A physics-guided modular deep-learning based automated framework for tumor segmentation in PET
- 1 April 2020
- journal article
- research article
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 65 (24), 245032
- https://doi.org/10.1088/1361-6560/ab8535
Abstract
An important need exists for reliable PET tumor-segmentation methods for tasks such as PET-based radiation-therapy planning and reliable quantification of volumetric and radiomic features. To address this need, we propose an automated physics-guided deep-learning-based three-module framework to segment PET images on a per-slice basis. The framework is designed to help address the challenges of limited spatial resolution and lack of clinical training data with known ground-truth tumor boundaries in PET. The first module generates PET images containing highly realistic tumors with known ground-truth using a new stochastic and physics-based approach, addressing lack of training data. The second module trains a modified U-net using these images, helping it learn the tumor-segmentation task. The third module fine-tunes this network using a small-sized clinical dataset with radiologist-defined delineations as surrogate ground-truth, helping the framework learn features potentially missed in simulated tumors. The framework was evaluated in the context of segmenting primary tumors in 18F-fluorodeoxyglucose (FDG)-PET images of patients with lung cancer. The framework's accuracy, generalizability to different scanners, sensitivity to partial volume effects (PVEs) and efficacy in reducing the number of training images were quantitatively evaluated using Dice similarity coefficient (DSC) and several other metrics. The framework yielded reliable performance in both simulated (DSC: 0.87 (95% CI: 0.86, 0.88)) and patient images (DSC: 0.73 (95% CI: 0.71, 0.76)), outperformed several widely used semi-automated approaches, accurately segmented relatively small tumors (smallest segmented cross-section was 1.83 cm2), generalized across five PET scanners (DSC: 0.74 (95% CI: 0.71, 0.76)), was relatively unaffected by PVEs, and required low training data (training with data from even 30 patients yielded DSC of 0.70 (95% CI: 0.68, 0.71)). In conclusion, the proposed automated physics-guided deep-learning-based PET-segmentation framework yielded reliable performance in delineating tumors in FDG-PET images of patients with lung cancer.Keywords
Funding Information
- National Institute of Biomedical Imaging and Bioengineering (P41-EB024495)
This publication has 36 references indexed in Scilit:
- Distributed deep learning networks among institutions for medical imagingJournal of the American Medical Informatics Association, 2018
- Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network studyPLOS ONE, 2018
- Generative Adversarial Networks: An OverviewIEEE Signal Processing Magazine, 2018
- A review on segmentation of positron emission tomography imagesComputers in Biology and Medicine, 2014
- A computational pipeline for quantification of pulmonary infections in small animal models using serial PET-CT imagingEJNMMI Research, 2013
- A novel fuzzy C‐means algorithm for unsupervised heterogeneous tumor quantification in PETMedical Physics, 2010
- A region growing method for tumor volume segmentation on PET images for rectal and anal cancer patientsMedical Physics, 2009
- Lesion quantification in oncological positron emission tomography: A maximum likelihood partial volume correction strategyMedical Physics, 2009
- Threshold segmentation for PET target volume delineation in radiation treatment planning: The role of target‐to‐background ratio and target sizeMedical Physics, 2008
- A Gaussian mixture model for definition of lung tumor volumes in positron emission tomographyMedical Physics, 2007