MyoV: a deep learning-based tool for the automated quantification of muscle fibers.

Accurate approaches for quantifying muscle fibers are essential in biomedical research and meat production. In this study, we address the limitations of existing approaches for hematoxylin and eosin-stained muscle fibers by manually and semiautomatically labeling over 660 000 muscle fibers to create a large dataset. Subsequently, an automated image segmentation and quantification tool named MyoV is designed using mask regions with convolutional neural networks and a residual network and feature pyramid network as the backbone network. This design enables the tool to allow muscle fiber processing with different sizes and ages. MyoV, which achieves impressive detection rates of 0.93-0.96 and precision levels of 0.91-0.97, exhibits a superior performance in quantification, surpassing both manual methods and commonly employed algorithms and software, particularly for whole slide images (WSIs). Moreover, MyoV is proven as a powerful and suitable tool for various species with different muscle development, including mice, which are a crucial model for muscle disease diagnosis, and agricultural animals, which are a significant meat source for humans. Finally, we integrate this tool into visualization software with functions, such as segmentation, area determination and automatic labeling, allowing seamless processing for over 400 000 muscle fibers within a WSI, eliminating the model adjustment and providing researchers with an easy-to-use visual interface to browse functional options and realize muscle fiber quantification from WSIs.

Identification of shared molecular mechanisms and diagnostic biomarkers between heart failure and idiopathic pulmonary fibrosis.

Background: Heart failure (HF) and idiopathic pulmonary fibrosis (IPF) are global public health concerns. The relationship between HF and IPF is widely acknowledged. However, the interaction mechanisms between these two diseases remain unclear, and early diagnosis is particularly difficult. Through the integration of bioinformatics and machine learning, our work aims to investigate common gene features, putative molecular causes, and prospective diagnostic indicators of IPF and HF. Methods: The Gene Expression Omnibus (GEO) database provided the RNA-seq datasets for HF and IPF. Utilizing a weighted gene co-expression network analysis (WGCNA), possible genes linked to HF and IPF were found. The Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) were then employed to analyze the genes that were shared by HF and IPF. Using the cytoHubba and iRegulon algorithms, a competitive endogenous RNA (ceRNA) network was built based on seven basic diagnostic indicators. Additionally, hub genes were identified using machine learning approaches. External datasets were used to validate the findings. Lastly, the association between the number of immune cells in tissues and the discovered genes was estimated using the CIBERSORT method. Results: In total, 63 shared genes were identified between HF- and IPF-related modules using WGCNA. Extracellular matrix (ECM)/structure organization, ECM-receptor interactions, focal, and protein digestion and absorption, were shown to be the most enrichment categories in GO and KEGG enrichment analysis of common genes. Furthermore, a total of seven fundamental genes, including COL1A1, COL3A1, THBS2, CCND1, ASPN, FAP, and S100A12, were recognized as pivotal genes implicated in the shared pathophysiological pathways of HF and IPF, and TCF12 may be the most important regulatory transcription factor. Two characteristic molecules, CCND1 and NAP1L3, were selected as potential diagnostic markers for HF and IPF, respectively, using a support vector machine-recursive feature elimination (SVM-RFE) model. Furthermore, the development of diseases and diagnostic markers may be associated with immune cells at varying degrees. Conclusions: This study demonstrated that ECM/structure organisation, ECM-receptor interaction, focal adhesion, and protein digestion and absorption, are common pathogeneses of IPF and HF. Additionally, CCND1 and NAP1L3 were identified as potential diagnostic biomarkers for both HF and IPF. The results of our study contribute to the comprehension of the co-pathogenesis of HF and IPF at the genetic level and offer potential biological indicators for the early detection of both conditions.