Anomaly detection on medical diagnosis using parametric methods and multiple classifiers

• Grant number: 12/12524-1
• Support Opportunities: Scholarships in Brazil - Master
• Start date: December 01, 2012
• End date: August 31, 2014
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Moacir Antonelli Ponti
• Grantee: Gabriel de Barros Paranhos da Costa
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Despite all the advances in medicine, medical diagnosis remains a very difficult task. Several factors, such as the experience of the physician and the quality of the exam, affect its outcome. Because of this, science is continually seeking tools to assist in this task, trying to reduce the ratio of errors occurred. Technological advances have allowed the creation of CADx (computer-aided diagnosis), systems that help doctors diagnose a patient by processing data obtained in the exams. However, most CADx are specific about the disease, the exam and even the model of the device used to perform it. In this context, anomaly detection methods and multiple-classifiers systems have potential and can be studied. This project proposes the use of methods based on geometric comparison on parametric spaces and serial combination of multiple-classifiers, as a way to improve the quality of the computer-aided diagnosis.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

COSTA, GABRIEL B. P.; PONTI, MOACIR; FRERY, ALEJANDRO C.; ZHOU, ZH; SCHWENKER, F. Partially Supervised Anomaly Detection Using Convex Hulls on a 2D Parameter Space. PARTIALLY SUPERVISED LEARNING, PSL 2013, v. 8193, p. 8-pg., 2013-01-01. (11/16411-4, 12/12524-1)