YOLOV10 AND SAM 2.1 FOR ENHANCED MRI SEGMENTATION AND IMPROVED NEUROLOGICAL DISEASE DIAGNOSIS
Journal: International Journal of Advanced Research (Vol.13, No. 02)Publication Date: 2025-02-22
Authors : Anand Ratnakar Suraj Sawant; Jayant Karajagikar;
Page : 454-483
Keywords : Neurological Disease Diagnosis MRI Imaging YOLOv10 Segment Anything Model (SAM) Medical Image Segmentation Explainable AI (XAI);
- ASSOCIATION OF CLINICO-EPIDEMIOLOGICAL AND BIOCHEMICAL PARAMETERS AFFECTING MATERNO- FETAL OUTCOME IN ACUTE LIVER INJURY AND FAILURE IN PREGNANCY
- An epidemiological study of assessment of fetal outcome in hypertensive disorders of pregnancy
- Study of serum calcidiol level in pregnancy and its association with fetal outcome
- ACUTE FATTY LIVER OF PREGNANCY WITH ATYPICAL PRESENTATION: A CASE COMPLICATED BY MULTIORGAN FAILURE AND SEVERE ACUTE PANCREATITIS
- PRAKI - Pregnancy Related Acute Kidney Injury - A Prospective Study of 42 Cases and Outcome
Abstract
Early and accurate diagnosis of neurological diseases through MRI imaging is crucial for effective treatment and patient management. This study presents a deep learning-based approach utilizing a diverse dataset of 12,121 MRI images spanning 12 categories across three major neurological diseases including Brain Tumor Disorders, Alzheimers Disease and Parkinsons Disease. The dataset was structured into 9,894 images for training and 2,227 for validation. Six YOLOv10 variants (N, S, M, B, L and X) were employed for multi-class classification and localization with the YOLOv10-X model achieving the highest diagnostic accuracy. To enhance interpretability the Segment Anything Model (SAM) 2.1 was applied for post-detection segmentation generating precise masks over detected regions further refined with plasma colormap visualization. Comparative evaluations highlight notable improvements in diagnostic performance demonstrating the effectiveness of integrating segmentation and explainable AI. This research contributes to the development of an advanced interpretable AI-driven framework for neurological disease detection.
Other Latest Articles
- ANALISIS MULTI, INTER Y TRANSDISCIPLINARIO DE CONVERGENCIA CURRICULAR PARA LA PROPUESTA DE UN RESTAURANTE-ESCUELA PARA LA UNIVERSIDAD NACIONAL ROSARIO CASTELLANOS
- THE NASAL SEPTUM HEMANGIOMA: A CASE REPORT
- DEMOGRAPHIC TRENDS AND SOCIO-ECONOMIC DISPARITIES IN KAMRUP DISTRICT: A CASE STUDY OF RAJAPAT VILLAGE, NORTH GAUHATI, ASSAM
- ENDOMETRIAL METASTASIS OF BREAST CANCER: A CASE REPORT AND REVIEW OF THE LITERATURE
- EFFECT OF COMPREHENSIVE NURSING INTERVENTION ON SELF-CARE PRACTICES OF PATIENTS UNDERGOING HEMODIALYSIS
Last modified: 2025-03-27 18:03:41