Experimental Examination of Conventional, Semi-Automatic, and Automatic Volumetry Tools for Segmentation of Pulmonary Nodules in a Phantom Study
Authors:
- Julian HlouschekJHJulian Hlouschek
- Britta KönigBKBritta König
- Denise BosDBDenise Bos
- Alina SantiagoASAlina Santiago
- Sebastian ZensenSZSebastian Zensen
- Johannes HauboldJHJohannes Haubold
- Christoph PöttgenCPChristoph Pöttgen
- Andreas HerzAHAndreas Herz
- Marcel OpitzMOMarcel Opitz
- Axel WetterAWAxel Wetter
- Maja GuberinaMGMaja Guberina
- Martin StuschkeMartin Stuschke
Open Access
- 22 December 2023
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 14 (1) , 28
Abstract
The aim of this study is to examine the precision of semi-automatic, conventional and automatic volumetry tools for pulmonary nodules in chest CT with phantom N1 LUNGMAN. The phantom is a life-size anatomical chest model with pulmonary nodules representing solid and subsolid metastases. Gross tumor volumes (GTVis) were contoured using various approaches: manually (0); as a means of semi-automated, conventional contouring with (I) adaptive-brush function; (II) flood-fill function; and (III) image-thresholding function. Furthermore, a deep-learning algorithm for automatic contouring was applied (IV). An intermodality comparison of the above-mentioned strategies for contouring GTVis was performed. For the mean GTVref (standard deviation (SD)), the interquartile range (IQR)) was 0.68 mL (0.33; 0.34–1.1). GTV segmentation was distributed as follows: (I) 0.61 mL (0.27; 0.36–0.92); (II) 0.41 mL (0.28; 0.23–0.63); (III) 0.65 mL (0.35; 0.32–0.90); and (IV) 0.61 mL (0.29; 0.33–0.95). GTVref was found to be significantly correlated with GTVis (I) p < 0.001, r = 0.989 (III) p = 0.001, r = 0.916, and (IV) p < 0.001, r = 0.986, but not with (II) p = 0.091, r = 0.595. The Sørensen–Dice indices for the semi-automatic tools were 0.74 (I), 0.57 (II) and 0.71 (III). For the semi-automatic, conventional segmentation tools evaluated, the adaptive-brush function (I) performed closest to the reference standard (0). The automatic deep learning tool (IV) showed high performance for auto-segmentation and was close to the reference standard. For high precision radiation therapy, visual control, and, where necessary, manual correction, are mandatory for all evaluated tools.Keywords
Funding Information
- University of Duisburg-Essen
This publication has 28 references indexed in Scilit:
- End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomographyNature Medicine, 2019
- Safety and Efficacy of a Five-Fraction Stereotactic Body Radiotherapy Schedule for Centrally Located Non–Small-Cell Lung Cancer: NRG Oncology/RTOG 0813 TrialJournal of Clinical Oncology, 2019
- Stereotactic Body Radiation Therapy for Operable Early-Stage Lung CancerJAMA Oncology, 2018
- ESTRO ACROP guidelines for target volume definition in the treatment of locally advanced non-small cell lung cancerRadiotherapy and Oncology, 2018
- A Generalized Deep Learning-Based Diagnostic System for Early Diagnosis of Various Types of Pulmonary NodulesTechnology in Cancer Research & Treatment, 2018
- 3D multi-view convolutional neural networks for lung nodule classificationPLOS ONE, 2017
- Segmentation of lung lesions on CT scans using watershed, active contours, and Markov random fieldMedical Physics, 2013
- Stereotactic Body Radiation Therapy for Inoperable Early Stage Lung CancerJAMA, 2010
- Variations in Target Volume Definition for Postoperative Radiotherapy in Stage III Non–Small-Cell Lung Cancer: Analysis of an International Contouring StudyInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2010
- Clinicopathologic Analysis of Microscopic Extension in Lung Adenocarcinoma: Defining Clinical Target Volume for RadiotherapyInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2007