Abstract Medical image segmentation based on deep learning is becoming popular. To improve the segmentation accuracy of medical images such as cells and vessels, we propose the LSUnetMix model, which can effectively enhance the ability to extract channel information and capture image details better. It surpasses both traditional and latest models on medical datasets. This model is mainly based on Unet, and three modules have been added. The first is the Channel Information Transmission module, which uses long–short term memory to get the sequential features of layers and unidirectionally transfer the channel information of the upper layer to the lower layer, which combines multiple layers of information while avoiding information redundancy. The second is the Prospect Enhancement module, which activates the channel information of the image and enhances the ability to recognise the segmentation targets. The third is the Multiscale Dilated Convolution module, which uses multi‐scale dilated convolution to strengthen the ability and to extract the image details. After experiments, their model performs best on GlaS and MoNuseg datasets, which can segment image details better and avoid redundant information, and the Dice coefficient reaches 91.92% on GlaS and 81.8% on MoNuSeg.

MOTIVATION: The accumulation of somatic mutations plays critical roles in cancer development and progression. However, the global patterns of somatic mutations, especially non-coding mutations, and their roles in defining molecular subtypes of cancer have not been well characterized due to the computational challenges in analysing the complex mutational patterns. RESULTS: Here, we develop a new algorithm, called MutSpace, to effectively extract patient-specific mutational features using an embedding framework for larger sequence context. Our method is motivated by the observation that the mutation rate at megabase scale and the local mutational patterns jointly contribute to distinguishing cancer subtypes, both of which can be simultaneously captured by MutSpace. Simulation evaluations show that MutSpace can effectively characterize mutational features from known patient subgroups and achieve superior performance compared with previous methods. As a proof-of-principle, we apply MutSpace to 560 breast cancer patient samples and demonstrate that our method achieves high accuracy in subtype identification. In addition, the learned embeddings from MutSpace reflect intrinsic patterns of breast cancer subtypes and other features of genome structure and function. MutSpace is a promising new framework to better understand cancer heterogeneity based on somatic mutations. AVAILABILITY AND IMPLEMENTATION: Source code of MutSpace can be accessed at: https://github.com/ma-compbio/MutSpace. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Text-based question answering (TBQA) has been studied extensively in recent years.Most existing approaches focus on finding the answer to a question within a single paragraph.However, many difficult questions require multiple supporting evidence from scattered text across two or more documents.In this paper, we propose the Dynamically Fused Graph Network (DFGN), a novel method to answer those questions requiring multiple scattered evidence and reasoning over them.Inspired by human's step-by-step reasoning behavior, DFGN includes a dynamic fusion layer that starts from the entities mentioned in the given query, explores along the entity graph dynamically built from the text, and gradually finds relevant supporting entities from the given documents.We evaluate DFGN on HotpotQA, a public TBQA dataset requiring multi-hop reasoning.DFGN achieves competitive results on the public board.Furthermore, our analysis shows DFGN could produce interpretable reasoning chains.