Clinical Validation of a Deep-Learning Segmentation Software in Head and Neck: An Early Analysis in a Developing Radiation Oncology Center

Andrea D’Aviero, Alessia Re, Francesco Catucci, Danila Piccari, Claudio Votta, Domenico Piro, Antonio Piras, Carmela Di Dio, Martina Iezzi, Francesco Preziosi, Sebastiano Menna, Flaviovincenzo Quaranta, Althea Boschetti, Marco Marras, Francesco Miccichè, Roberto Gallus, Luca Indovina, Francesco Bussu, Vincenzo Valentini, Davide Cusumano and Gian Carlo Mattiucci
Additional contact information
Andrea D’Aviero: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Alessia Re: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Francesco Catucci: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Danila Piccari: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Claudio Votta: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Domenico Piro: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Antonio Piras: UO Radioterapia Oncologica, Villa Santa Teresa, 90011 Bagheria, Italy
Carmela Di Dio: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Martina Iezzi: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Francesco Preziosi: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Sebastiano Menna: Medical Physics, Mater Olbia Hospital, 07026 Sassari, Italy
Flaviovincenzo Quaranta: Medical Physics, Mater Olbia Hospital, 07026 Sassari, Italy
Althea Boschetti: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Marco Marras: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy
Francesco Miccichè: UOC Radioterapia Oncologica, Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Roma, Italy
Roberto Gallus: Otolaryngology, Mater Olbia Hospital, 07026 Sassari, Italy
Luca Indovina: UOC Radioterapia Oncologica, Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Roma, Italy
Francesco Bussu: Otolaryngology, Azienda Ospedaliero Universitaria di Sassari, 07100 Sassari, Italy
Vincenzo Valentini: UOC Radioterapia Oncologica, Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Roma, Italy
Davide Cusumano: Medical Physics, Mater Olbia Hospital, 07026 Sassari, Italy
Gian Carlo Mattiucci: Radiation Oncology, Mater Olbia Hospital, 07026 Olbia, Italy

IJERPH, 2022, vol. 19, issue 15, 1-9

Abstract: Background: Organs at risk (OARs) delineation is a crucial step of radiotherapy (RT) treatment planning workflow. Time-consuming and inter-observer variability are main issues in manual OAR delineation, mainly in the head and neck (H & N) district. Deep-learning based auto-segmentation is a promising strategy to improve OARs contouring in radiotherapy departments. A comparison of deep-learning-generated auto-contours (AC) with manual contours (MC) was performed by three expert radiation oncologists from a single center. Methods: Planning computed tomography (CT) scans of patients undergoing RT treatments for H&N cancers were considered. CT scans were processed by Limbus Contour auto-segmentation software, a commercial deep-learning auto-segmentation based software to generate AC. H&N protocol was used to perform AC, with the structure set consisting of bilateral brachial plexus, brain, brainstem, bilateral cochlea, pharyngeal constrictors, eye globes, bilateral lens, mandible, optic chiasm, bilateral optic nerves, oral cavity, bilateral parotids, spinal cord, bilateral submandibular glands, lips and thyroid. Manual revision of OARs was performed according to international consensus guidelines. The AC and MC were compared using the Dice similarity coefficient (DSC) and 95% Hausdorff distance transform (DT). Results: A total of 274 contours obtained by processing CT scans were included in the analysis. The highest values of DSC were obtained for the brain (DSC 1.00), left and right eye globes and the mandible (DSC 0.98). The structures with greater MC editing were optic chiasm, optic nerves and cochleae. Conclusions: In this preliminary analysis, deep-learning auto-segmentation seems to provide acceptable H&N OAR delineations. For less accurate organs, AC could be considered a starting point for review and manual adjustment. Our results suggest that AC could become a useful time-saving tool to optimize workload and resources in RT departments.

Keywords: head and neck; radiotherapy artificial intelligence; deep-learning; auto-contouring (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1660-4601/19/15/9057/pdf (application/pdf)
https://www.mdpi.com/1660-4601/19/15/9057/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:19:y:2022:i:15:p:9057-:d:871387

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().