Ibrahim Patwary Khokan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ibrahim Patwary Khokan has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Kaniz Fatema
Department of Computer Science and Engineering, Health Informatics Research Laboratory, Daffodil International University, Dhaka, Bangladesh
2 shared publications - Tasnim Jahan Tonni
Department of Computer Science and Engineering, Health Informatics Research Laboratory, Daffodil International University, Dhaka, Bangladesh
2 shared publications - Zahid Hasan
Health Informatics Research Lab, Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh
2 shared publications - Asm Ashraf Mahmud
School of Computing Engineering and Physical and Sciences, University of the West of Scotland, Paisley, England
1 shared publication Awlad Hossen Rony
Department of Computer Science and Engineering, Health Informatics Research Laboratory, Daffodil International University, Dhaka, Bangladesh
1 shared publication- Awlad Hossen Rony
Health Informatics Research Lab, Department of Computer Science and Engineering, Daffodil International University, Dhaka, 1216, Bangladesh
1 shared publication
Latest Publications
- Open Access
- 5 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 71347-71369
A Decision Support System for Ovarian Cancer Classification Using Clinical Features From Ultrasound Imaging
Ovarian cancer is the eighth most common cancer in women. Early diagnosis is vital for effective treatment, but it presents challenges that require reliable diagnostic tools. This study proposes an automated Decision Support System (DSS) to enhance the accuracy of ovarian tumor classification, differentiating between normal, abnormal, benign, and malignant cases based on clinical features. The proposed DSS integrates a distance transform–based regional mapping approach to systematically categorize ovarian cystic structures into three configurations: single, multiple, and overlapping regions. This approach enables robust handling of diverse regional types and complex spatial patterns. Although an overlap-handling routine is included in the system, it remains disabled for the current dataset since no overlapping lesions are present. Clinically significant markers are extracted from ovarian ultrasound images, emphasizing key visual properties such as tumor location, size, shape, and architectural distortion. From each Region of Interest (ROI), obtained through bitwise segmentation, twelve prominent clinical features, such as solidity, SIFT key points, and circularity, are derived. Feature relevance is evaluated using the Random Forest Feature Importance method, and a probability density function (PDF) graph is employed to differentiate between normal and abnormal tumors. The proposed DSS achieves outstanding accuracy, with a classification performance of 97.92% in distinguishing normal vs. abnormal and benign vs. malignant tumors. Furthermore, its performance is compared against eight different machine learning models, demonstrating its effectiveness in ovarian tumor diagnosis. The automated DSS effectively enhances diagnostic accuracy for ovarian tumors, providing healthcare professionals with a reliable, time-efficient tool to support clinical decision-making. Integrating clinically significant features and regional mapping capabilities highlights its potential to improve patient outcomes in ovarian tumor diagnosis.
- 5 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 71347-71369
Open AccessA Decision Support System for Ovarian Cancer Classification Using Clinical Features From Ultrasound Imaging
Ovarian cancer is the eighth most common cancer in women. Early diagnosis is vital for effective treatment, but it presents challenges that require reliable diagnostic tools. This study proposes an automated Decision Support System (DSS) to enhance the accuracy of ovarian tumor classification, differentiating between normal, abnormal, benign, and malignant cases based on clinical features. The proposed DSS integrates a distance transform–based regional mapping approach to systematically categorize ovarian cystic structures into three configurations: single, multiple, and overlapping regions. This approach enables robust handling of diverse regional types and complex spatial patterns. Although an overlap-handling routine is included in the system, it remains disabled for the current dataset since no overlapping lesions are present. Clinically significant markers are extracted from ovarian ultrasound images, emphasizing key visual properties such as tumor location, size, shape, and architectural distortion. From each Region of Interest (ROI), obtained through bitwise segmentation, twelve prominent clinical features, such as solidity, SIFT key points, and circularity, are derived. Feature relevance is evaluated using the Random Forest Feature Importance method, and a probability density function (PDF) graph is employed to differentiate between normal and abnormal tumors. The proposed DSS achieves outstanding accuracy, with a classification performance of 97.92% in distinguishing normal vs. abnormal and benign vs. malignant tumors. Furthermore, its performance is compared against eight different machine learning models, demonstrating its effectiveness in ovarian tumor diagnosis. The automated DSS effectively enhances diagnostic accuracy for ovarian tumors, providing healthcare professionals with a reliable, time-efficient tool to support clinical decision-making. Integrating clinically significant features and regional mapping capabilities highlights its potential to improve patient outcomes in ovarian tumor diagnosis.
- 25 June 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 195, 110588
Framework for enhanced respiratory disease identification with clinical handcrafted features
- 25 June 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 195, 110588
Framework for enhanced respiratory disease identification with clinical handcrafted features