Claim Missing Document
Check
Articles

Found 3 Documents
Search

Segmentasi Objek Citra Ultrasonografi Terotomatisasi Menggunakan Metode Aktif Kontur Kombinatorial Nugroho, Anan; Sunarko, Budi; Wibawanto, Hari; Mulwinda, Anggraini; Fauzi, Anas; Oktaviyanti, Dwi; Savitri, Dina Wulung
Jurnal Teknologi dan Sistem Komputer [IN PRESS] Volume 11, Issue 1, Year 2023 (January 2023)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jtsiskom.2023.14712

Abstract

Active Contour (AC) merupakan algoritme yang banyak digunakan dalam melakukan segmentasi dalam mengembangkan sistem Computer Aided Diagnosis (CAD) pada pencitraan USG. Namun metode yang berkembang masih bersifat interaktif yang menyebabkan human error serta adanya berbagai masalah akibat inhomogenitas pada citra Ultrasonografi (USG) seperti leakage, terjadinya false area serta local minima. Pada studi ini dikembangkan metode segmentasi objek otomatis pada citra USG untuk membantu radiolog dalam proses diagnosis yang efisien. Metode yang dikembangkan disebut Automatic Combinatorial Active Contour (ACAC) yang mengkombinasikan turunan simplifikasi model global region-based CV (Chan-Vese) dan improved-GAC (Geodesic Active Contour) untuk segmentasi lokal. Hasil studi dengan 50 dataset yang diuji coba yaitu didapatkannya nilai accuracy sebesar 98.83%, precission 95.26%, sensitivity 86.58%, specificity 99.63%, similarity 90.58%, dan IoU 82.87%. performa kuantitatif ini membuktikan bahwa metode ACAC layak diimplementasikan pada sistem CAD yang lebih efisien dan akurat.
PEMANFAATAN TEKNOLOGI COMPUTER VISION BERBASIS YOLO UNTUK MENDETEKSI KERUMUNAN DI SMKN 4 MALANG Nugroho, Anan; Indaryanto, Faizal; Suni, Alfa Faridh; Arfriandi, Arief; Wibawanto, Hari; Oktaviyanti, Dwi; Savitri, Dina Wulung
Jurnal Abdi Insani Vol 11 No 1 (2024): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v11i1.1437

Abstract

In limited face-to-face learning, teachers and students must implement health protocols to prevent the spread of the Covid-19 virus. However, implementing health protocols in schools as a new habit in the midst of a pandemic is certainly not easy. There are many reports related to the number of violations of health protocols in schools during face-to-face learning. Therefore, by innovating and utilizing existing technology in the 4.0 era can help us to detect social boundaries. The purpose of this service activity is so that teachers and students can learn YOLO-based computer vision technology at SMKN 4 Malang as a means of preventing the spread of Covid-19. In addition, teachers and students can also learn to make simple applications based on YOLO. This activity begins with the socialization of YOLO-based computer vision technology as a crowd detection tool to the school. Then the design and manufacture of crowd detection tools by the service team, training in making crowd detection applications, and ending with a discussion between the trainees and the service team. The results of the service show that this activity has succeeded in developing a crowd detection tool that can help calculate the number and distance of people who do not apply health protocols at SMKN 4 Malang. This tool makes it easier for schools to monitor the activities of school residents in implementing health protocols. This service activity is very useful and in demand by teachers and students. This is evidenced by the enthusiasm of the participants in participating in the training of YOLO-based crowd detection tools.
Automated Ultrasound Object Segmentation Using Combinatorial Active Contour Method Anan Nugroho; Sunarko, Budi; Wibawanto, Hari; Mulwinda, Anggraini; Fauzi, Anas; Oktaviyanti, Dwi; Savitri, Dina Wulung
Jurnal Ilmu Komputer dan Informasi Vol. 17 No. 2 (2024): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v17i2.1298

Abstract

Active Contour (AC) is an algorithm widely used in segmentation for developing Computer-Aided Diagnosis (CAD) systems in ultrasound imaging. Existing AC models still retain an interactive nature. This is due to the large number of parameters and coefficients that require manual tuning to achieve stability. Which can result in human error and various issues caused by the inhomogeneity of ultrasound images, such as leakage, false areas, and local minima. In this study, an automatic object segmentation method was developed to assist radiologists in an efficient diagnosis process. The proposed method is called Automatic Combinatorial Active Contour (ACAC), which combines the simplification of the global region-based CV (Chan-Vese) model and improved-GAC (Geodesic Active Contour) for local segmentation. The results of testing with 50 datasets showed an accuracy value of 98.83%, precision of 95.26%, sensitivity of 86.58%, specificity of 99.63%, similarity of 90.58%, and IoU (Intersection over Union) of 82.87%. These quantitative performance metrics demonstrate that the ACAC method is suitable for implementation in a more efficient and accurate CAD system.