At present, multi-disease fundus image classification tasks still have the problems of small data volumes, uneven distributions, and low classification accuracy. In order to solve the problem of large data demand of deep learning models, a multi-disease fundus image classification ensemble model based on gradient-weighted class activation mapping (Grad-CAM) is proposed. The model uses VGG19 and ResNet50 as the classification networks. Grad-CAM is a data augmentation module used to obtain a network convolutional layer output activation map. Both the augmented and the original data are used as the input of the model to achieve the classification goal. The data augmentation module can guide the model to learn the feature differences of lesions in the fundus and enhance the robustness of the classification model. Model fine tuning and transfer learning are used to improve the accuracy of multiple classifiers. The proposed method is based on the RFMiD (Retinal Fundus Multi-Disease Image Dataset) dataset, and an ablation experiment was performed. Compared with other methods, the accuracy, precision, and recall of this model are 97%, 92%, and 81%, respectively. The resulting activation graph shows the areas of interest for model classification, making it easier to understand the classification network.

Lung cancer ranks among the world’s most prevalent and deadly diseases. Early detection is crucial for improving patient survival rates. Computed tomography (CT) is a common method for lung cancer screening and diagnosis. With the advancement of computer-aided diagnosis (CAD) systems, deep learning (DL) technologies have been extensively explored to aid in interpreting CT images for lung cancer identification. Therefore, this review aims to comprehensively examine DL techniques developed for lung cancer screening and diagnosis. It explores various datasets that play a crucial role in lung cancer CT image segmentation and classification tasks, analyzing their differences in aspects such as scale. Next, various evaluation metrics for measuring model performance are discussed. The segmentation section details convolutional neural network-based (CNN-based) segmentation methods, segmentation approaches using U-shaped network (U-Net) architectures, and the application and improvements of Transformer models in this domain. The classification section covers CNN-based classification methods, classification methods incorporating attention mechanisms, Transformer-based classification methods, and ensemble learning approaches. Finally, the paper summarizes the development of segmentation and classification techniques for lung cancer CT images, identifies current challenges, and outlines future research directions in areas such as dataset annotation, multimodal dataset construction, multi-model fusion, and model interpretability.

Retinal diseases are the leading causes of visual impairment, and early diagnosis is essential for treatment. Optical coherence tomography (OCT), a non-invasive imaging technique, provides high-resolution images for retinal disease classification; however, its complexity and the limitations of manual diagnosis require efficient automated classification methods. To enableearly clinical diagnosis, this paper proposes a Convolutional Block Attention Module (CBAM)- Automatic Mixing Precision (AMP) network (CANet) for automated classification of retinal images. The model categorizes diabetic macular oedema (DME), choroidal neovascularisation (CNV), drusen. and normal cases, which is built upon the ResNet-34 architecture. CBAM is introduced into the residual block to propose the CBAM-Block residual block embedded in the ResNet-34 network model, which combines the channel and spatial attention mechanism to enhance the lesion feature extraction capability. AMP is used to accelerate the training and combine with transfer learning to enhance the model generalization. Meanwhile, median filtering, normalization, dynamic thresholding to remove white edges and data enhancement are used to optimize data quality and alleviate the problem of category imbalance. Classification experiments were performed on the OCT-2017 dataset for the four categories and ablation experiments were performed to demonstrate their effectiveness. The total classification accuracy of the model reaches 0.9890, the AUC value of all categories is 1, where the recall of CNV reaches 1. CBAM, AMP, and transfer learning improve the classification accuracy by 0.9%, 1.6%, and 9.4%, respectively, and the ablation experiments likewise prove that the model remains highly robust to noisy data. The experimental results show that the CANet model significantly improves the OCT image classification performance through multi-module integration, which provides an efficient and reliable technical solution for the automated diagnosis of retinal diseases.

Lung cancer (LC) is a malignant tumor that poses a serious threat to human health. Positron emission tomography/computed tomography (PET/CT) imaging, which integrates both anatomical structure and metabolic activity, plays a crucial role in the auxiliary diagnosis of LC. Despite its advantages, the automated classification of LC subtypes is challenged by the overlapping imaging features among different subtypes and the complex morphological characteristics of the lesions. To address the aforementioned challenges, this paper proposes EfficientNet–MobileViT adaptive weighted fusion network, a dual-branch adaptive weight fusion network based on deep learning for LC classification using fused PET/CT images. The method employs a pretrained efficientnet-B1 as the local path to extract detailed structural features, while MobileViT serves as the global path to capture long-range contextual semantic information. A Transformer module is simultaneously introduced to facilitate cross-branch feature interaction. Furthermore, an adaptive weight fusion mechanism is designed to dynamically adjust the contribution of each feature branch during the classification process. Experimental results demonstrate that the proposed method achieves a classification accuracy of 0.9389 on the Lung-PET-CT-DX dataset for the three-class classification task of lung adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. It provides new insights for research on intelligent analysis and computer-aided diagnosis of LC using fused PET/CT images.

Background: Alzheimer's disease (AD) and frontotemporal dementia (FTD) exhibit substantial overlap in clinical manifestations and patterns of brain functional degeneration, which poses significant challenges for automated classification based on electroencephalography (EEG). Objective: This study aims to develop an EEG-based framework capable of simultaneously capturing temporal dynamics and frequency-related characteristics of EEG signals for discrimination among AD, FTD, and cognitively normal (CN) subjects. Methods: A Dual-Branch Time-Frequency Fusion Network (DBTF-Net) based on routine clinical resting-state EEG recordings acquired under eyes-closed conditions is proposed. The model employs parallel temporal and frequency branches to process raw EEG time-series signals and their corresponding time-frequency representations. A global temporal dependency construction mechanism is introduced in the temporal branch to capture both local temporal patterns and long-range temporal dependencies. Feature-level fusion is then performed across the two branches to achieve a collaborative representation of multidimensional brain functional information. The proposed method was systematically evaluated on one three-class classification task (AD versus FTD versus CN) and multiple binary classification tasks. Results: Experimental results from five-fold cross-validation at the epoch level show the classification accuracies of DBTF-Net as 86.36%±4.28%, 83.01%±6.15%, 92.13%±10.35%, and 88.74%±7.69%% for AD versus FTD versus CN, AD versus CN, FTD versus CN, and AD versus FTD, respectively. Conclusions: The proposed DBTF-Net leverages temporal and time-frequency information in EEG signals and provides classification of AD and FTD. Visualization analysis further indicates that the model attends to disease-relevant discriminative patterns in time-frequency representations, enhancing the interpretability of its classification decisions.

Alzheimer’s disease (AD) is a neurodegenerative disorder, and mild cognitive impairment (MCI) represents a transitional stage between AD and cognitively normal (CN) individuals. Early diagnosis is clinically important for delaying disease progression. To address the limitations of single-modal approaches and the insufficient modeling of complex cross-modal interactions in existing multimodal fusion methods, this paper proposes a multimodal deep learning (DL) classification framework integrating structural magnetic resonance imaging (sMRI) and clinical features. The framework employs a 3D ResNet-34 to extract imaging features and a multilayer perceptron to encode clinical data. A bidirectional cross-modal attention mechanism enhances associations between imaging and clinical modalities, followed by an adaptive gated fusion module that dynamically integrates concatenated global multimodal features with cross-modal interaction features. To evaluate the robustness of the proposed framework, all experiments were repeated using five different random seeds, and the results are reported as mean ± standard deviation. Experimental results demonstrate competitive performance across multiple classification tasks, achieving accuracies of 95.67% ± 1.70% for three-class classification (CN vs MCI vs AD) and 93.64% ± 2.36% for four-class classification (CN vs early MCI (EMCI) vs late MCI (LMCI) vs AD). For binary classification (AD vs CN, AD vs MCI, MCI vs CN, and EMCI vs LMCI), the method achieves accuracies of 96.83% ± 1.53%, 95.33% ± 1.00%, 95.83% ± 1.39%, and 93.61% ± 2.35%, respectively. The proposed framework provides an effective solution for multimodal DL-based computer-aided diagnosis of AD.