Texture feature based automated seeded region growing in abdominal MRI segmentation

The detection of pulmonary nodules on computed tomography scans provides a clue for the early diagnosis of lung cancer. Manual detection mandates a heavy radiological workload as it identifies nodules slice-by-slice. This paper presents a fully automated nodule detection with three significant contributions. First, an automated seeded region growing is designed to segment the lung regions from the tomography scans. Second, a three-dimensional chain code algorithm is implemented to refine the border of the segmented lungs. Lastly, nodules inside the lungs are detected using an optimized random forest classifier. The experiments for our proposed detection are conducted using 888 scans from a public dataset, and achieves a favorable result of 93.11% accuracy, 94.86% sensitivity, and 91.37% specificity, with only 0.0863 false positives per exam.

Download Full-text

Tri-texture feature extraction and region growing-level set segmentation in breast cancer diagnosis

International Journal of Biomedical Engineering and Technology ◽

10.1504/ijbet.2018.089958 ◽

2018 ◽

Vol 26 (3/4) ◽

pp. 279 ◽

Cited By ~ 4

Author(s):

S.L. Aarthy ◽

S. Prabu

Keyword(s):

Breast Cancer ◽

Feature Extraction ◽

Level Set ◽

Cancer Diagnosis ◽

Texture Feature ◽

Region Growing ◽

Breast Cancer Diagnosis ◽

Texture Feature Extraction ◽

Level Set Segmentation

Download Full-text

Liver tumour classification using average correction higher order local autocorrelation coefficient and legendre moments

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i2.6.11269 ◽

2018 ◽

Vol 7 (2.6) ◽

pp. 306

Author(s):

Aravinda H.L ◽

M.V Sudhamani

Keyword(s):

Texture Feature ◽

Region Growing ◽

Ct Images ◽

Higher Order ◽

Liver Carcinoma ◽

Tumor Segmentation ◽

Abdominal Ct ◽

Simple Linear Iterative Clustering ◽

Classification Of Tumors ◽

Legendre Moments

The major reasons for liver carcinoma are cirrhosis and hepatitis. In order to identify carcinoma in the liver abdominal CT images are used. From abdominal CT images, segmentation of liver portion using adaptive region growing, tumor segmentation from extracted liver using Simple Linear Iterative Clustering is already implemented. In this paper, classification of tumors as benign or malignant is accomplished using Rough-set classifier based on texture feature extracted using Average Correction Higher Order Local Autocorrelation Coefficients and Legendre moments. Classification accuracy achieved in proposed scheme is 90%. The results obtained are promising and have been compared with existing methods.

Download Full-text

La transformada de Radon aplicada a la segmentación de imágenes digitales en escala de grises

Revista Ingenierías Universidad de Medellín ◽

10.22395/rium.v17n32a10 ◽

2018 ◽

Vol 17 (32) ◽

pp. 213-227

Author(s):

Ricardo Joaquín de Armas Costa ◽

Shirley Viviana Quintero Torres ◽

Cristina Acosta Muñoz ◽

Carlos Camilo Guillermo Rey Torres

Keyword(s):

Region Growing ◽

Seeded Region Growing

En este artículo de investigación científica se da a conocer a la comunidad interesada en el procesamiento digital de imágenes, una aplicación inédita de la transformada de Radon para segmentar imágenes en escala de grises, lo que permite la identificación y clasificación de regiones u objetos, misma que puede extenderse a imágenes en color. Los resultados obtenidos se compararon con los resultados de dos algoritmos clásicos de segmentación: el algoritmo de umbralización Otsu optimizado, y el algoritmo de crecimiento de regiones Seeded Region Growing.

Download Full-text