[Paper Review] Automated Tumor Segmentation and Brain Mapping for the Tumor Area

Pranay Manocha, Snehal Bhasme+3 more|arXiv (Cornell University)|Oct 28, 2017

Brain Tumor Detection and Classification10 references3 citations

TL;DR

This paper proposes a two-step GUI-based method for automated brain tumor segmentation and Brodmann area mapping using T2-weighted MRI images. It employs Fuzzy C Means clustering for tumor segmentation and a template-based approach for anatomical localization, achieving robust and accurate results across diverse patient demographics in a dataset of 15 cases.

ABSTRACT

Magnetic Resonance Imaging (MRI) is an important diagnostic tool for precise detection of various pathologies. Magnetic Resonance (MR) is more preferred than Computed Tomography (CT) due to the high resolution in MR images which help in better detection of neurological conditions. Graphical user interface (GUI) aided disease detection has become increasingly useful due to the increasing workload of doctors. In this proposed work, a novel two steps GUI technique for brain tumor segmentation as well as Brodmann area detec-tion of the segmented tumor is proposed. A data set of T2 weighted images of 15 patients is used for validating the proposed method. The patient data incor-porates variations in ethnicities, gender (male and female) and age (25-50), thus enhancing the authenticity of the proposed method. The tumors were segmented using Fuzzy C Means Clustering and Brodmann area detection was done using a known template, mapping each area to the segmented tumor image. The proposed method was found to be fairly accurate and robust in detecting tumor.

Motivation & Objective

• To develop an automated, GUI-aided system for precise brain tumor segmentation in MRI scans.
• To map segmented tumors to specific Brodmann areas for improved neuroanatomical localization.
• To validate the method across diverse patient demographics, including age, gender, and ethnicity.
• To enhance clinical workflow by reducing radiologist workload through automated segmentation and mapping.
• To improve diagnostic accuracy in neurological conditions using high-resolution MRI data.

Proposed method

• Fuzzy C Means (FCM) clustering is applied to segment tumor regions in T2-weighted MRI images.
• A standardized Brodmann area template is used to map the segmented tumor regions to specific cortical areas.
• The method is implemented via a graphical user interface (GUI) to support clinical integration and user interaction.
• The approach uses a dataset of 15 T2-weighted MRI scans from patients aged 25–50, with varied gender and ethnic backgrounds.
• Segmentation accuracy is evaluated based on visual and anatomical consistency with known tumor patterns.
• The system is designed to be robust across diverse patient populations, enhancing clinical reliability.

Experimental results

Research questions

• RQ1 Can Fuzzy C Means clustering effectively segment brain tumors in T2-weighted MRI scans?
• RQ2 Can a template-based approach accurately map segmented tumor regions to Brodmann areas?
• RQ3 How robust is the proposed GUI-based method across diverse patient demographics?
• RQ4 To what extent does the method reduce radiologist workload while maintaining diagnostic accuracy?
• RQ5 Does the integration of anatomical mapping improve clinical interpretation of tumor location?

Key findings

• The proposed method achieved fairly accurate and robust tumor segmentation across all 15 patient cases in the dataset.
• Tumor regions were successfully mapped to specific Brodmann areas using a known anatomical template.
• The system demonstrated consistent performance across variations in age, gender, and ethnicity.
• The GUI-based interface supports practical clinical use and integration into radiology workflows.
• The method shows promise for reducing manual segmentation efforts while maintaining anatomical precision.
• The results indicate that FCM clustering is effective for tumor segmentation in high-resolution T2-MRI data.