A Combined Radiomics and Machine Learning Approach to Distinguish Clinically Significant Prostate Lesions on a Publicly Available MRI Dataset

Abstract

Although prostate cancer is one of the most common causes of mortality and morbidity in advancing-age males, early diagnosis improves prognosis and modifies the therapy of choice. The aim of this study was the evaluation of a combined radiomics and machine learning approach on a publicly available dataset in order to distinguish a clinically significant from a clinically non-significant prostate lesion. A total of 299 prostate lesions were included in the analysis. A univariate statistical analysis was performed to prove the goodness of the 60 extracted radiomic features in distinguishing prostate lesions. Then, a 10-fold cross-validation was used to train and test some models and the evaluation metrics were calculated; finally, a hold-out was performed and a wrapper feature selection was applied. The employed algorithms were Naïve bayes, K nearest neighbour and some tree-based ones. The tree-based algorithms achieved the highest evaluation metrics, with accuracies over 80%, and area-under-the-curve receiver-operating characteristics below 0.80. Combined machine learning algorithms and radiomics based on clinical, routine, multiparametric, magnetic-resonance imaging were demonstrated to be a useful tool in prostate cancer stratification.

Artificial intelligence in multiparametric magnetic resonance imaging: A review

“…Both GS and ISUP GG have been utilized to define clinically significant prostate cancer, and ISUP GG ≥ 2 or GS ≥ 7 were two commonly adopted criteria. 207,211,[214][215][216][217]224,225 Nevertheless, there are studies utilizing other criteria, such as GS ≥ 4 213 or ISUP GG ≥ 1 223 . Furthermore, estimating the exact GS value was conducted by some studies as well.…”

“…Therefore, identifying prostate cancers that are clinically significant is critical for the treatment planning of patients, which has been a central topic of prostate cancer research 243 . Abundant studies have been conducted to discriminate clinically significant prostate cancer or classify between low‐ and high‐grade prostate cancer 207,211,213–217,222–225 . However, the definition of clinically significant prostate cancer varies among the existing studies.…”

“…243 Abundant studies have been conducted to discriminate clinically significant prostate cancer or classify between low-and highgrade prostate cancer. 207,211,[213][214][215][216][217][222][223][224][225] However,the definition of clinically significant prostate cancer varies among the existing studies.…”

“…In 2014, the International Society of Urological Pathology (ISUP) released a revised prostate cancer grading system, called the Grade Group (GG), with ISUP GG1 referring to the cancer cells that look normal and are likely to grow slowly (if at all) and ISUP GG5 referring to the cancer cells that look very abnormal and are likely to grow very fast. Both GS and ISUP GG have been utilized to define clinically significant prostate cancer, and ISUP GG ≥ 2 or GS ≥ 7 were two commonly adopted criteria 207,211,214–217,224,225 . Nevertheless, there are studies utilizing other criteria, such as GS ≥ 4 213 or ISUP GG ≥ 1 223 .…”

A Model for Diagnosing Autism Patients Using Spatial and Statistical Measures Using rs-fMRI and sMRI by Adopting Graphical Neural Networks

“…Radiomics is used in medical imaging to augment the available data by applying a mathematical analysis to quantitative features and extracting pixel correlations and the distribution of signal intensities in brain regions (voxels). The features obtained through radiomics are (i) shape and size-based, (ii) image density histograms, (iii) correlations between voxels, (iv) texture from filtered images, and (v) form factor features [ 5 , 6 , 7 ].…”