- Log in to post comments
Introduction to the Seminar
On May 15th, Andrew Shawa, a research student from the Enterprise Medical Imaging in Zambia (EMIZ) project, presented an engaging colloquium titled "Intelligent DICOM Viewers: Orthanc Plugin for Semi-Automated Interpretation of Medical Images." This colloquium was part of a series of seminars for the 2023/24 CSC 5741 course, designed to bridge the gap between academic research and industry applications in the field of medical imaging.
Abstract
Medical image interpretation is a crucial part of radiological workflows, providing valuable input to the final output of the process: medical image interpretation reports. Radiologists typically employ Digital Imaging and Communication in Medicine (DICOM) Viewers. While numerous types of DICOM Viewers have been implemented, there has been arguably little focus on how such software tools can be made more effective by integrating them with Artificial Intelligence services.
This presentation highlighted a study conducted to design and implement an Orthanc Web-based Picture Archiving and Communication System (PACS) plugin DICOM Viewer for facilitating the semi-automated interpretation of medical images using Artificial Intelligence (AI). An Orthanc DICOM Viewer plugin, interoperable with two models—Pneumonia Classification and Detection models—was implemented using the Python programming language.
Implementation and Evaluation
The plugin was evaluated with Radiologist Residents at a large University Teaching Hospital in a controlled setting. The Technology Acceptance Model (TAM) 2 instrument was used to assess its perceived usefulness and ease of use. The TAM 2 constructs were rated positively, with study participants expressing a desire to incorporate other pathologies into the plugin. Additionally, there was a strong interest in integrating similar tools into more widely used DICOM Viewers such as RadiAnt and Weasis.
Impact and Future Implications
The integration of AI models has the potential to reduce the turnaround time and workload involved in interpreting medical images. More significantly, the positive responses related to the perceived usefulness of the tool suggest the potential such tools have in improving the delivery of services at the point of clinical care.
Andrew Shawa's presentation underscored the transformative impact that AI-enhanced DICOM Viewers could have on medical imaging practices. By facilitating semi-automated interpretation, these tools can enhance efficiency and accuracy in radiological workflows, ultimately benefiting patient care.
Conclusion
The colloquium was well-received by the MSc students from The University of Zambia, sparking lively discussions and an increased interest in the potential of AI in medical imaging. Andrew Shawa's work exemplifies the critical role of innovative research in driving advancements in healthcare technology, highlighting the promising future of AI integration in medical imaging.
As part of the ongoing 2023/24 CSC 5741 course series, this colloquium not only provided valuable insights but also inspired future research and development in the field of intelligent medical imaging solutions.