International Journal of Imaging Systems and Technology最新文献

{"title":"GBT-SAM: A Parameter-Efficient Depth-Aware Model for Generalizable Brain Tumor Segmentation on mp-MRI","authors":"Cecilia Diana-Albelda,&nbsp;Roberto Alcover-Couso,&nbsp;Álvaro García-Martín,&nbsp;Jesus Bescos,&nbsp;Marcos Escudero-Viñolo","doi":"10.1002/ima.70389","DOIUrl":"https://doi.org/10.1002/ima.70389","url":null,"abstract":"<p>Gliomas are aggressive brain tumors that require accurate imaging-based diagnosis, where automated segmentation plays a central role in assessing tumor morphology and guiding treatment decisions. Manual delineation of gliomas is time-consuming and prone to variability, motivating the use of deep learning to improve consistency and alleviate clinical workload. However, existing methods often fail to fully exploit the information available in multi-parametric MRI (mp-MRI), particularly inter-slice contextual information. In addition, they typically require considerable computational resources and often lack robustness across different tumor types and imaging conditions. We present GBT-SAM, a parameter-efficient deep learning framework that adapts the large-scale Segment Anything Model (SAM) to volumetric mp-MRI data. GBT-SAM reduces training complexity by selecting fewer than 2.6% of slices per scan while still incorporating all four MRI modalities, thereby preserving essential tumor-related information at minimal computational cost. Furthermore, our model is trained using a two-step fine-tuning strategy that combines a depth-aware module to capture inter-slice correlations with lightweight LoRA-based adaptation layers, resulting in only 9.97 M trainable parameters, the lowest among existing SAM-based approaches. GBT-SAM is trained exclusively on the BraTS Adult Glioma dataset and achieves a Dice score of 92.66. Also, it is evaluated on additional Meningioma, Pediatric Glioma, and Sub-Saharan Glioma datasets in order to demonstrate its robust generalization performance. These results highlight GBT-SAM as a computationally efficient and domain-robust framework for brain tumor segmentation from mp-MRI. Our code and models are available at https://github.com/vpulab/gbt-sam.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.70389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148237444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lung Nodule Classification Strategy via Dual-Branch Capsule Network With Routing Optimization","authors":"Feng Zhou,&nbsp;Huiyun Long,&nbsp;Fangfang Gou,&nbsp;Guangqian Kong,&nbsp;Xun Duan","doi":"10.1002/ima.70387","DOIUrl":"https://doi.org/10.1002/ima.70387","url":null,"abstract":"<div>\u0000 \u0000 <p>Lung cancer is one of the cancers with the highest incidence and mortality rates worldwide. The large volume of CT images and the limited resources of radiologists have highlighted the demand for computer-aided diagnostic (CAD) systems. Among existing methods, interpretable capsule networks face prominent challenges in pulmonary nodule classification, such as insufficient feature extraction and high computational costs associated with routing algorithms. To address these issues, this study proposes the BiCaps-VG model, which comprises three components: dual-branch feature extraction, capsule vector routing, and multi-task learning. One branch incorporates a receptive field adaptation module that employs multi-receptive field parallel heterogeneous convolutional paths to extract scale-sensitive nodule features. The other branch is a hierarchical semantic recovery module, which first adopts an encoder-decoder architecture and then leverages a spatial attention mechanism to model global contextual semantics. These two branches are fused to form a unified semantic representation space, thereby enhancing the representational capacity of nodule features. The capsule routing module adopts a variance-guided capsule routing algorithm that calculates activation values based on the variance between predicted low-level capsules and high-level capsules, thus avoiding iterative routing and reducing computational overhead. In the multi-task module, the extracted nodule attribute capsules are used for malignancy prediction, attribute grade classification, and mask reconstruction. Experimental results demonstrate that BiCaps-VG achieves an accuracy of 94.88% in pulmonary nodule malignancy grading, representing a 1.58% improvement over the baseline model. Combined with its inherent interpretability, the model exhibits considerable potential for clinical application. The code is available at https://github.com/fzhou924anpan-prog/BiCaps-VG.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148174455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Miniaturized Graphene-Based THz Biosensor for Noninvasive Early-Stage Breast Cancer Detection and TNM Staging","authors":"Mahesh Kumar Aghwariya,&nbsp;Vanshika Goel,&nbsp;Sasmita Dash,&nbsp;Sudhi Agarwal Kamboj,&nbsp;Tushar Goel","doi":"10.1002/ima.70385","DOIUrl":"https://doi.org/10.1002/ima.70385","url":null,"abstract":"<div>\u0000 \u0000 <p>Breast cancer (BC) is one of the predominant causes of cancer-related mortality among women worldwide. The rising incidence of BC highlights the critical need for portable medical devices that can detect malignancies in breast tissue at an early stage. This paper presents a miniaturized, noninvasive THz biosensor designed to detect the development of tumors in breast tissue at an early stage and determine the TNM stage of BC. The proposed graphene-based biosensor is placed over a SiO₂ substrate using metal radiators and graphene loads. The unique properties of graphene allow frequency reconfiguration ranging from 3.13 to 5.72 THz by adjusting its chemical potential (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>μ</mi>\u0000 <mi>c</mi>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {mu}_c $$</annotation>\u0000 </semantics></math>) through an external DC bias voltage. The proposed biosensor achieves an ultra-wide frequency band of 1.83 THz, a peak directivity of 7 dBi, and a peak gain of 6.1 dBi. Furthermore, a human breast phantom model, mimicking the dielectric characteristics of human breast tissue and nearby lymph nodes in the THz regime, has been developed. Reflectometry analysis is used to evaluate the biosensor's performance in detecting tumors ranging from 1 to 10 mm within breast tissue. Its performance is also evaluated at different angles and positions relative to the tissue, as well as in the presence of cancerous cells in nearby lymph nodes to determine the TNM (Tumor, Node, and Metastasis) staging of BC. The analysis results demonstrate that the proposed biosensor has the potential to detect tumor development in breast tissue at an early stage and determine the TNM stage of BC, making it suitable for both in vivo and ex vivo diagnostic applications.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148174458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and Diagnostic Potential of a Handheld Probe Polarization-Sensitive Optical Coherence Tomography in Oral Mucosa Imaging","authors":"Ting Chang,&nbsp;Chung Yu Chang,&nbsp;Cheng Chieh Yang,&nbsp;Ying-Ju Kuo,&nbsp;Wen Chuan Kuo","doi":"10.1002/ima.70381","DOIUrl":"https://doi.org/10.1002/ima.70381","url":null,"abstract":"<p>Early detection of oral cancer through routine screening is important. Therefore, developing noninvasive, good-resolution, and cost-effective screening tools that provide real-time in vivo oral health imaging is paramount. This study aimed to demonstrate a handheld probe (Polarization-Sensitive Optical Coherence Tomography PS-OCT) in the human oral cavity. A handheld PS-OCT probe was designed, measuring 180 mm in length, 12.7 mm in diameter, and weighing 440 g. The device captures three-dimensional images of the oral cavity within 10 s and creates enface projection images to visualize the distribution of scattering and birefringence. In vivo measurements were performed on high-risk areas in the oral cavities of four volunteers, and ex vivo testing was conducted on two patients with oral cancer. The handheld probe successfully identified various microarchitectures within the oral cavity, including the lower lip mucosa, lower gingiva, buccal mucosa, sublingual area, and tongue. Different oral mucosa layers, including the epithelium, lamina propria, and basement membrane, were well identified. Furthermore, eight clinicians evaluated their ability to differentiate between normal oral and cancerous mucosa using handheld PS-OCT images. The integration of enface scattering and birefringence maps demonstrated superior performance compared to the enface scattering map alone, achieving higher specificity (83.3% vs. 55.0%, <i>p</i> = 0.03) and accuracy (81.3% vs. 58.8%, <i>p</i> = 0.011). The handheld probe PS-OCT shows significant potential as a tool for oral screening, providing a practical and noninvasive solution for early oral cancer detection in clinical settings.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.70381","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148173792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computer Aided Analysis of Interictal SPECT Registered Into MRI Helps Detecting Epileptic Lesions and Cognitive Deficits","authors":"Bomeng Du,&nbsp;Yan Wang,&nbsp;Ziqiang Dong,&nbsp;Zhilin Qian,&nbsp;Mingzhu Zheng,&nbsp;Yu Liu,&nbsp;Xiaoxiao Wang,&nbsp;Xiaoyi Li,&nbsp;Yaying Li","doi":"10.1002/ima.70380","DOIUrl":"https://doi.org/10.1002/ima.70380","url":null,"abstract":"<div>\u0000 \u0000 <p>Interictal single-photon emission computed tomography (SPECT) registered into template (ISRT) was developed to enhance the localization of epileptogenic zone (EZ) and predict cognitive deficits in patients with drug-resistant epilepsy. Eighteen patients (age 26.2 ± 8.1 years) with drug-resistant focal epilepsy underwent interictal SPECT, MRI, and neuropsychological assessments. ISRT was constructed by spatially normalizing SPECT images to the ICBM 152 MNI template and generating hypoperfusion maps. Regional hypoperfusion and its correlation with Mini-Mental State Examination (MMSE) scores were analyzed. Fleiss' kappa (<i>κ</i>) statistic was used to assess inter-reader agreement in EZ lateralization. ISRT achieved moderate inter-reader agreement, with Fleiss' <i>κ</i> improving significantly (<i>t</i> = 3.13, <i>p</i> = 0.035) in the “perfusion + hypoperfusion” setting (<i>κ</i> = 0.378 ± 0.148) compared to the “perfusion only” setting (<i>κ</i> = 0.069 ± 0.118). Hypoperfusion in the Rolandic operculum and lingual gyrus was significantly associated with MMSE scores (<i>r</i> = −0.742, <i>p</i> = 0.00042, FDR <i>p</i> = 0.028; <i>r</i> = 0.721, <i>p</i> = 0.00074, FDR <i>p</i> = 0.028, respectively). ISRT showed potential to improve the consistency of EZ lateralization among readers and provided preliminary insights into cognitive associations. Further development of age-adjusted normative rCBF charts could enhance diagnostic precision.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148167132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Thyroid Disease Detection Using a Deep Learning Approach of Kolmogorov–Arnold Graph Neural Networks","authors":"T. Veda Reddy,&nbsp;Shadab Siddiqui","doi":"10.1002/ima.70379","DOIUrl":"https://doi.org/10.1002/ima.70379","url":null,"abstract":"<div>\u0000 \u0000 <p>Thyroid disease diagnosis using medical imaging has greatly benefited from deep learning by enabling automated feature extraction and reducing reliance on expert interpretation. However, challenges such as limited data availability, inadequate model interpretability, and restricted generalization continue to hinder clinical adoption. To address these issues, this research proposes a hybrid framework based on Kolmogorov–Arnold Graph Neural Networks (KAGNN) integrated with the Sobel Sequence-Based Hiking Optimization Algorithm (SSHOA) for accurate thyroid disease classification and segmentation. KAGNN effectively models spatial dependencies and inter-feature relationships, while a Dilated Composite Backbone Network (DCBN) extracts multi-scale contextual features from ultrasound images. SSHOA optimizes KAGNN parameters, ensuring improved convergence and enhanced diagnostic performance. Furthermore, interpretability is strengthened through the integration of a Score-CAM-based visualization module, enabling class-discriminative activation mapping and providing transparent insights into model predictions for clinical validation. Experimental evaluations on benchmark datasets demonstrate superior segmentation with an IoU of 98.12% and a Dice coefficient of 98.97%, and high classification performance with 99.21% accuracy, 98.85% precision, and 99.04% recall, outperforming models such as DW-Swin, MFMSNet, and GLFNet. Cross-validation, ablation analysis, and optimization fitness curves further validate the robustness and reliability of the proposed framework. Overall, the combination of KAGNN and SSHOA delivers a powerful, interpretable, and scalable solution for thyroid disease detection, offering substantial improvements in both segmentation and classification for clinical decision support.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148099894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DGT-MSB-Net: A Transformer-Based Framework With Boundary Awareness for Accurate Liver Tumor Segmentation in CT Images","authors":"Wenbin Yang,&nbsp;Xinyue Guo","doi":"10.1002/ima.70376","DOIUrl":"https://doi.org/10.1002/ima.70376","url":null,"abstract":"<div>\u0000 \u0000 <p>Liver tumor segmentation in computed tomography (CT) images is challenging due to diverse tumor morphologies, indistinct boundaries, and background noise, which hinder contextual understanding and boundary delineation. To address these issues, we propose DGT-MSB-Net, integrating a dynamically guided Transformer (DGT) with multiscale boundary supervision. The DGT module employs offset-guided deformable sampling and efficient channel modeling to capture complex and irregular tumor structures, while a multiscale spatial-channel attention (MSCA) mechanism leverages skip connections to fuse shallow boundary cues with deep semantic features. In addition, a boundary-aware (BA) module introduces explicit boundary supervision to refine edge prediction and enhance segmentation accuracy. Experiments on LiTS2017 and 3DIRCADb datasets show that DGT-MSB-Net outperforms existing methods, achieving consistent improvements in Dice, Precision, and Recall, validating its effectiveness and robustness. By combining dynamic feature modeling with BA strategies, DGT-MSB-Net effectively addresses the challenges of liver tumor segmentation and demonstrates strong potential for clinical decision support and automated analysis.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148099896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Category-Specific Uncertainty Learning for Retinal Disease Diagnosis","authors":"Lingyi Chu,&nbsp;Fei Lu,&nbsp;Luping Fang,&nbsp;Danli Shi,&nbsp;Kai Jin,&nbsp;Qing Pan","doi":"10.1002/ima.70377","DOIUrl":"https://doi.org/10.1002/ima.70377","url":null,"abstract":"<div>\u0000 \u0000 <p>Integrating artificial intelligence (AI) in retinal disease diagnosis faces challenges in effectively communicating prediction confidence and managing data uncertainty, which is critical for clinical acceptance. To address these limitations, we propose Category-Specific Uncertainty Learning (CSUL), an advanced AI framework for diagnosing eight retinopathies using optical coherence tomography (OCT) images. CSUL leverages a fine-tuned ResNet-50 architecture and an uncertainty-based classification mechanism to quantify prediction confidence. It further establishes category-specific thresholds based on uncertainty distributions from the validation set, optimizing the retention of reliable predictions. For the unlabeled test data, CSUL introduces a pseudo-labeling strategy using K-means++ clustering, enabling the assignment of appropriate category-specific thresholds. The proposed framework achieves exceptional performance, with a thresholded diagnostic accuracy of 99.58% and a retention rate of 85.18% on deterministic samples, outperforming conventional single-threshold models. Notably, for the challenging DRUSEN category, it attains a 97.10% accuracy and a 59.14% retention rate, marking a significant improvement over the existing state-of-the-art methods. In conclusion, the innovative integration of category-specific thresholding and pseudo-labeling in CSUL enhances diagnostic accuracy and reliability, addressing the key challenges in AI-driven retinal disease screening and advancing its clinical applicability.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148099895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FEMMIF—Federated and Explainable Multimodal Medical Image Fusion Framework for Alzheimer’s Disease Detection","authors":"Abdulrahman Alabduljabbar,&nbsp;Sajid Ullah Khan,&nbsp;Youssef N. Altherwy,&nbsp;Fahdah Almarshad,&nbsp;Anas Alsuhaibani","doi":"10.1002/ima.70375","DOIUrl":"https://doi.org/10.1002/ima.70375","url":null,"abstract":"<div>\u0000 \u0000 <p>Multimodal medical image fusion (MMIF) is essential for improving diagnostic accuracy by integrating useful details from various imaging modalities. However, current fusion methods have many challenges, such as modality-specific drawbacks, restricted generalizability, high processing costs, and limited explainability. This paper introduces a novel framework called Federated and Explainable Multimodal Medical Image Fusion (FEMMIF) designed to address several challenges in medical image fusion through a hybrid approach. FEMMIF employs a modality-agnostic dual-branch encoder based on MobileNetV3 to extract both anatomical and functional features. These features are integrated using a cross-attention technique and then processed through a Feature Importance Learning (FIL) module, which dynamically assigns weights to the contributions of each modality. The combined image is subsequently decoded with a decoder that utilizes residual refinement. Evaluations on various multimodal datasets, including MRI, PET, CT, and SPECT, show that FEMMIF consistently outperforms leading MMIF methodologies, achieving a structural similarity index (SSIM) greater than 0.91, improved entropy metrics, and faster inference speeds. The model demonstrates strong generalization across different modalities, reduced sensitivity to misalignment, and produces interpretable outputs suitable for clinical validation. The federated training approach also maintains privacy while achieving convergence comparable to centralized techniques. Overall, the FEMMIF framework demonstrates strong experimental performance but requires further prospective and multicenter validation before clinical deployment.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148099897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trustworthy Predictive Uncertainty Analysis Through Artificial Neural Network-Based Decision-Making","authors":"Arshpreet Kaur,&nbsp;Jagdeep Kaur","doi":"10.1002/ima.70368","DOIUrl":"https://doi.org/10.1002/ima.70368","url":null,"abstract":"<div>\u0000 \u0000 <p>Uncertainty quantification is also an area of classification of Alzheimer's Disease (AD) that has been largely underexplored using multimodal deep learning. Although there have been significant successes in the detection of AD, the factor of predictive uncertainty has not been widely addressed, especially in relation to the diagnosis of AD. The precision of uncertainty estimation is vital for assessing model reliability, as acquiring multimodal data is inherently complex and diagnostic errors may result in very high clinical risks. The inclusion of uncertainty measures can make models more interpretable and indicate predictions that may require additional clinical evaluation. This paper proposes a new density-based evidential network, the Kernel Density Estimation Evidential Deep Learning Network (KDE-EDLNet), that captures aleatoric uncertainty and epistemic uncertainty. Multimodal inputs to the model were tested using the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS) databases. The results of the experiment indicate that the given approach offers superior predictive performance than current techniques and underscore the importance of quantifying uncertainty to improve the reliability and clinical validity of model predictions.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148093710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}