Background and objective: Accurate diagnosis of brain tumors significantly impacts patient prognosis and treatment planning. Traditional diagnostic methods primarily rely on clinicians’ subjective interpretation of medical images, which is heavily dependent on physician experience and limited by time consumption, fatigue, and inconsistent diagnoses. Recently, deep learning technologies, particularly Convolutional Neural Networks (CNN), have achieved breakthrough advances in medical image analysis, offering a new paradigm for automated precise diagnosis. However, existing research largely focuses on single-task modeling, lacking comprehensive solutions that integrate tumor segmentation with classification diagnosis. This study aims to develop a multi-task deep learning model for precise brain tumor segmentation and type classification.Methods: The study included 485 pathologically confirmed cases, comprising T1-enhanced MRI sequence images of high-grade gliomas, metastatic tumors, and meningiomas. The dataset was proportionally divided into training (378 cases), testing (109 cases), and external validation (51 cases) sets. We designed and implemented BrainTumNet, a deep learning-based multi-task framework featuring an improved encoder-decoder architecture, adaptive masked Transformer, and multi-scale feature fusion strategy to simultaneously perform tumor region segmentation and pathological type classification. Five-fold cross-validation was employed for result verification.Results: In the test set evaluation, BrainTumNet achieved an Intersection over Union (IoU) of 0.921, Hausdorff Distance (HD) of 12.13, and Dice Similarity Coefficient (DSC) of 0.91 for tumor segmentation. For tumor classification, it attained a classification accuracy of 93.4% with an Area Under the ROC Curve (AUC) of 0.96. Performance remained stable on the external validation set, confirming the model’s generalization capability.Conclusion: The proposed BrainTumNet model achieves high-precision diagnosis of brain tumor segmentation and classification through a multi-task learning strategy. Experimental results demonstrate the model’s strong potential for clinical application, providing objective and reliable auxiliary information for preoperative assessment and treatment decision-making in brain tumor cases.

With the development of the Internet of things (IoT), federated learning (FL) has received increasing attention as a distributed machine learning (ML) framework that does not require data exchange. However, current FL frameworks follow an idealized setup in which the task size is fixed and the storage space is unlimited, which is impossible in the real world. In fact, new classes of these participating clients always emerge over time, and some samples are overwritten or discarded due to storage limitations. We urgently need a new framework to adapt to the dynamic task sequences and strict storage constraints in the real world. Continuous learning or incremental learning is the ultimate goal of deep learning, and we introduce incremental learning into FL to describe a new federated learning framework. New generation federated learning (NGFL) is probably the most desirable framework for FL, in which, in addition to the basic task of training the server, each client needs to learn its private tasks, which arrive continuously independent of communication with the server. We give a rigorous mathematical representation of this framework, detail several major challenges faced under this framework, and address the main challenges of combining incremental learning with federated learning (aggregation of heterogeneous output layers and the task transformation mutual knowledge problem), and show the lower and upper baselines of the framework.

A key feature of federated learning (FL) is that not all clients participate in every communication epoch of each global model update. The rationality for such partial client selection is largely to reduce the communication overhead. However, in many cases, the unselected clients are still able to compute their local model updates, but are not “authorized” to upload the updates in this round, which is a waste of computation capacity. In this work, we propose an algorithm FedUmf—Federated Learning with Unauthorized Model Fusion that utilizes the model updates from the unselected clients. More specifically, a client computes the stochastic gradient descent (SGD) even if it is not selected to upload in the current communication epoch. Then, if this client is selected in the next round, it non-trivially merges the outdated SGD stored in the previous round with the current global model before it starts to compute the new local model. A rigorous convergence analysis is established for FedUmf, which shows a faster convergence rate than the vanilla FedAvg. Comprehensive numerical experiments on several standard classification tasks demonstrate its advantages, which corroborate the theoretical results.

Language bias stands as a noteworthy concern in visual question answering (VQA), wherein models tend to rely on spurious correlations between questions and answers for prediction. This prevents the models from effectively generalizing, leading to a decrease in performance. In order to address this bias, we propose a novel modality fusion collaborative de-biasing algorithm (CoD). In our approach, bias is considered as the model’s neglect of information from a particular modality during prediction. We employ a collaborative training approach to facilitate mutual modeling between different modalities, achieving efficient feature fusion and enabling the model to fully leverage multimodal knowledge for prediction. Our experiments on various datasets, including VQA-CP v2, VQA v2, and VQA-VS, using different validation strategies, demonstrate the effectiveness of our approach. Notably, employing a basic baseline model resulted in an accuracy of 60.14% on VQA-CP v2.

Background: Meningiomas and gliomas represent the most common benign and malignant brain tumors, where accurate segmentation is essential for clinical assessment and surgical planning. Although magnetic resonance imaging (MRI) serves as a crucial diagnostic tool, precise segmentation remains challenging due to significant morphological and structural variations between tumor types and surrounding complex soft tissues. While Mamba models demonstrate excellence in sequence processing and attention mechanisms show promising performance, both face limitations in feature extraction and computational efficiency, respectively. To address these challenges, we propose the MamTrans algorithm, which integrates state-space models (SSMs) with attention mechanisms to significantly improve computational efficiency while maintaining segmentation accuracy. Methods: This study utilized 418 cases of axial T1-weighted contrast-enhanced MRI data of brain tumors, comprising 177 cases of high-grade gliomas and 241 cases of meningiomas. To validate the findings, five-fold cross-validation was employed. Results: The newly algorithm MamTrans achieved promising segmentation results in the high-grade glioma segmentation experiment, with an intersection over union (IoU) of 88.12, a Dice similarity coefficient (DSC) of 89.23, and a Hausdorff distance (HD) of 12.67. In the meningioma segmentation experiment, its segmentation metrics were IoU of 90.26, DSC of 91.27, and HD of 15.14, on the external dataset, the model obtained IoU of 90.34, DSC of 91.25, and HD of 14.17, outperforming other segmentation models such as U-Net, DeepLab, and Attention U-Net. Conclusions: The research results demonstrate that the proposed MamTrans algorithm outperforms various segmentation models in the segmentation tasks of gliomas and meningiomas. Innovatively, this single algorithm achieves high-precision segmentation for two tumor types with remarkably different morphologies, while significantly reducing model complexity and computational overhead, exhibiting substantial clinical application value.