Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

Abstract

Purpose In this study, we proposed an automated deep learning (DL) method for head and neck cancer (HNC) gross tumor volume (GTV) contouring on positron emission tomography-computed tomography (PET-CT) images. Materials and Methods PET-CT images were collected from 22 newly diagnosed HNC patients, of whom 17 (Database 1) and 5 (Database 2) were from two centers, respectively. An oncologist and a radiologist decided the gold standard of GTV manually by consensus. We developed a deep convolutional neural network (DCNN) and trained the network based on the two-dimensional PET-CT images and the gold standard of GTV in the training dataset. We did two experiments: Experiment 1, with Database 1 only, and Experiment 2, with both Databases 1 and 2. In both Experiment 1 and Experiment 2, we evaluated the proposed method using a leave-one-out cross-validation strategy. We compared the median results in Experiment 2 (GTVa) with the performance of other methods in the literature and with the gold standard (GTVm). Results A tumor segmentation task for a patient on coregistered PET-CT images took less than one minute. The dice similarity coefficient (DSC) of the proposed method in Experiment 1 and Experiment 2 was 0.481∼0.872 and 0.482∼0.868, respectively. The DSC of GTVa was better than that in previous studies. A high correlation was found between GTVa and GTVm (R = 0.99, P < 0.001). The median volume difference (%) between GTVm and GTVa was 10.9%. The median values of DSC, sensitivity, and precision of GTVa were 0.785, 0.764, and 0.789, respectively. Conclusion A fully automatic GTV contouring method for HNC based on DCNN and PET-CT from dual centers has been successfully proposed with high accuracy and efficiency. Our proposed method is of help to the clinicians in HNC management.

Tumor Segmentation and Feature Extraction from Whole-Body FDG-PET/CT Using Cascaded 2D and 3D Convolutional Neural Networks

“…This level of performance was obtained on eyes to thighs datasets where overall lesion burden is sparse and anatomical background is highly heterogeneous. Previous published work ( [22,23], with DSC of 0.732 and 0.85, respectively) was based on more limited, less sparse, and more homogeneous regional scans.…”

Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy

“…Automatic nasopharyngeal carcinoma tumor segmentation from 18 F-FDG PET/CT scans using a U-Net architecture proved the feasibility of this task (dice coefficient = 0.87) using AI-based algorithms (Zhao et al 2019a). Similar studies on head and neck (Huang et al 2018), as well as lung cancers (Zhao et al 2018) exhibited promising results using convolutional neural networks for automated tumor segmentation from PET/CT images. Nevertheless, fully automated lesion delineation from PET, CT, and MR images or any combination of these images still remains a major challenge owing to the large variability of lesion shape and uptake associated with various malignant diseases.…”

Artificial Intelligence in Nuclear Medicine

“…Zhao et al showed, for a small group of 30 patients, that the automatic segmentation of such tumors on 18 F-FDG PET/CT data was, in principle, possible using the U-Net architecture (mean Dice score of 87.47%) (44). Other groups applied similar approaches to head and neck cancer (45) and lung cancer (46,47). Still, fully automated tumor segmentation remains a challenge, probably because of the extremely diverse appearance of these diseases.…”