Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Majalah Forum Teknik UGM Seminar Nasional Aplikasi Teknologi Informasi (SNATI)
Thomas Sri Widodo
Unknown Affiliation
Computer Science & IT Engineering

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Identifikasi Citra Massa Kistik Berdasar Fitur Gray-Level Co-Occurrence Matrix Hari Wibawanto; Adhi Susanto; Thomas Sri Widodo; S. Maesadji Tjokronegoro
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2008
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

We have studied the effectiveness of using texture features derived from gray-level co-occurrence matrix(GLCM) matrices for classification of cystic mass and non-cystic mass in ultra sonograms. Twenty-three (23)region of interest (ROIs) containing cystic masses and fifty-five (55) non-cystic masses were extracted from ultrasonogram for this study. For each ROI of 50x50 pixels, seven features (energy, inertia, entropy, homogeneity,maximum probability, inverse difference moment, and correlation) were calculated. The importance of eachfeature in distinguishing cystic masses from non-cystic masses was determined by linear discriminant analysiswith SPSS version 11.5 program. As a result of a study, it was found that all seven features can distinguishingcystic masses from non-cystic masses with an accuracy about 91 %-92.3%. Those levels of accuracy also foundwhen two features (energy and inverse difference moment) was excluded from analysis. The result demonstratethe feasibility of using texture features based on GLCM for distinguishing cystic masses from non-cystic massesof ultra sonogram .Keywords: Gray-level Co-occurrence Matrix Ultrasonografi, massa kistik, fitur tekstur, analisis tekstur, analisisdiskriminan
Identifikasi Citra Massa Kistik Berdasar Fitur Graylevel Co Occurrence Matrix Hari Wibawanto; Adhi Susanto; Thomas Sri Widodo; S. Maesadji Tjokronegoro
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2009
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

We have studied the effectiveness of using texture features derived from gray-level co-occurrence matrix(GLCM) matrices for classification of cystic mass and non-cystic mass in ultra sonograms. Twenty-three (23)region of interest (ROIs) containing cystic masses and fifty-five (55) non-cystic masses were extracted from ultrasonogram for this study. For each ROI of 50x50 pixels, seven features (energy, inertia, entropy, homogeneity,maximum probability, inverse difference moment, and correlation) were calculated. The importance of eachfeature in distinguishing cystic masses from non-cystic masses was determined by linear discriminant analysiswith SPSS version 11.5 program. As a result of a study, it was found that all seven features can distinguishingcystic masses from non-cystic masses with an accuracy about 91 %-92.3%. Those levels of accuracy also foundwhen two features (energy and inverse difference moment) was excluded from analysis. The result demonstratethe feasibility of using texture features based on GLCM for distinguishing cystic masses from non-cystic massesof ultra sonogram .Keywords: Gray-level Co-occurrence Matrix Ultrasonografi, massa kistik, fitur tekstur, analisis tekstur, analisisdiskriminan
Pengaruh Parameter Number Of Excitation (NEX) Terhadap SNR Dwi Rochmayanti; Thomas Sri Widodo; Indah Soesanti
Forum Teknik Vol 33, No 3 (2010)
Publisher : Faculty of Engineering, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research aims to observe the influence of Number of Excitation (NEX) to bothparameters the Signal to Noise Ratio (SNR) and the scanning time when performing the MRneck . Some MR scan parameters (TR, TE, FOV, slice thickness, matrix, flip angle andbandwidth) are strictly under controlled. All SNR data, due to the 6 NEX variations (NEX 1 toNEX 6), are required by comparing the ROI’s intensity between the noise background and theareas of corpus and spinal cord on the images. The scan times are also recorded for each of theNEX variations being observed. In conclusion, increasing NEX values will simultaneously risethe SNR and the scanning time.Keywords : NEX, SNR, Image MRI, Scan time
Ektraksi Ciri Citra Termogram Payudara Berbasis Dimensi Fraktal Oky Dwi Nurhayati; Thomas Sri Widodo; Adhi Susanto; Maesadji Tjokronagoro
Forum Teknik Vol 33, No 2 (2010)
Publisher : Faculty of Engineering, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

AbstractThe primary purpose of infrared thermography is the locating of thermal differences and anomalies.  Infrared thermography can  detect  numerous  conditions  in  which  an  anomaly is characterized by an increase or decrease in surface temperature. In this research, we specifically applied calculation of fractal dimension method to a total of20 thermograms of normal breasts as well as of those in advanced breast cancer. In addition standard  image  pre-processing  were  also  used  to  enhance  the  detection capabilitity.  Severalmethods in image processing which are pre-processing with canny edge detection, thresholding, calculation of fractal dimension use box-counting and Hausdorff dimension.The results of this research are shown that Hausdorff dimension in the normal thermogramshave range value 0,4 – 0,95 smaller than the advanced thermograms which have value more than  1,26.Finally  this  results  show  that  the  difference  of  fractal dimension  can  be  used  todistinguish between normal and advanced thermograms.Keywords: canny edge detection, thresholding, fractal dimension, box-counting, Hausdorff
Analisis Komputasi pada Segmentasi Citra Medis Adaptif Berbasis Logika Fuzzy Teroptimasi Indah Soesanti; Adhi Susanto; Thomas Sri Widodo; Maesadji Tjokronegoro
Forum Teknik Vol 33, No 2 (2010)
Publisher : Faculty of Engineering, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstract The objective of this research is to analyze the computation of medical image adaptive segmentation based on optimized fuzzy logic. The success of the image analysis system depends on the quality of the segmentation. The image segmentation is separating the image into regions that are meaningful for a given purpose. In this research, the Fuzzy C-Means (FCM) algorithm with spatial information is presented to segment Magnetic Resonance Imaging (MRI) medical images. The FCM clustering utilizes the distance between pixels and cluster centers in the spectral domain to compute the membership function. The pixels of an object in image are highly correlated, and this spatial information is an important characteristic that can be used to aid their labeling. This scheme greatly reduces the effect of noise. The FCM method successfully classifies the brain MRI images into five clusters. This technique is therefore a powerful method in computation for noisy image segmentation. Keywords: computation analysis, MRI Medical image, adaptive image segmentation, fuzzy c-means
Ekstraksi Ciri dan Identifikasi Citra Otak MRI Berbasis Eigenbrain Image Indah Soesanti; Adhi Susanto; Thomas Sri Widodo; Maesadji Tjokronagoro
Forum Teknik Vol 34, No 1 (2011)
Publisher : Faculty of Engineering, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In this research, we exctract and identify MRI brain images based on eigbrain image.  MRI barain images are used to be input for feature exctraction and identitication. Feature exctraction is done by using the eigbrain image. For all reference image, we find image mean and eigbrain image, and the results are stored. If there is test image, we will find the nearest distance of eigenbrain between test image and reference images. The feature extraction is used to identify the image is whether the normal brain image or the brain image with tumor.The results show that the method successfully classifies MRI images into tree clusters: normal,  glioma, and metastase. The input test images can be identified accurately 100% for image  sizes from 256 x 256 pixels to 64 x 64 pixels.Keywords : feature extraction, image identification, MRI medical image, eigenbrain image.
Co-Authors Adhi Susanto Dwi Rochmayanti Hari Wibawanto Indah Soesanti Maesadji Tjokronagoro Maesadji Tjokronegoro Oky Dwi Nurhayati S. Maesadji Tjokronegoro