spinal structures, the segmentation of 3D multiple spinal structures with consistently reliable and high accuracy is still a significant challenge. We developed and validated a relatively complete solution for the simultaneous 3D semantic segmentation of multiple spinal structures at the voxel level named as the S 3 egANet. Firstly, S 3 egANet explicitly solved the high variety and variability of complex 3D spinal structures through a multi-modality autoencoder module that was capable of extracting fine-grained structural information. Secondly, S 3 egANet adopted a cross-modality voxel fusion module to incorporate comprehensive spatial information from multi-modality MRI images. Thirdly, we presented a multi-stage adversarial learning strategy to achieve high accuracy and reliability segmentation of multiple spinal structures simultaneously. Extensive experiments on MRI images of 90 patients demonstrated that S 3 egANet achieved mean Dice coefficient of 88.3% and mean Sensitivity of 91.45%, which revealed its effectiveness and potential as a clinical tool.