Abstract
BackgroundThe current clinical workflow for esophageal gross tumor volume (GTV) contouring relies on manual delineation with high labor costs and inter-user variability.PurposeTo validate the clinical applicability of a deep learning multimodality esophageal GTV contouring model, developed at one institution whereas tested at multiple institutions.Materials and MethodsWe collected 606 patients with esophageal cancer retrospectively from four institutions. Among them, 252 patients from institution 1 contained both a treatment planning CT (pCT) and a pair of diagnostic FDG-PET/CT; 354 patients from three other institutions had only pCT scans under different staging protocols or lacking PET scanners. A two-streamed deep learning model for GTV segmentation was developed using pCT and PET/CT scans of a subset (148 patients) from institution 1. This built model had the flexibility of segmenting GTVs via only pCT or pCT+PET/CT combined when available. For independent evaluation, the remaining 104 patients from institution 1 behaved as an unseen internal testing, and 354 patients from the other three institutions were used for external testing. Degrees of manual revision were further evaluated by human experts to assess the contour-editing effort. Furthermore, the deep model’s performance was compared against four radiation oncologists in a multi-user study using 20 randomly chosen external patients. Contouring accuracy and time were recorded for the pre- and post-deep learning-assisted delineation process.
Highlights
Gross tumor volume (GTV) contouring is an essential task in radiotherapy planning
The mean Dice similarity coefficient (DSC), HD95, and average surface distance (ASD) were correlated to the degrees of manual revision (DSC: R = -0.58, p < 0.001; HD95: R = 0.60, p < 0.001; ASD: R = 0.60, p < 0.001). These results indicated the reliability of using DSC, HD95, and ASD as contouring accuracy evaluation criteria, consistent with the contour editing effort necessitated in actual clinical practice
It is observed that when editing upon deep model predictions, 2 out of 4 radiation oncologists’ performance had been significantly improved in DSC and HD95 (Figure 5 and Appendix Table A5)
Summary
Gross tumor volume (GTV) contouring is an essential task in radiotherapy planning. GTV refers to the demonstrable gross tumor region. For precise GTV delineation, radiation oncologists often need to consider multimodality imaging of MRI, FDG-PET, contrast-enhanced CT, and radiology reports and other relevant clinical information. This manual process is both labor-intensive and highly variable. 2) Assessing the longitudinal esophageal tumor extension is difficult on CT, even with additional information from PET This leads to considerable GTV contouring variations at the cranial-caudal border [4, 5]. 3) Treatment planning CT (pCT) exhibits poor contrast between the esophageal tumor and surrounding tissues This limitation is addressed by frequently manually referring to adjacent slices to delineate GTV’s radial borders, further increasing the manual burden and time. Purpose: To validate the clinical applicability of a deep learning multimodality esophageal GTV contouring model, developed at one institution whereas tested at multiple institutions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
