Exploiting Geometric Features via Hierarchical Graph Pyramid Transformer for Cancer Diagnosis using Histopathological Images.

Cancer is widely recognized as the primary cause of mortality worldwide, and pathology analysis plays a pivotal role in achieving accurate cancer diagnosis. The intricate representation of features in histopathological images encompasses abundant information crucial for disease diagnosis, regarding cell appearance, tumor microenvironment, and geometric characteristics. However, recent deep learning methods have not adequately exploited geometric features for pathological image classification due to the absence of effective descriptors that can capture both cell distribution and gathering patterns, which often serve as potent indicators. In this paper, inspired by clinical practice, a Hierarchical Graph Pyramid Transformer (HGPT) is proposed to guide pathological image classification by effectively exploiting a geometric representation of tissue distribution which was ignored by existing state-of-the-art methods. First, a graph representation is constructed according to morphological feature of input pathological image and learn geometric representation through the proposed multi-head graph aggregator. Then, the image and its graph representation are feed into the transformer encoder layer to model long-range dependency. Finally, a locality feature enhancement block is designed to enhance the 2D local representation of feature embedding, which is not well explored in the existing vision transformers. An extensive experimental study is conducted on Kather-5K, MHIST, NCT-CRC-HE, and GasHisSDB for binary or multi-category classification of multiple cancer types. Results demonstrated that our method is capable of consistently reaching superior classification outcomes for histopathological images, which provide an effective diagnostic tool for malignant tumors in clinical practice.

Multi-task contrastive learning for semi-supervised medical image segmentation with multi-scale uncertainty estimation.

Objective. Automated medical image segmentation is vital for the prevention and treatment of disease. However, medical data commonly exhibit class imbalance in practical applications, which may lead to unclear boundaries of specific classes and make it difficult to effectively segment certain tail classes in the results of semi-supervised medical image segmentation.Approach. We propose a novel multi-task contrastive learning framework for semi-supervised medical image segmentation with multi-scale uncertainty estimation. Specifically, the framework includes a student-teacher model. We introduce global image-level contrastive learning in the encoder to address the class imbalance and local pixel-level contrastive learning in the decoder to achieve intra-class aggregation and inter-class separation. Furthermore, we propose a multi-scale uncertainty-aware consistency loss to reduce noise caused by pseudo-label bias.Main results. Experiments on three public datasets ACDC, LA and LiTs show that our method achieves higher segmentation performance compared with state-of-the-art semi-supervised segmentation methods.Significance. The multi-task contrastive learning in our method facilitates the negative impact of class imbalance and achieves better classification results. The multi-scale uncertainty estimation encourages consistent predictions for the same input under different perturbations, motivating the teacher model to generate high-quality pseudo-labels. Code is available athttps://github.com/msctransu/MCSSMU.git.

SENIES: DNA Shape Enhanced Two-Layer Deep Learning Predictor for the Identification of Enhancers and Their Strength.

Identifying enhancers is a critical task in bioinformatics due to their primary role in regulating gene expression. For this reason, various computational algorithms devoted to enhancer identification have been put forward over the years. More features are extracted from the single DNA sequences to boost the performance. Nevertheless, DNA structural information is neglected, which is an essential factor affecting the binding preferences of transcription factors to regulatory elements like enhancers. Here, we propose SENIES, a DNA shape enhanced deep learning predictor, to identify enhancers and their strength. The predictor consists of two layers where the first layer is for enhancer and non-enhancer identification, and the second layer is for predicting the strength of enhancers. Apart from two common sequence-derived features (i.e., one-hot and k-mer), DNA shape is introduced to describe the 3D structures of DNA sequences. Performance comparison with state-of-the-art methods conducted on public datasets demonstrates the effectiveness and robustness of our predictor. The code implementation of SENIES is publicly available at https://github.com/hlju-liye/SENIES.

GasHisSDB: A new gastric histopathology image dataset for computer aided diagnosis of gastric cancer.

BACKGROUND AND OBJECTIVE: Gastric cancer is the fifth most common cancer globally, and early detection of gastric cancer is essential to save lives. Histopathological examination of gastric cancer is the gold standard for the diagnosis of gastric cancer. However, computer-aided diagnostic techniques are challenging to evaluate due to the scarcity of publicly available gastric histopathology image datasets. METHODS: In this paper, a noble publicly available Gastric Histopathology Sub-size Image Database (GasHisSDB) is published to identify classifiers' performance. Specifically, two types of data are included: normal and abnormal, with a total of 245,196 tissue case images. In order to prove that the methods of different periods in the field of image classification have discrepancies on GasHisSDB, we select a variety of classifiers for evaluation. Seven classical machine learning classifiers, three Convolutional Neural Network classifiers, and a novel transformer-based classifier are selected for testing on image classification tasks. RESULTS: This study performed extensive experiments using traditional machine learning and deep learning methods to prove that the methods of different periods have discrepancies on GasHisSDB. Traditional machine learning achieved the best accuracy rate of 86.08% and a minimum of just 41.12%. The best accuracy of deep learning reached 96.47% and the lowest was 86.21%. Accuracy rates vary significantly across classifiers. CONCLUSIONS: To the best of our knowledge, it is the first publicly available gastric cancer histopathology dataset containing a large number of images for weakly supervised learning. We believe that GasHisSDB can attract researchers to explore new algorithms for the automated diagnosis of gastric cancer, which can help physicians and patients in the clinical setting.

Hybrid Graph Transformer for Tissue Microstructure Estimation with Undersampled Diffusion MRI Data.

Advanced contemporary diffusion models for tissue microstructure often require diffusion MRI (DMRI) data with sufficiently dense sampling in the diffusion wavevector space for reliable model fitting, which might not always be feasible in practice. A potential remedy to this problem is by using deep learning techniques to predict high-quality diffusion microstructural indices from sparsely sampled data. However, existing methods are either agnostic to the data geometry in the diffusion wavevector space ( q -space) or limited to leveraging information from only local neighborhoods in the physical coordinate space ( x -space). Here, we propose a hybrid graph transformer (HGT) to explicitly consider the q -space geometric structure with a graph neural network (GNN) and make full use of spatial information with a novel residual dense transformer (RDT). The RDT consists of multiple densely connected transformer layers and a residual connection to facilitate model training. Extensive experiments on the data from the Human Connectome Project (HCP) demonstrate that our method significantly improves the quality of microstructural estimations over existing state-of-the-art methods.

MEAL: Meta enhanced Entropy-driven Adversarial Learning for Optic Disc and Cup Segmentation.

Accurate segmentation of optic disc (OD) and optic cup (OC) can assist the effective and efficient diagnosis of glaucoma. The domain shift caused by cross-domain data, however, affect the performance of a well-trained model on new datasets from different domain. In order to overcome this problem, we propose a domain adaption model based OD and OC segmentation called Meta enhanced Entropy-driven Adversarial Learning (MEAL). Our segmentation network consists of a meta-enhanced block (MEB) to enhance the adaptability of high-level features, and an attention-based multi-feature fusion (AMF) module for attentive integration of multi-level feature representations. For the optimization, an adversarial cost function driven by entropy map is used to improve the adaptability of the framework. Evaluations and ablation studies on two public fundus image datasets demonstrate the effectiveness of our model, and outstanding performance over other domain adaption methods in comparison.

AMF-NET: Attention-aware Multi-scale Fusion Network for Retinal Vessel Segmentation.

Automatic retinal vessel segmentation in fundus image can assist effective and efficient diagnosis of retina disease. Microstructure estimation of capillaries is a prolonged challenging issue. To tackle this problem, we propose attention-aware multi-scale fusion network (AMF-Net). Our network is with dense convolutions to perceive microscopic capillaries. Additionally, multi-scale features are extracted and fused with adaptive weights by channel attention module to improve the segmentation performance. Finally, spatial attention is introduced by position attention modules to capture long-distance feature dependencies. The proposed model is evaluated using two public datasets including DRIVE and CHASE_DB1. Extensive experiments demonstrate that our model outperforms existing methods. Ablation study valid the effectiveness of the proposed components.

COVID-19 lung infection segmentation with a novel two-stage cross-domain transfer learning framework.

With the global outbreak of COVID-19 in early 2020, rapid diagnosis of COVID-19 has become the urgent need to control the spread of the epidemic. In clinical settings, lung infection segmentation from computed tomography (CT) images can provide vital information for the quantification and diagnosis of COVID-19. However, accurate infection segmentation is a challenging task due to (i) the low boundary contrast between infections and the surroundings, (ii) large variations of infection regions, and, most importantly, (iii) the shortage of large-scale annotated data. To address these issues, we propose a novel two-stage cross-domain transfer learning framework for the accurate segmentation of COVID-19 lung infections from CT images. Our framework consists of two major technical innovations, including an effective infection segmentation deep learning model, called nCoVSegNet, and a novel two-stage transfer learning strategy. Specifically, our nCoVSegNet conducts effective infection segmentation by taking advantage of attention-aware feature fusion and large receptive fields, aiming to resolve the issues related to low boundary contrast and large infection variations. To alleviate the shortage of the data, the nCoVSegNet is pre-trained using a two-stage cross-domain transfer learning strategy, which makes full use of the knowledge from natural images (i.e., ImageNet) and medical images (i.e., LIDC-IDRI) to boost the final training on CT images with COVID-19 infections. Extensive experiments demonstrate that our framework achieves superior segmentation accuracy and outperforms the cutting-edge models, both quantitatively and qualitatively.

Cryotherapy mediates histopathological and microstructural changes during the treatment of skin and subcutaneous tumors in dogs.

The therapeutic effects of cryotherapy on skin and subcutaneous tumors in dogs were retrospectively studied in 20 dogs with 37 tumor lesions, of which 30 were benign and seven were malignant. Our results showed that during follow-up, 94.5% of lesions were completely exfoliated, without relapse or metastasis (mean time = 245.7 days). To investigate the effects of cryotherapy, we compared histopathological observations and microstructural changes in healthy tissues and tumor tissues, before and after cryotherapy. After cryotherapy, both normal skin and tumor tissue exhibited edema and hyperemia, with inflammatory cell infiltration. The cell nuclei exhibited pyknosis, disintegration and necrosis, and tight junctions were decreased in size. Cell morphology was varied, along with fragmented cell nuclear envelopes, crenulated nuclei and indistinct and necrotic intracellular organelles. Vacuoles were apparent in the cytoplasm and intercellular desmosomes were absent. These observations suggested that cryosurgery inhibited skin and subcutaneous tumors via cold-induced injury to cells, and cellular microenvironment changes induced by apoptosis. The results suggested that cryosurgery prevented skin and subcutaneous tumors via cold-induced injury to cells, and cellular microenvironment changes induced by apoptosis. We believe these data will provide general cryotherapy guidance to scientists and veterinary surgeons.

Estimating Tissue Microstructure with Undersampled Diffusion Data via Graph Convolutional Neural Networks.

Advanced diffusion models for tissue microstructure are widely employed to study brain disorders. However, these models usually require diffusion MRI (DMRI) data with densely sampled q-space, which is prohibitive in clinical settings. This problem can be resolved by using deep learning techniques, which learn the mapping between sparsely sampled q-space data and the high-quality diffusion microstructural indices estimated from densely sampled data. However, most existing methods simply view the input DMRI data as a vector without considering data structure in the q-space. In this paper, we propose to overcome this limitation by representing DMRI data using graphs and utilizing graph convolutional neural networks to estimate tissue microstructure. Our method makes full use of the q-space angular neighboring information to improve estimation accuracy. Experimental results based on data from the Baby Connectome Project demonstrate that our method outperforms state-of-the-art methods both qualitatively and quantitatively.

Integrative Pathway Analysis of Genes and Metabolites Reveals Metabolism Abnormal Subpathway Regions and Modules in Esophageal Squamous Cell Carcinoma.

Aberrant metabolism is one of the main driving forces in the initiation and development of ESCC. Both genes and metabolites play important roles in metabolic pathways. Integrative pathway analysis of both genes and metabolites will thus help to interpret the underlying biological phenomena. Here, we performed integrative pathway analysis of gene and metabolite profiles by analyzing six gene expression profiles and seven metabolite profiles of ESCC. Multiple known and novel subpathways associated with ESCC, such as 'beta-Alanine metabolism', were identified via the cooperative use of differential genes, differential metabolites, and their positional importance information in pathways. Furthermore, a global ESCC-Related Metabolic (ERM) network was constructed and 31 modules were identified on the basis of clustering analysis in the ERM network. We found that the three modules located just to the center regions of the ERM network-especially the core region of Module_1-primarily consisted of aldehyde dehydrogenase (ALDH) superfamily members, which contributes to the development of ESCC. For Module_4, pyruvate and the genes and metabolites in its adjacent region were clustered together, and formed a core region within the module. Several prognostic genes, including GPT, ALDH1B1, ABAT, WBSCR22 and MDH1, appeared in the three center modules of the network, suggesting that they can become potentially prognostic markers in ESCC.

Survey of gene splicing algorithms based on reads.

Gene splicing is the process of assembling a large number of unordered short sequence fragments to the original genome sequence as accurately as possible. Several popular splicing algorithms based on reads are reviewed in this article, including reference genome algorithms and de novo splicing algorithms (Greedy-extension, Overlap-Layout-Consensus graph, De Bruijn graph). We also discuss a new splicing method based on the MapReduce strategy and Hadoop. By comparing these algorithms, some conclusions are drawn and some suggestions on gene splicing research are made.

A novel dysregulated pathway-identification analysis based on global influence of within-pathway effects and crosstalk between pathways.

Identifying dysregulated pathways from high-throughput experimental data in order to infer underlying biological insights is an important task. Current pathway-identification methods focus on single pathways in isolation; however, consideration of crosstalk between pathways could improve our understanding of alterations in biological states. We propose a novel method of pathway analysis based on global influence (PAGI) to identify dysregulated pathways, by considering both within-pathway effects and crosstalk between pathways. We constructed a global gene­gene network based on the relationships among genes extracted from a pathway database. We then evaluated the extent of differential expression for each gene, and mapped them to the global network. The random walk with restart algorithm was used to calculate the extent of genes affected by global influence. Finally, we used cumulative distribution functions to determine the significance values of the dysregulated pathways. We applied the PAGI method to five cancer microarray datasets, and compared our results with gene set enrichment analysis and five other methods. Based on these analyses, we demonstrated that PAGI can effectively identify dysregulated pathways associated with cancer, with strong reproducibility and robustness. We implemented PAGI using the freely available R-based and Web-based tools (http://bioinfo.hrbmu.edu.cn/PAGI).

MPINet: metabolite pathway identification via coupling of global metabolite network structure and metabolomic profile.

High-throughput metabolomics technology, such as gas chromatography mass spectrometry, allows the analysis of hundreds of metabolites. Understanding that these metabolites dominate the study condition from biological pathway perspective is still a significant challenge. Pathway identification is an invaluable aid to address this issue and, thus, is urgently needed. In this study, we developed a network-based metabolite pathway identification method, MPINet, which considers the global importance of metabolites and the unique character of metabolomic profile. Through integrating the global metabolite functional network structure and the character of metabolomic profile, MPINet provides a more accurate metabolomic pathway analysis. This integrative strategy simultaneously captures the global nonequivalence of metabolites in a pathway and the bias from metabolomic experimental technology. We then applied MPINet to four different types of metabolite datasets. In the analysis of metastatic prostate cancer dataset, we demonstrated the effectiveness of MPINet. With the analysis of the two type 2 diabetes datasets, we show that MPINet has the potentiality for identifying novel pathways related with disease and is reliable for analyzing metabolomic data. Finally, we extensively applied MPINet to identify drug sensitivity related pathways. These results suggest MPINet's effectiveness and reliability for analyzing metabolomic data across multiple different application fields.