Background: The digital pathology images obtain the essential information about the patient’s disease, and the automated nuclei segmentation results can help doctors make better decisions about diagnosing the disease. With the speedy advancement of convolutional neural networks in image processing, deep learning has been shown to play a significant role in the various analysis of medical images, such as nuclei segmentation, mitosis detection and segmentation etc. Recently, several U-net based methods have been developed to solve the automated nuclei segmentation problems. However, these methods fail to deal with the weak features representation from the initial layers and introduce the noise into the decoder path. In this paper, we propose a multiscale attention learning network (MSAL-Net), where the dense dilated convolutions block captures more comprehensive nuclei context information, and a newly modified decoder part is introduced, which integrates with efficient channel attention and boundary refinement modules to effectively learn spatial information for better prediction and further refine the nuclei cell of boundaries.Results: Both qualitative and quantitative results are obtained on the publicly available MoNuseg dataset. Extensive experiment results verify that our proposed method significantly outperforms state-of-the-art methods as well as the vanilla Unet method in the segmentation task. Furthermore, we visually demonstrate the effect of our modified decoder part.Conclusion: The MSAL-Net shows superiority with a novel decoder to segment the touching and blurred background nuclei cells obtained from histopathology images with better performance for accurate decoding.

Tissue segmentation in histopathological images plays a crucial role in computational pathology, owing to its significant potential to indicate the prognosis of cancer patients. Presently, numerous Weakly Supervised Semantic Segmentation (WSSS) methods strive to utilize image-level labels to achieve pixel-level segmentation, aiming to minimize the need for detailed annotations. Most of these methods rely on Class Activation Maps (CAM) extracted from classification models, frequently leading to poor coverage of objects. The major cause is attributed to the strong inductive bias of the classification model, focusing primarily on discriminative feature of objects, rather than non-discriminative features. Inspired by this, we propose a simple yet effective method that introduces a self-supervised task by exploiting both the discriminative and non-discriminative features, and generate Unbiased Activation Maps (UAM) to encompass the whole object. Specifically, our method entails clustering all spatial features of an object class to derive semantic centers. Each center then works as a spatial filter that amplifies similar feature and suppresses dissimilar feature, and extract high-quality pseudo-labels (some noise at object boundaries). Moreover, we further propose a Noise-Reduced (NR) Learning method to train the segmentation network towards credible signals and lessen the impact of false predictions. Comprehensive experimental results on two public histopathology image datasets demonstrate the superior performance of our method over the state-of-the-art weakly supervised segmentation methods.

Introduction: Thymoma classification is challenging due to its diverse morphology. Accurate classification is crucial for diagnosis, but current methods often struggle with complex tumor subtypes. This study presents an AI-assisted diagnostic model that combines weakly supervised learning with a divide-and-conquer multi-instance learning (MIL) approach to improve classification accuracy and interpretability.Methods: We applied the model to 222 thymoma slides, simplifying the five-class classification into binary and ternary steps. The model features an attention-based mechanism that generates heatmaps, enabling visual interpretation of decisions. These heatmaps align with clinically validated morphological differences between thymoma subtypes. Additionally, we embedded domain-specific pathological knowledge into the interpretability framework.Results: The model achieved a classification AUC of 0.9172. The generated heatmaps accurately reflected the morphological distinctions among thymoma subtypes, as confirmed by pathologists. The model's transparency allows pathologists to visually verify AI decisions, enhancing diagnostic reliability.Discussion: This model offers a significant advancement in thymoma classification, combining high accuracy with interpretability. By integrating weakly supervised learning, MIL, and attention mechanisms, it provides an interpretable AI framework that is applicable in clinical settings. The model reduces the diagnostic burden on pathologists and has the potential to improve patient outcomes by making AI tools more transparent and clinically relevant.

Introduction: Helicobacter pylori (H. pylori) infection is considered to be a primary causative factor for gastric cancer and a common cause of chronic gastritis worldwide. Identifying H. pylori infection through hematoxylin and eosin (H&E) staining is demanding and tedious for pathologists. We aimed to use artificial intelligence (AI) models to improve the accuracy and efficiency of H. pylori diagnosis and to reduce the workload of pathologists.Methods: Here, we developed three multi-instance learning (MIL) models: AB-MIL, DS-MIL, and Trans-MIL, to automatically detect H. pylori infection. A total of 1,020 digitized histological whole-slide images (WSI) from 817 patients were used for training, validating and testing sets at a ratio of 3:1:1. Additionally, 100 cases (218 WSIs) were randomly selected from the test set for pathologists to identify H. pylori under the microscope. The accuracy, specificity, sensitivity, false negative rate, false positive rate, and other metrics were calculated separately for the MIL models and the pathologists.Results: All three models demonstrated good diagnostic performance in predicting H. pylori infection, with the DS-MIL classification model showing the best diagnostic performance, achieving an accuracy of 89.7% and an area under the curve (AUC) of 0.949, which is higher than the accuracy rate of senior pathologists at 81.7%. Furthermore, the model demonstrates superior performance in terms of sensitivity and specificity. The reliability of DS-MIL is confirmed through the Visual model.Discussion: Our research presents an AI - based predictive model for H. pylori infection, which significantly enhances clinical efficiency and diagnostic accuracy. Currently, we are conducting multi-center validation to enhance the model’s generalization capability.