Automated Lung Cancer Segmentation Using a PET and CT Dual-Modality Deep Learning Neural Network

Purpose: To develop an automated lung tumor segmentation method for radiation therapy planning based on deep learning and dual-modality positron emission tomography (PET) and computed tomography (CT) images.Methods and Materials: A 3-dimensional (3D) convolutional neural network using inputs from diagnostic PETs and simula-tion CTs was constructed with 2 parallel convolution paths for independent feature extraction at multiple resolution levels and a single deconvolution path. At each resolution level, the extracted features from the convolution arms were concatenated and fed through the skip connections into the deconvolution path that produced the tumor segmentation. Our network was trained/validated/tested by a 3:1:1 split on 290 pairs of PET and CT images from patients with lung cancer treated at our clinic, with manual physician contours as the ground truth. A stratified training strategy based on the magnitude of the gross tumor volume (GTV) was investigated to improve performance, especially for small tumors. Multiple radiation oncologists assessed the clinical acceptability of the network-produced segmentations.Results: The mean Dice similarity coefficient, Hausdorff distance, and bidirectional local distance comparing manual versus automated contours were 0.79 & PLUSMN; 0.10, 5.8 & PLUSMN; 3.2 mm, and 2.8 & PLUSMN; 1.5 mm for the unstratified 3D dual-modality model. Stratifica-tion delivered the best results when the model for the large GTVs (>25 mL) was trained with all-size GTVs and the model for the small GTVs (<25 mL) was trained with small GTVs only. The best combined Dice similarity coefficient, Hausdorff dis-tance, and bidirectional local distance from the 2 stratified models on their corresponding test data sets were 0.83 & PLUSMN; 0.07, 5.9 & PLUSMN; 2.5 mm, and 2.8 & PLUSMN; 1.4 mm, respectively. In the multiobserver review, 91.25% manual versus 88.75% automatic contours were accepted or accepted with modifications.Conclusions: By using an expansive clinical PET and CT image database and a dual-modality architecture, the proposed 3D network with a novel GTVbased stratification strategy generated clinically useful lung cancer contours that were highly accept-able on physician review. & COPY; 2022 Elsevier Inc. All rights reserved.

Automated summary

This study developed an automated lung tumor segmentation method for radiation therapy planning using deep learning and dual-modality PET-CT images. A 3D convolutional neural network was constructed to extract features and segment tumors based on PET and CT images. The network achieved clinically acceptable results on physician review after training and validation with a large dataset.