Deep learning offers notable promise for computational pathology, but its performance is constrained by the need for extensively annotated datasets, which are costly and laborious to produce. Self-Supervised Learning (SSL) provides an effective paradigm for learning discriminative representations from unannotated pathological images. However, existing SSL methods often overlook domain-specific characteristics of pathological images and suffer from the adverse effects of low-quality negative samples, leading to sub-optimal feature representations for downstream tasks. To overcome these limitations, we propose a novel Domain-Specific Self-supervised Contrastive Learning (DSSCL) framework, which incorporates two novel components: (1) a Stain-Separation Based Data Augmentation (SSDA) module that enhances stain-aware representation learning by fusing stain-separated components with original hematoxylin and eosin images, and (2) a Contrast-Aware Pair Refinement (CAPR) module that improves feature discriminability by filtering potential positives and mining hard negatives, thereby mitigating the influence of low-quality negatives. Extensive experiments demonstrate that DSSCL achieves comparable accuracy in classification tasks using only 0.1% labeled data compared to a network fine-tuned from ImageNet with 10% labeled data, while also delivering competitive performance in detection and segmentation tasks, underscoring its effectiveness in learning transferable and robust feature representations across diverse downstream tasks. The code is available at https://github.com/junjianli106/DSSCL.

Accurately predicting the survival of patients with esophageal cancer after esophagectomy is crucial for clinical precision treatment. However, the existing methods of predicting Overall Survival time (OStime) mostly build supervised learning with the uncensored data, ignoring the potential information hidden in the censored data. To utilize the information hidden in the clinically abundant censored data, we propose a Semi-Supervised Learning with Adaptive pseudo-label Selection and Correction (SSLASC) to predict the OStime of esophageal cancer using both uncensored and censored data. Specifically, we first transform the OStime regression problem to a classification task followed by Softmax Expected Value Refinement (SEVR) and train a Transformer network using the uncensored data, which is then used to predict the OStime for the censored data. Secondly, we design an adaptive pseudo-label selection strategy to dynamically select more classes and more balanced samples from the predicted censored data by allocating adaptive thresholds for different classes of samples when performing pseudo-label selection. Finally, a distribution correction and a meta label correction modules are proposed to make the selected pseudo-labels closer to the real overall OStime. We test SSLASC on an internal dataset and two external datasets with sample sizes of 327, 104, and 16, respectively. The experimental results demonstrate that SSLASC achieves Mean Absolute Error (MAE) of 12.23, 12.64, and 12.47 months on the three test datasets. Compared to the optimal State-Of-The-Art (SOTA) method, SSLASC improves performance by 1.09, 1.07, and 1.09 months, respectively. In addition, SSLASC also achieves the best performance in dichotomized survival analysis.

Dementia is a syndrome causing a progressive loss of brain function and mainly includes subtypes, such as Alzheimer’s Disease (AD), FrontoTemporal Dementia (FTD), and Vascular Cognitive Impairment (VCI). Electroencephalography (EEG) is widely used in dementia diagnosis to detect brain electrophysiological signals efficiently. However, the small number of samples available in EEG-based dementia diagnosis results in poor performance of existing methods. To address this issue, we propose a Multi-scale Adaptive Graph Learning based on Multi-wave EEG data (MAGLM) for dementia diagnosis. Firstly, we extract both time-domain and frequency-domain features of multi-wave EEG data. Secondly, to reliably expand the insufficient samples, we propose a multi-wave EEG data augmentation model based on generative learning. Finally, to explore the rich patterns between scales, waves, and samples, we propose a multi-scale adaptive graph learning model to perform dementia diagnosis based on augmented EEG data. MAGLM is validated on an in-house EEG dataset, including AD, FTD, and VCI. The experimental and visualization results show the superiority of the proposed MAGLM over the state-of-the-art methods. In conclusion, MAGLM is not only effective in dementia diagnosis, but also provides experience for EEG-based brain science research.

Accurately diagnosing Alzheimer’s disease is essential for improving elderly health. Meanwhile, accurate prediction of the mini-mental state examination score also can measure cognition impairment and track the progression of Alzheimer’s disease. However, most of the existing methods perform Alzheimer’s disease diagnosis and mini-mental state examination score prediction separately and ignore the relation between these two tasks. To address this challenging problem, we propose a novel multi-task learning method, which uses feature interaction to explore the relationship between Alzheimer’s disease diagnosis and mini-mental state examination score prediction. In our proposed method, features from each task branch are firstly decoupled into candidate and non-candidate parts for interaction. Then, we propose feature sharing module to obtain shared features from candidate features and return shared features to task branches, which can promote the learning of each task. We validate the effectiveness of our proposed method on multiple datasets. In Alzheimer’s disease neuroimaging initiative 1 dataset, the accuracy in diagnosis task and the root mean squared error in prediction task of our proposed method is 87.86% and 2.5, respectively. Experimental results show that our proposed method outperforms most state-of-the-art methods. Our proposed method enables accurate Alzheimer’s disease diagnosis and mini-mental state examination score prediction. Therefore, it can be used as a reference for the clinical diagnosis of Alzheimer’s disease, and can also help doctors and patients track disease progression in a timely manner.