Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow
Proper delineation of both target volumes and organs at risk is a crucial step in the radiation therapy workflow. This process is normally carried out manually by medical doctors, hence demanding timewise. To improve efficiency, auto-contouring methods have been proposed. We assessed a specific comm...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/12/12/2088 |
| _version_ | 1827638073066782720 |
|---|---|
| author | Lorenzo Radici Silvia Ferrario Valeria Casanova Borca Domenico Cante Marina Paolini Cristina Piva Laura Baratto Pierfrancesco Franco Maria Rosa La Porta |
| author_facet | Lorenzo Radici Silvia Ferrario Valeria Casanova Borca Domenico Cante Marina Paolini Cristina Piva Laura Baratto Pierfrancesco Franco Maria Rosa La Porta |
| author_sort | Lorenzo Radici |
| collection | DOAJ |
| description | Proper delineation of both target volumes and organs at risk is a crucial step in the radiation therapy workflow. This process is normally carried out manually by medical doctors, hence demanding timewise. To improve efficiency, auto-contouring methods have been proposed. We assessed a specific commercial software to investigate its impact on the radiotherapy workflow on four specific disease sites: head and neck, prostate, breast, and rectum. For the present study, we used a commercial deep learning-based auto-segmentation software, namely Limbus Contour (LC), Version 1.5.0 (Limbus AI Inc., Regina, SK, Canada). The software uses deep convolutional neural network models based on a U-net architecture, specific for each structure. Manual and automatic segmentation were compared on disease-specific organs at risk. Contouring time, geometrical performance (volume variation, Dice Similarity Coefficient—DSC, and center of mass shift), and dosimetric impact (DVH differences) were evaluated. With respect to time savings, the maximum advantage was seen in the setting of head and neck cancer with a 65%-time reduction. The average DSC was 0.72. The best agreement was found for lungs. Good results were highlighted for bladder, heart, and femoral heads. The most relevant dosimetric difference was in the rectal cancer case, where the mean volume covered by the 45 Gy isodose was 10.4 cm<sup>3</sup> for manual contouring and 289.4 cm<sup>3</sup> for automatic segmentation. Automatic contouring was able to significantly reduce the time required in the procedure, simplifying the workflow, and reducing interobserver variability. Its implementation was able to improve the radiation therapy workflow in our department. |
| first_indexed | 2024-03-09T16:11:29Z |
| format | Article |
| id | doaj.art-eb1e7e4ad56b439ab903e24a573b6085 |
| institution | Directory Open Access Journal |
| issn | 2075-1729 |
| language | English |
| last_indexed | 2024-03-09T16:11:29Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj.art-eb1e7e4ad56b439ab903e24a573b60852023-11-24T16:13:23ZengMDPI AGLife2075-17292022-12-011212208810.3390/life12122088Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on WorkflowLorenzo Radici0Silvia Ferrario1Valeria Casanova Borca2Domenico Cante3Marina Paolini4Cristina Piva5Laura Baratto6Pierfrancesco Franco7Maria Rosa La Porta8Department of Medical Physics, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyDepartment of Radiation Oncology, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyDepartment of Medical Physics, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyDepartment of Radiation Oncology, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyDepartment of Radiation Oncology, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyDepartment of Radiation Oncology, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyDepartment of Medical Physics, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyDepartment of Translational Medicine (DIMET), ‘Maggiore della Carità’ University Hospital, University of Eastern Piedmont, 28100 Novara, ItalyDepartment of Radiation Oncology, ASL TO4, Ivrea Community Hospital, 10015 Ivrea, ItalyProper delineation of both target volumes and organs at risk is a crucial step in the radiation therapy workflow. This process is normally carried out manually by medical doctors, hence demanding timewise. To improve efficiency, auto-contouring methods have been proposed. We assessed a specific commercial software to investigate its impact on the radiotherapy workflow on four specific disease sites: head and neck, prostate, breast, and rectum. For the present study, we used a commercial deep learning-based auto-segmentation software, namely Limbus Contour (LC), Version 1.5.0 (Limbus AI Inc., Regina, SK, Canada). The software uses deep convolutional neural network models based on a U-net architecture, specific for each structure. Manual and automatic segmentation were compared on disease-specific organs at risk. Contouring time, geometrical performance (volume variation, Dice Similarity Coefficient—DSC, and center of mass shift), and dosimetric impact (DVH differences) were evaluated. With respect to time savings, the maximum advantage was seen in the setting of head and neck cancer with a 65%-time reduction. The average DSC was 0.72. The best agreement was found for lungs. Good results were highlighted for bladder, heart, and femoral heads. The most relevant dosimetric difference was in the rectal cancer case, where the mean volume covered by the 45 Gy isodose was 10.4 cm<sup>3</sup> for manual contouring and 289.4 cm<sup>3</sup> for automatic segmentation. Automatic contouring was able to significantly reduce the time required in the procedure, simplifying the workflow, and reducing interobserver variability. Its implementation was able to improve the radiation therapy workflow in our department.https://www.mdpi.com/2075-1729/12/12/2088radiation therapycontouringauto segmentationartificial intelligencedelineation |
| spellingShingle | Lorenzo Radici Silvia Ferrario Valeria Casanova Borca Domenico Cante Marina Paolini Cristina Piva Laura Baratto Pierfrancesco Franco Maria Rosa La Porta Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow Life radiation therapy contouring auto segmentation artificial intelligence delineation |
| title | Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow |
| title_full | Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow |
| title_fullStr | Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow |
| title_full_unstemmed | Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow |
| title_short | Implementation of a Commercial Deep Learning-Based Auto Segmentation Software in Radiotherapy: Evaluation of Effectiveness and Impact on Workflow |
| title_sort | implementation of a commercial deep learning based auto segmentation software in radiotherapy evaluation of effectiveness and impact on workflow |
| topic | radiation therapy contouring auto segmentation artificial intelligence delineation |
| url | https://www.mdpi.com/2075-1729/12/12/2088 |
| work_keys_str_mv | AT lorenzoradici implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT silviaferrario implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT valeriacasanovaborca implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT domenicocante implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT marinapaolini implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT cristinapiva implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT laurabaratto implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT pierfrancescofranco implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow AT mariarosalaporta implementationofacommercialdeeplearningbasedautosegmentationsoftwareinradiotherapyevaluationofeffectivenessandimpactonworkflow |