Claim Missing Document
Check
Articles

Found 2 Documents
Search

Internal content classification of ultrasound thyroid nodules based on textural features Anan Nugroho; Hanung Adi Nugroho; Noor Akhmad Setiawan; Lina Choridah
Communications in Science and Technology Vol 1 No 2 (2016)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.1.2.2016.25

Abstract

Ultrasound (US) is one of the best imaging modalities on thyroid identification. The suspicious thyroid is indicated in the existence of palpable nodules whose solid or cystic composition. Solid nodules have high possibility to be malignant than cystic. An effort to detect and classify the internal content of thyroid nodule has become challenge problem in radiology area. Operator dependence of ultrasound imaging makes it complicated due to missing interpretation among radiologists. Objective Computer Aided Diagnosis (CAD) was designed to solve it which works on texture analysis of histogram statistic, gray level co-occurrence matrice (GLCM) and gray level run length matrices (GLRLM). The fine-needle aspiration cytology (FNAC) is not needed because the textural pattern is significantly different between solid and cystic nodules.  Multi-layer perceptron (MLP) was adopted to do classification process for 72 US thyroid images yield an accuracy of 90.28%, the sensitivity of 87.80%, specificity of 93.55% and precision of 94.74%.
SIMPLIFIKASI MODEL CV BERPADU OPERASI MORFOLOGI UNTUK DETEKSI OBJEK KANKER PADA CITRA USG Anan Nugroho; Anas Fauzi; Budi Sunarko; Hari Wibawanto; Nur Iksan
Jurnal Informatika Polinema Vol. 8 No. 2 (2022): Vol 8 No 2 (2022)
Publisher : UPT P2M State Polytechnic of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jip.v8i2.923

Abstract

Saat ini, Computer Aided Diagnosis (CAD) tengah dikembangkan secara masif sebagai second opinion reader di berbagai modalitas pencitraan medis, salah satunya ultrasonografi (USG). Untuk skrining otomatis citra USG yang banyak, berulang-ulang dan terus-menerus, teknik deteksi objek memainkan peran krusial pada sistem CAD. Deteksi objek kanker pada citra USG tidak mudah karena objek-objek tersebut berkontras rendah dan bertepi kabur akibat gangguan derau speckle dan artifak. Studi ini mengatasi tantangan ini dengan mengusulkan metode deteksi berbasis model active-contour Chan-Vese (CV) tersimplifikasi diikuti operasi morfologi. Adapun performa kuantitatif diperoleh menggunakan skor Intersection of Union (IoU) antara objek-objek terdeteksi dengan ground truth-nya. Usulan metode divalidasi menggunakan 20 citra USG tiroid dan payudara dengan hasil rerata skor IoU mencapai 92,36%. Performa yang menjanjikan ini menunjukkan bahwa usulan metode layak diimplementasikan pada sistem CAD.