Automatic tongue image segmentation and tongue classification are two crucial tongue characterization tasks in traditional Chinese medicine (TCM). Due to the complexity of automatic tongue segmentation and the fine-grained traits of tongue classification, both tasks are challenging. However, as discussed in the introduction section, these two tasks are interrelated, making them highly compatible with the idea of multitask joint learning (MTL). By sharing the underlying parameters and adding two different task objective functions, a MTL method for segmenting and classifying tongue images is proposed in this paper. Moreover, two state-of-the-art deep neural network variants (UNET and discriminative filter bank (DFL)) are fused into the MTL to perform the tongue segmentation and tongue classification tasks, respectively. To the best of our knowledge, our method is the first attempt to manage both tasks simultaneously with MTL. We conducted extensive experiments on reliable and quality assured datasets. The experimental results show that our joint method outperforms both the existing tongue segmentation methods and the existing tongue classification methods. Visualizations and ablation studies are provided to aid in understanding our approach, which suggest that our method is highly consistent with human perception

Resembling the role of disease diagnosis in Western medicine, pathogenesis (also called Bing Ji) diagnosis is one of the utmost important tasks in traditional Chinese medicine (TCM). In TCM theory, pathogenesis is a complex system composed of a group of interrelated factors, which is highly consistent with the character of systems science (SS). In this paper, we introduce a heuristic definition called pathogenesis network (PN) to represent pathogenesis in the form of the directed graph. Accordingly, a computational method of pathogenesis diagnosis, called network differentiation (ND), is proposed by integrating the holism principle in SS. ND consists of three stages. The first stage is to generate all possible diagnoses by Cartesian Product operated on specified prior knowledge corresponding to the input symptoms. The second stage is to screen the validated diagnoses by holism principle. The third stage is to pick out the clinical diagnosis by physician-computer interaction. Some theorems are stated and proved for the further optimization of ND in this paper. We conducted simulation experiments on 100 clinical cases. The experimental results show that our proposed method has an excellent capability to fit the holistic thinking in the process of physician inference.

Bisphenols (BPs) are widespread environmental endocrine disruptors, but their potential depression-related neurotoxicity has not been systematically assessed. Here, we combined machine learning (ML), network toxicology, molecular docking, and in vivo experiments to screen 26 bisphenols for depression-related neurotoxic risk. We first integrated bisphenol A (BPA)-related targets with depression-related genes to build a chemical-gene-phenotype-disease network and an adverse outcome pathway (AOP) framework. We then used nine ML algorithms to rank the predicted risk of the 26 bisphenols. Molecular docking showed that the predicted high-risk compounds had strong binding affinity for estrogen receptor 1 (ESR1). The AOP analysis further suggested the involvement of the ESR1–cAMP response element-binding protein 1 (CREB1)–glutamate ionotropic receptor N-methyl-D-aspartate type subunit 2B (GRIN2B) pathway. In vivo experiments showed that BPA exposure caused neuronal damage in the cornu ammonis 3 (CA3) region of the rat hippocampus and significantly reduced the messenger RNA (mRNA) expression of the corresponding genes Esr1, Creb1, and Grin2b in hippocampal tissue. Overall, this study screened and prioritized the model-predicted depression-related neurotoxic risk of 26 bisphenols, supports a role for the ESR1–CREB1–GRIN2B pathway in BPA-induced neurotoxicity, and provides mechanistic evidence for bisphenol risk assessment.