1
|
Cavus H, Bulens P, Tournel K, Orlandini M, Jankelevitch A, Crijns W, Reniers B. Safety and efficiency of a fully automatic workflow for auto-segmentation in radiotherapy using three commercially available deep learning-based applications. Phys Imaging Radiat Oncol 2024; 31:100627. [PMID: 39253729 PMCID: PMC11381787 DOI: 10.1016/j.phro.2024.100627] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Revised: 08/08/2024] [Accepted: 08/08/2024] [Indexed: 09/11/2024] Open
Abstract
Advancements in radiotherapy auto-segmentation necessitate reliable and efficient workflows. Therefore, a standardized fully automatic workflow was developed for three commercially available deep learning-based auto-segmentation applications and compared to a manual workflow for safety and efficiency. The workflow underwent safety evaluation with failure mode and effects analysis. Notably, eight failure modes were reduced, including seven with severity factors ≥7, indicating the effect on patients, and two with Risk Priority Number value >125, which assesses relative risk level. Efficiency, measured by mouse clicks, showed zero clicks with the automatic workflow. This automation illustrated improvement in both safety and efficiency of workflow.
Collapse
Affiliation(s)
- Hasan Cavus
- Department of Radiation Oncology, Jessa Hospital, 3500 Hasselt, Belgium
- Limburg Oncology Center, 3500 Hasselt, Belgium
- Faculty of Engineering Technology, Hasselt University, B-3590 Diepenbeek, Belgium
| | - Philippe Bulens
- Department of Radiation Oncology, Jessa Hospital, 3500 Hasselt, Belgium
- Limburg Oncology Center, 3500 Hasselt, Belgium
| | - Koen Tournel
- Department of Radiation Oncology, Jessa Hospital, 3500 Hasselt, Belgium
- Limburg Oncology Center, 3500 Hasselt, Belgium
| | - Marc Orlandini
- Department of Radiation Oncology, Jessa Hospital, 3500 Hasselt, Belgium
- Limburg Oncology Center, 3500 Hasselt, Belgium
| | - Alexandra Jankelevitch
- Department of Radiation Oncology, Jessa Hospital, 3500 Hasselt, Belgium
- Limburg Oncology Center, 3500 Hasselt, Belgium
| | - Wouter Crijns
- Department Oncology, Laboratory of Experimental Radiotherapy, KU Leuven, Belgium
- Department of Radiation Oncology, UZ Leuven, Belgium
| | - Brigitte Reniers
- Faculty of Engineering Technology, Hasselt University, B-3590 Diepenbeek, Belgium
| |
Collapse
|
2
|
Goddard L, Velten C, Tang J, Skalina KA, Boyd R, Martin W, Basavatia A, Garg M, Tomé WA. Evaluation of multiple-vendor AI autocontouring solutions. Radiat Oncol 2024; 19:69. [PMID: 38822385 PMCID: PMC11143643 DOI: 10.1186/s13014-024-02451-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2024] [Accepted: 05/10/2024] [Indexed: 06/03/2024] Open
Abstract
BACKGROUND Multiple artificial intelligence (AI)-based autocontouring solutions have become available, each promising high accuracy and time savings compared with manual contouring. Before implementing AI-driven autocontouring into clinical practice, three commercially available CT-based solutions were evaluated. MATERIALS AND METHODS The following solutions were evaluated in this work: MIM-ProtégéAI+ (MIM), Radformation-AutoContour (RAD), and Siemens-DirectORGANS (SIE). Sixteen organs were identified that could be contoured by all solutions. For each organ, ten patients that had manually generated contours approved by the treating physician (AP) were identified, totaling forty-seven different patients. CT scans in the supine position were acquired using a Siemens-SOMATOMgo 64-slice helical scanner and used to generate autocontours. Physician scoring of contour accuracy was performed by at least three physicians using a five-point Likert scale. Dice similarity coefficient (DSC), Hausdorff distance (HD) and mean distance to agreement (MDA) were calculated comparing AI contours to "ground truth" AP contours. RESULTS The average physician score ranged from 1.00, indicating that all physicians reviewed the contour as clinically acceptable with no modifications necessary, to 3.70, indicating changes are required and that the time taken to modify the structures would likely take as long or longer than manually generating the contour. When averaged across all sixteen structures, the AP contours had a physician score of 2.02, MIM 2.07, RAD 1.96 and SIE 1.99. DSC ranged from 0.37 to 0.98, with 41/48 (85.4%) contours having an average DSC ≥ 0.7. Average HD ranged from 2.9 to 43.3 mm. Average MDA ranged from 0.6 to 26.1 mm. CONCLUSIONS The results of our comparison demonstrate that each vendor's AI contouring solution exhibited capabilities similar to those of manual contouring. There were a small number of cases where unusual anatomy led to poor scores with one or more of the solutions. The consistency and comparable performance of all three vendors' solutions suggest that radiation oncology centers can confidently choose any of the evaluated solutions based on individual preferences, resource availability, and compatibility with their existing clinical workflows. Although AI-based contouring may result in high-quality contours for the majority of patients, a minority of patients require manual contouring and more in-depth physician review.
Collapse
Affiliation(s)
- Lee Goddard
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Christian Velten
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Justin Tang
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Karin A Skalina
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Robert Boyd
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - William Martin
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
| | - Amar Basavatia
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Madhur Garg
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Wolfgang A Tomé
- Department of Radiation Oncology, Montefiore Medical Center, Bronx, NY, 10467, USA.
- Albert Einstein College of Medicine, Bronx, NY, 10461, USA.
- Division of Medical Physics, Albert Einstein College of Medicine, 1300 Morris Park Ave, Block Building Room 106, Bronx, NY, 10461, USA.
| |
Collapse
|
3
|
Sciurello SA, Graziano F, Laganà MM, Compalati E, Pappacoda G, Gambazza S, Navarro J, Cecconi P, Baglio F, Banfi P. Feasibility of high-frequency percussions in people with severe acquired brain injury and tracheostomy: an observational study. Monaldi Arch Chest Dis 2024. [PMID: 38247397 DOI: 10.4081/monaldi.2024.2734] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Accepted: 01/02/2024] [Indexed: 01/23/2024] Open
Abstract
People with severe acquired brain injury (pwSABI) frequently experience pulmonary complications. Among these, atelectasis can occur as a result of pneumonia, thus increasing the chance of developing acute respiratory failure. Respiratory physiotherapy contribution to the management of atelectasis in pwSABI is yet poorly understood. We conducted a retrospective analysis on 15 non-cooperative pwSABI with tracheostomy and spontaneously breathing, hospitalized and treated with high-frequency percussion physiotherapy between September 2018 and February 2021 at the Neurological Rehabilitation Unit of the IRCCS "S.Maria Nascente - Fondazione Don Gnocchi", Milan. Our primary aim was to investigate the feasibility of such a physiotherapy intervention method. Then, we assessed changes in respiratory measures (arterial blood gas analysis and peripheral night-time oxygen saturation) and high-resolution computed tomography lung images, evaluated before and after the physiotherapy treatment. The radiological measures were a modified radiological atelectasis score (mRAS) assigned by two radiologists, and an opacity score automatically provided by the software CT Pneumonia Analysis® that identifies the regions of abnormal lung patterns. Treatment diaries showed that all treatments were completed, and no adverse events during treatment were registered. Among the 15 pwSABI analyzed, 8 were treated with IPV® and 7 with MetaNeb®. After a median of 14 (I-III quartile=12.5-14.5) days of treatment, we observed a statistical improvement in various arterial blood gas measures and peripheral night-time oxygen saturation measures. We also found radiological improvement or stability in more than 80% of pwSABI. In conclusion, our physiotherapy approach was feasible, and we observed respiratory parameters and radiological improvements. Using technology to assess abnormal tomographic patterns could be of interest to disentangle the short-term effects of respiratory physiotherapy on non-collaborating people.
Collapse
Affiliation(s)
| | - Francesca Graziano
- Bicocca Bioinformatics Biostatistics and Bioimaging Center B4, School of Medicine and Surgery, University of Milano Bicocca; Biostatistics and Clinical Epidemiology, Fondazione IRCCS San Gerardo dei Tintori, Monza.
| | | | | | | | - Simone Gambazza
- Healthcare Professions Department, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan.
| | | | | | | | - Paolo Banfi
- IRCCS Fondazione Don Carlo Gnocchi ONLUS, Milan.
| |
Collapse
|
4
|
Mikalsen SG, Skjøtskift T, Flote VG, Hämäläinen NP, Heydari M, Rydén-Eilertsen K. Extensive clinical testing of Deep Learning Segmentation models for thorax and breast cancer radiotherapy planning. Acta Oncol 2023; 62:1184-1193. [PMID: 37883678 DOI: 10.1080/0284186x.2023.2270152] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2023] [Accepted: 10/04/2023] [Indexed: 10/28/2023]
Abstract
BACKGROUND The performance of deep learning segmentation (DLS) models for automatic organ extraction from CT images in the thorax and breast regions was investigated. Furthermore, the readiness and feasibility of integrating DLS into clinical practice were addressed by measuring the potential time savings and dosimetric impact. MATERIAL AND METHODS Thirty patients referred to radiotherapy for breast cancer were prospectively included. A total of 23 clinically relevant left- and right-sided organs were contoured manually on CT images according to ESTRO guidelines. Next, auto-segmentation was executed, and the geometric agreement between the auto-segmented and manually contoured organs was qualitatively assessed applying a scale in the range [0-not acceptable, 3-no corrections]. A quantitative validation was carried out by calculating Dice coefficients (DSC) and the 95% percentile of Hausdorff distances (HD95). The dosimetric impact of optimizing the treatment plans on the uncorrected DLS contours, was investigated from a dose coverage analysis using DVH values of the manually delineated contours as references. RESULTS The qualitative analysis showed that 93% of the DLS generated OAR contours did not need corrections, except for the heart where 67% of the contours needed corrections. The majority of DLS generated CTVs needed corrections, whereas a minority were deemed not acceptable. Still, using the DLS-model for CTV and heart delineation is on average 14 minutes faster. An average DSC=0.91 and H95=9.8 mm were found for the left and right breasts, respectively. Likewise, and average DSC in the range [0.66, 0.76]mm and HD95 in the range [7.04, 12.05]mm were found for the lymph nodes. CONCLUSION The validation showed that the DLS generated OAR contours can be used clinically. Corrections were required to most of the DLS generated CTVs, and therefore warrants more attention before possibly implementing the DLS models clinically.
Collapse
Affiliation(s)
| | | | | | | | - Mojgan Heydari
- Department of Medical Physics, Oslo University Hospital, Oslo, Norway
| | | |
Collapse
|