Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review
As yet, no systematic review on commercial deep learning-based auto-segmentation (DLAS) software for breast cancer radiation therapy (RT) planning has been published, although NRG Oncology has highlighted the necessity for such. The purpose of this systematic review is to investigate the performance...
| Main Author: | |
|---|---|
| Format: | Journal Article |
| Published: |
MDPI
2024
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/96661 |
| _version_ | 1848766191345074176 |
|---|---|
| author | Ng, Curtise |
| author_facet | Ng, Curtise |
| author_sort | Ng, Curtise |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | As yet, no systematic review on commercial deep learning-based auto-segmentation (DLAS) software for breast cancer radiation therapy (RT) planning has been published, although NRG Oncology has highlighted the necessity for such. The purpose of this systematic review is to investigate the performances of commercial DLAS software packages for breast cancer RT planning and methods for their performance evaluation. A literature search was conducted with the use of electronic databases. Fifteen papers met the selection criteria and were included. The included studies evaluated eight software packages (Limbus Contour, Manteia AccuLearning, Mirada DLCExpert, MVision.ai Contour+, Radformation AutoContour, RaySearch RayStation, Siemens syngo.via RT Image Suite/AI-Rad Companion Organs RT, and Therapanacea Annotate). Their findings show that the DLAS software could contour ten organs at risk (body, contralateral breast, esophagus-overlapping area, heart, ipsilateral humeral head, left and right lungs, liver, and sternum and trachea) and three clinical target volumes (CTVp_breast, CTVp_chestwall, and CTVn_L1) up to the clinically acceptable standard. This can contribute to 45.4%–93.7% contouring time reduction per patient. Although NRO Oncology has suggested that every clinical center should conduct its own DLAS software evaluation before clinical implementation, such testing appears particularly crucial for Manteia AccuLearning, Mirada DLCExpert, and MVision.ai Contour+ as a result of the methodological weaknesses of the corresponding studies, such as the use of small datasets collected retrospectively from single centers for the evaluation. |
| first_indexed | 2025-11-14T11:47:13Z |
| format | Journal Article |
| id | curtin-20.500.11937-96661 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:47:13Z |
| publishDate | 2024 |
| publisher | MDPI |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-966612025-01-28T00:28:37Z Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review Ng, Curtise Artificial Intelligence Artificial Neural Network Automatic Clinical Target Volumes Computed Tomography Contouring Delineation Machine Learning Organs at Risk Radiotherapy As yet, no systematic review on commercial deep learning-based auto-segmentation (DLAS) software for breast cancer radiation therapy (RT) planning has been published, although NRG Oncology has highlighted the necessity for such. The purpose of this systematic review is to investigate the performances of commercial DLAS software packages for breast cancer RT planning and methods for their performance evaluation. A literature search was conducted with the use of electronic databases. Fifteen papers met the selection criteria and were included. The included studies evaluated eight software packages (Limbus Contour, Manteia AccuLearning, Mirada DLCExpert, MVision.ai Contour+, Radformation AutoContour, RaySearch RayStation, Siemens syngo.via RT Image Suite/AI-Rad Companion Organs RT, and Therapanacea Annotate). Their findings show that the DLAS software could contour ten organs at risk (body, contralateral breast, esophagus-overlapping area, heart, ipsilateral humeral head, left and right lungs, liver, and sternum and trachea) and three clinical target volumes (CTVp_breast, CTVp_chestwall, and CTVn_L1) up to the clinically acceptable standard. This can contribute to 45.4%–93.7% contouring time reduction per patient. Although NRO Oncology has suggested that every clinical center should conduct its own DLAS software evaluation before clinical implementation, such testing appears particularly crucial for Manteia AccuLearning, Mirada DLCExpert, and MVision.ai Contour+ as a result of the methodological weaknesses of the corresponding studies, such as the use of small datasets collected retrospectively from single centers for the evaluation. 2024 Journal Article http://hdl.handle.net/20.500.11937/96661 10.3390/mti8120114 http://creativecommons.org/licenses/by/4.0/ MDPI fulltext |
| spellingShingle | Artificial Intelligence Artificial Neural Network Automatic Clinical Target Volumes Computed Tomography Contouring Delineation Machine Learning Organs at Risk Radiotherapy Ng, Curtise Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review |
| title | Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review |
| title_full | Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review |
| title_fullStr | Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review |
| title_full_unstemmed | Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review |
| title_short | Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review |
| title_sort | performance of commercial deep learning-based auto-segmentation software for breast cancer radiation therapy planning: a systematic review |
| topic | Artificial Intelligence Artificial Neural Network Automatic Clinical Target Volumes Computed Tomography Contouring Delineation Machine Learning Organs at Risk Radiotherapy |
| url | http://hdl.handle.net/20.500.11937/96661 |