Combined texture analysis and machine learning in suspicious calcifications detected by mammography: Potential to avoid unnecessary stereotactical biopsies.

OBJECTIVES: To investigate whether combined texture analysis and machine learning can distinguish malignant from benign suspicious mammographic calcifications, to find an exploratory rule-out criterion to potentially avoid unnecessary benign biopsies. METHODS: Magnification views of 235 patients which underwent vacuum-assisted biopsy of suspicious calcifications (BI-RADS 4) during a two-year period were retrospectively analyzed using the texture analysis tool MaZda (Version 4.6). Microcalcifications were manually segmented and analyzed by two readers, resulting in 249 image features from gray-value histogram, gray-level co-occurrence and run-length matrices. After feature reduction with principal component analysis (PCA), a multilayer perceptron (MLP) artificial neural network was trained using histological results as the reference standard. For training and testing of this model, the dataset was split into 70 % and 30 %. ROC analysis was used to calculate diagnostic performance indices. RESULTS: 226 patients (150 benign, 76 malignant) were included in the final analysis due to missing data in 9 cases. Feature selection yielded nine image features for MLP training. Area under the ROC-curve in the testing dataset (n = 54) was 0.82 (95 %-CI: 0.70-0.94) and 0.832 (95 %-CI 0.72-0.94) for both readers, respectively. A high sensitivity threshold criterion was identified in the training dataset and successfully applied to the testing dataset, demonstrating the potential to avoid 37.1-45.7 % of unnecessary biopsies at the cost of one false-negative for each reader. CONCLUSION: Combined texture analysis and machine learning could be used for risk stratification in suspicious mammographic calcifications. At low costs in terms of false-negatives, unnecessary biopsies could be avoided.

[Biochemical cartilage imaging-update 2019]. / Biochemische Knorpeldiagnostik ­ Update 2019.

BACKGROUND: Cartilage imaging using magnetic resonance imaging (MRI) is increasingly used for early detection of cartilage damage. Biochemical MR methods to assess cartilage damage are essential for optimal treatment planning. PURPOSE: The aim of this review is to provide an update on advanced cartilage imaging based on biochemical MR techniques. The clinical applications and additional benefits compared to conventional MRI are presented. MATERIALS AND METHODS: A literature search of PubMed regarding the clinical applications of various biochemical MR methods and morphological MR imaging was performed. RESULTS: While T2 mapping can be easily implemented on clinical routine MR scanners, the T1rho method is technically more demanding and is not available on all MR scanners. dGEMRIC, which can be performed with all field strengths, is now severely restricted due to the recent decision of the European Medical Agency (EMA) to withdraw linear gadolinium contrast agents from the market because of proven gadolinium deposition in the brain. Sodium imaging is the most sensitive MRI method for glycosaminoglycan (GAG), but is limited to 7 T. In addition to early diagnosis of cartilage degeneration before morphological changes are visible, biochemical MRI offers predictive markers, e.g., effect of lifestyle changes or assessing results of cartilage repair surgery. CONCLUSION: Cartilage imaging based on biochemical MRI allows a shift from qualitative to quantitative MRI. Biochemical MRI plays an increasingly important role in the early diagnosis of cartilage degeneration for monitoring of disease-modifying drugs and as predictive imaging biomarker in clinical diagnostics. In cartilage repair, monitoring of the efficacy of different cartilage repair surgery techniques to develop hyaline-like cartilage can be performed with biochemical MRI.

[When is cartilage repair successful?] / Wann ist eine Knorpelreparatur erfolgreich?

Focal cartilage lesions are a cause of long-term disability and morbidity. After cartilage repair, it is crucial to evaluate long-term progression or failure in a reproducible, standardized manner. This article provides an overview of the different cartilage repair procedures and important characteristics to look for in cartilage repair imaging. Specifics and pitfalls are pointed out alongside general aspects. After successful cartilage repair, a complete, but not hypertrophic filling of the defect is the primary criterion of treatment success. The repair tissue should also be completely integrated to the surrounding native cartilage. After some months, the transplants signal should be isointense compared to native cartilage. Complications like osteophytes, subchondral defects, cysts, adhesion and chronic bone marrow edema or joint effusion are common and have to be observed via follow-up. Radiological evaluation and interpretation of postoperative changes should always take the repair method into account.