Accurate and Fully Automatic Hippocampus Segmentation Using Subject-specific 3D Optimal Local Maps into a Hybrid ActiveContour Model
Assessing the structural integrity of the hippocampus (HC) is an essential step towards prevention, diagnosis and follow-up of various brain disorders due to the implication of the structural changes of HC in those disorders. In this respect, the development of automatic segmentation methods that can accurately, reliably and reproducibly segment the HC, has attracted considerable attention over the past decades. This paper presents an innovative 3D fully automatic method to be used on top of the multi-atlas concept for the HC segmentation. The method is based on a subject-specific set of 3D Optimal Local Maps (OLMs) that locally control the influence of each energy term of a hybrid Active Contour Model (ACM). The complete set of OLMs for a set of training images is defined simultaneously via an optimization scheme. At the same time, the optimal ACM parameters are also calculated. Therefore, heuristic parameter fine-tuning is not required. Training OLMs are subsequently combined, by applying an extended multiatlas concept, to produce the OLMs that are anatomically more suitable to the test image. The proposed algorithm was tested on three different and publicly available datasets. Its accuracy was compared with that of state-of-the-art methods demonstrating the efficacy and robustness of the proposed method.
View full article
See complete bios of the authors in the full version of this article.
Mr. Zarpalas is a PhD candidate in the Lab of Medical Informatics, the Medical School, A.U.Th. and an associate researcher at the Information Technologies Institute (ITI), of the Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece. His main research interests include 3D medical image processing, 3D shape analysis, real time 3D reconstruction from multiple passive/active sensors, dynamic mesh coding, 3D motion analysis, 3D object recognition, search and retrieval and classiﬁcation of 3D objects.
Ms. Gkontra has worked as a research assistant at the Information Technologies Institute (ITI) of the Centre for Research and Technology Hellas (CERTH). Her research interests lie in the area of biomedical engineering, including biomedical image and signal processing and analysis, with a special focus on processing of brain MRI, prostate ultrasound, multi-photon microscopy, IVUS, neurocognitive testing and vital signs.
Mr. Daras is a Researcher Grade B (equivalent to Associate Professor) at the Information Technologies Institute (ITI) of the Centre for Research and Technology Hellas (CERTH). His main research interests include multimedia processing, multimedia & multimodal search engines, 3D reconstruction from multiple sensors, dynamic mesh coding, medical image processing and bioinformatics.
Dr. Maglaveras is head of the graduate program in medical informatics at the Aristotle University of Thessaloniki, and is a collaborating researcher with the Center of Research and Technology Hellas, the Institute of Applied Biosciences (CERTH-INAB). His current research interests include nonlinear biological systems simulation, cardiovascular engineering, biomedical informatics, ehealth, AAL, personalized health, biosignal analysis, medical imaging, CDSS and neusciences.