Recently our paper called “Computer-Aided Detection and Quantification of Cavitary Tuberculosis from CT Scans” was accepted for publication in MEDICAL PHYSICS journal.
We conducted this study in collaboration with Johns Hopkins University Professors and scientists, and all the laboratory experiments were conducted over in Baltimore, JHU. Drs Andre Kubler and Brian Luna performed imaging of 12 rabbits infected by M. Tuberculosis H37Rv over 7 weeks. Serial CT scans were collected and sent to our lab, CIDI, for the quantitative analysis of the images, particularly cavity formations and its spatial evolution over time. Dr Ziyue Xu, my postdoc, is the leading author for this paper.
Purpose: In this study, we present a computer-aided detection tool for identifying, quantifying, and evaluating tuberculosis cavities in the infected lungs from computed tomography scans.
Methods: Our proposed method is based on a novel shape-based automated detection algorithm on CT scans followed by a fuzzy connectedness (FC) delineation procedure. In order to assess interaction between cavities and airways, we first roughly identified air-filled structures (airway, cavities, esophagus, and etc.) by thresholding over Hounsfield unit (HU) of CT image. Then, airway and cavity structure detection was conducted within the support vector machine (SVM) classification algorithm. Once airway and cavities were detected automatically, we extracted airway tree using a hybrid multi-scale approach based on novel affinity relations within the FC framework and segmented cavities using intensity-based FC algorithm. At final step, we refined airway structures within the local regions of FC with finer control. Cavity segmentation results were compared to the reference truths provided by expert radiologists and cavity formation was tracked longitudinally from serial CT scans through shape and volume information automatically determined through our proposed system. Morphological evolution of the cavitary TB were analyzed accordingly with this process. Lastly, we computed the minimum distance between cavity surface and nearby airway structures by using the linear time distance transform (LTDT) algorithm to explore potential role of airways in cavity formation and morphological evolution.
Results and the other details can be found in our paper. Please visit MEDICAL PHYSICS journal webpage, or download the paper link below.
To our best of knowledge, this is the first study in computerized analysis of cavitary tuberculosis from CT scans.
Computer-Aided Detection and Quantification of Cavitary Tuberculosis from CT Scans
Z.Xu, U.Bagci, A.Kubler, B. Luna, S. Jain, W.R.Bishai, D.J. Mollura