Local staging of prostate cancer with multiparametric-MRI: accuracy and inter-reader agreement

Popiţa, Cristian; Popița, Anca-Raluca; Andrei, Adina; Rusu, Adriana; Petruț, Bogdan; Kacsó, Gabriel; Bungărdean, Cătălina; Bolog, Nicolae; Coman, Ioan

doi:10.15386/mpr-1390

Cited by 7 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the biggest challenges in the clinical use of mpMRI, and consequently bpMRI, is that its interpretation is dependent on the radiologist’s subjective opinion and, thus, is inevitably affected by a high rate of inter-reader variability [ 12 ]. In order to reduce these effects, a standardized reporting system was developed, the Prostate Imaging Reporting and Data System (PI-RADS) [ 13 ], which assigns a specific score of suspicion to the MRI sequences.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics

Rodrigues

Santinha

Galvao

et al. 2021

Cancers

View full text Add to dashboard Cite

Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results. Thus, the main goal of this work was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method and machine learning algorithm. On a cohort of 281 lesions from 183 patients, it was found that (1) radiomic features extracted from the lesion volume of interest were less stable to segmentation than the equivalent extraction from the whole gland volume of interest; and (2) radiomic features extracted from the whole gland volume of interest produced higher performance and less overfitted classifiers than radiomic features extracted from the lesions volumes of interest. This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics

Rodrigues

Santinha

Galvao

et al. 2021

Cancers

View full text Add to dashboard Cite

show abstract

“…As discussed above, our statistical model might be overfitted and might perform worse in external validation cohorts. MRIs and prostatectomy specimens were reviewed by a single radiologist/pathologist at each institution and we did not assess for inter-reader variability, which is documented in the literature for radiologists [ 41 , 42 ] and pathologists [ 43 , 44 ].…”

Section: Discussionmentioning

confidence: 99%

International Multi-Site Initiative to Develop an MRI-Inclusive Nomogram for Side-Specific Prediction of Extraprostatic Extension of Prostate Cancer

Wibmer

Kattan

Alessandrino

et al. 2021

Cancers

View full text Add to dashboard Cite

Background: To develop an international, multi-site nomogram for side-specific prediction of extraprostatic extension (EPE) of prostate cancer based on clinical, biopsy, and magnetic resonance imaging- (MRI) derived data. Methods: Ten institutions from the USA and Europe contributed clinical and side-specific biopsy and MRI variables of consecutive patients who underwent prostatectomy. A logistic regression model was used to develop a nomogram for predicting side-specific EPE on prostatectomy specimens. The performance of the statistical model was evaluated by bootstrap resampling and cross validation and compared with the performance of benchmark models that do not incorporate MRI findings. Results: Data from 840 patients were analyzed; pathologic EPE was found in 320/840 (31.8%). The nomogram model included patient age, prostate-specific antigen density, side-specific biopsy data (i.e., Gleason grade group, percent positive cores, tumor extent), and side-specific MRI features (i.e., presence of a PI-RADSv2 4 or 5 lesion, level of suspicion for EPE, length of capsular contact). The area under the receiver operating characteristic curve of the new, MRI-inclusive model (0.828, 95% confidence limits: 0.805, 0.852) was significantly higher than that of any of the benchmark models (p < 0.001 for all). Conclusions: In an international, multi-site study, we developed an MRI-inclusive nomogram for the side-specific prediction of EPE of prostate cancer that demonstrated significantly greater accuracy than clinical benchmark models.

show abstract

“…Une rupture de la capsule prostatique était notée chez 40% de nos patients. L'IRM possède une sensibilité et une spécificité élevée pour la détection de l'extension extra prostatique [19,20]. En plus de l'appréciation visuelle, une mesure de la longueur de contact entre la tumeur et la capsule, avec un seuil de 15 mm, permet le diagnostic de l'extension extra prostatique [21].…”

Section: Données Morphologiques Et Fonctionnellesunclassified

IRM prostatiques au CHN Dalal Jamm : revue des résultats de 35 cas.

Administrateur- JAIM,

DIOP Abdoulaye Dione,

NDIAYE Khadim

et al. 2023

J Afr Imag Méd

View full text Add to dashboard Cite

Objectives: To describe the MRI aspects of prostate tumors. Materials and Methods: This retrospective, descriptive study spanned 8 months in the radiology department of CHN Dalal Jaam. It included all patients referred for prostate MRI due to clinical and/or biological signs suggestive of prostate cancer. The examinations were conducted using a 1.5 Tesla HITACHI Echelon Smart MRI. The protocol comprised T2 sequences in 3 planes, B1500 diffusion, and dynamic T1 Fatsat Gado. Lesions were classified according to PIRADS 2.1 and correlated with ultrasound-guided biopsy results and PSA levels. Results: A total of 35 patients with an average age of 65 were included. Prostatic lesions were identified in 30 patients (85.7%), predominantly located in the peripheral zone (76.7%) and the transitional zone (23.3%). Round lesions were the most frequent (40%), with a mean size of 19 mm. Capsular rupture was present in 40% of cases. All lesions were T2 hypointense, demonstrating diffusion restriction (70%) and contrast enhancement (90%). The type 2 enhancement curve was 44.4%. PIRADS stage 5 was found in 49% of cases. Among the 3 patients with PSA levels below 6 ng/l, all had lesions classified as PIRADS 2. Conversely, 7 out of 10 patients with PSA levels above 6 ng/l exhibited PIRADS 4 or 5 lesions. Within the PIRADS 4 or 5 group, 7 underwent biopsy, revealing a Gleason score ≥ 7 (or ISUP ≥ 2) in 5 patients and a Gleason score of 6 (or ISUP 1) in 2 patients. Conclusion: Multiparametric MRI provided a comprehensive assessment of prostate tumors, with a robust correlation observed between the PIRADS classification and biological and histological data. RÉSUMÉ Objectifs: Décrire les aspects à l’IRM des tumeurs de la prostate. Matériels et méthodes : Il s’agissait d’une étude rétrospective, descriptive sur 8 mois au service de radiologie du CHN Dalal Jaam. Ont été inclus, tous les patients adressés pour une IRM prostatique devant des signes cliniques et ou biologiques faisant suspectés un cancer de la prostate. Les examens ont été fait sur une IRM 1,5 Tesla de marque HITACHI Echelon Smart. Le protocole utilisé était des séquences T2 dans les 3 plans, diffusion B1500 et T1Fatsat Gado dynamique. Les lésions ont été classées selon PIRADS 2.1 et corrélées avec les résultats de la biopsie échoguidée et au taux de PSA. Résultats : La population était au nombre de 35 avec un âge moyen de 65 ans. Une lésion prostatique était retrouvée chez 30 patients (85,7 %), siégeant dans la zone périphérique (76,7 %), la zone transitionnelle (23,3 %). Les lésions de formes arrondies étaient les plus fréquentes (40%). La taille moyenne des lésions était de 19 mm. Il y avait une rupture capsulaire dans 40% des cas (40 %). Toutes les lésions étaient en hyposignal T2 avec une restriction de diffusion (70%) et une prise de contraste (90 %). La courbe de rehaussement de type 2 était de 44,4 %. Le stade 5 du score PI-RADS était retrouvé dans 49% des cas. Les 3 patients ayant un taux de PSA inférieur à 6 ng/l avaient tous des lésions classées PIRADS 2. Tandis que 7 des 10 patients présentant un taux de PSA supérieur à 6 ng/l avaient des lésions de PIRADS 4 ou 5. Dans le groupe des patients avec un score de PIRADS 4 ou 5, 7 ont eu une biopsie avec un score de Gleason ³ 7 (ou ISUP ³ 2) chez 5 patients et un score de Gleason à 6 (ou ISUP 1) chez 2 patients. Conclusion : L'IRM multiparamétrique a permis une bonne évaluation des tumeurs de la prostate, avec une classification PIRADS en accord avec les données biologiques et histologiques.

show abstract

Local staging of prostate cancer with multiparametric-MRI: accuracy and inter-reader agreement

Cited by 7 publications

References 24 publications

Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics

Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics

International Multi-Site Initiative to Develop an MRI-Inclusive Nomogram for Side-Specific Prediction of Extraprostatic Extension of Prostate Cancer

IRM prostatiques au CHN Dalal Jamm : revue des résultats de 35 cas.

Contact Info

Product

Resources

About