Clinical evaluation of a deep learning segmentation model including manual adjustments afterwards for locally advanced breast cancer

被引:7
作者
Bakx, Nienke [1 ]
Rijkaart, Dorien [1 ]
van der Sangen, Maurice
Theuws, Jacqueline [1 ]
van der Toorn, Peter -Paul
Verrijssen, An-Sofie [1 ]
van der Leer, Jorien
Mutsaers, Joline [1 ]
Van Nunen, Therese [1 ]
Reinders, Marjon [1 ]
Schuengel, Inge [1 ]
Smits, Julia [1 ]
Hagelaar, Els [1 ]
van Gruijthuijsen, Dave [1 ]
Bluemink, Johanna [1 ]
Hurkmans, Coen [1 ,2 ]
机构
[1] Catharina Hosp, Dept Radiat Oncol, Eindhoven, Netherlands
[2] Tech Univ Eindhoven, Fac Elect Engn, Eindhoven, Netherlands
关键词
Deep learning; Auto; -segmentation; Breast cancer; Radiotherapy; ELECTIVE RADIATION-THERAPY; ESTRO CONSENSUS GUIDELINE; TARGET VOLUME DELINEATION; AUTOMATIC SEGMENTATION; RADIOTHERAPY; VARIABILITY; PERFORMANCE; ORGANS;
D O I
10.1016/j.tipsro.2023.100211
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Introduction: Deep learning (DL) models are increasingly developed for auto-segmentation in radiotherapy. Qualitative analysis is of great importance for clinical implementation, next to quantitative. This study evaluates a DL segmentation model for left- and right-sided locally advanced breast cancer both quantitatively and qualitatively. Methods: For each side a DL model was trained, including primary breast CTV (CTVp), lymph node levels 1-4, heart, lungs, humeral head, thyroid and esophagus. For evaluation, both automatic segmentation, including correction of contours when needed, and manual delineation was performed and both processes were timed. Quantitative scoring with dice-similarity coefficient (DSC), 95% Hausdorff Distance (95%HD) and surface DSC (sDSC) was used to compare both the automatic (not-corrected) and corrected contours with the manual contours. Qualitative scoring was performed by five radiotherapy technologists and five radiation oncologists using a 3-point Likert scale. Results: Time reduction was achieved using auto-segmentation in 95% of the cases, including correction. The time reduction (mean +/- std) was 42.4% +/- 26.5% and 58.5% +/- 19.1% for OARs and CTVs, respectively, corresponding to an absolute mean reduction (hh:mm:ss) of 00:08:51 and 00:25:38. Good quantitative results were achieved before correction, e.g. mean DSC for the right-sided CTVp was 0.92 +/- 0.06, whereas correction statistically significantly improved this contour by only 0.02 +/- 0.05, respectively. In 92% of the cases, autocontours were scored as clinically acceptable, with or without corrections. Conclusions: A DL segmentation model was trained and was shown to be a time-efficient way to generate clinically acceptable contours for locally advanced breast cancer.
引用
收藏
页数:6
相关论文
共 50 条
[31]   Development of a national deep learning-based auto-segmentation model for the heart on clinical delineations from the DBCG RT nation cohort [J].
Skarso, Emma Riis ;
Refsgaard, Lasse ;
Saini, Abhilasha ;
Sloth Moller, Ditte ;
Lorenzen, Ebbe Laugaard ;
Maae, Else ;
Andersen, Karen ;
Maraldo, Maja Vestmo ;
Milo, Marie Louise ;
Nyeng, Tine Bisballe ;
Vrou Offersen, Birgitte ;
Korreman, Stine Sofia .
ACTA ONCOLOGICA, 2023, 62 (10) :1201-1207
[32]   Segmentation of Mammogram Images Using Deep Learning for Breast Cancer Detection [J].
Deb, Sagar Deep ;
Jha, Rajib Kumar .
2022 2ND INTERNATIONAL CONFERENCE ON IMAGE PROCESSING AND ROBOTICS (ICIPROB), 2022,
[33]   Automated Meningioma Segmentation in Multiparametric MRIComparable Effectiveness of a Deep Learning Model and Manual Segmentation [J].
Kai Roman Laukamp ;
Lenhard Pennig ;
Frank Thiele ;
Robert Reimer ;
Lukas Görtz ;
Georgy Shakirin ;
David Zopfs ;
Marco Timmer ;
Michael Perkuhn ;
Jan Borggrefe .
Clinical Neuroradiology, 2021, 31 :357-366
[34]   Clinical target volume segmentation based on gross tumor volume using deep learning for head and neck cancer treatment [J].
Kihara, Sayaka ;
Koike, Yuhei ;
Takegawa, Hideki ;
Anetai, Yusuke ;
Nakamura, Satoaki ;
Tanigawa, Noboru ;
Koizumi, Masahiko .
MEDICAL DOSIMETRY, 2023, 48 (01) :20-24
[35]   Clinical Target Volume Auto-Segmentation of Esophageal Cancer for Radiotherapy After Radical Surgery Based on Deep Learning [J].
Cao, Ruifen ;
Pei, Xi ;
Ge, Ning ;
Zheng, Chunhou .
TECHNOLOGY IN CANCER RESEARCH & TREATMENT, 2021, 20
[36]   Development and comprehensive evaluation of a national DBCG consensus-based auto-segmentation model for lymph node levels in breast cancer radiotherapy [J].
Buhl, Emma Skarso ;
Lorenzen, Ebbe Laugaard ;
Refsgaard, Lasse ;
Nielsen, Anders Winther Molby ;
Brixen, Annette Torbol Lund ;
Maae, Else ;
Holm, Hanne Spangsberg ;
Scholer, Joachim ;
Thai, Linh My Hoang ;
Matthiessen, Louise Wichmann ;
Maraldo, Maja Vestmo ;
Nielsen, Mathias Maximiliano ;
Johansen, Marianne Besserman ;
Milo, Marie Louise ;
Mogensen, Marie Benzon ;
Nielsen, Mette Holck ;
Moller, Mette ;
Sand, Maja ;
Schultz, Peter ;
Al-Rawi, Sami Aziz-Jowad ;
Esser-Naumann, Saskia ;
Yammeni, Sophie ;
Petersen, Stine Elleberg ;
Offersen, Birgitte Vrou ;
Korreman, Stine Sofia .
RADIOTHERAPY AND ONCOLOGY, 2024, 201
[37]   CLINICAL-TRIALS IN LOCALLY ADVANCED BREAST-CANCER [J].
WALLGREN, A .
ACTA ONCOLOGICA, 1990, 29 (03) :357-360
[38]   A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics [J].
Bleker, Jeroen ;
Kwee, Thomas C. ;
Rouw, Dennis ;
Roest, Christian ;
Borstlap, Jaap ;
de Jong, Igle Jan ;
Dierckx, Rudi A. J. O. ;
Huisman, Henkjan ;
Yakar, Derya .
EUROPEAN RADIOLOGY, 2022, 32 (09) :6526-6535
[39]   A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics [J].
Jeroen Bleker ;
Thomas C. Kwee ;
Dennis Rouw ;
Christian Roest ;
Jaap Borstlap ;
Igle Jan de Jong ;
Rudi A. J. O. Dierckx ;
Henkjan Huisman ;
Derya Yakar .
European Radiology, 2022, 32 :6526-6535
[40]   Automated Meningioma Segmentation in Multiparametric MRI Comparable Effectiveness of a Deep Learning Model and Manual Segmentation [J].
Laukamp, Kai Roman ;
Pennig, Lenhard ;
Thiele, Frank ;
Reimer, Robert ;
Goertz, Lukas ;
Shakirin, Georgy ;
Zopfs, David ;
Timmer, Marco ;
Perkuhn, Michael ;
Borggrefe, Jan .
CLINICAL NEURORADIOLOGY, 2021, 31 (02) :357-366