This is an AI for Health MSc project. Students are elgible to receive a monthly reimbursement of €500,- for a period of six months. For more information please read the requirements.
Clinical Problem
Brief Description of the project Lung cancer is the leading cause of cancer death among both men and women, accounting for nearly 25% of all cancer deaths. While lung cancer typically shows up as pulmonary nodules on CT images, most nodules are benign and do not require further clinical workup. However, radiologist workload is expected to drastically increase soon with the widespread implementation of lung cancer screening programs. Therefore, accurate detection and characterization of pulmonary nodules is crucial for optimizing screening.
Among the different kinds of nodules, subsolid pulmonary nodules are routinely encountered in screening and carry a higher malignancy risk. Clinical reporting guidelines recommend different management strategies based on the radiological appearance and biological behaviour of nodules. For subsolid nodules, the management decisions are dependent on accurate volumetric measurements and tracking the evolution of the solid core.
Solution
The Diagnostic Image Analysis Group (DIAG) at Radboud University Medical Center has brought Veolity, a dedicated software solution for efficient reading of chest CT scans in lung cancer screening programs, to the market with MeVis Medical Solutions (Bremen, Germany). This product is actively being used by several sites in North America, Europe, Asia and Australia. The software includes computer-aided detection and traditional image processing algorithms for volumetric measurements of both solid and subsolid nodules. The aim of the project will be to build on top of this work and develop an algorithm for automatic segmentation of the full nodule, the solid core, and the vessels in subsolid nodules using deep learning.
Data
DIAG has a scientific archive of over 100,000 chest CT scans. The archive also has voxel-level labels for more than 20,000 screen-detected nodules which may be utilized for development of nodule segmentation algorithms. The algorithm(s) that come out of this project will be made publicly available for research use as Docker containers through the grand-challenge.org platform. Significant findings will result in a publication as well.
Embedding
The student will be embedded in the Diagnostic Image Analysis Group and will be supervised by a research member whose research is dedicated to AI for lung cancer screening. We have a strong collaboration with both clinical and radiological experts in lung cancer screening. The student will also have access to a Deep Learning GPU Cluster (SOL) to run deep learning experiments.
Results
The algorithm(s) that come out of this project will be made publicly available for research use as Docker containers through the grand-challenge.org platform. Significant findings will result in a publication.
Requirements
- Students Artificial Intelligence, Data Science, Computer Science, Bioinformatics in the final stages of their Master education.
- You should be proficient in python programming and have a theoretical understanding of deep learning architectures.
- Basic biological / biomedical knowledge is preferred.
Information
- Project duration: 6 months
- Location: Radboud University Medical Center
- More information can be obtained from Kiran Vaidhya Venkadesh (mailto: kiranvaidhya.venkadesh@radboudumc.nl)
