Inter-Rater Variability of Prostate Lesion Segmentation on Multiparametric Prostate MRI

被引:1
|
作者
Jeganathan, Thibaut [1 ]
Salgues, Emile [1 ]
Schick, Ulrike [2 ,3 ]
Tissot, Valentin [1 ]
Fournier, Georges [3 ,4 ]
Valeri, Antoine [3 ,4 ]
Nguyen, Truong-An [3 ,4 ]
Bourbonne, Vincent [2 ,3 ]
机构
[1] Univ Hosp, Radiol Dept, F-29200 Brest, France
[2] Univ Hosp, Radiat Oncol Dept, F-29200 Brest, France
[3] Univ Western Brittany, INSERM, LaTIM UMR 1101, F-29238 Brest, France
[4] Univ Hosp, Urol Dept, F-29200 Brest, France
关键词
prostate cancer; multiparametric MRI; segmentation; variability; CANCER; LOCALIZATION; RADIOTHERAPY; VOLUME; TRIAL; BOOST; 3T;
D O I
10.3390/biomedicines11123309
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Introduction: External radiotherapy is a major treatment for localized prostate cancer (PCa). Dose escalation to the whole prostate gland increases biochemical relapse-free survival but also acute and late toxicities. Dose escalation to the dominant index lesion (DIL) only is of growing interest. It requires a robust delineation of the DIL. In this context, we aimed to evaluate the inter-observer variability of DIL delineation. Material and Methods: Two junior radiologists and a senior radiation oncologist delineated DILs on 64 mpMRIs of patients with histologically confirmed PCa. For each mpMRI and each reader, eight individual DIL segmentations were delineated. These delineations were blindly performed from one another and resulted from the individual analysis of the T2, apparent diffusion coefficient (ADC), b2000, and dynamic contrast enhanced (DCE) sequences, as well as the analysis of combined sequences (T2ADC, T2ADCb2000, T2ADCDCE, and T2ADCb2000DCE). Delineation variability was assessed using the DICE coefficient, Jaccard index, Hausdorff distance measure, and mean distance to agreement. Results: T2, ADC, T2ADC, b2000, T2 + ADC + b2000, T2 + ADC + DCE, and T2 + ADC + b2000 + DCE sequences obtained DICE coefficients of 0.51, 0.50, 0.54, 0.52, 0.54, 0.55, 0.53, respectively, which are significantly higher than the perfusion sequence alone (0.35, p < 0.001). The analysis of other similarity metrics lead to similar results. The tumor volume and PI-RADS classification were positively correlated with the DICE scores. Conclusion: Our study showed that the contours of prostatic lesions were more reproducible on certain sequences but confirmed the great variability of prostatic contours with a maximum DICE coefficient calculated at 0.55 (joint analysis of T2, ADC, and perfusion sequences).
引用
收藏
页数:11
相关论文
共 50 条
  • [1] Deep Learning Enables Prostate MRI Segmentation: A Large Cohort Evaluation With Inter-Rater Variability Analysis
    Liu, Yongkai
    Miao, Qi
    Surawech, Chuthaporn
    Zheng, Haoxin
    Nguyen, Dan
    Yang, Guang
    Raman, Steven S.
    Sung, Kyunghyun
    FRONTIERS IN ONCOLOGY, 2021, 11
  • [2] Automated segmentation of FLAIR lesion volume and number: validation and comparison to manual inter-rater variability
    Egger, C.
    Opfer, R.
    Wang, C.
    Kepp, T.
    Spies, L.
    Sormani, M. P.
    Barnett, M.
    Schippling, S.
    MULTIPLE SCLEROSIS JOURNAL, 2016, 22 : 517 - 517
  • [3] Prostate tumor delineation using multiparametric MRI: Inter observer variability and pathology validation
    Steenbergen, P.
    Haustermans, K.
    Pos, F.
    Oyen, R.
    Heijmink, S.
    De Wever, L.
    Kalisvaart, R.
    Teertstra, J.
    Van den Bergh, L.
    Van der Heide, U.
    RADIOTHERAPY AND ONCOLOGY, 2014, 111 : S53 - S54
  • [4] Multiparametric MRI for Localized Prostate Cancer: Lesion Detection and Staging
    Margolis, Daniel J. A.
    BIOMED RESEARCH INTERNATIONAL, 2014, 2014
  • [5] Multiparametric MRI of the prostate
    Schlemmer, Heinz-Peter
    RADIOLOGE, 2017, 57 (08): : 621 - 630
  • [6] Multiparametric MRI of the prostate
    Herrmann, Judith
    Kaufmann, Sascha
    Zhang, Cecilia
    Rausch, Steffen
    Bedke, Jens
    Stenzl, Arnulf
    Nikolaou, Konstantin
    Kruck, Stephan
    Seith, Ferdinand
    UROLOGE, 2022, 61 (04): : 428 - 440
  • [7] Multiparametric MRI of the prostate
    Herrmann, Judith
    Kaufmann, Sascha
    Zhang, Cecilia
    Rausch, Steffen
    Bedke, Jens
    Stenzl, Arnulf
    Nikolaou, Konstantin
    Kruck, Stephan
    Seith, Ferdinand
    UROLOGIE, 2022, 61 (04): : 428 - 438
  • [8] INTER-RATER VARIABILITY IN NOCTURNAL OXIMETRY INTERPRETATION
    Iqbal, M. N.
    Ayach, M.
    Strohl, K.
    SLEEP, 2017, 40 : A184 - A185
  • [9] Evaluation of Multimodal Algorithms for the Segmentation of Multiparametric MRI Prostate Images
    Nai, Ying-Hwey
    Teo, Bernice W.
    Tan, Nadya L.
    Chua, Koby Yi Wei
    Wong, Chun Kit
    O'Doherty, Sophie
    Stephenson, Mary C.
    Schaefferkoetter, Josh
    Thian, Yee Liang
    Chiong, Edmund
    Reilhac, Anthonin
    COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2020, 2020
  • [10] An Analysis of the Extent of Intra and Inter-rater Variability in OSCE
    Pathak, Swanand Shrikant
    Mishra, Gaurav Vedprakash
    Warbhe, Rupesh Anna
    INDIAN JOURNAL OF PHARMACEUTICAL EDUCATION AND RESEARCH, 2023, 57 (03) : S507 - S510