Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Prostate cancer (2)
- Artificial intelligence (1)
- HoLEP (1)
- Holmium laser enucleation (1)
- Incidental prostate cancer (1)
- Machine learning (1)
- Multiparametric MRI (1)
- Radiomics (1)
- TUR-P (1)
- Transurethral resection of the prostate (1)
Institute
- Medizin (2) (remove)
The aim of this study is to investigate the incidental prostate cancer (iPCa) detection rates of different embedding methods in a large, contemporary cohort of patients with bladder outlet obstruction (BOO) treated with transurethral surgery. We relied on an institutional tertiary-care database to identify BOO patients who underwent either transurethral loop resection or laser (Holmium:yttrium–aluminium garnet) enucleation of the prostate (HoLEP) between 01/2012 and 12/2019. Embedding methods differed with regard to the extent of the additional prostate tissue submitted following the first ten cassettes of primary embedding (cohort A: one [additional] cassette/10 g residual tissue vs. cohort B: complete embedding of the residual tissue). Detection rates of iPCa among the different embedding methods were compared. Subsequently, subgroup analyses by embedding protocol were repeated in HoLEP-treated patients only. In the overall cohort, the iPCa detection rate was 11% (46/420). In cohort A (n = 299), tissue embedding resulted in a median of 8 cassettes/patient (range 1–38) vs. a median of 15 (range 2–74) in cohort B (n = 121) (p < .001). The iPCa detection rate was 8% (23/299) and 19% (23/121) in cohort A vs. cohort B, respectively (p < .001). Virtual reduction of the number of tissue cassettes to ten cassettes resulted in a iPCa detection rate of 96% in both cohorts, missing one stage T1a/ISUP grade 1 carcinoma. Increasing the number of cassettes by two and eight cassettes, respectively, resulted in a detection rate of 100% in both cohorts without revealing high-grade carcinomas. Subgroup analyses in HoLEP patients confirmed these findings, demonstrated by a 100 vs. 96% iPCa detection rate following examination of the first ten cassettes, missing one case of T1a/ISUP 1. Examination of 8 additional cassettes resulted in a 100% detection rate. The extent of embedding of material obtained from transurethral prostate resection correlates with the iPCa detection rate. However, the submission of 10 cassettes appears to be a reasonable threshold to reduce resource utilization while maintaining secure cancer detection.
Objectives: To analyze the performance of radiological assessment categories and quantitative computational analysis of apparent diffusion coefficient (ADC) maps using variant machine learning algorithms to differentiate clinically significant versus insignificant prostate cancer (PCa). Methods: Retrospectively, 73 patients were included in the study. The patients (mean age, 66.3 ± 7.6 years) were examined with multiparametric MRI (mpMRI) prior to radical prostatectomy (n = 33) or targeted biopsy (n = 40). The index lesion was annotated in MRI ADC and the equivalent histologic slides according to the highest Gleason Grade Group (GrG). Volumes of interest (VOIs) were determined for each lesion and normal-appearing peripheral zone. VOIs were processed by radiomic analysis. For the classification of lesions according to their clinical significance (GrG ≥ 3), principal component (PC) analysis, univariate analysis (UA) with consecutive support vector machines, neural networks, and random forest analysis were performed. Results: PC analysis discriminated between benign and malignant prostate tissue. PC evaluation yielded no stratification of PCa lesions according to their clinical significance, but UA revealed differences in clinical assessment categories and radiomic features. We trained three classification models with fifteen feature subsets. We identified a subset of shape features which improved the diagnostic accuracy of the clinical assessment categories (maximum increase in diagnostic accuracy ΔAUC = + 0.05, p < 0.001) while also identifying combinations of features and models which reduced overall accuracy. Conclusions: The impact of radiomic features to differentiate PCa lesions according to their clinical significance remains controversial. It depends on feature selection and the employed machine learning algorithms. It can result in improvement or reduction of diagnostic performance.