Chuan Zhou - US grants

[unreadable] DESCRIPTION (provided by applicant): Pulmonary embolism (PE) is a leading cause of death in the United States if untreated. Prompt diagnosis and treatment can dramatically reduce the mortality rate and morbidity of the disease. Computed tomographic pulmonary angiography (CTPA) has been reported to be an effective means for clinical diagnosis of PE. Interpretation of a CT scan for PE demands extensive reading efforts from a radiologist who has to visually track a large number of vessels in the lungs to detect suspected PEs. Despite the efforts, the sensitivities were reported to range from 53% to 100%. Preliminary results from the PIOPED II study indicated a sensitivity of 83% by multi-detector CTPA. Computer-aided diagnosis (CAD) can be a viable approach to improving the sensitivity and efficiency of PE detection in CTPA images, as well as reducing inter-observer variability. The overall goal of the proposed project is to develop a robust CAD system that can provide a systematic screening of PE on CTPA scans and serve as a second opinion by automatically alerting the radiologists to suspicious locations on 2D slice and 3D volume rendering display of the CTPA images. We will develop advanced computer vision techniques to enhance the characteristics of vessels, automatically extract the pulmonary vessels, reconstruct the vessel tree, detect candidate PEs, differentiate PE from normal pulmonary structures, and identify the true PEs. The techniques will be specifically designed for analysis of the complex vascular structures on CTPA images. The specific aims of this project include: (1) developing image preprocessing method to enhance vessel characteristics, (2) developing a new rolling balloon technique in combination with structure analysis to track vessels accurately, including vessels partially or completely occluded by PEs, (3) developing multi-prescreening method for the identification of suspicious PEs at different levels of artery branches, especially for PEs in small subsegmental arteries, (4) analyzing PE features for development of classification methods, (5) developing false positive reduction method based on feature analysis and fuzzy rule-based, linear, or neural network classifiers, (6) exploring performance evaluation methodology for computerized detection of PEs, and (7) performing observer ROC study to evaluate the effects of CAD on radiologists' accuracy in PE diagnosis. The relevance of this research to public health lies in the fact that there is substantial false-negative diagnosis of PEs. CAD will potentially reduce missed PEs and improve the chance of timely treatment of patients, thus reducing the mortality rate and speed up recovery from this condition. [unreadable] [unreadable]

Lung cancer is a leading cause of death in the United States. The National Lung Screening Trial (NLST) showed that more lung cancers can be detected at an early stage with low dose CT screening. However, over-diagnosis of indolent lung cancer and benign nodules is one of the major limitations of screening, resulting in unnecessary treatment, biopsy, follow-up, increased radiation exposure, patient anxiety, and cost. Due to a lack of in-depth knowledge of the correlation of structural image features and histologic findings of lung nodules and the absence of validated diagnostic biomarkers for accurate disease categorization, the current diagnosis and management of the screen-detected nodules remains challenging. The goal of this proposed project is to develop a decision support system (DSS) based on quantitative histopathology correlated CT descriptor (q-PCD) of pulmonary nodules using advanced computer vision and machine learning techniques to characterize the histopathologic features of nodules and analyze their correlations with CT image features for improvement of early detection of lung cancer. We hypothesize that the proposed q-PCD analysis will have strong association with histopathologic characterization, and therefore will be a more effective biomarker for differentiation of invasive, pre-invasive, and benign nodules than conventional image-based features or radiologists' visual judgement. Accurate characterization of the nodule types will assist radiologists in making decision for management of the detected nodules; e.g., enabling early detection and treatment of invasive lung cancer, safe surveillance or replacing lobectomy with limited sublobar resection for pre-invasive lung cancer, and sparing biopsy of benign nodules, thereby reducing morbidity and costs in lung cancer screening programs. Our major specific aims are to 1) collect a large database of LDCT screening cases from NLST project and our institute to develop automated image analysis methods, 2) to develop a new DSS based on quantitative pathologic correlated CT descriptors (q-PCD) of lung nodules, 3) validate the effectiveness of DSS in lung cancer diagnosis. To achieve these aims, we will collect a large data set from the National Lung Screening Trial (NLST) and our institute. The collected database will include the baseline and follow up scans, pathology data, demographic information and other information provided by NLST. We will develop automated segmentation methods to extract the volumes of the solid and sub-solid components of detected lung nodules, develop quantitative methods to characterize the radiologic and pathologic features of lung nodules as well as the surrounding lung parenchyma, develop a novel radiopathomics strategy to correlate pathomics with radiomics, and to identify new imaging biomarkers. We will develop a clinically-translatable DSS with a joint biomarker combining both image and patient information, and evaluate its performance in lung cancer diagnosis, including its effectiveness in baseline screening CT exams and in follow up exams.