showing 3 related works from this author
Interobserver variability in rectum contouring in high-dose-rate brachytherapy for prostate cancer: A multi-institutional prospective analysis
2017
PURPOSE: The aim of this study was to evaluate the interobserver variability (KW) of rectum contouring, and its dosimetric consequences, for high-dose-rate brachytherapy in patients with prostate cancer across multiple institutions. METHODS AND MATERIALS: Five radiation oncologists contoured rectums in 10 patients on transperineal ultrasound image sets after establishing a delineation consensus. The D-0.1cc, D-1cc, and D-2cc rectum volume parameters were determined. The mean, standard deviation, and range of each dose-volume histogram parameter were evaluated for each patient. The JOY was determined using the coefficient of variation, and the dosimetric impacts on the total dose were analyz…
Comment on “Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibili…
2017
We have read with great interest the article published by Tiwari et al, “Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study.”[1][1] In their article, they refer to our work regarding brain metastasis
Support vector machine classification of brain metastasis and radiation necrosis based on texture analysis in MRI
2015
Purpose To develop a classification model using texture features and support vector machine in contrast-enhanced T1-weighted images to differentiate between brain metastasis and radiation necrosis. Methods Texture features were extracted from 115 lesions: 32 of them previously diagnosed as radiation necrosis, 23 as radiation-treated metastasis and 60 untreated metastases; including a total of 179 features derived from six texture analysis methods. A feature selection technique based on support vector machine was used to obtain a subset of features that provide optimal performance. Results The highest classification accuracy evaluated over test sets was achieved with a subset of ten features…