Literature DB >> 32700021

Test-retest repeatability of a deep learning architecture in detecting and segmenting clinically significant prostate cancer on apparent diffusion coefficient (ADC) maps.

Amogh Hiremath1, Rakesh Shiradkar2, Harri Merisaari2,3, Prateek Prasanna2,4, Otto Ettala5, Pekka Taimen6, Hannu J Aronen7, Peter J Boström5, Ivan Jambor3,8, Anant Madabhushi2,9.   

Abstract

OBJECTIVES: To evaluate short-term test-retest repeatability of a deep learning architecture (U-Net) in slice- and lesion-level detection and segmentation of clinically significant prostate cancer (csPCa: Gleason grade group > 1) using diffusion-weighted imaging fitted with monoexponential function, ADCm.
METHODS: One hundred twelve patients with prostate cancer (PCa) underwent 2 prostate MRI examinations on the same day. PCa areas were annotated using whole mount prostatectomy sections. Two U-Net-based convolutional neural networks were trained on three different ADCm b value settings for (a) slice- and (b) lesion-level detection and (c) segmentation of csPCa. Short-term test-retest repeatability was estimated using intra-class correlation coefficient (ICC(3,1)), proportionate agreement, and dice similarity coefficient (DSC). A 3-fold cross-validation was performed on training set (N = 78 patients) and evaluated for performance and repeatability on testing data (N = 34 patients).
RESULTS: For the three ADCm b value settings, repeatability of mean ADCm of csPCa lesions was ICC(3,1) = 0.86-0.98. Two CNNs with U-Net-based architecture demonstrated ICC(3,1) in the range of 0.80-0.83, agreement of 66-72%, and DSC of 0.68-0.72 for slice- and lesion-level detection and segmentation of csPCa. Bland-Altman plots suggest that there is no systematic bias in agreement between inter-scan ground truth segmentation repeatability and segmentation repeatability of the networks.
CONCLUSIONS: For the three ADCm b value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level. The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility. KEY POINTS: • For the three ADCm b value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level. • The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility.

Entities:  

Keywords:  Diffusion MRI; Neural network models; Prostate cancer; Test-retest reliability

Mesh:

Year:  2020        PMID: 32700021      PMCID: PMC7821380          DOI: 10.1007/s00330-020-07065-4

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  19 in total

1.  Inter-reader agreement of the ESUR score for prostate MRI using in-bore MRI-guided biopsies as the reference standard.

Authors:  L Schimmöller; M Quentin; C Arsov; R S Lanzman; A Hiester; R Rabenalt; G Antoch; P Albers; D Blondin
Journal:  Eur Radiol       Date:  2013-06-12       Impact factor: 5.315

2.  Clinically significant prostate cancer detection on MRI: A radiomic shape features study.

Authors:  Renato Cuocolo; Arnaldo Stanzione; Andrea Ponsiglione; Valeria Romeo; Francesco Verde; Massimiliano Creta; Roberto La Rocca; Nicola Longo; Leonardo Pace; Massimo Imbriaco
Journal:  Eur J Radiol       Date:  2019-05-07       Impact factor: 3.528

3.  Evaluation of radiomic texture feature error due to MRI acquisition and reconstruction: A simulation study utilizing ground truth.

Authors:  Fei Yang; Nesrin Dogan; Radka Stoyanova; John Chetley Ford
Journal:  Phys Med       Date:  2018-05-22       Impact factor: 2.685

4.  Computer-aided classification of prostate cancer grade groups from MRI images using texture features and stacked sparse autoencoder.

Authors:  Bejoy Abraham; Madhu S Nair
Journal:  Comput Med Imaging Graph       Date:  2018-08-25       Impact factor: 4.790

Review 5.  Motion artifacts in MRI: A complex problem with many partial solutions.

Authors:  Maxim Zaitsev; Julian Maclaren; Michael Herbst
Journal:  J Magn Reson Imaging       Date:  2015-01-28       Impact factor: 4.813

6.  Evaluation of different mathematical models for diffusion-weighted imaging of normal prostate and prostate cancer using high b-values: a repeatability study.

Authors:  Ivan Jambor; Harri Merisaari; Pekka Taimen; Peter Boström; Heikki Minn; Marko Pesola; Hannu J Aronen
Journal:  Magn Reson Med       Date:  2014-07-12       Impact factor: 4.668

7.  Optimization of b-value distribution for four mathematical models of prostate cancer diffusion-weighted imaging using b values up to 2000 s/mm(2): simulation and repeatability study.

Authors:  Harri Merisaari; Ivan Jambor
Journal:  Magn Reson Med       Date:  2014-07-09       Impact factor: 4.668

8.  Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: Cross-validation of a machine learning method.

Authors:  Xiangde Min; Min Li; Di Dong; Zhaoyan Feng; Peipei Zhang; Zan Ke; Huijuan You; Fangfang Han; He Ma; Jie Tian; Liang Wang
Journal:  Eur J Radiol       Date:  2019-03-15       Impact factor: 3.528

9.  Prostate Magnetic Resonance Imaging Interpretation Varies Substantially Across Radiologists.

Authors:  Geoffrey A Sonn; Richard E Fan; Pejman Ghanouni; Nancy N Wang; James D Brooks; Andreas M Loening; Bruce L Daniel; Katherine J To'o; Alan E Thong; John T Leppert
Journal:  Eur Urol Focus       Date:  2017-12-07

10.  Combining Prostate-Specific Antigen Parameters With Prostate Imaging Reporting and Data System Score Version 2.0 to Improve Its Diagnostic Accuracy.

Authors:  Sasanka Kumar Baruah; Nabajeet Das; Saumar Jyoti Baruah; T P Rajeev; Puskal Kumar Bagchi; Debanga Sharma; Mandeep Phukan
Journal:  World J Oncol       Date:  2019-12-16
View more
  5 in total

Review 1.  Challenges in ensuring the generalizability of image quantitation methods for MRI.

Authors:  Kathryn E Keenan; Jana G Delfino; Kalina V Jordanova; Megan E Poorman; Prathyush Chirra; Akshay S Chaudhari; Bettina Baessler; Jessica Winfield; Satish E Viswanath; Nandita M deSouza
Journal:  Med Phys       Date:  2021-09-29       Impact factor: 4.506

Review 2.  Role of Deep Learning in Prostate Cancer Management: Past, Present and Future Based on a Comprehensive Literature Review.

Authors:  Nithesh Naik; Theodoros Tokas; Dasharathraj K Shetty; B M Zeeshan Hameed; Sarthak Shastri; Milap J Shah; Sufyan Ibrahim; Bhavan Prasad Rai; Piotr Chłosta; Bhaskar K Somani
Journal:  J Clin Med       Date:  2022-06-21       Impact factor: 4.964

3.  Prostate Surface Distension and Tumor Texture Descriptors From Pre-Treatment MRI Are Associated With Biochemical Recurrence Following Radical Prostatectomy: Preliminary Findings.

Authors:  Rakesh Shiradkar; Soumya Ghose; Amr Mahran; Lin Li; Isaac Hubbard; Pingfu Fu; Sree Harsha Tirumani; Lee Ponsky; Andrei Purysko; Anant Madabhushi
Journal:  Front Oncol       Date:  2022-05-20       Impact factor: 5.738

4.  The Primacy of High B-Value 3T-DWI Radiomics in the Prediction of Clinically Significant Prostate Cancer.

Authors:  Alessandro Bevilacqua; Margherita Mottola; Fabio Ferroni; Alice Rossi; Giampaolo Gavelli; Domenico Barone
Journal:  Diagnostics (Basel)       Date:  2021-04-21

Review 5.  Current Value of Biparametric Prostate MRI with Machine-Learning or Deep-Learning in the Detection, Grading, and Characterization of Prostate Cancer: A Systematic Review.

Authors:  Henrik J Michaely; Giacomo Aringhieri; Dania Cioni; Emanuele Neri
Journal:  Diagnostics (Basel)       Date:  2022-03-24
  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.