A novel bayesian functional spatial partitioning method with application to prostate cancer lesion detection using MRI

Multiparametric MRI of the prostate combines high-resolution anatomic imaging with functional imaging of alterations in normal tissue caused by neoplastic transformation for the identification and characterization ofin situprostate cancer. Lesion detection relies on a systematic approach to the analysis of both anatomic and functional imaging using established criteria for the delineation of suspicious areas. Staging includes visual and functional analysis of the prostate “capsule” to determine ifin situdisease is, in fact, organ-confined, as well as the evaluation of pelvic structures including lymph nodes and bones for the detection of metastasis. Although intertwined, the protocol can be optimized depending on whether lesiondetectionorstagingis of the highest priority.

Download Full-text

Prostate Cancer Index Lesion Detection and Volume Estimation: Is Dynamic Contrast-Enhanced MRI Really Reliable?

American Journal of Roentgenology ◽

10.2214/ajr.19.21764 ◽

2019 ◽

Vol 213 (6) ◽

pp. W289-W289 ◽

Cited By ~ 2

Author(s):

Michele Scialpi ◽

Pietro Scialpi ◽

Eugenio Martorana

Keyword(s):

Prostate Cancer ◽

Lesion Detection ◽

Volume Estimation ◽

Index Lesion ◽

Dynamic Contrast Enhanced Mri ◽

Dynamic Contrast Enhanced ◽

Enhanced Mri ◽

Contrast Enhanced ◽

Contrast Enhanced Mri

Download Full-text

Lesion Detection and Interobserver Agreement with Advanced Image Reconstruction for 18F-DCFPyL PET/CT in Patients with Biochemically Recurrent Prostate Cancer

Journal of Nuclear Medicine ◽

10.2967/jnumed.118.222513 ◽

2019 ◽

Vol 61 (2) ◽

pp. 210-216

Author(s):

Bernard H.E. Jansen ◽

Robin W. Jansen ◽

Maurits Wondergem ◽

Sandra Srbljin ◽

John M.H. de Klerk ◽

...

Keyword(s):

Prostate Cancer ◽

Image Reconstruction ◽

Interobserver Agreement ◽

Lesion Detection ◽

Recurrent Prostate Cancer ◽

Pet Ct

Download Full-text

OTSU’s Thresholding with supervised learning approach for cancer lesion detection

IOSR Journal of VLSI and Signal processing ◽

10.9790/4200-04120109 ◽

2014 ◽

Vol 4 (1) ◽

pp. 01-09 ◽

Cited By ~ 1

Author(s):

S.Asif Hussain ◽

Keyword(s):

Supervised Learning ◽

Lesion Detection ◽

Learning Approach ◽

Cancer Lesion

Download Full-text

Additional Value of PET Radiomic Features for the Initial Staging of Prostate Cancer: A Systematic Review from the Literature

Cancers ◽

10.3390/cancers13236026 ◽

2021 ◽

Vol 13 (23) ◽

pp. 6026

Author(s):

Priscilla Guglielmo ◽

Francesca Marturano ◽

Andrea Bettinelli ◽

Michele Gregianin ◽

Marta Paiusco ◽

...

Keyword(s):

Prostate Cancer ◽

Systematic Review ◽

Imaging Modality ◽

Small Sample ◽

High Order ◽

Lesion Detection ◽

Qualitative Assessment ◽

Number Of Patients ◽

Additional Value ◽

Initial Staging

We performed a systematic review of the literature to provide an overview of the application of PET radiomics for the prediction of the initial staging of prostate cancer (PCa), and to discuss the additional value of radiomic features over clinical data. The most relevant databases and web sources were interrogated by using the query “prostate AND radiomic* AND PET”. English-language original articles published before July 2021 were considered. A total of 28 studies were screened for eligibility and 6 of them met the inclusion criteria and were, therefore, included for further analysis. All studies were based on human patients. The average number of patients included in the studies was 72 (range 52–101), and the average number of high-order features calculated per study was 167 (range 50–480). The radiotracers used were [68Ga]Ga-PSMA-11 (in four out of six studies), [18F]DCFPyL (one out of six studies), and [11C]Choline (one out of six studies). Considering the imaging modality, three out of six studies used a PET/CT scanner and the other half a PET/MRI tomograph. Heterogeneous results were reported regarding radiomic methods (e.g., segmentation modality) and considered features. The studies reported several predictive markers including first-, second-, and high-order features, such as “kurtosis”, “grey-level uniformity”, and “HLL wavelet mean”, respectively, as well as PET-based metabolic parameters. The strengths and weaknesses of PET radiomics in this setting of disease will be largely discussed and a critical analysis of the available data will be reported. In our review, radiomic analysis proved to add useful information for lesion detection and the prediction of tumor grading of prostatic lesions, even when they were missed at visual qualitative assessment due to their small size; furthermore, PET radiomics could play a synergistic role with the mpMRI radiomic features in lesion evaluation. The most common limitations of the studies were the small sample size, retrospective design, lack of validation on external datasets, and unavailability of univocal cut-off values for the selected radiomic features.

Download Full-text

Prospective Comparison of PET Imaging with PSMA-Targeted 18F-DCFPyL Versus Na18F for Bone Lesion Detection in Patients with Metastatic Prostate Cancer

Journal of Nuclear Medicine ◽

10.2967/jnumed.119.227793 ◽

2019 ◽

Vol 61 (2) ◽

pp. 183-188 ◽

Cited By ~ 3

Author(s):

Steven P. Rowe ◽

Xin Li ◽

Bruce J. Trock ◽

Rudolf A. Werner ◽

Sarah Frey ◽

...

Keyword(s):

Prostate Cancer ◽

Pet Imaging ◽

Metastatic Prostate Cancer ◽

Bone Lesion ◽

Lesion Detection ◽

Prospective Comparison

Download Full-text

4159 Prostate cancer multiparametric MRI comparison study of 3T versus 7T in terms of lesion detection and image quality

Journal of Clinical and Translational Science ◽

10.1017/cts.2020.141 ◽

2020 ◽

Vol 4 (s1) ◽

pp. 35-35

Author(s):

Ethan Leng ◽

Benjamin Spilseth ◽

Anil Chauhan ◽

Joseph Gill ◽

Ana Rosa ◽

...

Keyword(s):

Prostate Cancer ◽

Image Quality ◽

Cancer Detection ◽

Quality Characteristics ◽

Multiparametric Mri ◽

Lesion Detection ◽

7 Tesla ◽

Contrast Enhanced ◽

Technological Developments ◽

Study Population

OBJECTIVES/GOALS: The goal of this study was to perform a comparative, multi-reader, retrospective clinical evaluation of prostate multiparametric MRI (mpMRI) at 3 Tesla (3T) vs. 7 Tesla (7T) primarily in terms of prostate cancer localization. Subjective measures of image quality and artifacts were also evaluated. METHODS/STUDY POPULATION: Nineteen subjects were imaged at 3T and 7T between March 2016 and October 2018 under IRB-approved protocols. Four radiologists retrospectively and independently reviewed the data, and completed a two-part assessment for each dataset. First, readers assessed likelihood of cancer using Prostate Imaging Reporting & Data System (PI-RADS) guidelines. Accuracy of cancer detection was compared to findings from prostate biopsy. The numbers of correctly or incorrectly classified sextants were summed across all four readers, then used to summarize detection performance. Second, readers assigned a score on a five-point Likert scale to multiple image quality characteristics for the 3T and 7T datasets. RESULTS/ANTICIPATED RESULTS: Sensitivity and specificity of 3T and 7T datasets for sextant-wise cancer detection were compared by paired two-tailed t-tests. Readers identified more sextants harboring cancer with the 3T datasets while false-positive rates were similar, resulting in significantly higher sensitivity at 3T with no significant differences in specificity. Likert scores for image quality characteristics for 3T and 7T datasets were compared by applying paired two-tailed t-tests to mean scores of the four radiologists for each dataset. Readers generally preferred the 3T datasets, in particular for staging and assessment of extraprostatic extension as well as overall quality of the contrast-enhanced data. DISCUSSION/SIGNIFICANCE OF IMPACT: Readers agreed 7T prostate mpMRI produced images with more anatomic detail, though with equivocal clinical relevance and more pronounced artifacts. Reader unfamiliarity with 7T images is a major extenuating factor. Forthcoming technological developments are anticipated to improve upon the results.

Download Full-text

Automated prostate lesion detection and PI-RADS assessment with deep learning.

Journal of Clinical Oncology ◽

10.1200/jco.2019.37.15_suppl.e16605 ◽

2019 ◽

Vol 37 (15_suppl) ◽

pp. e16605-e16605

Author(s):

Choongheon Yoon ◽

Jasper Van ◽

Michelle Bardis ◽

Param Bhatter ◽

Alexander Ushinsky ◽

...

Keyword(s):

Neural Network ◽

Prostate Cancer ◽

Neural Networks ◽

Deep Learning ◽

Lesion Detection ◽

Dice Coefficient ◽

Cohen’S Kappa ◽

Transrectal Biopsy ◽

Cohen's Kappa ◽

Feature Pyramid

e16605 Background: Prostate Cancer is the most commonly diagnosed male cancer in the U.S. Multiparametric magnetic resonance imaging (mpMRI) is increasingly used for both prostate cancer evaluation and biopsy guidance. The PI-RADS v2 scoring paradigm was developed to stratify prostate lesions on MRI and to predict lesion grade. Prostate organ and lesion segmentation is an essential step in pre-biopsy surgical planning. Deep learning convolutional neural networks (CNN) for image recognition are becoming a more common method of machine learning. In this study, we develop a comprehensive deep learning pipeline of 3D/2D CNN based on U-Net architecture for automatic localization and segmentation of prostates, detection of prostate lesions and PI-RADS v2 lesion scoring of mpMRIs. Methods: This IRB approved retrospective review included a total of 303 prostate nodules from 217 patients who had a prostate mpMRI between September 2014 and December 2016 and an MR-guided transrectal biopsy. For each T2 weighted image, a board-certified abdominal radiologist manually segmented the prostate and each prostate lesion. The T2 weighted and ADC series were co-registered and each lesion was assigned an overall PI-RADS score, T2 weighted PI-RADS score, and ADC PI-RADS score. After a U-Net neural network segmented the prostate organ, a mask regional convolutional neural network (R-CNN) was applied. The mask R-CNN is composed of three neural networks: feature pyramid network, region proposal network, and head network. The mask R-CNN detected the prostate lesion, segmented it, and estimated its PI-RADS score. Instead, the mask R-CNN was implemented to regress along dimensions of the PI-RADS criteria. The mask R-CNN performance was assessed with AUC, Sørensen–Dice coefficient, and Cohen’s Kappa for PI-RADS scoring agreement. Results: The AUC for prostate nodule detection was 0.79. By varying detection thresholds, sensitivity/PPV were 0.94/.54 and 0.60/0.87 at either ends of the spectrum. For detected nodules, the segmentation Sørensen–Dice coefficient was 0.76 (0.72 – 0.80). Weighted Cohen’s Kappa for PI-RADS scoring agreement was 0.63, 0.71, and 0.51 for composite, T2 weighted, and ADC respectively. Conclusions: These results demonstrate the feasibility of implementing a comprehensive 3D/2D CNN-based deep learning pipeline for evaluation of prostate mpMRI. This method is highly accurate for organ segmentation. The results for lesion detection and categorization are modest; however, the PI-RADS v2 score accuracy is comparable to previously published human interobserver agreement.

Download Full-text