International Journal of Imaging Systems and Technology最新文献_第8页

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-26

引用次数: 0

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-26

引用次数: 0

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-19

引用次数: 0

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-19

引用次数: 0

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-19

引用次数: 0

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-19

引用次数: 0

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-16

引用次数: 0

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-16

引用次数: 0

Advancing Cervical Cancer Classification Through a Fusion of CNN and Vision Transformer Models 通过融合CNN和视觉变压器模型推进宫颈癌分类

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-06 DOI: 10.1002/ima.70352

Fida Hussain Dahri, Ghulam Mustafa, Ashfaque Khowaja, Awais Khan Jumani, Vania V. Estrela, Asif Ali Laghari

{"title":"Advancing Cervical Cancer Classification Through a Fusion of CNN and Vision Transformer Models","authors":"Fida Hussain Dahri, Ghulam Mustafa, Ashfaque Khowaja, Awais Khan Jumani, Vania V. Estrela, Asif Ali Laghari","doi":"10.1002/ima.70352","DOIUrl":"10.1002/ima.70352","url":null,"abstract":"<div>\u0000 \u0000 <p>Cervical cancer remains a major contributor to cancer-related mortality among women worldwide, with a disproportionately high burden in low- and middle-income countries. Pap smear imaging is a standard screening modality for detecting precancerous and malignant cervical abnormalities; however, manual interpretation is labor-intensive, subjective, and susceptible to interobserver variability. To mitigate these limitations, this study proposes a hybrid deep learning framework for automated cervical cell classification that integrates Vision Transformers (ViT) with Convolutional Neural Networks (CNN). The proposed framework incorporates a structured preprocessing pipeline, including image resampling and data augmentation strategies such as random horizontal flipping and controlled rotations, to enhance model generalization and mitigate overfitting. Input images are divided into fixed-size patches and processed through a ViT backbone to capture long-range contextual dependencies. Complementary CNN layers are employed to extract localized morphological features critical for cytological analysis. The extracted representations are combined through a feature fusion mechanism and passed to fully connected layers for classification. The ViT component is initialized with pretrained weights and subsequently fine-tuned on cervical cytology datasets. Experimental evaluation on the Herlev and SIPaKMeD datasets achieved classification accuracies of 97.31% and 96.62%, respectively. Ablation analysis showed that the CNN branch improves local morphological feature discrimination, while class-wise evaluation indicated stable performance across multiple cytological categories. These results support the effectiveness of the proposed CNN–ViT fusion framework for automated cervical cell classification and motivate further validation on larger and patient-indexed clinical datasets.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147668164","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}

引用次数: 0

Advanced Machine Learning and Deep Learning Approaches for Accurate Epileptic Seizure Detection Using EEG Signals 利用脑电图信号精确检测癫痫发作的先进机器学习和深度学习方法

IF 2.5 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-04-03 DOI: 10.1002/ima.70342

Malika Garg, Jasbir Kaur, Neelam Rup Prakash

{"title":"Advanced Machine Learning and Deep Learning Approaches for Accurate Epileptic Seizure Detection Using EEG Signals","authors":"Malika Garg, Jasbir Kaur, Neelam Rup Prakash","doi":"10.1002/ima.70342","DOIUrl":"10.1002/ima.70342","url":null,"abstract":"<div>\u0000 \u0000 <p>Epilepsy, a neurological disorder that is caused by improper brain activity that results in seizures, is prevalent in millions of persons across the world and for which diagnosis is extremely crucial for treatment. Early detection of epileptic seizures is paramount as it enables timely intervention, improves quality of life, and prevents potential risks during seizures. Machine learning (ML) and deep learning (DL) algorithms have emerged as powerful tools in revolutionizing medical field, particularly in domains involving images, signals, and other types of visual representations. In our study, we have utilized the capability of these algorithms in exploring their impact on the epileptic seizure detection with the help of EEG Signals. Nine DL models, namely LSTM, GRU, Bi-LSTM, CNN, FCNN, Hybrid CNN-LSTM, EEGNet, Shallow ConvNet, and Hybrid CNN-GRU and seven machine learning models that is, Random Forest, XGBoost, KNN, Logistic Regression, Naïve Bayes, Decision Tree, and Stacking Ensemble are employed for classification of epileptic seizures on EEG signal dataset. All the models have been evaluated using the standard performance metrics for determining the effectiveness of these models on the epileptic seizure classification as epileptic and nonepileptic. Visual representations like accuracy-loss graphs and confusion matrix were also generated for better visual understanding of the performance of the model. Among all DL Models, CNN emerged as the best performing model with 85% accuracy, whereas, among ML models, XGBoost performs best with accuracy of 88%. The study underscores the potential and effectiveness of ML and DL models in detecting complex patterns and generating predictive insights for classification and detection of epileptic seizure from EEG signals.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147668040","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}

引用次数: 0