Consultation System for Lung Nodule Detection

This project will develop a computer-assisted consultation system for clinical radiologists in thedetection of lung nodules (cancer) on chest radiographs. An automated screening of digital chestradiographs can be further developed when this system is fully tested in various clinical settings. Thesuccess of this project will inspire revolutionary improvements in other cancer diagnostic proceduresthrough further research and development. We have demonstrated that the newly developed "visiontype" neural network and training methods for the detection of lung nodules are also applicable to thedetection of microcalcifications on mammograms by presenting microcalcification patterns in the training.The pre-scan methods and vision type neural networks simulate radiologists' routine practices in readingchest radiographs Radiologists' viewing patterns and decision making processes will be modeled andconverted to computer readable form. Preliminary studies have shown the promise of this approach.The Phase I study will address issues related to the differentiation of end-on vessels from true nodules.The plan of the Phase II study is to (i) analyze the learning patterns of the vision type neural network,(ii) consolidate the research outcome of the neural network learning, and (iii) implement a prototypeconsultation system for clinical use.