1. Home »
  2. Supervisor: Dr. Shehzad Khalid
Supervisor: Dr. Shehzad Khalid

 

Automated Report Generation for Radiology Images

 

Supervisor: Dr. Shehzad Khalid, Professor

Campus/School/Dept: BUIC H-11/BSEAS/CE

Supervisory Record:  

  • PhD Produced: 7
  • PhD Enrolled: 3
  • MS/MPhil Produced: 26
  • MS/MPhil Enrolled:

 

Topic Brief Description:

Advancing healthcare diagnostics through AI-driven automated reporting from radiology images holds immense potential to enhance diagnostic accuracy, reduce reporting times, and improve patient outcomes. This research aims to develop and validate machine learning models capable of interpreting radiology images and generating precise, human-readable reports. By integrating cutting-edge deep learning techniques with domain expertise, this study seeks to address existing challenges in radiology, such as inter-observer variability and the growing workload of radiologists. The proposed solution emphasizes transparency and explainability in AI predictions to ensure trustworthiness and facilitate clinical adoption.

 

Research Objectives/Deliverables:

  1. Develop AI models to automate the generation of diagnostic reports from radiology images.
  2. Evaluate the performance of AI models against human radiologists in terms of accuracy, speed, and reliability.
  3. Investigate the interpretability and explainability of AI-driven radiology reports.
  4. Identify ethical and practical considerations for implementing AI in clinical workflows.

 

Research Questions: 

  1. How accurately can AI models interpret radiology images and generate diagnostic reports compared to human radiologists?
  2. What methods can enhance the interpretability and trustworthiness of AI-driven diagnostic reports?
  3. What are the primary challenges and barriers to the clinical adoption of automated reporting systems?
  4. How can AI-driven systems improve efficiency and reduce diagnostic errors in radiology?

 

Candidate’s Eligibility Profile:

  1. The applicant must have an MS/MPhil/Equivalent degree in electrical engineering with CGPA >0. Besides, applicants must have a strong background in mathematics, programming, optimization theory and related fields.
  2. Experience with programming languages such as MATLAB, or Python is advantageous. Candidates should thrive in an international environment and have excellent communication skills to actively contribute to team research efforts.
  3. Proficiency in spoken and written English is essential. We value independence and responsibility while promoting teamwork and collaboration among colleagues.