# Multi-institutional Validation of Two-Streamed Deep Learning Method for Automated Delineation of Esophageal Gross Tumor Volume using planning-CT and FDG-PETCT

arXiv: https://arxiv.org/abs/2110.05280 · HTML: https://mlsanity.com/paper/2110.05280/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 42 references that are in the map.
- First posted on arXiv 11 Oct 2021.

## Builds on (most cited first, 13 of 13)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy](https://mlsanity.com/paper/1809.04430/) (2018)
- [A New 2.5D Representation for Lymph Node Detection using Random Sets of Deep Convolutional Neural Network Observations](https://mlsanity.com/paper/1406.2639/) (2014)
- [CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation](https://mlsanity.com/paper/1806.04051/) (2018)
- [Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Search](https://mlsanity.com/paper/2004.08426/) (2020)
- [Lymph Node Gross Tumor Volume Detection and Segmentation via Distance-based Gating using 3D CT/PET Imaging in Radiotherapy](https://mlsanity.com/paper/2008.11870/) (2020)
- [Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network](https://mlsanity.com/paper/2008.13013/) (2020)
- [Progressive and Multi-Path Holistically Nested Neural Networks for Pathological Lung Segmentation from CT Images](https://mlsanity.com/paper/1706.03702/) (2017)
- [DeepStationing: Thoracic Lymph Node Station Parsing in CT Scans using Anatomical Context Encoding and Key Organ Auto-Search](https://mlsanity.com/paper/2109.09271/) (2021)
- [Accurate Esophageal Gross Tumor Volume Segmentation in PET/CT using Two-Stream Chained 3D Deep Network Fusion](https://mlsanity.com/paper/1909.01524/) (2019)
- [Deep Esophageal Clinical Target Volume Delineation using Encoded 3D Spatial Context of Tumors, Lymph Nodes, and Organs At Risk](https://mlsanity.com/paper/1909.01526/) (2019)

## Built on by (most cited first, 2 of 2)

- [Comprehensive and Clinically Accurate Head and Neck Organs at Risk Delineation via Stratified Deep Learning: A Large-scale Multi-Institutional Study](https://mlsanity.com/paper/2111.01544/) (2021)
- [Iterative pseudo-labeling based adaptive copy-paste supervision for semi-supervised tumor segmentation](https://mlsanity.com/paper/2508.04044/) (2025)

## Abstract (arXiv)

Background: The current clinical workflow for esophageal gross tumor volume (GTV) contouring relies on manual delineation of high labor-costs and interuser variability. Purpose: To validate the clinical applicability of a deep learning (DL) multi-modality esophageal GTV contouring model, developed at 1 institution whereas tested at multiple ones. Methods and Materials: We collected 606 esophageal cancer patients from four institutions. 252 institution-1 patients had a treatment planning-CT (pCT) and a pair of diagnostic FDG-PETCT; 354 patients from other 3 institutions had only pCT. A two-streamed DL model for GTV segmentation was developed using pCT and PETCT scans of a 148 patient institution-1 subset. This built model had the flexibility of segmenting GTVs via only pCT or pCT+PETCT combined. For independent evaluation, the rest 104 institution-1 patients behaved as unseen internal testing, and 354 institutions 2-4 patients were used for external testing. We evaluated manual revision degrees by human experts to assess the contour-editing effort. The performance of the deep model was compared against 4 radiation oncologists in a multiuser study with 20 random external patients. Contouring accuracy and time were recorded for the pre-and post-DL assisted delineation process. Results: Our model achieved high segmentation accuracy in internal testing (mean Dice score: 0.81 using pCT and 0.83 using pCT+PET) and generalized well to external evaluation (mean DSC: 0.80). Expert assessment showed that the predicted contours of 88% patients need only minor or no revision. In multi-user evaluation, with the assistance of a deep model, inter-observer variation and required contouring time were reduced by 37.6% and 48.0%, respectively. Conclusions: Deep learning predicted GTV contours were in close agreement with the ground truth and could be adopted clinically with mostly minor or no changes.