D. Aju

Bio: D. Aju is an academic researcher from VIT University. The author has contributed to research in topics: 3D reconstruction & Iterative reconstruction. The author has an hindex of 2, co-authored 3 publications receiving 8 citations.

T1-t2 weighted mr image composition and cataloguing of brain tumor using regularized logistic regression

Abstract: In medical diagnosis, the functional and structural information of the brain as well as the impending abnormal tissues is very crucial and important with an MR image. A collective CAD system that detects and classifies the brain tumor by exploiting the structural information is presented. Magnetic Resonance Imaging (MRI) T1-weighted and T2-weighted images provides suitable variation of contrast between the different soft tissues of the brain which is suitable for detecting the brain tumor. Both the Magnetic Resonance (MR) image sequences are composited using the alpha blending technique. The tumor area in the MR images will be segmented using the Enhanced Watershed Segmentation (EWATS) algorithm. The feature extraction is a means of signifying the raw image data in its abridged form to ease the classification in a better way. An expert classification assistant is tried out to help the physicians to classify the detected MRI brain tumor in an efficient manner. The proposed method uses the Regularized Logistic Regression (RLR) for the efficient cataloguing of brain tumor in which it achieves an effective accuracy rate of 96%, specificity rate of 86% and sensitivity rate of 97%.

A Comparative Objective Assessment on Mesh-Based and SVM-Based 3D Reconstruction of MRI Brain

Abstract: Three-dimensional reconstruction is the process of acquiring the volumetric information from two dimensions, converting and representing it in three dimensions. The reconstructed images play a vital role in the disease diagnosis, treatment and surgery. Brain surgery is one of the main treatment options following the diagnosis of brain damage. The risk associated with brain surgery is high. Reconstructed brain images help the surgeons to visualize the exact location of tumor, plan and perform the surgical procedures from craniotomy to tumor resection with high precision. This survey provides an overview of the three-dimensional reconstruction techniques in MRI brain and brain tumors. The triangle generation methods and support vector machine methods are briefly described. The advantages and disadvantages of each method is discussed. The comparison reveals that Immune Sphere Shaped Support Vector Machine is the best choice when execution time is considered and triangle mesh generation algorithm is the best when visual quality is considered.

A Comparative Survey on Three-Dimensional Reconstruction of Medical Modalities Based on Various Approaches

Abstract: The area of three-dimensional reconstructions has made advances in the recent years. Image reconstruction is the mathematical process which converts the signals obtained from the scanning machine into an image. Particularly in the medical field, the reconstructed images aid in the surgery and research. This survey provides an overview of three-dimensional reconstruction techniques in medical images using various imaging modalities like MRI, CT, biplanar radiography, and light microscopy along with the related disease. The reconstruction techniques such as Marching Cubes, Delaunay’s Triangulation, Outlier Removal, Edge Enhancement and Binarization, False Positive Pruning, Contours, Support Vector Machines, Poisson Surface Reconstruction, Dictionary Learning, and Parametric Models are briefly described. The advantages and disadvantages of each technique are discussed and some possible future directions are suggested.

Survey of Brain Tumor Segmentation Techniques on Magnetic Resonance Imaging

Abstract: Brain tumor extraction is challenging task because brain image and its structure are complicated that can be analyzed only by expert physicians or radiologist. Brain tumor detection and segmentation is one of the most challenging and time consuming task in medical image processing. The image segmentation is a very difficult job in the image processing and challenging task for clinical diagnostic tools. MRI (Magnetic Resonance Imaging) is a visualization medical technique, which provides plentiful information about the human soft tissue, which helps in the diagnosis of brain tumor. Accurate segmentation of the MRI images is extremely important and essential for the exact diagnosis by computer aided clinical tools. There are different types of segmentation algorithms for MRI brain images. This paper is to check existing approaches of Brain tumor segmentation techniques in MRI image for Computer aided diagnosis.

Impact of Model-based Risk Analyses for Liver Surgery Planning.

Abstract: Purpose A model-based risk analysis for oncologic liver surgery was described in previous work (Preim et al. in Proceedings of international symposium on computer assisted radiology and surgery (CARS), Elsevier, Amsterdam, pp. 353–358, 2002; Hansen et al. Int I Comput Assist Radiol Surg 4(5):469–474, 2009). In this paper, we present an evaluation of this method.Methods To prove whether and how the risk analysis facilitates the process of liver surgery planning, an explorative user study with 10 liver experts was conducted. The purpose was to compare and analyze their decision-making.Results The results of the study show that model-based risk analysis enhances the awareness of surgical risk in the planning stage. Participants preferred smaller resection volumes and agreed more on the safety margins’ width in case the risk analysis was available. In addition, time to complete the planning task and confidence of participants were not increased when using the risk analysis.Conclusion This work shows that the applied model-based risk analysis may influence important planning decisions in liver surgery. It lays a basis for further clinical evaluations and points out important fields for future research.

Medical Imaging With Intelligent Systems: A Review

Abstract: A review of how machine learning methodology can be incorporated into the diagnosis of brain tumor and the recent segmentation and classification techniques on brain magnetic resonance images (MRI) is the objective of this paper. Early detection of a brain tumor and its grade facilitates easy diagnosis and treatment. In MRI, the tumor might appear clear to a physician but to extract all features that are not visible to human eye, digital image processing along with machine learning methodology is applied. This article aims to review the current trends in the grading of brain tumor with a focus on gliomas which include astrocytoma and also the reasons why gliomas are to be focused and studied. The leading-edge software packages, evaluation and validation metrics used in various approaches are discussed. With escalating brain tumor cases being reported, there is a demand for more and more advanced imaging methodologies, for their quicker grading and identification. The methodologies used in processing a digital image, when used along with machine learning, aids further diagnosis, treatment, prognosis and pre- and post-surgical procedures. In-depth understanding of medical images and diagnosis provided improvements in terms of accuracy. This was possible because these hybrid techniques assisted radiologists in taking a second opinion. The review article aims to give a brief introduction to brain tumors and imaging of brain tumors with a focus on gliomas. We discuss the different types of tumor and summarize about gliomas, tumor grading, symptoms, diagnosis, and treatment of brain tumor. The review extends with sections on imaging techniques, supervised and unsupervised methods of machine learning, deep learning, the different software's used in the area of medical imaging for image analysis segmentation, visualization, computing, reconstruction, registration, etc. The various imaging protocols that can be embedded and integrated into clinical practices are also listed. An in-depth review of why there is a need for advanced and efficient automated grading methods is exemplified in this work. This multidisciplinary work integrates various disciplines of pathology, radiology, machine learning and image processing. Finally, the current works, future developments, and trends are also discussed.