Self-transfer learning via patches: A prostate cancer triage approach based on bi-parametric MRI

Prostate cancer (PCa) is the second most common cancer diagnosed among men worldwide. The current PCa diagnostic pathway comes at the cost of substantial overdiagnosis, leading to unnecessary treatment and further testing. Bi-parametric magnetic resonance imaging (bp-MRI) based on apparent diffusion coefficient maps (ADC) and T2-weighted (T2w) sequences has been proposed as a triage test to differentiate between clinically significant (cS) and non-clinically significant (ncS) prostate lesions. However, analysis of the sequences relies on expertise, requires specialized training, and suffers from inter-observer variability. Deep learning (DL) techniques hold promise in tasks such as classification and detection. Nevertheless, they rely on large amounts of annotated data which is not common in the medical field. In order to palliate such issues, existing works rely on transfer learning (TL) and ImageNet pre-training, which has been proven to be sub-optimal for the medical imaging domain. In this paper, we present a patch-based pre-training strategy to distinguish between cS and ncS lesions which exploit the region of interest (ROI) of the patched source domain to efficiently train a classifier in the full-slice target domain which does not require annotations by making use of transfer learning (TL). We provide a comprehensive comparison between several CNNs architectures and different settings which are presented as a baseline. Moreover, we explore cross-domain TL which exploits both MRI modalities and improves single modality results. Finally, we show how our approaches outperform the standard approaches by a considerable margin

[1]  Morten Goodwin Olsen,et al.  Improving Prostate Whole Gland Segmentation In T2-Weighted MRI With Synthetically Generated Data , 2021, 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI).

[2]  R. Cuocolo,et al.  Quality control and whole-gland, zonal and lesion annotations for the PROSTATEx challenge public dataset. , 2021, European journal of radiology.

[3]  Lin Liu,et al.  A Comprehensive Study of Data Augmentation Strategies for Prostate Cancer Detection in Diffusion-Weighted MRI Using Convolutional Neural Networks , 2020, Journal of Digital Imaging.

[4]  K. Oppedal,et al.  Prostate cancer screening and socioeconomic disparities in Mexican older adults. , 2020, Salud publica de Mexico.

[5]  H. Ahmed,et al.  All change in the prostate cancer diagnostic pathway , 2020, Nature Reviews Clinical Oncology.

[6]  A. Jemal,et al.  Cancer statistics, 2020 , 2020, CA: a cancer journal for clinicians.

[7]  F. Deckers,et al.  Magnetic resonance imaging sequences for prostate cancer triage: two is a couple, three is a crowd? , 2019, Translational andrology and urology.

[8]  D. Margolis,et al.  Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2. , 2019, European urology.

[9]  Masoom A. Haider,et al.  Prostate Cancer Detection using Deep Convolutional Neural Networks , 2019, Scientific Reports.

[10]  Ruiming Cao,et al.  Joint Prostate Cancer Detection and Gleason Score Prediction in mp-MRI via FocalNet , 2019, IEEE Transactions on Medical Imaging.

[11]  Jon Kleinberg,et al.  Transfusion: Understanding Transfer Learning for Medical Imaging , 2019, NeurIPS.

[12]  Bulat Ibragimov,et al.  Prostate cancer classification with multiparametric MRI transfer learning model , 2019, Medical physics.

[13]  Lubomir M. Hadjiiski,et al.  PROSTATEx Challenges for computerized classification of prostate lesions from multiparametric magnetic resonance images , 2018, Journal of medical imaging.

[14]  R. Gillies,et al.  Repeatability and Reproducibility of Radiomic Features: A Systematic Review , 2018, International journal of radiation oncology, biology, physics.

[15]  Itsuo Kumazawa,et al.  MP20-10 DEEP LEARNING WITH A CONVOLUTIONAL NEURAL NETWORK ALGORITHM FOR FULLY AUTOMATED DETECTION OF PROSTATE CANCER USING PRE-BIOPSY MRI , 2018 .

[16]  John W. Davis,et al.  Multiparametric magnetic resonance imaging: Overview of the technique, clinical applications in prostate biopsy and future directions. , 2018, Turkish journal of urology.

[17]  Emil N. Sørensen,et al.  Recognition , 2018, Routledge Library Editions: Epistemology.

[18]  A. Ng,et al.  CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning , 2017, ArXiv.

[19]  Tao Liu,et al.  Searching for prostate cancer by fully automated magnetic resonance imaging classification: deep learning versus non-deep learning , 2017, Scientific Reports.

[20]  Li Shen,et al.  Deep Learning to Improve Breast Cancer Detection on Screening Mammography , 2017, Scientific Reports.

[21]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[22]  Xin Yang,et al.  Automated diagnosis of prostate cancer in multi-parametric MRI based on multimodal convolutional neural networks , 2017, Physics in medicine and biology.

[23]  Purang Abolmaesumi,et al.  Classification of clinical significance of MRI prostate findings using 3D convolutional neural networks , 2017, Medical Imaging.

[24]  Wei Li,et al.  Prostate cancer diagnosis using deep learning with 3D multiparametric MRI , 2017, Medical Imaging.

[25]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[26]  Adam T Froemming,et al.  Interobserver Reproducibility of the PI-RADS Version 2 Lexicon: A Multicenter Study of Six Experienced Prostate Radiologists. , 2016, Radiology.

[27]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[28]  Tristan Barrett,et al.  Defining the learning curve for multiparametric magnetic resonance imaging (MRI) of the prostate using MRI‐transrectal ultrasonography (TRUS) fusion‐guided transperineal prostate biopsies as a validation tool , 2016, BJU international.

[29]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  J. K. Kim,et al.  Multiparametric magnetic resonance imaging for prostate cancer: A review and update for urologists , 2015, Korean journal of urology.

[32]  A. Jemal,et al.  Global cancer statistics, 2012 , 2015, CA: a cancer journal for clinicians.

[33]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[34]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[35]  Nico Karssemeijer,et al.  Computer-Aided Detection of Prostate Cancer in MRI , 2014, IEEE Transactions on Medical Imaging.

[36]  Amita Shukla-Dave,et al.  Role of MRI in prostate cancer detection , 2014, NMR in biomedicine.

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  Michael J Barry,et al.  Screening for prostate cancer--the controversy that refuses to die. , 2009, The New England journal of medicine.

[39]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  J. Richie,et al.  COMPARISON OF DIGITAL RECTAL EXAMINATION AND SERUM PROSTATE SPECIFIC ANTIGEN IN THE EARLY DETECTION OF PROSTATE CANCER: RESULTS OF A MULTICENTER CLINICAL TRIAL OF 6,630 MEN , 1994, The Journal of urology.

[41]  T. Stamey,et al.  Ultrasound guided transrectal core biopsies of the palpably abnormal prostate. , 1989, The Journal of urology.

[42]  P. Choyke,et al.  Role of MRI in Prostate Cancer Assessment , 2021, Interventional Urology.

[43]  M. Hallek Prostate Cancer , 2018, Springer International Publishing.

[44]  N. Lumen,et al.  Dynamic contrast-enhanced imaging has limited added value over T2-weighted imaging and diffusion-weighted imaging when using PI-RADSv2 for diagnosis of clinically significant prostate cancer in patients with elevated PSA. , 2017, Clinical radiology.

[45]  D. Margolis,et al.  PI-RADS Prostate Imaging - Reporting and Data System: 2015, Version 2. , 2016, European urology.

[46]  M. Brawer,et al.  Prostate cancer detection. , 1994, The Journal of urology.

[47]  N. Dubrawsky Cancer statistics , 1989, CA: a cancer journal for clinicians.