Refine
Document Type
- Article (12)
Language
- English (12)
Has Fulltext
- yes (12)
Is part of the Bibliography
- no (12)
Keywords
- radical prostatectomy (3)
- systematic biopsy (3)
- Artificial intelligence (2)
- Cancer (2)
- Neoplasms (2)
- concordance (2)
- fusion biopsy (2)
- prostate cancer (2)
- Age determination by skeleton (1)
- Algorithms (1)
Institute
- Medizin (12)
- Informatik und Mathematik (1)
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.
Background: Evaluation of automated attenuation-based tube potential selection and its impact on image quality and radiation dose in CT (computed tomography) examinations for cancer staging.
Methods: A total of 110 (59 men, 51 women) patients underwent chest-abdomen-pelvis CT examinations; 55 using a fixed tube potential of 120 kV/current of 210 Reference mAs (using CareDose4D), and 55 using automated attenuation-based tube potential selection (CAREkV) also using a current of 210 Reference mAs. This evaluation was performed as a single-centre, observer-blinded retrospective analysis. Image quality was assessed by two readers in consensus. Attenuation, image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured or calculated for objective image evaluation. For the evaluation of radiation exposure, dose-length-product (DLP) values were compared and Size-specific dose estimates (SSDE) values were calculated.
Results: Diagnostic image quality was obtained from all patients. The median DLP (703.5 mGy · cm, range 390–2203 mGy · cm) was 7.9% lower when using the algorithm compared with the standard 120 kV protocol (median 756 mGy · cm, range 345–2267 mGy · cm). A reduction in potential to 100 kV occurred in 32 cases; therefore, these patients received significantly lower radiation exposure compared with the 120 kV protocol.
Conclusion: Automated attenuation-based tube potential selection produces good diagnostic image quality in chest-abdomen-pelvis CT and reduces the patient’s overall radiation dose by 7.9% compared to the standard 120 kV protocol.