Honglun Xu

Bio: Honglun Xu is an academic researcher from University of Texas at El Paso. The author has contributed to research in topics: Knowledge extraction & Prognostics. The author has an hindex of 1, co-authored 3 publications receiving 4 citations.

An automatic approach to lung region segmentation in chest x-ray images using adapted U-Net architecture

Abstract: Segmentation of the lung field is considered as the first and crucial stage in diagnosis of pulmonary diseases. In clinical practice, computer-aided systems are used to segment the lung region from chest X-ray (CXR) or CT images. The task of segmentation is challenging due to the presence of opacities or consolidation in CXR, which are typically produced by overlaps between the lung region and intense abnormalities caused by pulmonary diseases such as pneumonia, tuberculosis, or COVID-19. Recently, Convolution Neural Networks (CNNs) have been shown promising for segmentation and detection in digital images. In this paper, we propose a two-stage framework based on adapted U-Net architecture to leverage automatic lung segmentation. In the first stage, we extract CXR-patches and train a modified U-Net architecture to generate an initial segmentation of lung field. The second stage is the post-processing step, where we deploy image processing techniques to obtain a clear final segmentation. The performance of the proposed method is evaluated on a set of 138 CXR images obtained from Montgomery County’s Tuberculosis Control Program, producing an average Dice Coefficient (DC) of 94.21%, and an average Intersection-Over-Union (IoU) of 91.37%.

Data mining in telemedicine

Abstract: To date, the field of telemedicine is at a critical standpoint and faces a wide variety of challenges. Voluminous data are generated through the interaction among the telemedicine stakeholders, which are ever increasing. It is well conjectured that the successful implementation of telemedicine largely depends on the effective and efficient knowledge extraction from this available data cloud. However, due to lack of proper integration of the data mining techniques, the stakeholders are not getting the full-fledged benefit from this promising platform. Considering the aforementioned fact, this book chapter provides a contrivance to integrate data mining techniques into telemedicine connecting all the stakeholders into a single podium using data engine. It illustrates the prospects of different data mining techniques and their integration for telemedicine. These techniques combine all the basic classification and clustering method including the state-of-the-art artificial neural network (ANN) and deep learning procedure for disease prediction. Two case studies, heart diseases, and breast cancer prediction have been demonstrated applications of the integrated data mining engine.