From left to right CVIT members Cindy McCabe, Fong Chi Ho, Ehsan Abadi, Saman Sotoudeh Paima, Ehsan Samei, Mojtaba Zarei, and Mridul Bhattarai.
Last week, CVIT member Saman Sotoudeh-Paima received the Finalist for the Robert F. Wagner all-conference best student paper award at SPIE Medical Imaging conference held in San Diego, California. The SPIE medical imaging chapter is focused on the latest advances in image processing, physics, computer-aided diagnosis, perception, image guided procedures, biomedical applications, ultrasound, informatics, radiology and digital computational pathology.
Saman, togethers with co-authors Dr. Ehsan Abadi and Dr. Ehsan Samei, presented a study about a new CT imaging harmonizer providing robust pulmonary emphysema quantifications and enabling objective disease characterizations in large-scale, multi-center, and longitudinal studies. In particular, pulmonary emphysema is a form of Chronic Obstructive Pulmonary Disease (COPD) and a chronic lung condition that results in a breakdown of alveoli walls. Quantitative Computed Tomography is increasingly used to assess the presence or progression of emphysema. However, CT quantifications are affected by the acquisition protocols and scanner makes and models. This variability is a major concern for cross-sectional and longitudinal disease characterizations with largescale, multi-institutional datasets. Therefore, CT images need to be harmonized to reflect the patient condition and not the attributes of the imaging systems.
The proposed new framework, named CT-HARMONICA, was developed using a virtual imaging trial (VIT) platform at the Center for Virtual Imaging Trials. CT-HARMONICA transforms CT images to a reference quality index (iso resolution and noise conditions) enabling robust emphysema quantifications across varied CT conditions. The developed harmonizer was applied to clinical data from the COPDGene dataset to demonstrate its clinical utility. The established imaging biomarkers of LAA-950 and Perc15 were selected for emphysema quantifications. Results demonstrated that the harmonizer improved the quantification performance by reducing the bias in LAA-950 from 7.03 (CI: [6.38, 7.68]) to 0.14 (CI: [0.08, 0.20]) after matching for kernel and from 2.48 (CI: [2.21, 2.76]) to −0.34 (CI: [−0.48, −0.20]) after matching for noise settings on the COPDGene dataset.
Saman is a second year Ph.D. student at the Department of Electrical & Computer Engineering, Pratt School of Engineering, Duke University. Currently, he is a Research Assistant at Carl E. Ravin Advanced Imaging Laboratories (RAI Labs) and the Center of Virtual Imaging Trials (CVIT). His research is primarily focused on improving the accuracy and precision of CT quantification for COPD patients, mainly using image processing- and deep learning-based techniques.
