Feature Extraction Optimized For Prostate Lesion Classification

Sobecki, Piotr; Życka-Malesa, Dominika; Mykhalevych, Ihor; Góra, Anna; Sklinda, Katarzyna; Przelaskowski, Artur

doi:10.1145/3093293.3093312

Cited by 5 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The winning group for the recent PROSTATEx challenge in differentiating between significant (GS ≥ 6) and nonsignificant (GS < 6) lesion reached an AUC of 0.87 for their model among 33 participating groups . An AUC of 0.92 was obtained using a KNN‐classifier with textural and statistical features from T2W, DWI, ADC, and Ktrans for differentiation PCa from benign conditions . Several studies have previously investigated the use of histogram and texture features extracted from mpMRI for PCa imaging .…”

Section: Discussionmentioning

confidence: 99%

“…Clinical factors, like patient age, PSA (prostate specific antigen), prostate/lesion volume, and T‐stage might improve the performance of the models and could be included in future models. However, one study did include patient characteristics and did not see any improvement in AUC . According to PIRADS v2 both ADC map and high b‐value images should be included in the PCa analysis.…”

Section: Discussionmentioning

confidence: 99%

“…K‐Nearest Neighbor (KNN) is a simple nonparametric supervised classifier, which produces a classification output based on a distance search to find the nearest neighbor between training and testing data. KNN was chosen for this study because it is fast, has the ability to learn from small example sets and has shown good results in previous PCa diagnosis mpMRI studies …”

Section: Methodsmentioning

confidence: 99%

“…The two‐tier systems were designed to differentiation between malignant and nonmalignant prostate tissue, or separate indolent/low grade (3 + 3) from clinically significant/high grade (≥3 + 4) disease . Only one study investigated a three‐tier (low, intermediate, and high grade) system and reported low performance compared to their two‐tier system .…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Assessment of prostate cancer prognostic Gleason grade group using zonal‐specific features extracted from biparametric MRI using a KNN classifier

Jensen

Carl

Boesen

et al. 2019

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose: To automatically assess the aggressiveness of prostate cancer (PCa) lesions using zonal-specific image features extracted from diffusion weighted imaging (DWI) and T2W MRI. Methods: Region of interest was extracted from DWI (peripheral zone) and T2W MRI (transitional zone and anterior fibromuscular stroma) around the center of 112 PCa lesions from 99 patients. Image histogram and texture features, 38 in total, were used together with a k-nearest neighbor classifier to classify lesions into their respective prognostic Grade Group (GG) (proposed by the International Society of Urological Pathology 2014 consensus conference). A semi-exhaustive feature search was performed (1-6 features in each feature set) and validated using threefold stratified cross validation in a one-versus-rest classification setup. Results: Classifying PCa lesions into GGs resulted in AUC of 0.87, 0.88, 0.96, 0.98, and 0.91 for GG1, GG2, GG1 + 2, GG3, and GG4 + 5 for the peripheral zone, respectively. The results for transitional zone and anterior fibromuscular stroma were AUC of 0.85, 0.89, 0.83, 0.94, and 0.86 for GG1, GG2, GG1 + 2, GG3, and GG4 + 5, respectively. Conclusion: This study showed promising results with reasonable AUC values for classification of all GG indicating that zonal-specific imaging features from DWI and T2W MRI can be used to differentiate between PCa lesions of various aggressiveness.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Assessment of prostate cancer prognostic Gleason grade group using zonal‐specific features extracted from biparametric MRI using a KNN classifier

Jensen

Carl

Boesen

et al. 2019

J Applied Clin Med Phys

View full text Add to dashboard Cite

show abstract

“…A form of median normalisation, originally proposed by Kwak et al (2015) was utilised, preceded by the identification and removal of potential outliers. Other normalisation methods were considered, as proposed in previous research ( Sobecki et al, 2017 ). Median normalisation, however, achieved the best model performance.…”

Section: Methodsmentioning

confidence: 99%

Effect of domain knowledge encoding in CNN model architecture—a prostate cancer study using mpMRI images

Sobecki

Jóźwiak

Sklinda

et al. 2021

PeerJ

Self Cite

View full text Add to dashboard Cite

Background Prostate cancer is one of the most common cancers worldwide. Currently, convolution neural networks (CNNs) are achieving remarkable success in various computer vision tasks, and in medical imaging research. Various CNN architectures and methodologies have been applied in the field of prostate cancer diagnosis. In this work, we evaluate the impact of the adaptation of a state-of-the-art CNN architecture on domain knowledge related to problems in the diagnosis of prostate cancer. The architecture of the final CNN model was optimised on the basis of the Prostate Imaging Reporting and Data System (PI-RADS) standard, which is currently the best available indicator in the acquisition, interpretation, and reporting of prostate multi-parametric magnetic resonance imaging (mpMRI) examinations. Methods A dataset containing 330 suspicious findings identified using mpMRI was used. Two CNN models were subjected to comparative analysis. Both implement the concept of decision-level fusion for mpMRI data, providing a separate network for each multi-parametric series. The first model implements a simple fusion of multi-parametric features to formulate the final decision. The architecture of the second model reflects the diagnostic pathway of PI-RADS methodology, using information about a lesion’s primary anatomic location within the prostate gland. Both networks were experimentally tuned to successfully classify prostate cancer changes. Results The optimised knowledge-encoded model achieved slightly better classification results compared with the traditional model architecture (AUC = 0.84 vs. AUC = 0.82). We found the proposed model to achieve convergence significantly faster. Conclusions The final knowledge-encoded CNN model provided more stable learning performance and faster convergence to optimal diagnostic accuracy. The results fail to demonstrate that PI-RADS-based modelling of CNN architecture can significantly improve performance of prostate cancer recognition using mpMRI.

show abstract

Radiomic features for prostate cancer grade detection through formal verification

et al. 2021

View full text Add to dashboard Cite

Feature Extraction Optimized For Prostate Lesion Classification

Cited by 5 publications

References 5 publications

Assessment of prostate cancer prognostic Gleason grade group using zonal‐specific features extracted from biparametric MRI using a KNN classifier

Assessment of prostate cancer prognostic Gleason grade group using zonal‐specific features extracted from biparametric MRI using a KNN classifier

Effect of domain knowledge encoding in CNN model architecture—a prostate cancer study using mpMRI images

Radiomic features for prostate cancer grade detection through formal verification

Contact Info

Product

Resources

About