SEJONG UNIVERSITY College of Software Convergence
Deep Learning for Imaging Data

QuIIL We are highly interested in developing and applying cutting edge computational techniques for resolving real-world problems. Deep learing is, in particular, of our great interest. We focus on developing deep learning techniques for disease detection, diagnosis, and prognosis.

Surveillance and Monitoring Drone System

QuIIL Drones have recently gained much attention for surveillance and monitoring purposes. Drones, equipped with high-resolution camera, computer vision, object recognition, and tracking techniques, enable collecting imaging data from a distance or altitude. We develop computerized methods to process and analyze the data/information obtained from drones.
Our aim is to develop an agricultural surveillance and monitoring system that 1) detects plant pest and disease at early stage, 2) predicts the spread of the pest and disease.

Computer-aided Diagnosis (CAD) for MRI

QuIIL Multiparametric magnetic resonance imaging (MRI) can visualize the more aggressive lesions and significantly improve the detection of clinically significant cancers. However, examining multiparametic imaging is a complex and time consuming process, requiring specific training and expertise.
We develop a MRI CAD system for detecting cancers. The system includes 1) extracting imaging patterns/features 2) selecting the most discriminative features 3) producing a diagnostic cancer prediction map. Our goal is to develop methods to precisely detect and localize cancers on MRI.

Digital Pathology

QuIIL Digital pathology is an emerging practice of computerized image processing, analysis, and interpretation of digitized tissue specimen images at microscopic scales. The practice entails 1) preprocessing/normalization of images, 2) quantification of structural/biochemical/functional tissue characteristics, 3) discovery of useful knowledge, 4) decision making/support.
We have been working on developing segmentation methods for tissues/cells/nuclei as well as machine learning methods for accurate and robust cancer detection, diagnosis, and prognosis. We are also dedicated to developing computational methods to analyze and understand tumor microstructure and heterogeneity.

Content-based Image Retrieval (CBIR)

QuIIL The amount of medical images and data exponentially grows. But, the current practice of cancer pathology is limited in speed and accuracy. The current diagnostic paradigm does not fully describe the complex and complicated patterns of cancer. The development of effecient and intelligent management system will significantly improve the diagnostic accuracy and throughput.
Our approach is to 1) construct a database of previously evaluated cases with clinical information 2) extract image descriptors 3) develop an image retreival prcoess to search for the closest matching cases. We also develop a new scoring scheme that can better describe image chracteristics and measurue image similarities.

Radiology-Pathology Correlation

QuIIL Magnetic resonance imaging (MRI) permits non-invasive visualization of suspicious lesions. Digital pathology enables reproducible and quantitative measures of tissue microstructures. These quantitative measures are not only useful in improving cancer diagnosis and prognosis but also provide an index of tumor heterogeneity.
We investigate the relationship between MRI and digital pathology analysis in a systematic fashion, including advanced image processing and registration, 3-D printing, machine learning techniques. Our goal is to facilitate the detailed histological and prognostic characterization of cancers on MRI.