Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Latar Belakang: Indonesia menduduki urutan kedua terbanyak kasus karsinoma nasofaring (KNF) di dunia. CT masih menjadi modalitas awal untuk mendeteksi KNF. Akan tetapi gambaran CT pada KNF kadang sulit untuk dibedakan dengan nasofaringitis kronis (NFK) terutama jika ukuran tumor masih kecil. Texture analysis (TA) merupakan suatu metode matematika yang digunakan untuk menganalisis distribusi dan hubungan pixel gray level suatu gambar. TA banyak diteliti di bidang onkologi kepala dan leher untuk membedakan karakteristik tumor, jinak atau ganas, menilai respon terapi serta memprediksi prognosis pasien. Metode: Studi komparatif dengan desain potong lintang. Terdapat 27 sampel KNF dan 18 sampel NFK yang dilakukan ROI pada regio tumor, kemudian dilakukan pengukuran nilai histogram yang terdiri dari mean, skewness, kurtosis dan nilai grey level co-occurencce matrix (GLCM) terdiri dari homogeinity, energy, contrast, correlation, entropy. Nilai yang diperoleh dari kedua kelompok kemudian dibandingkan dengan menggunakan T-test atau Mann-Whitney U Test. Hasil: Tidak didapatkan perbedaan signifikan secara statistik untuk mean (P = 0,098), kurtosis (P = 0,914), skewness (P = 0,775), Homogeinity (P = 0,943), Energy (P = 0,745), Contrast (P = 0,891), Correlation (P = 0,517), Entropy (P = 0,286) antara kelompok KNF dan NFK Kesimpulan: Tidak terdapat perbedaan signifikan dari nilai histogram (mean, skewness, kurtosis) dan nilai GLCM (homogeinity, energy, contrast, correlation, entropy) antara kelompok KNF dan NFK. ......Background: : Indonesia is the second country with most nasopharyngeal carcinoma (NPC) cases in the world. CT is still the initial modality for detecting NPC. However, CT imaging of NPC are sometimes difficult to distinguish from chronic nasopharyngitis (CNP), especially with small tumor size. Texture analysis (TA) is a mathematical method used to analyze the distribution and relationship of gray level pixels of an image. TA is widely studied in head and neck oncology to distinguish the characteristics of tumors, benign or malignant, assess response to therapy and predict patient prognosis. Methods: This is a cross-sectional comparative study. There were 27 NPC samples and 18 CNP samples with ROI performed on the tumor region, then measured the histogram value consisting of mean, skewness, kurtosis and the gray level co-occurrence matrix (GLCM) consisting of homogeinity, energy, contrast, correlation, entropy. The values between two groups were then compared using the T-test or the Mann-Whitney U Test. Results: There were no statistically significant differences for mean (P = 0.098), kurtosis (P = 0.914), skewness (P = 0.775), Homogeinity (P = 0.943), Energy (P = 0.745), Contrast (P = 0.891), Correlation (P = 0.517), Entropy (P = 0.286) between NPC and CNP group. Conclusion: There were no significant difference for histogram values (mean, skewness, kurtosis) and GLCM values (homogeinity, energy, contrast, correlation, entropy) between the NPC and NFK groups.

Abstrak :
Interferometric SAR (IFSAR) offers a solution for a country like Indonesia to map areas that are covered by cloud all year long. In using IFSAR data for producing topographic maps, our main requirement is to set the procedures that resemble photogrametric process as close as possible due to the operators, background and the already available sofware and haedware....

Abstrak :
Tuberkulosis (TB) adalah penyakit menular dan dapat berakibat fatal, terutama di negara berkembang. WHO merekomendasikan penggunaan screening yang sistematis dan luas, salah satunya menggunakan citra X-ray dada. Sayangnya, jumlah ahli radiologi masih kurang dan belum terdistribusi dengan baik di negara berkembang seperti Indonesia. Oleh karena itu, penelitian ini mengembangkan sistem Computer-Aided Detection (CAD) untuk membantu mendeteksi TB menggunakan analisis tekstur. Terdapat tiga tahap pada sistem, yaitu segmentasi otomatis, koreksi segmentasi manual, dan deteksi lesi TB. Hasil akhir sistem memberikan visualisasi heatmap berdasarkan probabilitas lesi TB pada citra X-ray dada. Penelitian ini fokus pada tahap deteksi lesi TB. Analisis tekstur diimplementasi menggunakan berbagai kombinasi dari fitur tekstur Hogeweg, Gray-Level Co-occurrence matrix (GLCM), dan Gabor. Selain itu, metode reduksi dimensi juga diimplementasikan untuk mendapatkan representasi optimal. Analisis tekstur ini digunakan pada area lokal patch melalui perhitungan probabilitas untuk klasifikasi patch lesi TB dan patch normal. Klasifikasi ini dilatih menggunakan Logistic Regression, Support Vector Machine (SVM), dan Multilayer Perceptron (MLP). Hasil terbaik dicapai oleh Logistic Regression dengan kombinasi fitur Hogeweg, GLCM, dan Gabor yang diimplementasikan PCA yang mampu mencapai nilai 0.734 sensitivity. Dokter spesialis radiologi menilai bahwa beberapa visualisasi model ini cukup baik dalam mengenali lesi TB, namun masih ada beberapa kesalahan dalam mendeteksi area normal sebagai lesi TB. ......Tuberculosis (TB) is an infectious disease and can be fatal, especially in developing countries. WHO recommends the use of systematic and broad screening, one of which is using chest X-ray images. Unfortunately, the number of radiologists is still lacking and not well distributed in developing countries such as Indonesia. Therefore, this study developed a Computer-Aided Detection (CAD) system to help detect TB using texture analysis. There are three stages in the system, they are automatic segmentation, manual segmentation correction, and TB lesion detection. The final result of the system provides a heatmap visualization based on the probability of TB lesions on a chest X-ray image. This study focused on the stage of TB lesion detection. Texture analysis was implemented using various combinations of Hogeweg texture features, Gray-Level Co- occurrence matrix (GLCM), and Gabor. In addition, the dimensional reduction method is also implemented to obtain the optimal representation. This texture analysis is applied to the local area of the patch by calculating the probability for the classification of the TB lesion patch and the normal patch. This classification is trained using Logistic Regression, Support Vector Machine (SVM), and Multilayer Perceptron (MLP). The best result was achieved by Logistic Regression with a combination of Hogeweg, GLCM, and Gabor features implemented by PCA which was able to reach a value of 0.734 sensitivity. Radiology specialists considered that some of the visualizations of this model were quite good in recognizing TB lesions, but there were still some errors in detecting normal areas as TB lesions.