Ekstrasi Fitur Citra MRI Otak Menggunakan Data Wavelet Transform (DWT) untuk Klasifikasi Penyakit Tumor Otak

Abstract

<jats:p>&lt;p class="SammaryHeader" align="center"&gt;&lt;strong&gt;ABSTRACT&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;em&gt;The brain is formed from two types of cells: glia and neurons. Glia functions to support and protect neurons, while neurons carry information in the form of electrical pulses known as potential action. The brain regulates and coordinates most of the body's movements, behavior, and homeostasis functions such as heart rate, blood pressure, body fluid balance and body temperature. A brain tumor is a mass of abnormally growing brain cells. Most brain tumors can spread through brain tissue, but rarely spread to other areas of the body. But in the case of benign brain tumors, as they grow they can destroy and suppress other normal brain tissue, which can result in paralysis. Several methods are used to detect disorders of the brain nerve tissue, including: Magnetic Resonance Imaging (MRI). This research is intended to build a classification system for brain image data using Magnetic Resonance Imaging (MRI) with the category, normal, Glioma, metastatic bronchogenic carcinoma or Alzheimer's using Magnetic Resonance Imaging (MRI) so that it can assist in decision making for medical experts. While the method used in this research is Discrete Wavelet Transformation (DWT) for the feature extraction process so that the unique characteristics of an object can be recognized, as well as the classification process using the adaptive neighborhood neural network method. This research is able to integrate the two methods with the acquisition of significant accuracy.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;Keywords&lt;/em&gt;&lt;/strong&gt;&lt;strong&gt;&lt;em&gt; &lt;/em&gt;&lt;/strong&gt;&lt;strong&gt;&lt;em&gt;: &lt;/em&gt;&lt;/strong&gt;&lt;em&gt;feature extraction, classification, MRI, Brain&lt;/em&gt;&lt;/p&gt;&lt;p class="SammaryHeader" align="center"&gt;&lt;strong&gt;ABSTRAK&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;em&gt;Otak terbentuk dari dua jenis sel: glia dan neuron. Glia berfungsi untuk menunjang dan melindungi neuron, sedangkan neuron membawa informasi dalam bentuk pulsa listrik yang di kenal sebagai&lt;/em&gt;&lt;em&gt; potensi aksi&lt;/em&gt;&lt;em&gt;.&lt;/em&gt;&lt;em&gt; &lt;/em&gt;&lt;em&gt;Otak mengatur dan mengkordinir sebagian besar,&lt;/em&gt;&lt;em&gt;gerakan&lt;/em&gt;&lt;em&gt;, &lt;/em&gt;&lt;em&gt;perilaku&lt;/em&gt;&lt;em&gt; dan fungsi tubuh homeostasis seperti detak jantung, tekanan darah, keseimbangan cairan tubuh dan suhu tubuh&lt;/em&gt;&lt;em&gt;.&lt;/em&gt;&lt;em&gt; Tumor otak adalah sekumpulan massa sel-sel otak yang tumbuh abnormal. Sebagian besar tumor otak dapat menyebar melalui jaringan otak, tetapi jarang sekali menyebar ke area lain dari tubuh. Namun pada kasus tumor otak yang jinak, saat mereka tumbuh dapat menghancurkan dan menekan jaringan otak normal lainnya, yang dapat berakibat pada kelumpuhan. Beberapa metode dipergunakan untuk mendeteksi gangguan pada jaringan syaraf otak, diantaranya: &lt;/em&gt;&lt;em&gt;Magnetic&lt;/em&gt;&lt;em&gt; &lt;/em&gt;&lt;em&gt;Resonance Imaging&lt;/em&gt;&lt;em&gt; (MRI)&lt;/em&gt;&lt;em&gt;.&lt;/em&gt;&lt;em&gt; &lt;/em&gt;&lt;em&gt;Penelitian &lt;/em&gt;&lt;em&gt;ini dimaksudkan untuk m&lt;/em&gt;&lt;em&gt;embangun sistem klasifikasi &lt;/em&gt;&lt;em&gt;untuk data citra otak menggunakan Magnetic Resonance Imaging (MRI) dengan kategori, normal, Glioma, metastatic bronchogenic carcinoma atau Alzheimer menggunakan Magnetic Resonance Imaging (MRI) sehingga dapat membantu dalam pengambilan keputusan bagi tenaga ahli dibidang kedokteran. Sedangkan metode yang digunakan dalam penelitian adalah Discrete Wavelet Transformation (DWT) untuk proses ekstrasi fitur (feature extraction) &lt;/em&gt;&lt;em&gt;agar&lt;/em&gt;&lt;em&gt; karakteristik unik dari suatu objek&lt;/em&gt;&lt;em&gt; dapat dikenali&lt;/em&gt;&lt;em&gt;, serta proses k&lt;/em&gt;&lt;em&gt;lasifikasi&lt;/em&gt;&lt;em&gt; meng&lt;/em&gt;&lt;em&gt;gunakan metode adaptive neighborhood neural network. Penelitian ini mampu mengintegrasikan kedua metoda dengan perolehan hasil akurasi yang signifikan.&lt;/em&gt;&lt;/p&gt;&lt;strong&gt;&lt;em&gt;Kata kunci : &lt;/em&gt;&lt;/strong&gt;&lt;em&gt;ekstrasi fitur, klasifikasi, MRI, Otak&lt;/em&gt;</jats:p>

Comparison Measurement and Calculation of Brain Tumor in Mri Modalities Utilising Spin-Echo Pulse Sequence T1-Weighted Contrast and Digital Image Processing Applications

“…Kasus tumor otak disebabkan oleh adanya pertumbuhan sel otak secara cepat dan abnormal (Basyid and Adi, 2014;Adriyanto and Agung, 2018). Berdasarkan penyebarannya, rata-rata tumor otak jarang menyebar ke area lain dari tubuh manusia, namun sering ditemukan penyebaran melalui jaringan otak (Astuti, 2019;Liu et al, 2014). Pada dunia radiologi, sering disebut sebagai benjolan atau Space Occupying Lesion (SOL) (Astuti, 2019).…”

“…Berdasarkan penyebarannya, rata-rata tumor otak jarang menyebar ke area lain dari tubuh manusia, namun sering ditemukan penyebaran melalui jaringan otak (Astuti, 2019;Liu et al, 2014). Pada dunia radiologi, sering disebut sebagai benjolan atau Space Occupying Lesion (SOL) (Astuti, 2019). Pertumbuhan tumor otak biasanya ditandai oleh pertumbuhan massa padat tidak terkendali yang dibentuk oleh sel-sel yang tidak dikehendaki.…”

Comparison Between the Image Information of T2WI FLAIR Sequences and TSE T2WI Axial Slice Brain MRI Examination with Cases of Intracranial Tumors

“…A brain tumor is a mass of abnormal and uncontrolled growth of cells in or around the brain. This growth is not purposeful, is parasitic, and develops at the expense of the human host (Astuti, 2019). Diagnosing a brain tumor usually involves a neurological examination, and diagnostic imaging such as an MRI and requires analysis of brain tissue.…”

Modification CNN Transfer Learning for Classification MRI Brain Tumor

“…The stages in diagnosing or identifying diseases based on computer vision science include feature extraction or characteristics of image objects so that they can recognize patterns from an object and can be used for diagnosis. The feature extraction methods used in brain images in previous studies were tumor area, brain area, and presentation of tumor area to brain area, mean value, standard deviation, entropy, and variance of brain images (Akbar et al, 2019); Another feature used is LDA (Linear Discriminant Analysis) (Adinegoro et al, 2015); image mean value feature, image eigenbrain http://dx.doi.org/10.35671/telematika.v16i2.2272 (Soesanti et al, 2011); PCA (Principle Component Analysis) feature (Susmikanti, 2010); the feature used is the value GLCM (Gray Level Co-occurrence Matrix) (Widhiarso et al, 2018); another feature is the DWT (Discrete Wavelet Transformation) (Astuti, 2019), (Varuna Shree & Kumar, 2018), (Kumar et al, 2017; Histogram of Oriented Gradient (HOG) (M & Azizah, 2022); texture features with values of Contrast, Correlation, Energy, Dissimilarity, ASM (Angular Second Moment), Homogeneity, and Entropy (Febrianti et al, 2020).…”

“…Finding malignancies on brain MRI pictures or extracting features from the images has been the subject of numerous research. Several methods are used to identify or diagnose brain tumors Naive Bayes (Akbar et al, 2019); SVM (Adinegoro et al, 2015), (Kumar et al, 2017), (M & Azizah, 2022), (Febrianti et al, 2020); Multi-Layer Neural Network (Susmikanti, 2010), (Astuti, 2019), (Varuna Shree & Kumar, 2018), (Gu & Li, 2021); CNN (Convolution Neural Network) or Deep Learning (Widhiarso et al, 2018), (Tjahyaningtijas et al, 2021), (Irmak, 2021), (Aamir et al, 2022), (Harish & Baskar, 2020), (Abiwinanda et al, 2020), (Daniel & Ruxandra, 2021), (Deepak & Ameer, 2019), (Yuliawan & 'Uyun, 2022).…”