Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network

被引:3
|
作者
Jiang, Wenting [1 ]
Lin, Yingying [1 ]
Vardhanabhuti, Varut [1 ]
Ming, Yanzhen [1 ]
Cao, Peng [1 ]
机构
[1] Univ Hong Kong, Dept Diagnost Radiol, Hong Kong, Peoples R China
关键词
prostate cancer; PI-RADS classification; multi-parametric MRI; CapsuleNet; convolutional neural network; ACCURACY;
D O I
10.3390/diagnostics13040615
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
MRI is the primary imaging approach for diagnosing prostate cancer. Prostate ImagingReporting and Data System (PI-RADS) on multiparametric MRI (mpMRI) provides fundamentalMRI interpretation guidelines but suffers from inter-reader variability. Deep learning networks showgreat promise in automatic lesion segmentation and classification, which help to ease the burdenon radiologists and reduce inter-reader variability. In this study, we proposed a novel multi-branchnetwork, MiniSegCaps, for prostate cancer segmentation and PI-RADS classification on mpMRI.MiniSeg branch outputted the segmentation in conjunction with PI-RADS prediction, guided by theattention map from the CapsuleNet. CapsuleNet branch exploited the relative spatial information ofprostate cancer to anatomical structures, such as the zonal location of the lesion, which also reducedthe sample size requirement in training due to its equivariance properties. In addition, a gatedrecurrent unit (GRU) is adopted to exploit spatial knowledge across slices, improving through-planeconsistency. Based on the clinical reports, we established a prostate mpMRI database from 462 patientspaired with radiologically estimated annotations. MiniSegCaps was trained and evaluated withfivefold cross-validation. On 93 testing cases, our model achieved a 0.712 dice coefficient on lesionsegmentation, 89.18% accuracy, and 92.52% sensitivity on PI-RADS classification (PI-RADS >= 4) inpatient-level evaluation, significantly outperforming existing methods. In addition, a graphical userinterface (GUI) integrated into the clinical workflow can automatically produce diagnosis reportsbased on the results from MiniSegCaps.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] PI-RADS: multiparametric MRI in prostate cancer
    Aileen O’Shea
    Mukesh Harisinghani
    Magnetic Resonance Materials in Physics, Biology and Medicine, 2022, 35 : 523 - 532
  • [2] PI-RADS: multiparametric MRI in prostate cancer
    O'Shea, Aileen
    Harisinghani, Mukesh
    MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE, 2022, 35 (04) : 523 - 532
  • [3] Detection and Localization of Prostate Cancer at 3-T Multiparametric MRI Using PI-RADS Segmentation
    Wibulpolprasert, Pornphan
    Raman, Steven S.
    Hsu, William
    Margolis, Daniel J. A.
    Asvadi, Nazanin H.
    Khoshnoodi, Pooria
    Moshksar, Amin
    Tan, Nelly
    Ahuia, Preeti
    Maehara, Cleo K.
    Huang, Jiaoti
    Sayre, James
    Lu, David S. K.
    Reiter, Robert E.
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2019, 212 (06) : W122 - W131
  • [4] PI-RADS Steering Committee: The PI-RADS Multiparametric MRI and MRI-directed Biopsy Pathway
    Padhani, Anwar R.
    Barentsz, Jelle
    Villeirs, Geert
    Rosenkrantz, Andrew B.
    Margolis, Daniel J.
    Turkbey, Bares
    Thoeny, Harriet C.
    Cornud, Francois
    Haider, Masoom A.
    Macura, Katarzyna F.
    Tempany, Clare M.
    Verma, Sadhna
    Weinreb, Jeffery C.
    RADIOLOGY, 2019, 292 (02) : 464 - 474
  • [5] PI-RADS and Multiparametric MRI: The Shape of Things to Come for Prostate Cancer
    Goh, Vicky
    RADIOLOGY, 2023, 307 (04)
  • [6] Index lesion detection in multifocal prostate cancer: Simplified PI-RADS biparametric MRI vs PI-RADS v2.1 multiparametric MRI
    Scialpi, Michele
    Martorana, Eugenio
    Torre, Riccardo
    Scalera, Giovanni Battista
    Belatti, Eugenio
    Improta, Antonio
    Aisa, Maria Cristina
    Burani, Aldo
    Santini, Nicola
    D'Andrea, Alfredo
    Mancioli, Francesco Maria
    Scialpi, Pietro
    Di Blasi, Aldo
    CLINICAL IMAGING, 2023, 94 : 108 - 115
  • [7] PREDICTING CANCER DETECTION RATES FROM MULTIPARAMETRIC PROSTATE MRI: REFINING BEYOND THE PI-RADS CLASSIFICATION SYSTEM
    Ramos, Francisco
    Fleishman, Aaron
    Kaul, Sumedh
    Korets, Ruslan
    Johnson, Michael
    Olumi, Aria
    Tsai, Leo
    Gershman, Boris
    JOURNAL OF UROLOGY, 2021, 206 : E790 - E791
  • [8] Deep learning model for the detection of prostate cancer and classification of clinically significant disease using multiparametric MRI in comparison to PI-RADs score
    Yang, Chunguang
    Li, Basen
    Luan, Yang
    Wang, Shiwei
    Bian, Yang
    Zhang, Junbiao
    Wang, Zefeng
    Liu, Bo
    Chen, Xin
    Hacker, Marcus
    Li, Zhen
    Li, Xiang
    Wang, Zhihua
    UROLOGIC ONCOLOGY-SEMINARS AND ORIGINAL INVESTIGATIONS, 2024, 42 (05) : 158.e17 - 158.e27
  • [9] PI-RADS Classification: Structured Reporting for MRI of the Prostate
    Roethke, M.
    Blondin, D.
    Schlemmer, H. -P.
    Franiel, T.
    ROFO-FORTSCHRITTE AUF DEM GEBIET DER RONTGENSTRAHLEN UND DER BILDGEBENDEN VERFAHREN, 2013, 185 (03): : 253 - 261
  • [10] Association of PI-RADS score of multiparametric MRI and prostate biopsy results
    Gupta, D. R.
    Khera, Rakesh
    Ahlawat, Kulbir
    Yadav, Rajiv
    Bansal, Somender
    INTERNATIONAL JOURNAL OF UROLOGY, 2016, 23 : 66 - 66