International Journal of Imaging Systems and Technology最新文献

Lung cancer significantly contributes to cancer mortality worldwide, and prompt diagnosis is essential for enhancing patient outcomes. Identifying the condition at an early stage remains challenging, particularly in regions with limited medical facilities and experienced radiologists. The paper aims to introduce a fully automated DL system capable of identifying, segmenting, and classifying lung cancer at an early phase. This approach aims to enhance the precision and efficacy of lung cancer screening in resource-constrained environments. The recommended architecture has three stages: (1) lung preprocessing, employing a bilateral filter to enhance image quality; (2) lung segmentation, utilizing Otsu's thresholding to delineate lung areas; and (3) lung cancer classification, implementing a modified CNN referred to as the P-Model. The framework was assessed utilizing the publicly available IQ-OTH/NCCD dataset. The proposed framework exhibited high performance metrics, with lung segmentation accuracy at 96%, classification precision at 97%, sensitivity at 96%, and an F1 score of 96%. Additionally, the Matthews correlation coefficient was recorded at 0.9406. The findings indicate that our paradigm surpasses previous studies across all pertinent evaluation metrics. The proposed deep learning approach shows considerable potential for precise detection and classification of lung cancer, particularly in areas with limited resources. This study significantly advances the field of lung cancer detection and has the capacity to enhance healthcare outcomes and patient care standards globally.

The increasing global burden of lung diseases necessitates the development of improved diagnostic tools. According to the WHO, hundreds of millions of individuals worldwide are currently affected by various forms of lung disease. The rapid advancement of artificial neural networks has revolutionized lung disease diagnosis, enabling the development of highly effective detection and classification systems. This article presents dual channel neural networks in image feature extraction based on classical CNN and vision transformers for multi-label lung disease diagnosis. Two separate subnetworks are employed to capture both global and local feature representations, thereby facilitating the extraction of more informative and discriminative image features. The global network analyzes all-organ regions, while the local network simultaneously focuses on multiple single-organ regions. We then apply a novel feature fusion operation, leveraging a multi-head attention mechanism to weight global features according to the significance of localized features. Through this multi-channel approach, the framework is designed to identify complicated and subtle features within images, which often go unnoticed by the human eye. Evaluation on the ChestX-ray14 benchmark dataset demonstrates that our hybrid model consistently outperforms established state-of-the-art architectures, including ResNet-50, DenseNet-121, and CheXNet, by achieving significantly higher AUC scores across multiple thoracic disease classification tasks. By incorporating test-time augmentation, the model achieved an average accuracy of 95.7% and a specificity of 99%. The experimental findings indicated that our model attained an average testing AUC of 87%. In addition, our method tackles a more practical clinical problem, and preliminary results suggest its feasibility and effectiveness. It could assist clinicians in making timely decisions about lung diseases.

Minimally invasive surgery can benefit significantly from automated surgical tool detection, enabling advanced analysis and assistance. However, the limited availability of annotated data in surgical settings poses a challenge for training robust deep learning models. This paper introduces a novel staged adaptive fine-tuning approach consisting of two steps: a linear probing stage to condition additional classification layers on a pre-trained CNN-based architecture and a gradual freezing stage to dynamically reduce the fine-tunable layers, aiming to regulate adaptation to the surgical domain. This strategy reduces network complexity and improves efficiency, requiring only a single training loop and eliminating the need for multiple iterations. We validated our method on the Cholec80 dataset, employing CNN architectures (ResNet-50 and DenseNet-121) pre-trained on ImageNet for detecting surgical tools in cholecystectomy endoscopic videos. Our results demonstrate that our method improves detection performance compared to existing approaches and established fine-tuning techniques, achieving a mean average precision (mAP) of 96.4%. To assess its broader applicability, the generalizability of the fine-tuning strategy was further confirmed on the CATARACTS dataset, a distinct domain of minimally invasive ophthalmic surgery. These findings suggest that gradual freezing fine-tuning is a promising technique for improving tool presence detection in diverse surgical procedures and may have broader applications in general image classification tasks.

Medical image segmentation plays a crucial role in biomedical engineering and computer-aided medical systems. Fully supervised medical image segmentation algorithms have achieved significant performance improvements. However, these improvements often rely on large amounts of finely annotated data, while semi-supervised medical image segmentation can better address this issue. In this work, we propose the MaFMatch model based on the principle of weak-to-strong consistency. It effectively addresses the limitations of current semi-supervised medical image segmentation, such as noise generated by perturbation leading the model to learn in unfavorable directions, and simple feature perturbations being insufficient to explore a broader perturbation space. On the one hand, this approach introduces a mixed data perturbation flow to utilize all pixel information, making the model inclined to consider global semantic information rather than simply discarding unreliable pixels. On the other hand, to fully utilize feature perturbation information flow, we propose a feature augmentation perturbation scheme that simultaneously supplements and discards information from the original feature flow, enabling the model to effectively overcome the diminishing marginal returns brought about by multi-branch perturbations. MaFMatch achieved an mDsc of 90.8 on the automatic cardiac diagnosis challenge (ACDC) dataset. It outperforms most methods across major metrics on both ACDC and LA datasets. The code is available at https://github.com/HandsomeRed/MaFMatch-main.

Accurate segmentation of brain tumors in magnetic resonance imaging (MRI) is critical for diagnosis, treatment planning, and longitudinal monitoring. The development of robust and generalizable deep learning models for tumor segmentation is hindered by challenges such as data privacy, limited annotations, and domain variability across clinical institutions. To address these issues, we propose a dual-model federated learning model for brain tumor segmentation that enables collaborative model training without sharing patient data. The model employs two specialized architectures: a Multi-Scale Encoder U-Net (MSE-UNet) for fine-grained, multi-resolution feature extraction and a Residual Attention Transpose U-Net (ART-UNet) that leverages residual learning and dual attention mechanisms to enhance contextual sensitivity and robustness under non-IID conditions. To ensure effective learning across distributed, heterogeneous clients, we introduce a Dual-Model Architecture-Aware Aggregation (DAAA) strategy, which performs independent, performance-weighted aggregation of each architecture's updates. The proposed method is evaluated on two benchmark datasets, BraTS 2018 and TCGA-LGG, demonstrating superior performance compared to several state-of-the-art baselines. The model achieves Dice scores of 91.30% and 90.10% on BraTS and TCGA-LGG, respectively, with improved IoU, sensitivity, and boundary precision. Ablation studies confirm that each component, including auxiliary supervision, architectural duality, and adaptive aggregation, contributes significantly to overall performance. Clinically, this framework offers a scalable and privacy-preserving solution that can be integrated into real-world healthcare systems without compromising patient data security. By enabling cross-institutional collaboration and ensuring robust performance across diverse imaging protocols, the proposed model facilitates early and accurate tumor delineation, supporting radiologists in critical decision-making processes such as surgical planning, radiotherapy guidance, and follow-up assessment. This study establishes a foundation for practical deployment in federated clinical environments, particularly within resource-constrained or privacy-sensitive institutions.

Skin cancer is a prevalent and potentially life-threatening condition that requires accurate and timely diagnosis. Dermoscopic imaging aids in diagnosis but is often limited by manual interpretation, which can be time–intensive and error–prone. Automated classification systems using convolutional neural networks (CNNs) have shown significant promise in enhancing accuracy and efficiency. To further improve classification performance, we propose a novel deep learning-based Multi–Scale Feature Map Fusion (MFMF) model that extracts and fuses features from multiple convolutional layers. The MFMF module effectively combines these multi–scale features, enabling robust feature capture even with limited datasets. Additionally, a hair removal algorithm is proposed to enhance prediction accuracy through improved image preprocessing. On the HAM10000 dataset, our proposed model achieves an overall accuracy of 96.12%, an AUC of 98.7%, and an F1 Score of 93.29%, along with notable improvements in precision, recall, and sensitivity.

Accurate organ segmentation from magnetic resonance imaging (MRI) or computed tomography (CT) images is essential for surgical planning and decision-making. Traditional fully supervised deep learning methods often exhibit a significant decline in performance when applied to datasets that differ from the training data, thus limiting their clinical applicability. This study proposes a novel segmentation method based on unsupervised domain adaptation, aiming to improve cross-domain segmentation performance without the need for ground truth labels in the target domain. Specifically, our method trains the network with labeled source images and unlabeled target images, introducing a bidirectional feature-prototype contrastive loss to align features across domains, minimizing within-class variations and maximizing between-class variations. To further improve model performance, we propose a prototype-guided pseudo-label fusion module that generates high-quality pseudo-labels for the unlabeled target images between domain prototypes. Experimental results show that our method outperforms other unsupervised domain adaptation segmentation approaches, achieving state-of-the-art performance. Code is available at: https://github.com/WANGSIQII/UDA.git.

Automatic segmentation and classification methods of glioblastomas in magnetic resonance imaging (MRI) scans are essential to overcome the limitations of error-prone manual methods, especially given the intrinsic challenges such as intensity nonuniformity, diverse anatomical brain alterations, and significant variations in tumor shape, size, and location. These complexities pose major hurdles for radiologists in diagnosis and surgical planning, underscoring the critical significance of robust automated solutions. This study presents a novel fully automated approach for segmentation and classification of glioblastoma brain tumors using multi-spectral MRI data. Our proposed framework innovatively integrates two key steps. In the first step, a new level set method is presented for segmentation, which is uniquely enhanced by super-pixel fuzzy entropy-based clustering—a technique designed to effectively handle image inhomogeneities and noise—density peak clustering, and a lattice Boltzmann solver for efficient contour evolution. In the second step, a VGG-16 deep neural network is employed for precise classification. To assess the capability of the proposed method in both segmentation and classification tasks, real T2-weighted and fluid-attenuated inversion recovery magnetic resonance images of glioblastomas from the BraTS 2020 dataset are used simultaneously in a multi-spectral manner. Our segmentation results, evaluated by measuring the Dice coefficient, Jaccard index, sensitivity, specificity, and running time. The mean values (Mean ± Standard deviation) of these metrics are 0.8915 ± 0.0293, 0.8055 ± 0.0478, 0.9535 ± 0.0644, 0.9910 ± 0.0364, 2.2909 ± 0.2597, respectively. Additionally, the average values of accuracy, precision, recall, and F1-score across the fivefold cross-validation of the classification method are 0.9149, 0.9532, 0.9160, and 0.9349, respectively. According to the experiments, our proposed fully automated framework not only achieves superior performance in simultaneous segmentation and classification compared to other state-of-the-art segmentation methods but also offers a robust and efficient solution for clinical applications. While this study demonstrates strong potential, future work will focus on extending the framework for multi-label segmentation of different tumor sub-regions and validating its efficacy on even larger and more diverse clinical datasets.