Browsing by Author "Jim, Risul Islam"

Now showing 1 - 3 of 3

Deep Learning-Based Analysis of COVID-19 X-Ray Images: Incorporating Clinical Significance and Assessing Misinterpretation
(SAGE Publications, 2023-11-06) Bhuiyan, Md. Rahad Islam; Azam, Sami; Montaha, Sidratul; Jim, Risul Islam; Karim, Asif; Khan, Inam Ullah; Brady, Mark; Hasan, Md. Zahid; Boer, Friso De; Mukta, Md. Saddam Hossain
COVID-19, pneumonia, and tuberculosis have had a significant effect on recent global health. Since 2019, COVID-19 has been a major factor underlying the increase in respiratory-related terminal illness. Early-stage interpretation and identification of these diseases from X-ray images is essential to aid medical specialists in diagnosis. In this study, (COV-X-net19) a convolutional neural network model is developed and customized with a soft attention mechanism to classify lung diseases into four classes: normal, COVID-19, pneumonia, and tuberculosis using chest X-ray images. Image preprocessing is carried out by adjusting optimal parameters to preprocess the images before undertaking training of the classification models. Moreover, the proposed model is optimized by experimenting with different architectural structures and hyperparameters to further boost performance. The performance of the proposed model is compared with eight state-of-the-art transfer learning models for a comparative evaluation. Results suggest that the COV-X-net19 outperforms other models with a testing accuracy of 95.19%, precision of 96.49% and F1-score of 95.13%. Another novel approach of this study is to find out the probable reason behind image misclassification by analyzing the handcrafted imaging features with statistical evaluation. A statistical analysis known as analysis of variance test is performed, to identify at which point the model can identify a class accurately, and at which point the model cannot identify the class. The potential features responsible for the misclassification are also found. Moreover, Random Forest Feature importance technique and Minimum Redundancy Maximum Relevance technique are also explored. The methods and findings of this study can benefit in the clinical perspective in early detection and enable a better understanding of the cause of misclassification.
EAH-Net: A Novel Ensemble Attention-Based Hybrid Architecture for Breast Cancer Diagnosis Utilizing Ultrasound Images
(Scopus, 2024-10-31) Hasan, Md. Zahid; Hossain, Shahed; Jim, Risul Islam; Bulbul, Abdullah Al-Mamun; Rahman, Md. Tanvir; Moni, Mohammad Ali
Breast cancer is a complex and often fatal malignancy in women worldwide, requiring thorough medical examinations. Accurately detecting breast cancer is challenging due to its diverse forms, stages, symptoms, and diagnostic techniques. With advancements in artificial intelligence, an automated computerized method can potentially aid radiologists in the early detection of breast cancer. This study presents a novel and robust deep neural network, EAH-Net, for breast cancer diagnosis using ultrasound images. The EAH-Net architecture comprises an ensemble attention module, a modified UNet model that performs segmentation by isolating regions of interest, and a hybrid approach to classify breast cancers accurately. Besides, we employed explainable AI techniques to highlight the most significant regions, assisting radiologists in making more informed decisions. The proposed segmentation framework yields promising outcomes across Jaccard, Precision, Recall, Specificity, and Dice metrics, averaging 89.26 ± 0.36, 91.79 ± 1.13, 92.98 ± 1.08, 99.38 ± 0.35, and 95.26 ± 0.45 percents, respectively. The hybrid classification framework demonstrates outstanding performance with an accuracy of 98.48 ± 0.18%. Overall, EAH-Net offers a reliable and robust computer-aided solution for automated breast cancer diagnosis.
GDRNet: A Novel Graph Neural Network Architecture for Diabetic Retinopathy Detection
(2024-01-24) Hossain, Shahed; Hasan, Md. Zahid; Jim, Risul Islam; Bulbul, Abdullah Al-Mamun; Khan, Risala Tasin; Kaise, M. Shamim; Ali Moni, Mohammad
Diabetic retinopathy is a significant cause of global blindness, requiring practical early detection approaches that could save vision loss in millions of people. However, manual DR analysis is time-consuming and requires skilled clinicians. The advancement of artificial intelligence can facilitate early DR predictions. This study proposed GDRNet, a novel AI-empowered diagnosis system that utilizes graph theory for effective feature selection in DR grading classification. The EyePACS, Messidor, APTOS, IDRid, and DDR datasets are initially balanced using the nearest neighbor oversampling approach. A deep graph correlation network (DGCN) extracts unique features from color eye fundus images by identifying intra-class connections. Then, an iterative random forest algorithm is employed for feature curation, ranking the most significant features from the DGCN. Subsequently, the iterative random forest enhances classification robustness by refining feature representations and aggregating multi-scale contextual information. Finally, a classifier using extreme gradient boosting based on a decision tree algorithm is trained with the optimized features to predict the outcomes. Experimental results reveal that GDRNet outperforms state-of-the-art DR grading classification methods with outstanding performance across various datasets: 100% specificity, 99.67% sensitivity, and 99.80% accuracy on Messidor; 100% specificity, 99.61% sensitivity, and 99.41% accuracy on APTOS; and comparable results on IDRid and DDR datasets. On the EyePACS dataset, it achieves 100% specificity, 99.20% sensitivity, and 99.50% accuracy. Based on these numerical findings, we expect that GDRNet could be utilized in healthcare for early and automated DR detection.