Elaine Cha1, Sharif Elguindi2, Ifeanyirochukwu Onochie1, Daniel Gorovets1, Joseph O Deasy2, Michael Zelefsky1, Erin F Gillespie3. 1. Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, United States. 2. Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, United States. 3. Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, United States. Electronic address: efgillespie@ucsd.edu.
Abstract
BACKGROUND AND PURPOSE: Artificial intelligence advances have stimulated a new generation of autosegmentation, however clinical evaluations of these algorithms are lacking. This study assesses the clinical utility of deep learning-based autosegmentation for MR-based prostate radiotherapy planning. MATERIALS AND METHODS: Data was collected prospectively for patients undergoing prostate-only radiation at our institution from June to December 2019. Geometric indices (volumetric Dice-Sørensen Coefficient, VDSC; surface Dice-Sørensen Coefficient, SDSC; added path length, APL) compared automated to final contours. Physicians reported contouring time and rated autocontours on 3-point protocol deviation scales. Descriptive statistics and univariable analyses evaluated relationships between the aforementioned metrics. RESULTS: Among 173 patients, 85% received SBRT. The CTV was available for 167 (97%) with median VDSC, SDSC, and APL for CTV (prostate and SV) 0.89 (IQR 0.83-0.95), 0.91 (IQR 0.75-0.96), and 1801 mm (IQR 1140-2703), respectively. Physicians completed surveys for 43/55 patients (RR 78%). 33% of autocontours (14/43) required major "clinically significant" edits. Physicians spent a median of 28 min contouring (IQR 20-30), representing a 12-minute (30%) time savings compared to historic controls (median 40, IQR 25-68, n = 21, p < 0.01). Geometric indices correlated weakly with contouring time, and had no relationship with quality scores. CONCLUSION: Deep learning-based autosegmentation was implemented successfully and improved efficiency. Major "clinically significant" edits are uncommon and do not correlate with geometric indices. APL was supported as a clinically meaningful quantitative metric. Efforts are needed to educate and generate consensus among physicians, and develop mechanisms to flag cases for quality assurance.
BACKGROUND AND PURPOSE: Artificial intelligence advances have stimulated a new generation of autosegmentation, however clinical evaluations of these algorithms are lacking. This study assesses the clinical utility of deep learning-based autosegmentation for MR-based prostate radiotherapy planning. MATERIALS AND METHODS: Data was collected prospectively for patients undergoing prostate-only radiation at our institution from June to December 2019. Geometric indices (volumetric Dice-Sørensen Coefficient, VDSC; surface Dice-Sørensen Coefficient, SDSC; added path length, APL) compared automated to final contours. Physicians reported contouring time and rated autocontours on 3-point protocol deviation scales. Descriptive statistics and univariable analyses evaluated relationships between the aforementioned metrics. RESULTS: Among 173 patients, 85% received SBRT. The CTV was available for 167 (97%) with median VDSC, SDSC, and APL for CTV (prostate and SV) 0.89 (IQR 0.83-0.95), 0.91 (IQR 0.75-0.96), and 1801 mm (IQR 1140-2703), respectively. Physicians completed surveys for 43/55 patients (RR 78%). 33% of autocontours (14/43) required major "clinically significant" edits. Physicians spent a median of 28 min contouring (IQR 20-30), representing a 12-minute (30%) time savings compared to historic controls (median 40, IQR 25-68, n = 21, p < 0.01). Geometric indices correlated weakly with contouring time, and had no relationship with quality scores. CONCLUSION: Deep learning-based autosegmentation was implemented successfully and improved efficiency. Major "clinically significant" edits are uncommon and do not correlate with geometric indices. APL was supported as a clinically meaningful quantitative metric. Efforts are needed to educate and generate consensus among physicians, and develop mechanisms to flag cases for quality assurance.
Authors: Roel J H M Steenbakkers; Joop C Duppen; Isabelle Fitton; Kirsten E I Deurloo; Lambert Zijp; Apollonia L J Uitterhoeve; Patrick T R Rodrigus; Gijsbert W P Kramer; Johan Bussink; Katrien De Jaeger; José S A Belderbos; Augustinus A M Hart; Peter J C M Nowak; Marcel van Herk; Coen R N Rasch Journal: Radiother Oncol Date: 2005-10-26 Impact factor: 6.280
Authors: Simon L Duke; Li-Tee Tan; Nina B K Jensen; Tamara Rumpold; Astrid A C De Leeuw; Christian Kirisits; Jacob C Lindegaard; Kari Tanderup; Richard C Pötter; Remi A Nout; Ina M Jürgenliemk-Schulz Journal: Radiother Oncol Date: 2020-03-30 Impact factor: 6.280
Authors: Tim Lustberg; Johan van Soest; Mark Gooding; Devis Peressutti; Paul Aljabar; Judith van der Stoep; Wouter van Elmpt; Andre Dekker Journal: Radiother Oncol Date: 2017-12-05 Impact factor: 6.280
Authors: Scott C Morgan; Karen Hoffman; D Andrew Loblaw; Mark K Buyyounouski; Caroline Patton; Daniel Barocas; Soren Bentzen; Michael Chang; Jason Efstathiou; Patrick Greany; Per Halvorsen; Bridget F Koontz; Colleen Lawton; C Marc Leyrer; Daniel Lin; Michael Ray; Howard Sandler Journal: Pract Radiat Oncol Date: 2018-10-11
Authors: M Austin-Seymour; G T Chen; J Rosenman; J Michalski; K Lindsley; M Goitein Journal: Int J Radiat Oncol Biol Phys Date: 1995-12-01 Impact factor: 7.038
Authors: Asma Amjad; Jiaofeng Xu; Dan Thill; Colleen Lawton; William Hall; Musaddiq J Awan; Monica Shukla; Beth A Erickson; X Allen Li Journal: Med Phys Date: 2022-02-07 Impact factor: 4.071
Authors: Jeremiah W Sanders; Rajat J Kudchadker; Chad Tang; Henry Mok; Aradhana M Venkatesan; Howard D Thames; Steven J Frank Journal: Radiol Artif Intell Date: 2022-01-26
Authors: Rosie J Goodburn; Marielle E P Philippens; Thierry L Lefebvre; Aly Khalifa; Tom Bruijnen; Joshua N Freedman; David E J Waddington; Eyesha Younus; Eric Aliotta; Gabriele Meliadò; Teo Stanescu; Wajiha Bano; Ali Fatemi-Ardekani; Andreas Wetscherek; Uwe Oelfke; Nico van den Berg; Ralph P Mason; Petra J van Houdt; James M Balter; Oliver J Gurney-Champion Journal: Magn Reson Med Date: 2022-09-21 Impact factor: 3.737
Authors: Michael V Sherer; Diana Lin; Sharif Elguindi; Simon Duke; Li-Tee Tan; Jon Cacicedo; Max Dahele; Erin F Gillespie Journal: Radiother Oncol Date: 2021-05-11 Impact factor: 6.901
Authors: Jordan Wong; Vicky Huang; Derek Wells; Joshua Giambattista; Jonathan Giambattista; Carter Kolbeck; Karl Otto; Elantholi P Saibishkumar; Abraham Alexander Journal: Radiat Oncol Date: 2021-06-08 Impact factor: 3.481
Authors: Jordan Wong; Vicky Huang; Joshua A Giambattista; Tony Teke; Carter Kolbeck; Jonathan Giambattista; Siavash Atrchian Journal: Front Oncol Date: 2021-06-07 Impact factor: 6.244
Authors: Daniel Wegener; Daniel Zips; Cihan Gani; Simon Boeke; Konstantin Nikolaou; Ahmed E Othman; Haidara Almansour; Frank Paulsen; Arndt-Christian Müller Journal: Radiologe Date: 2021-07-23 Impact factor: 0.635