Brain Tumour Segmentation Strategies Utilizing Mean Shift Clustering and Content Based Active Contour Segmentation

Abstract

This paper proposes an automatic brain tumor segmentation using Mean shift clustering and content based active contour segmentation. In diagnosis of the disease medical imaging has more advantages. Many people suffer from brain tumor, it is a serious and dangerous disease. A brain tumor occurs when abnormal cells form in the brain. A proper diagnosis of brain tumor is provided by the medical imaging. The detection of tumor from brain is an important and difficult task in the medical field. One essential part in detecting the tumor is image segmentation. The brain tumor detection technique in the MRI images is very significant in many symptomatic and cure applications. In view of high amount information in MRI pictures, tumor segmentation and classification are hard. The image segmentation is performed on different dataset of MRI cerebrum tumor pictures. The segmentation gives an automatic brain tumor recognition method to build the exactness, yields with decline in the analysis time. The image segmentation technique includes image acquisition, image preprocessing, denoising, and finally the feature extraction. The input image is pre-processed using wiener filtering and the noise is removed using Edge Adaptive Total Variation Denoising (EATVD) technique. Once the noise is removed from the image, it undergoes segmentation process, where Mean Shift Clustering and Content based active segmentation techniques are used. Finally, the features are extracted from the segmented image using gray level co-occurrence matrix (GLCM). The image segmentation is implemented using MATLAB software. Finally, the tumor is segmented and energy, contrast, correlation, homogeneity is extracted, and comparison results are analyzed.

Klasifikasi Bunga Mawar Menggunakan KNN Dan Ekstraksi Fitur GLCM Dan HSV

“…Dimana nilai fitur yang digunakan adalah contrast, correlation, homogenity dan energy. Metode GLCM bekerja dengan menggambil nilai skala keabuan dari objek yang nantinya dijadikan sebagai identitas objek tersebut [2]- [4]. Metode yang digunakan untuk mendapatkan nilai warna yaitu menggunakan metode HSV.…”

Convolutional Neural Network (Cnn) Untuk Klasifikasi Citra Penyakit Diabetes Retinopathy

“…Pengklasifikasi biasanya terdiri dari lapisan yang terhubung penuh. Deep learning adalah proses pelatihan jaringan saraf untuk melakukan tugas yang diberikan [14]- [18]. Algoritme pembelajaran mendalam (CNN) menghitung tingkat keparahan DR dengan menganalisis intensitas piksel pada setiap saluran secara terpisah [2], [6], [8], [19].…”

“…Jaringan yang sangat efisien ini mencapai akurasi tercanggih menggunakan campuran embedding berdimensi rendah dan filter spasial berukuran heterogen21. Peningkatan lapisan konvolusi dan peningkatan pemanfaatan sumber daya komputasi jaringan internal memungkinkan jaringan untuk mempelajari fitur lebih dalam [14], [20]. Misalnya, lapisan pertama mungkin mempelajari tepi sementara lapisan terdalam belajar menafsirkan eksudat keras, fitur klasifikasi DR. Jaringan berisi blok konvolusi dengan aktivasi pada lapisan atas yang mendefinisikan pemetaan fungsional yang komp leks antara input dan variabel respons, diikuti dengan normalisasi batch setelah setiap lapisan konvolusi [8], [21].…”

Classification of Bird Based on Face Types Using Gray Level Co-Occurrence Matrix (GLCM) Feature Extraction Based on the k-Nearest Neighbor (K-NN) Algorithm

“…The widely used degree values are 0°, 45°, 90°, and 135°. In Gray level cooccurrence matrix (GLCM) [14], [22] has feature extraction that produces several features such as contrast, correlation, energy, homogeneity and entropy. Contrast is a feature that can represent the difference in both of the colors level or the grayscale that appears in an image.…”