End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effect of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reduction

@article{Saha2021EndtoendPC,
  title={End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effect of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reduction},
  author={Anindo Saha and Matin Hosseinzadeh and Henkjan J. Huisman},
  journal={Medical image analysis},
  year={2021},
  volume={73},
  pages={
          102155
        }
}

Figures and Tables from this paper

Controlling False Positive/Negative Rates for Deep-Learning-Based Prostate Cancer Detection on Multiparametric MR images
TLDR
A novel PCa detection network that incorporates a lesion-level cost-sensitive loss and an additional slice-level loss based on a lesION-to-slice mapping function, to manage the lesionand slice- level costs, respectively is proposed.
Annotation-efficient cancer detection with report-guided lesion annotation for deep learning-based prostate cancer detection in bpMRI
TLDR
Semisupervised detection models can be trained semi-supervised with automatic annotations generated using model predictions, guided by sparse information from clinical reports, to demonstrate efficacy and demonstrate the feasibility of the training procedure.
Report-Guided Automatic Lesion Annotation for Deep Learning-Based Prostate Cancer Detection in bpMRI
TLDR
It is hypothesised that dense annotations for detection tasks can be generated using model predictions, guided by sparse information from these reports, and generated clinically significant prostate cancer (csPCa) annotations,guided by the number of clinically significant findings in the radiology reports.
Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI - Should Different Clinical Objectives Mandate Different Loss Functions?
TLDR
It is found that distribution-based loss functions are well-suited for diagnostic or panoptic segmentation tasks such as lesion detection, primarily due to their implicit property of inducing better calibration.
Detection of COVID-19 from chest radiology using histogram equalization combined with a CNN convolutional network
TLDR
A new method of detection of the presence of this virus in patients was implemented based on deep learning using a deep learning model by convolutional neural network architecture (CNN) using a COVID-QU chest X- ray imaging database.
Cross-modality learning for tumor segmentation in dosimetric planning
  • Medicine, Physics
  • 2022
TLDR
Automatic and robust GTV segmentation based on multiple multi-modal acquisitions including MR T2, ADC, B2000, perfusion and computed tomography images with contrast agent injection, is requested to standardize the dosimetric planning while alleviating the expert variability induced by the delineation task.
The use of deep learning in interventional radiotherapy (brachytherapy): a review with a focus on open source and open data
TLDR
It is shown that deep learning plays already a major role in some areas of interventional radiotherapy, but is still hardly presented in others, and there is room for improvement when it comes to reproducible results and standardised evaluation methods.
A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics
TLDR
A deep learning masked (DLM) auto-fixed VOI segmentation method can provide a potentially more accurate radiomics diagnosis of CS PCa than expert manual segmentation while also reducing expert time investment by more than 97%.
Integrating zonal priors and pathomic MRI biomarkers for improved aggressive prostate cancer detection on MRI
TLDR
The utility of integrating prior information about the zonal distribution of prostate cancers with a radiology-pathology fusion model in reliably identifying aggressive and indolent prostate cancers on MRI is studied.
Automatic zonal segmentation of the prostate from 2D and 3D T2-weighted MRI and evaluation for clinical use
TLDR
UFNet, a deep learning-based method for automatic zonal segmentation of the prostate from T2-weighted T2w MRI, takes into account the image anisotropy, includes both spatial and channelwise attention mechanisms and uses loss functions to enforce prostate partition.
...
...

References

SHOWING 1-10 OF 100 REFERENCES
Encoding Clinical Priori in 3D Convolutional Neural Networks for Prostate Cancer Detection in bpMRI
TLDR
This work introduces a probabilistic population prior which captures the spatial prevalence and zonal distinction of clinically significant prostate cancer (csPCa) in order to improve its computer-aided detection (CAD) in bi-parametric MR imaging (bpMRI).
Joint Prostate Cancer Detection and Gleason Score Prediction in mp-MRI via FocalNet
TLDR
A novel multi-class CNN, FocalNet, is proposed to jointly detect PCa lesions and predict their aggressiveness using Gleason score (GS), which characterizes lesion aggressiveness and fully utilizes distinctive knowledge from mp-MRI.
Prostate Cancer Semantic Segmentation by Gleason Score Group in bi-parametric MRI with Self Attention Model on the Peripheral Zone
TLDR
A novel end-to-end multi-class attention network to jointly perform peripheral zone (PZ) segmentation and PZ lesions detection with Gleason score (GS) group grading with the addition of the attention mechanism improves the CAD performance in comparison to the baseline model.
False Positive Reduction Using Multiscale Contextual Features for Prostate Cancer Detection in Multi-Parametric MRI Scans
  • Xin Yu, B. Lou, D. Szolar
  • Computer Science, Medicine
    2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)
  • 2020
TLDR
A novel false positive reduction network to be added to the overall detection system to further analyze lesion candidates and utilizes multiscale 2D image stacks of these candidates to discriminate between true and false positive detections.
Simulated clinical deployment of fully automatic deep learning for clinical prostate MRI assessment
TLDR
U-Net maintained similar diagnostic performance compared to radiological assessment of PI-RADS ≥ 4 when applied in a simulated clinical deployment, and the proposed prospective dynamic calibration method successfully adjusted U-Net performance within acceptable limits of the PI- RADS reference over time.
Prostate Cancer Detection using Deep Convolutional Neural Networks
TLDR
This work developed and implemented an automated CNN-based pipeline for detection of clinically significant prostate cancer (PCa) for a given axial DWI image and for each patient.
Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network
TLDR
The diagnostic performance of the 3D CNN in detecting clinically significant prostate cancer is characterized by a good AUC and sensitivity and high specificity, and is comparable to that of an experienced radiologist.
Effect of Adding Probabilistic Zonal Prior in Deep Learning-based Prostate Cancer Detection.
TLDR
Results show that fusing zonal prior knowledge improves the baseline detection model with a preference for probabilistic over deterministic zonal segmentation.
Prostate Cancer Inference via Weakly-Supervised Learning using a Large Collection of Negative MRI
TLDR
The baseline MRI model is proposed to alternatively learn the appearance of mp-MRI using radiology-confirmed negative MRI cases via weakly supervised learning and to infer the pixel-wise suspiciousness of PCa by comparing the original and synthesized MRI with two distance functions.
...
...