Refine
Document Type
- Article (2)
- Contribution to a Periodical (2)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
- Artificial intelligence (1)
- Machine learning (1)
- Masquelet technique (1)
- Multiparametric MRI (1)
- Prostate cancer (1)
- Radiomics (1)
- bone marrow derived mononuclear cells (1)
- critical size defect (1)
- induced membrane (1)
- scaffold size (1)
Institute
- Medizin (2)
- Informatik und Mathematik (1)
- Neuere Philologien (1)
- Präsidium (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.
The Masquelet technique for the treatment of large bone defects is a two‐stage procedure based on an induced membrane. The size of a scaffold is reported to be a critical factor for bone healing response. We therefore aimed to investigate the influence of the granule size of a bone graft substitute on bone marrow derived mononuclear cells (BMC) supported bone healing in combination with the induced membrane. We compared three different sizes of Herafill® granules (Heraeus Medical GmbH, Wehrheim) with or without BMC in vivo in a rat femoral critical size defect. A 10 mm defect was made in 126 rats and a membrane induced by a PMMA‐spacer. After 3 weeks, the spacer was taken out and membrane filled with different granule sizes. After 8 weeks femurs were taken for radiological, biomechanical, histological, and immunohistochemical analysis. Further, whole blood of the rat was incubated with granules and expression of 29 peptide mediators was assessed. Smallest granules showed significantly improved bone healing compared to larger granules, which however did not lead to an increased biomechanical stability in the defect zone. Small granules lead to an increased accumulation of macrophages in situ which could be assigned to the inflammatory subtype M1 by majority. Increased release of chemotactic respectively proangiogenic active factors in vitro compared to syngenic bone and beta‐TCP was observed. Granule size of the bone graft substitute Herafill® has significant impact on bone healing of a critical size defect in combination with Masquelet's technique in terms of bone formation and inflammatory.
