Lightweight Framework for Medical Workflow Video Analysis
IDP by: Johannes Klein
Advisor: Prof. Nassir Navab
Supervision by: Benjamin Frisch
, Ralf Stauder
and Aslı Okur
Understanding the clinical workflow is the first step towards new technological developments. As such, it is important to have a framework that allows to analyze procedures, both surgical and non-surgical. The aim of this project is the development of a lightweight and extendable software for the analysis of synchronized videos in order to gain a better understanding of medical workflow. Its performance will be tested in various scenarios.
The definition of projects and the drafting of new proposals in the domain of medical engineering requires a profound understanding of medical procedures. It is necessary that engineers grasp the challenges physicians meet in their daily clinical routines in order to define solutions that present a real improvement of established methods. One major challenge during this first step are the differences in education and scientific jargon between both groups. In particular, a simple explanation of the workflow is often not sufficient for the engineer to understand what exactly happens during the medical procedures.
A way to remedy this problem is the systematic analysis of procedures. In particular, interventions can be filmed from different viewpoints: physician, nurse, fixed cameras, endoscopic camera in the case of minimally-invasive surgery. The aim of this project is the development of a Graphical User Interface (GUI) that allows the simultaneous analysis of such videos. It shall be able to load several videos and synchronize them by adding a time delay. During the review of the videos, it will be possible to take screenshots of individual videos or several videos at once and to add annotations of key moments. Finally, the software should be able to generate a report and export the screenshots to an individual folder such that this information can later be used as a basis for discussions.
Although similar approaches have been pursued by this and other research groups, the originality of this project is the development of a light-weight framework that will serve as a clean and open base for future software developments in the domain of medical workflow analysis. The practicability of this approach will be tested during several surgeries that the student will attend, document and report on.
The project will be conducted in close collaboration of the chair for Computer Aided Medical Procedures (CAMP) at Technische Universität München with the Chirurgische Klinik and Poliklinik at Klinikum Rechts der Isar, with Prof. Marc Martignoni and Dr. Florian Muschalla being the medical contact persons.
Project Outline / Milestones
- Get familiar with the surgical environment.
- Draft requirement specifications in collaboration with the medical colleagues.
Develop a framework that allows analyzing videos recorded during surgery. This framework should include:
- the ability of loading several videos and reproducing them at different speed
- the possibility of synchronizing these videos
- the possibility of creating annotations that are synchronized with the videos
- the possibility of taking screen-shots of individual videos
- a report generator that includes annotations and screenshots
- a GUI to perform the above-mentioned steps
3. Data Collection
- Participate in surgeries, film them and provide reports that can be used for the discussion of the workflow.
4. Documentation and Presentation
- Write a final report that includes both a description of the software and a summary of the surgeries attended.
- Provide commented code in a revision control system.
- Oral presentation plus discussion in our seminar
The student is expected to have followed general lectures introducing him to general and graphical programming, in particular with C++.
| ProjectForm |
| Title: || Lightweight Framework for Medical Workflow Video Analysis |
| Abstract: || Understanding the clinical workflow is the first step towards new technological developments. As such, it is important to have a framework that allows to analyze procedures, both surgical and non-surgical. The aim of this project is the development of a lightweight and extendable software for the analysis of synchronized videos in order to gain a better understanding of medical workflow. Its performance will be tested in various scenarios. |
| Student: || Johannes Klein |
| Director: || Prof. Nassir Navab |
| Supervisor: || Benjamin Frisch |
| Type: || IDP/Klinisches Anwendungsprojekt |
| Area: || Surgical Workflow |
| Status: || finished |
| Start: || 2014/08/01 |
| Finish: || 2015/02/01 |
| Thesis (optional): || |
| Picture: || |