GUI-CAD Tool for Segmentation and Classification of Abnormalities in Lung CT Image

GUI-CAD Tool for Segmentation and Classification of Abnormalities in Lung CT Image

V. Vijaya Kishore (G. Pullaiah College of Engineering and Technology, Kurnool, India) and R.V.S. Satyanarayana (S.V. University College OF Engineering, Tirupathi, India)
Copyright: © 2019 |Pages: 23
DOI: 10.4018/IJBCE.2019010102

Abstract

A vital necessity for clinical determination and treatment is an opportunity to prepare a procedure that is universally adaptable. Computer aided diagnosis (CAD) of various medical conditions has seen a tremendous growth in recent years. The frameworks combined with expanding capacity, the coliseum of CAD is touching new spaces. The goal of proposed work is to build an easy to understand multifunctional GUI Device for CAD that performs intelligent preparing of lung CT images. Functions implemented are to achieve region of interest (ROI) segmentation for nodule detection. The nodule extraction from ROI is implemented by morphological operations, reducing the complexity and making the system suitable for real-time applications. In addition, an interactive 3D viewer and performance measure tool that quantifies and measures the nodules is integrated. The results are validated through clinical expert. This serves as a foundation to determine, the decision of treatment and the prospect of recovery.
Article Preview
Top

Introduction

The computed tomography (CT) technology is broadly utilized as a part of diagnosing and measuring distinctive maladies. CT is the standard scanning for aspiratory regions. For diagnosing lung diseases, CT images are widely utilized examining lung parenchyma knobble disclosure, thickness investigation, and aviation routes examination (Ayman, Farag, Robert, & Renato, 2002). Computed Tomography offers high, determined resolutions and quick securing times. The expansion of picture information alongside the extending volume of thoracic CT contemplates underscores the requirement for Computer Aided Diagnosis (CAD) and plans to help the radiologists (clinicians) performing their day by day indicative assignment to identify little lung nodules, which might indicate lung abnormal growths at a prior and conceivably at more treatable stage. Radiologists are not only the users; but they are also medical experts who contributed in improving and development of whole framework of CAD. A medical expert involvement in the CAD development is beyond image readings and clinical verification. Their involvement in the CAD begins with the restorative examination along with their participation in medical analysis and workflow design. A CAD progress starts at the theoretical level took after by a restorative depiction of the analytic issue. Computer Aided Diagnosis of CT lung image is critical and an essential inventive advancement supporting the radiologists in their diagnostic decisions. The most noteworthy choice of certainty in the estimation of lung abnormal variation from the norm depends on effective segmentation of lung region from the background. Subsequently, it is critical for extricating the lung area for efficient detection or identification of nodules. The innovative development of CAD is based on three essential ideas from the original starting point to the present time (Doi, 2005). The essential methodology for improvement of systems and procedures for recognition and measurement of sores in medicinal images depends on understanding the approaches that are included in reading of images by radiologists. This technique showed up entirely intelligent and straight forward for radiologists to perpetrate image perusing and radiologic determination. Therefore, PC-based algorithms should be developed based on the understandability of image erudition, such as how radiologists can detect the abnormal change in the structure of organs or parts, why they miss some irregularities, and how they can distinguish and recognize dangerous sores. Second method aims in measuring the abnormalities for the improvement of CAD to be effective and fruitful. This achievement is for the utilization of CAD in routine clinical work. In this manner, it is important to create and secure scholarly properties identified with essential technological advancements of CAD plans as licenses (Doi, 2005). The third was to advance more extensive acknowledgment of the CAD idea and to encourage the worldwide circulation of CAD examination by numerous specialists at various establishments. The accomplishment of CAD would require substantial endeavors on research to make use of electronic advancements for a wide range of abnormalities in various modalities, clinical trials and commercialization (Doi, 2005). The main goal of proposed work is to plan and build up an understandable multifunctional Graphical User Interface Device for Computer Aided Diagnosis (GUI-CAD) that performs perceptive developments of lung CT images. The tool is progressed in MATLAB. The various functions implemented are to achieve region of interest (ROI) segmentation and nodule detection. In addition, an interactive 3D viewer and performance measure tool are integrated to quantify and measure the nodules. Besides these, other functions in the GUI are: basic functions such as read images of different formats like tif, jpg, DICOM series and single, displaying information about the loaded image of the selected format, read and save images from and to workspace, determining the value of pixel, histogram pattern, horizontal and vertical profiles of selected lines on the image, color maps of CT window that include CT bone, CT spine, CT mediastinal, auto adjustment of global intensity and selective intensity, image smoothening, manual and auto-thresholding. The algorithm developed for nodule extraction from region of interest in the tool is implemented by using morphological operations, thereby reducing the computational complexity to a greater extent and making the system suitable for real-time applications. The results of the approach are validated through expert clinical opinion. The GUI-CAD can serve as a compelling apparatus in overseeing and early finding of lung tumor. This serves as a foundation to determine, the decision of treatment and the prospect of recovery.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 9: 2 Issues (2020): 1 Released, 1 Forthcoming
Volume 8: 2 Issues (2019)
Volume 7: 2 Issues (2018)
Volume 6: 2 Issues (2017)
Volume 5: 2 Issues (2016)
Volume 4: 2 Issues (2015)
Volume 3: 2 Issues (2014)
Volume 2: 2 Issues (2013)
Volume 1: 2 Issues (2012)
View Complete Journal Contents Listing