Health Informatics Research Lab-HIRL

A remarkable beginning to the “Foundations of Research: A 3-Day Workshop for Research Assistants”, organized by the DIU Health Informatics Research Lab (HIRL). ✨

Day 1 of the workshop featured an insightful session on “Introduction to Research Paper, Domain Selection & Literature Searching,” where participants explored the fundamentals of academic research, effective literature search techniques, and strategies for identifying impactful research domains.

The session was moderated by Dr. Md. Zahid Hasan, Associate Professor & Director, HIRL, and Convener, Research Coordinators Committee, Department of CSE.

The session was conducted by Md. Mizanur Rahman, Lecturer (Senior Scale), Department of CSE, and Member, Research Coordinators Committee. His valuable insights, practical guidance, and engaging discussions made the session highly informative, interactive, and inspiring for all participants.

We extend our sincere appreciation to the respected speakers and participants for their enthusiastic participation and active engagement in making the session a great success.

Looking forward to the upcoming sessions and an inspiring journey of learning, research, and innovation ahead.

Alhamdulillah! 🌸

We are grateful to share our latest research publication titled:

📄 “A Decision Support System for Ovarian Cancer Classification Using Clinical Features from Ultrasound Imaging”

Ovarian cancer remains one of the most challenging cancers for women, where early and accurate diagnosis can make a life-changing difference. In this work, we proposed an automated Decision Support System (DSS) that helps classify ovarian tumors into normal, abnormal, benign, and malignant categories using ultrasound imaging and machine learning techniques.

✨ Our proposed system achieved an outstanding classification accuracy of 97.92%, showing promising potential to support healthcare professionals in faster and more reliable clinical decision-making.

This research highlights:
🔹 Clinical feature extraction from ultrasound images
🔹 Intelligent regional mapping techniques
🔹 Machine learning–based classification
🔹 Improved diagnostic support for ovarian tumor analysis

We sincerely thank everyone who supported and inspired us throughout this journey. May this work contribute positively to the healthcare and research community. 🤍

📖 Read the full paper here:
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11506353