Prostate Cancer Radiogenomics—From Imaging to Molecular Characterization

Ferro, Matteo; Cobelli, O. De; Vartolomei, Mihai Dorin; Lucarelli, Giuseppe; Crocetto, Felice; Barone, Biagio; Sciarra, Alessandro; Giudice, Francesco Del; Muto, Matteo; Maggi, Martina; Carrieri, Giuseppe; Busetto, Gian Maria; Falagario, Ugo Giovanni; Terracciano, Daniela; Cormio, Luigi; Musi, Gennaro; Tătaru, Octavian Sabin

doi:10.3390/ijms22189971

Cited by 56 publications

(64 citation statements)

References 194 publications

(210 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although radiomics shows huge potential for the improvement of clinical diagnosis and risk stratification, its practical clinical application is still subject to many difficulties, and its real benefits are required to be further confirmed in prospective cohort studies (49). However, radiomics plays an increasingly important role in medical imaging, and it provides a unique basis for personalized precision treatment (50).…”

Section: Discussionmentioning

confidence: 99%

Multiparametric MRI and Machine Learning Based Radiomic Models for Preoperative Prediction of Multiple Biological Characteristics in Prostate Cancer

et al. 2022

View full text Add to dashboard Cite

ObjectivesThis study aims to develop and evaluate multiparametric MRI (MP-MRI)-based radiomic models as a noninvasive diagnostic method to predict several biological characteristics of prostate cancer.MethodsA total of 252 patients were retrospectively included who underwent radical prostatectomy and MP-MRI examinations. The prediction characteristics of this study were as follows: Ki67, S100, extracapsular extension (ECE), perineural invasion (PNI), and surgical margin (SM). Patients were divided into training cohorts and validation cohorts in the ratio of 4:1 for each group. After lesion segmentation manually, radiomic features were extracted from MP-MRI images and some clinical factors were also included. Max relevance min redundancy (mRMR) and recursive feature elimination (RFE) based on random forest (RF) were adopted to select features. Six classifiers were included (SVM, KNN, RF, decision tree, logistic regression, XGBOOST) to find the best diagnostic performance among them. The diagnostic efficiency of the construction models was evaluated by ROC curves and quantified by AUC.ResultsRF performed best among the six classifiers for the four groups according to AUC values (Ki67 = 0.87, S100 = 0.80, ECE = 0.85, PNI = 0.82). The performance of SVM was relatively the best for SM (AUC = 0.77). The number and importance of DCE features ranked first in the models of each group. The combined models of MP-MRI and clinical characteristics showed no significant difference compared with MP-MRI models according to Delong’s tests.ConclusionsRadiomics models based on MP-MRI have the potential to predict biological characteristics and are expected to be a noninvasive method to evaluate the risk stratification of prostate cancer.

show abstract

Section: Discussionmentioning

confidence: 99%

Multiparametric MRI and Machine Learning Based Radiomic Models for Preoperative Prediction of Multiple Biological Characteristics in Prostate Cancer

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The detection of significant PCa utilizing CAD systems that were based either on deep learning or radiomics has generated many papers in the scientific literature [ 29 , 30 , 31 ]. Both approaches offer different capabilities, challenges and difficulties [ 16 ].…”

Section: Discussionmentioning

confidence: 99%

Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics

Arif

Starmans

Niessen

et al. 2021

Cancers

View full text Add to dashboard Cite

The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using various external data sets is crucial. While both deep-learning and radiomics approaches have been compared based on the same data set of one center, the comparison of the performances of both approaches on various data sets from different centers and different scanners is lacking. The goal of this study was to compare the performance of a deep-learning model with the performance of a radiomics model for the significant-PCa diagnosis of the cohorts of various patients. We included the data from two consecutive patient cohorts from our own center (n = 371 patients), and two external sets of which one was a publicly available patient cohort (n = 195 patients) and the other contained data from patients from two hospitals (n = 79 patients). Using multiparametric MRI (mpMRI), the radiologist tumor delineations and pathology reports were collected for all patients. During training, one of our patient cohorts (n = 271 patients) was used for both the deep-learning- and radiomics-model development, and the three remaining cohorts (n = 374 patients) were kept as unseen test sets. The performances of the models were assessed in terms of their area under the receiver-operating-characteristic curve (AUC). Whereas the internal cross-validation showed a higher AUC for the deep-learning approach, the radiomics model obtained AUCs of 0.88, 0.91 and 0.65 on the independent test sets compared to AUCs of 0.70, 0.73 and 0.44 for the deep-learning model. Our radiomics model that was based on delineated regions resulted in a more accurate tool for significant-PCa classification in the three unseen test sets when compared to a fully automated deep-learning model.

show abstract

“…For this reason, the application of bioinformatics and statistical analysis is necessary in order to interpret the obtained data. The use of bioinformatics in the case of radiomic, genomic and radiogenomic research for the detection of prostate cancer was reported by Ferro et al [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Citric Acid as a Potential Prostate Cancer Biomarker Determined in Various Biological Samples

et al. 2022

View full text Add to dashboard Cite

Despite numerous studies, the molecular mechanism of prostate cancer development is still unknown. Recent investigations indicated that citric acid and lipids—with a special emphasis on fatty acids, steroids and hormones (ex. prolactin)—play a significant role in prostate cancer development and progression. However, citric acid is assumed to be a potential biomarker of prostate cancer, due to which, the diagnosis at an early stage of the disease could be possible. For this reason, the main goal of this study is to determine the citric acid concentration in three different matrices. To the best of our knowledge, this is the first time for citric acid to be determined in three different matrices (tissue, urine and blood). Samples were collected from patients diagnosed with prostate cancer and from a selected control group (individuals with benign prostatic hyperplasia). The analyses were performed using the rapid fluorometric test. The obtained results were correlated with both the histopathological data (the Gleason scale as well as the Classification of Malignant Tumors (pTNM) staging scale) and the biochemical data (the values of the following factors: prostate specific antigen, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, triglyceride, total cholesterol, creatinine and prolactin) using chemometric methods. For tissue samples, the results indicated a decreased level of citric acid in the case of prostate cancer. The analyte average concentrations in serum and urine appeared to be corresponding and superior in the positive cohort. This trend was statistically significant in the case of urinary citric acid. Moreover, a significant negative correlation was demonstrated between the concentration of citric acid and the tumor stage. A negative correlation between the total cholesterol and high-density lipoprotein and prolactin was particularly prominent in cancer cases. Conversely, a negative association between low-density lipoprotein and prolactin levels was observed solely in the control group. On the basis of the results, one may assume the influence of hormones, particularly prolactin, on the development of prostate cancer. The present research allowed us to verify the possibility of using citric acid as a potential biomarker for prostate cancer.

show abstract

Prostate Cancer Radiogenomics—From Imaging to Molecular Characterization

Cited by 56 publications

References 194 publications

Multiparametric MRI and Machine Learning Based Radiomic Models for Preoperative Prediction of Multiple Biological Characteristics in Prostate Cancer

Multiparametric MRI and Machine Learning Based Radiomic Models for Preoperative Prediction of Multiple Biological Characteristics in Prostate Cancer

Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics

Citric Acid as a Potential Prostate Cancer Biomarker Determined in Various Biological Samples

Contact Info

Product

Resources

About