Lung tumor segmentation in 4D CT images using motion convolutional neural networks
- 1 September 2021
- journal article
- research article
- Published by Wiley in Medical Physics
- Vol. 48 (11), 7141-7153
- https://doi.org/10.1002/mp.15204
Abstract
Purpose : Manual delineation on all breathing phases of lung cancer 4D CT image datasets can be challenging, exhaustive, and prone to subjective errors because of both the large number of images in the datasets and variations in the spatial location of tumors secondary to respiratory motion. The purpose of this work is to present a new deep learning-based framework for fast and accurate segmentation of lung tumors on 4D CT image sets. Methods The proposed DL framework leverages motion region convolutional neural network (R-CNN). Through integration of global and local motion estimation network architectures, the network can learn both major and minor changes caused by tumor motion. Our network design first extracts tumor motion information by feeding 4D CT images with consecutive phases into an integrated backbone network architecture, locating volume-of-interest (VOIs) via a regional proposal network and removing irrelevant information via a regional convolutional neural network. Extracted motion information is then advanced into the subsequent global and local motion head network architecture to predict corresponding deformation vector fields (DVFs) and further adjust tumor VOIs. Binary masks of tumors are then segmented within adjusted VOIs via a mask head. A self-attention strategy is incorporated in the mask head network to remove any noisy features that might impact segmentation performance. We performed two sets of experiments. In the first experiment, a five-fold cross validation on 20 4D CT datasets, each consisting of 10 breathing phases (i.e., 200 3D image volumes in total). The network performance was also evaluated on an additional unseen 200 3D images volumes from 20 hold-out 4D CT datasets. In the second experiment, we trained another model with 40 patients’ 4D CT datasets from experiment 1 and evaluated on additional unseen 9 patients’ 4D CT datasets. The Dice similarity coefficient (DSC), center of mass distance (CMD), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and volume difference (VD) between the manual and segmented tumor contour were computed to evaluate tumor detection and segmentation accuracy. The performance of our method was quantitatively evaluated against four different methods (VoxelMorph, U-Net, network without global and local networks, and network without attention gate strategy) across all evaluation metrics through a paired t-test. Results : The proposed fully automated DL method yielded good overall agreement with the ground truth for contoured tumor volume and segmentation accuracy. Our model yielded significantly better values of evaluation metrics (P < 0.05) than all four competing methods in both experiments. On hold-out datasets of experiment 1 and 2, our method yielded DSC of 0.86 and 0.90 compared to 0.82 and 0.87, 0.75 and 0.83, 081 and 0.89, and 0.81 and 0.89 yielded by VoxelMorph, U-Net, network without global & local networks, and networks without attention gate strategy. Tumor VD between ground truth and our method was the smallest with the value of 0.50 compared to 0.99, 1.01, 0.92, and 0.93 for between ground truth and VoxelMorph, U-Net, network without global & local networks, and networks without attention gate strategy, respectively. Conclusion : Our proposed DL framework of tumor segmentation on lung cancer 4D CT datasets demonstrate a significant promise for fully automated delineation. The promising results of this work provide impetus for its integration into the 4D CT treatment planning workflow to improve the accuracy and efficiency of lung radiotherapy. This article is protected by copyright. All rights reservedKeywords
Funding Information
- Winship Cancer Institute
This publication has 42 references indexed in Scilit:
- Automated delineation of lung tumors from CT images using a single click ensemble segmentation approachPattern Recognition, 2012
- Stereotactic Body Radiotherapy (SBRT) for Operable Stage I Non–Small-Cell Lung Cancer: Can SBRT Be Comparable to Surgery?International Journal of Radiation Oncology*Biology*Physics, 2011
- A multi-region algorithm for markerless beam's-eye view lung tumor trackingPhysics in Medicine & Biology, 2010
- Comparison of Rigid and Adaptive Methods of Propagating Gross Tumor Volume Through Respiratory Phases of Four-Dimensional Computed Tomography Image Data SetInternational Journal of Radiation Oncology*Biology*Physics, 2008
- Assessment of Intrafraction Mediastinal and Hilar Lymph Node Movement and Comparison to Lung Tumor Motion Using Four-Dimensional CTInternational Journal of Radiation Oncology*Biology*Physics, 2007
- Assessment of Gross Tumor Volume Regression and Motion Changes During Radiotherapy for Non–Small-Cell Lung Cancer as Measured by Four-Dimensional Computed TomographyInternational Journal of Radiation Oncology*Biology*Physics, 2007
- Design of 4D treatment planning target volumesInternational Journal of Radiation Oncology*Biology*Physics, 2006
- Prediction of lung tumour position based on spirometry and on abdominal displacement: Accuracy and reproducibilityRadiotherapy and Oncology, 2006
- Use of maximum intensity projections (MIP) for target volume generation in 4DCT scans for lung cancerInternational Journal of Radiation Oncology*Biology*Physics, 2005
- Comparing images using the Hausdorff distanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993