Classification and Detection of Pneumonia | Malaizyo Muzumala | Talks | Data Mining Seminars

Malaizyo Muzumala gave a talk titled "Semi-Automated Classification and Detection of Community Acquired Pneumonia" on May 15, 2024, at 17H30 GMT+2.
This talk is part of a series of seminars organised as part of the "CSC 5741: Data Mining and Warehousing" [1] postgraduate course in the Department of Computer Science [2] at The University of Zambia [3]
Video Timeline
00:00:00 Talk Overview
00:00:30 Presentation Outline
00:01:15 Enterprise Medical Imaging Project
00:02:25 Artificial Intelligence in Radiology
00:03:02 AI in Radiology in Zambia: Challenges and Opportunities
00:09:28 Data Sourcing
00:09:52 Methodology
00:12:57 Results: NASA-TLX
00:13:55 Results: TAM 2
00:14:36 Conclusion
00:15:07 Demonstration
Title of Talk
Semi-Automated Classification and Detection of Community Acquired Pneumonia
Abstract
The use of Artificial Intelligence (AI) techniques in radiological workflows is increasingly becoming mainstream. However, the uptake of AI techniques is still low in low-resource settings in places such as the Global South. This paper presents a study conducted to determine the impact on AI on medical image interpretation turnaround time and its influence of Radiologists' workload when interpreting medical images. Two (2) AI models-a classification model and detection model-were implemented to facilitate the semi-automated interpretation of medical images for Pneumonia. In addition, a Web-based DICOM Viewer was implemented to interface the AI models. To determine the appropriate model configuration, two (2) experts-a Radiologist and Radiology Resident-participated in a focus group discussion aimed at determining how the AI models could facilitate interpretation processes. A comparative controlled experiment was subsequently conducted with 12 Radiology Residents at a large University Teaching Hospital, to assess the impact of AI on the workload and its perceived usefulness. NASA Task Load Index (TLX) and TAM 2 questionnaires were employed to measure the workload and usefulness. The results indicate that the perceived workload is significantly less when using the AI solution, with an overall NASA-TLX score of 1.86. Furthermore, the perceived usefulness of the AI solution is demonstrated through the positive responses for all the eight TAM 2 constructs. This study experimentally demonstrates the potential of utilising AI for the semi-automated interpretation of medical images in low-resource settings.
Biography
Malaizyo Gabriel Muzumala [4, 5] is an Innovator, researcher and starting academic, affiliated with the Enterprise Medical Imaging in Zambia Project [6]. He is the co-founder of Lendbox.io and holds a Bachelor's Degree in Computer Science from the University of Zambia and is pursuing a Masters Degree in the same field. He has deep interest in solutions and problem solving.
[1] lightonphiri.org/teaching
[2] www.cs.unza.zm
[3] unza.zm
[4] emi.org.zm/user/6
[5] datalab.unza.zm/index.php/peo...
[6] emi.org.zm