Due to their location, malignant brain tumors are one of humanity's greatest killers, among these tumors, gliomas are the most common. The early detection of gliomas can contribute to the design of ...proper treatment schemes and, thus, improve the survival rate of patients. However, it is a challenging task to detect the gliomas within the complex structure of the brain. The conventional artificial diagnosis is time-consuming and relies on the clinical experience of radiologists. To detect gliomas more efficiently, this paper proposes a noninvasive automatic diagnosis system for gliomas based on the machine learning methods. First, image standardization, including size normalization and background removal, is applied to produce standard images; then, the modified dynamic histogram equalization is implemented to enhance the low-contrast standard brain images, and skull removal based on outlier detection is presented. Furthermore, hybrid features, including gray-level co-occurrence matrix, pyramid histogram of the oriented gradient, modified completed local binary pattern, and intensity-based features are extracted together from the enhanced images, and their dimensions are reduced by principal component analysis. Kernel support vector machine (KSVM) combined with the particle swarm optimization is eventually adopted to train classifiers; in this paper, brain magnetic resonance imaging images are labeled with normal, glioma, and other. The experimental results show that the accuracy, sensitivity, and specificity of the proposed method can reach 98.36%, 99.17%, and 97.83%, respectively, which indicates that the proposed method performs better than many current systems.
This paper discusses the practice of skull removal in the Late Epipalaeolithic and Pre-Pottery Neolithic in the Northern and Southern Levant, a feature which may serve as a basis for comparison of ...funerary customs between regions. Even though the topic of skull removal has been widely debated, factual data remain incomplete and funerary treatment is complex and highly variable. We have undertaken a preliminary synthesis based on 65 sites (MNI: 3001 individuals) distributed across the Southern and Northern Levant, the Upper Tigris and Central Anatolia from the Early Natufian period (13000 cal. BC) through to the first half of the 7th millennium BC. All burial categories were taken into account but the focus of the article is on acephalous skeletons. They represent 6.1% of the corpus but interestingly this proportion changes over time and space. An increase in skull removals is noticed at the beginning of the Pre-Pottery Neolithic but a clear break between the Southern and Northern Levant took place in the MPPNB. Removal then appears to be very selective in the North while it affects more than a third of the dead in the South. In the Southern Levant, removal mostly affects only the cranium and seems to be later in time. Nevertheless, out of this standard interpretative framework, a forgotten grave in Jericho calls into question the probability of pre-burial retrieval and encouraged to be vigilant in digging and interpreting Pre-Pottery Neolithic graves. L'objectif de cette contribution est de proposer un fil conducteur pour une comparaison entre le Nord et le Sud Levant du point de vue des pratiques funéraires (Épipaléolithique final et Néolithique précéramique). Les obstacles à une telle approche sont nombreux à cause notamment du manque de données disponibles et de traitements funéraires complexes et variés. Bien que le prélèvement du crâne soit un sujet largement débattu, les données factuelles demeurent incomplètes et dissociées. Nous avons entrepris une synthèse préliminaire basée sur 65 sites (NMI: 3001 individus) attribués à la période qui va du Natoufien ancien (13000 cal. BC) à la première moitié du 7e millénaire (cal. BC) et situés au Levant nord et sud, dans la haute vallée du Tigre et en Anatolie centrale. Toutes les catégories d'inhumation ont été inventoriées et les squelettes acéphales ont fait l'objet d'une attention spécifique. Ceux-ci représentent 6,1 % du corpus, mais cette proportion varie en fonction des zones géographiques et au fil du temps. Au début du Néolithique Précéramique, la pratique du prélèvement se développe conjointement de part et d'autre du Levant. Mais le PPNB moyen marque une rupture claire alors que le prélèvement devient très sélectif au nord mais concerne, au contraire, plus d'un tiers des défunts au sud. Les données qualitatives apportent également quelques éléments de discussion sur le processus de prélèvement et sur les chaînes opératoires liées au traitement funéraire. Au sud, le prélèvement concerne en majorité le seul bloc crânio-facial et semble intervenir plus tardivement qu'au nord. Toutefois, hors de ce cadre interprétatif standard, une sépulture oubliée de Jéricho témoigne d'un prélèvement antérieur à l'inhumation du cadavre, nous encourageant à davantage de prudence lors de la fouille et de l'interprétation des sépultures du Néolithique précéramique levantin.
Improving Deep Learning for Brain Localization Mohammed Aarif, K O; Borah, Nayana; Mishra, Awakash
2024 IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT),
2024-Feb.-9, Letnik:
5
Conference Proceeding
When utilizing advanced medical imaging techniques like high-resolution magnetic resonance imaging (MRI), the measurement of critical parameters such as total cranial volume (TCV) and the volume of ...the posterior cranial fossa (PCF) plays a pivotal role in volumetric brain analysis. Whole-brain segmentation, a non-invasive methodology, facilitates the precise delineation of various brain regions. Moreover, to ensure the protection of individuals' privacy, a growing trend involves sharing neuroimaging data in a format where the skull information has been removed. Hence, the development of a robust deep learning algorithm that can perform accurate brain segmentation, whether with or without prior skull removal, is an intriguing challenge. One major obstacle in this endeavor is the limited availability of manually annotated reference datasets containing complete whole-brain information and TCV/PCF measurements. In this research, we employ U-Net-based tiling techniques to perform comprehensive brain segmentation on MRI scans, both with and without the skull. Simultaneously, we aim to estimate cranial volumes. To address the shortage of fully annotated whole-brain volumes, we propose a transfer learning approach. Initially, we pre-train the U-Net model using a substantial dataset comprising BrainCOLOR atlases that have been segmented using multiple references, including TCV and PCF measurements. Subsequently, we fine-tune these pre-trained models using a set of carefully curated BrainCOLOR atlases containing precise TCV and PCF labels. This process enables us to improve the accuracy of our brain segmentation models. Furthermore, we extend our methodology to accommodate MRI scans that have undergone skull removal, ensuring the versatility and applicability of our approach across various imaging scenarios.
Efficient segmentation of noisy Magnetic Resonance (MR) brain images is a challenging task, as pre and post surgery decisions are required to make accurately in achieving better medical practices ...while treating brain disorders. This paper presents an automatic segmentation technique to remove non brain tissue (skull, fat, skin, muscle) of noisy MR brain images and to extract brain tissue (cortex and cerebellum). Here, Contourlet transform is applied to denoise a noisy MR brain image and threshold based morphological operations are applied to extract brain region on denoised images. Hence a comparative study is developed on skull removed MR brain images with and without denoising based on similarity index and segmentation error. The experimental results prove that the proposed method yields consistent results irrespective of noise levels.