På svenska

Presentation Information     2017-12-04 (14:15)   •  4307

Speaker Ashis Kumar Dhara   (CBA)
Title Self-learning tool for radiologists using content-based image retrieval technique
Abstract Lung cancer accounts for the highest number of cancer-related deaths as compared to other types of cancer in both men and women. Several studies show that screening of lung cancer can substantially reduce the mortality rate. Pulmonary nodules are potential manifestation of lung cancer and accurate interpretation of pulmonary nodules is essential for the diagnosis of lung cancer and subsequent plan of treatment. Trainee radiologists have to depend on experienced professionals for interpretation of pulmonary nodules. The lack of time of experienced radiologists is the major bottleneck for such traditional learning procedure. In diagnostic decision making, a radiologist typically compares the present case with few closed cases from a medical archive. A large and ever growing number of digital images demands efficient use of relevant cases in diagnostic decision. This self-learning tool could assist radiologists to understand wide variety of nodules by retrieving similar nodules from a large database. Moreover, this tool could be used in diagnosis of lung cancer with minimal user intervention.