Medical Image segmentation is an important image processing step. Comparing images to evaluate the quality of segmentation is an essential part of measuring progress in this research area. Some of the challenges in evaluating medical segmentation are: metric selection, the use in the literature of multiple definitions for certain metrics, inefficiency of the metric calculation implementations leading to difficulties with large volumes, and lack of support for fuzzy segmentation by existing metrics. First we present an overview of 20 evaluation metrics selected based on a comprehensive literature review. For fuzzy segmentation, which shows the level of membership of each voxel to multiple classes, fuzzy definitions of all metrics are provided. We present a discussion about metric properties to provide a guide for selecting evaluation metrics. Finally, we propose an efficient evaluation tool implementing the 20 selected metrics. The tool is optimized to perform efficiently in terms of speed and required memory, also if the image size is extremely large as in the case of whole body MRI or CT volume segmentation. An implementation of this tool is available as an open source project. We propose an efficient evaluation tool for 3D medical image segmentation using 20 evaluation metrics and provide guidelines for selecting a subset of these metrics that is suitable for the data and the segmentation task.

/pdf/metrics-for-evaluating-3d-medical-image-segmentation-9r93of3dkp.pdf

Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

The segmentation, detection, and extraction of infected tumor area from magnetic resonance (MR) images are a primary concern but a tedious and time taking task performed by radiologists or clinical experts, and their accuracy depends on their experience only. So, the use of computer aided technology becomes very necessary to overcome these limitations. In this study, to improve the performance and reduce the complexity involves in the medical image segmentation process, we have investigated Berkeley wavelet transformation (BWT) based brain tumor segmentation. Furthermore, to improve the accuracy and quality rate of the support vector machine (SVM) based classifier, relevant features are extracted from each segmented tissue. The experimental results of proposed technique have been evaluated and validated for performance and quality analysis on magnetic resonance brain images, based on accuracy, sensitivity, specificity, and dice similarity index coefficient. The experimental results achieved 96.51% accuracy, 94.2% specificity, and 97.72% sensitivity, demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from brain MR images. The experimental results also obtained an average of 0.82 dice similarity index coefficient, which indicates better overlap between the automated (machines) extracted tumor region with manually extracted tumor region by radiologists. The simulation results prove the significance in terms of quality parameters and accuracy in comparison to state-of-the-art techniques.

/pdf/image-analysis-for-mri-based-brain-tumor-detection-and-583xpc0g82.pdf

Image Analysis for MRI Based Brain Tumor Detection and Feature Extraction Using Biologically Inspired BWT and SVM

MRI based medical image analysis: Survey on brain tumor grade classification

A distinctive approach in brain tumor detection and classification using MRI

A review on brain tumor segmentation of MRI images.

https://cyberleninka.org/article/n/1240161.pdf

Brain tumor segmentation based on a hybrid clustering technique

In this paper, we developed a medical image segmentation system based on hybrid clustering techniques to provide an accurate detection of brain tumor with minimal execution time. Two hybrid techniques have been proposed in our proposed medical image segmentation system. The first hybrid technique is based on k-means and fuzzy c-means (KFCM) while the second is based on k-means and particle swarm optimization (KPSO). We compared the two proposed techniques with k-means; fuzzy c-means, expectation maximization, mean shift, and particle swarm optimization using three different benchmark brain data sets. The results clarify the effectiveness of our second proposed technique.

MRI Brain Tumor Segmentation System Based on Hybrid Clustering Techniques

The popularity of clustering in segmentation encouraged us to develop a new medical image segmentation system based on two-hybrid clustering techniques. Our medical system provides an accurate detection of brain tumor with minimal time. The hybrid techniques make full use of merits of these clustering techniques and overcome the shortcomings of them. The first is based on K-means and fuzzy C-means (KIFCM). The second is based on K-means and particle swarm optimization (KIPSO). KIFCM helps Fuzzy C-means to overcome the slow convergence speed. KIPSO provides global optimization with less time. It helps K-means to escape from local optima by using particle swarm optimization (PSO). In addition, it helps PSO to reduce the computation time by using K-means. Comparisons were made between the proposed techniques and K-means, Fuzzy C-means, expectation maximization, mean shift, and PSO using three benchmark brain datasets. The results clarify the effectiveness of our second proposed technique (KIPSO).

Rashid Mokhtar Al-Awadi

Papers

Brain tumor segmentation based on a hybrid clustering technique

MRI Brain Tumor Segmentation System Based on Hybrid Clustering Techniques

Segmentation of Brain Tumor from MRI Images Based on Hybrid Clustering Techniques