دورية أكاديمية
E pluribus unum: prospective acceptability benchmarking from the Contouring Collaborative for Consensus in Radiation Oncology crowdsourced initiative for multiobserver segmentation.
| العنوان: | E pluribus unum: prospective acceptability benchmarking from the Contouring Collaborative for Consensus in Radiation Oncology crowdsourced initiative for multiobserver segmentation. |
|---|---|
| المؤلفون: | Lin D; Memorial Sloan Kettering Cancer Center, Department of Radiation Oncology, New York, New York, United States., Wahid KA; The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, Texas, United States., Nelms BE; Canis Lupus, LLC, Merrimac, Wisconsin, United States., He R; The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, Texas, United States., Naser MA; The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, Texas, United States., Duke S; Cambridge University Hospitals, Department of Radiation Oncology, Cambridge, United Kingdom., Sherer MV; University of California San Diego, Department of Radiation Medicine and Applied Sciences, La Jolla, California, United States., Christodouleas JP; The University of Pennsylvania Cancer Center, Department of Radiation Oncology, Philadelphia, Pennsylvania, United States.; Elekta AB, Stockholm, Sweden., Mohamed ASR; The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, Texas, United States., Cislo M; Memorial Sloan Kettering Cancer Center, Department of Radiation Oncology, New York, New York, United States., Murphy JD; University of California San Diego, Department of Radiation Medicine and Applied Sciences, La Jolla, California, United States., Fuller CD; The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, Texas, United States., Gillespie EF; Memorial Sloan Kettering Cancer Center, Department of Radiation Oncology, New York, New York, United States.; University of Washington Fred Hutchinson Cancer Center, Department of Radiation Oncology, Seattle, Washington, United States. |
| المصدر: | Journal of medical imaging (Bellingham, Wash.) [J Med Imaging (Bellingham)] 2023 Feb; Vol. 10 (Suppl 1), pp. S11903. Date of Electronic Publication: 2023 Feb 08. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Society of Photo-Optical Instrumentation Engineers Country of Publication: United States NLM ID: 101643461 Publication Model: Print-Electronic Cited Medium: Print ISSN: 2329-4302 (Print) Linking ISSN: 23294302 NLM ISO Abbreviation: J Med Imaging (Bellingham) Subsets: PubMed not MEDLINE |
| أسماء مطبوعة: | Original Publication: Bellingham, Wash. : Society of Photo-Optical Instrumentation Engineers |
| مستخلص: | Purpose: Contouring Collaborative for Consensus in Radiation Oncology (C3RO) is a crowdsourced challenge engaging radiation oncologists across various expertise levels in segmentation. An obstacle to artificial intelligence (AI) development is the paucity of multiexpert datasets; consequently, we sought to characterize whether aggregate segmentations generated from multiple nonexperts could meet or exceed recognized expert agreement. Approach: Participants who contoured ≥ 1 region of interest (ROI) for the breast, sarcoma, head and neck (H&N), gynecologic (GYN), or gastrointestinal (GI) cases were identified as a nonexpert or recognized expert. Cohort-specific ROIs were combined into single simultaneous truth and performance level estimation (STAPLE) consensus segmentations. STAPLE nonexpert ROIs were evaluated against STAPLE expert contours using Dice similarity coefficient (DSC). The expert interobserver DSC ( IODSC expert ) was calculated as an acceptability threshold between STAPLE nonexpert and STAPLE expert . To determine the number of nonexperts required to match the IODSC expert for each ROI, a single consensus contour was generated using variable numbers of nonexperts and then compared to the IODSC expert . Results: For all cases, the DSC values for STAPLE nonexpert versus STAPLE expert were higher than comparator expert IODSC expert for most ROIs. The minimum number of nonexpert segmentations needed for a consensus ROI to achieve IODSC expert acceptability criteria ranged between 2 and 4 for breast, 3 and 5 for sarcoma, 3 and 5 for H&N, 3 and 5 for GYN, and 3 for GI. Conclusions: Multiple nonexpert-generated consensus ROIs met or exceeded expert-derived acceptability thresholds. Five nonexperts could potentially generate consensus segmentations for most ROIs with performance approximating experts, suggesting nonexpert segmentations as feasible cost-effective AI inputs. (© 2023 The Authors.) |
| References: | J Med Internet Res. 2021 Jul 12;23(7):e26151. (PMID: 34255661) Radiat Oncol. 2012 Mar 13;7:32. (PMID: 22414264) JCO Clin Cancer Inform. 2019 Oct;3:1-9. (PMID: 31756136) Pract Radiat Oncol. 2016 Nov - Dec;6(6):442-449. (PMID: 27374191) Pract Radiat Oncol. 2013 Jul-Sep;3(3):186-193. (PMID: 24674363) Radiol Oncol. 2016 May 09;50(3):254-62. (PMID: 27679540) Front Oncol. 2017 Sep 25;7:221. (PMID: 28993798) Int J Radiat Oncol Biol Phys. 2018 Mar 15;100(4):1057-1066. (PMID: 29485047) J Clin Oncol. 2015 Jan 10;33(2):156-64. (PMID: 25488965) Pract Radiat Oncol. 2021 May-Jun;11(3):226-229. (PMID: 33607331) Radiat Oncol. 2021 Jun 28;16(1):120. (PMID: 34183040) JAMA Oncol. 2019 May 01;5(5):654-661. (PMID: 30998808) Pract Radiat Oncol. 2016 Sep-Oct;6(5):e203-e213. (PMID: 27032573) Phys Med Biol. 2020 Aug 27;65(17):175007. (PMID: 32503027) J Natl Cancer Inst. 2016 May 19;108(9):. (PMID: 27206636) J Digit Imaging. 2021 Jun;34(3):541-553. (PMID: 34027588) Radiother Oncol. 2002 Jan;62(1):37-49. (PMID: 11830311) IEEE Trans Med Imaging. 2004 Jul;23(7):903-21. (PMID: 15250643) J Digit Imaging. 2018 Jun;31(3):290-303. (PMID: 29181613) Int J Radiat Oncol Biol Phys. 2020 Jul 15;107(4):827-835. (PMID: 32311418) J Med Imaging (Bellingham). 2018 Jul;5(3):034002. (PMID: 30840724) Radiother Oncol. 2019 Jan;130:56-61. (PMID: 30420234) Adv Radiat Oncol. 2022 Jul 29;7(6):101009. (PMID: 36092987) Clin Transl Radiat Oncol. 2018 Aug 02;12:40-46. (PMID: 30148217) Radiother Oncol. 2021 Jul;160:185-191. (PMID: 33984348) J Med Phys. 2008 Oct;33(4):136-40. (PMID: 19893706) Int J Radiat Oncol Biol Phys. 2011 Feb 1;79(2):481-9. (PMID: 20400244) Int J Radiat Oncol Biol Phys. 2013 May 1;86(1):27-33. (PMID: 23154075) Radiother Oncol. 2014 Sep;112(3):418-24. (PMID: 24996454) Int J Radiat Oncol Biol Phys. 2022 Jun 1;113(2):426-436. (PMID: 35124134) Pract Radiat Oncol. 2015 Mar-Apr;5(2):e67-75. (PMID: 25413413) |
| معلومات مُعتمدة: | R01 DE028290 United States DE NIDCR NIH HHS; P30 CA008748 United States CA NCI NIH HHS; UL1 TR002384 United States TR NCATS NIH HHS; R18 HS026881 United States HS AHRQ HHS; F31 DE031502 United States DE NIDCR NIH HHS |
| فهرسة مساهمة: | Keywords: artificial intelligence; autosegmentation; contouring; crowdsourcing; radiation oncology; segmentation |
| تواريخ الأحداث: | Date Created: 20230210 Latest Revision: 20240425 |
| رمز التحديث: | 20240425 |
| مُعرف محوري في PubMed: | PMC9907021 |
| DOI: | 10.1117/1.JMI.10.S1.S11903 |
| PMID: | 36761036 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 2329-4302 |
|---|---|
| DOI: | 10.1117/1.JMI.10.S1.S11903 |