Brain tumor segmentation approach based on the extreme learning machine and significantly fast and robust fuzzy C-means clustering algorithms running on Raspberry Pi hardware

• Published in: Medical hypotheses Vol. 136; p. 109507
• Main Authors: ŞİŞİK, Fatih, SERT, Eser
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2020
• Subjects: Algorithms; Brain - diagnostic imaging; Brain Neoplasms - diagnosis; Brain tumor segmentation; Cluster Analysis; Diagnosis, Computer-Assisted - instrumentation; Diagnosis, Computer-Assisted - methods; Extreme learning machine; Fuzzy Logic; Glioblastoma - diagnosis; Humans; Image Processing, Computer-Assisted - methods; Magnetic Resonance Imaging; Neurons - metabolism; Raspberry Pi; Segmentation; Significantly fast and robust fuzzy C-means clustering; Software; Support Vector Machine; Brain tumor segmentation; Raspberry Pi; Extreme learning machine; Segmentation; Magnetic resonance imaging; Significantly fast and robust fuzzy C-means clustering
• ISSN: 0306-9877; 1532-2777; 1532-2777
• DOI: 10.1016/j.mehy.2019.109507

•In this study, brain tumor segmentation was performed using ELM and FRFCM approaches.•BTS-ELM-FRFCM approach was run on Raspberry PI hardware.•ELM and FRFCM are new algorithms with high performance.•A system to be used as mobile in hospitals is designed.•Experimental studies reveal the superiority of the proposed method. Automatic decision support systems have gained importance in health sector in recent years. In parallel with recent developments in the fields of artificial intelligence and image processing, embedded systems are also used in decision support systems for tumor diagnosis. Extreme learning machine (ELM), is a recently developed, quick and efficient algorithm which can quickly and flawlessly diagnose tumors using machine learning techniques. Similarly, significantly fast and robust fuzzy C-means clustering algorithm (FRFCM) is a novel and fast algorithm which can display a high performance. In the present study, a brain tumor segmentation approach is proposed based on extreme learning machine and significantly fast and robust fuzzy C-means clustering algorithms (BTS-ELM-FRFCM) running on Raspberry Pi (PRI) hardware. The present study mainly aims to introduce a new segmentation system hardware containing new algorithms and offering a high level of accuracy the health sector. PRI’s are useful mobile devices due to their cost-effectiveness and satisfying hardware. 3200 training images were used to train ELM in the present study. 20 pieces of MRI images were used for testing process. Figure of merid (FOM), Jaccard similarity coefficient (JSC) and Dice indexes were used in order to evaluate the performance of the proposed approach. In addition, the proposed method was compared with brain tumor segmentation based on support vector machine (BTS-SVM), brain tumor segmentation based on fuzzy C-means (BTS-FCM) and brain tumor segmentation based on self-organizing maps and k-means (BTS-SOM). The statistical analysis on FOM, JSC and Dice results obtained using four different approaches indicated that BTS-ELM-FRFCM displayed the highest performance. Thus, it can be concluded that the embedded system designed in the present study can perform brain tumor segmentation with a high accuracy rate.