MRI radiomics-based machine-learning classification of bone chondrosarcoma.

PURPOSE: To evaluate the diagnostic performance of machine learning for discrimination between low-grade and high-grade cartilaginous bone tumors based on radiomic parameters extracted from unenhanced magnetic resonance imaging (MRI). METHODS: We retrospectively enrolled 58 patients with histologically-proven low-grade/atypical cartilaginous tumor of the appendicular skeleton (n = 26) or higher-grade chondrosarcoma (n = 32, including 16 appendicular and 16 axial lesions). They were randomly divided into training (n = 42) and test (n = 16) groups for model tuning and testing, respectively. All tumors were manually segmented on T1-weighted and T2-weighted images by drawing bidimensional regions of interest, which were used for first order and texture feature extraction. A Random Forest wrapper was employed for feature selection. The resulting dataset was used to train a locally weighted ensemble classifier (AdaboostM1). Its performance was assessed via 10-fold cross-validation on the training data and then on the previously unseen test set. Thereafter, an experienced musculoskeletal radiologist blinded to histological and radiomic data qualitatively evaluated the cartilaginous tumors in the test group. RESULTS: After feature selection, the dataset was reduced to 4 features extracted from T1-weighted images. AdaboostM1 correctly classified 85.7 % and 75 % of the lesions in the training and test groups, respectively. The corresponding areas under the receiver operating characteristic curve were 0.85 and 0.78. The radiologist correctly graded 81.3 % of the lesions. There was no significant difference in performance between the radiologist and machine learning classifier (P = 0.453). CONCLUSIONS: Our machine learning approach showed good diagnostic performance for classification of low-to-high grade cartilaginous bone tumors and could prove a valuable aid in preoperative tumor characterization.

Superb microvascular imaging (SMI) in the evaluation of musculoskeletal disorders: a systematic review.

OBJECTIVES: To systematically review the current literature concerning the role of superb microvascular imaging (SMI), a novel Doppler technique that enables detection of fine vessels and slow blood flow, in the evaluation of musculoskeletal disorders. METHODS: An online search of the literature was conducted for the period 2013 to April 2019 and included original articles written in English language. A data analysis was performed at the end of the literature search. RESULTS: Eight original articles with prospective design and one with retrospective design were included in this review: 4 studies focused on rheumatoid arthritis, 2 on rheumatoid and other arthritides, 1 on lateral epicondylosis and 2 on carpal tunnel syndrome. Sample size ranged from 26 to 83 patients. Despite some methodological differences, all studies compared the performance of SMI with that of a conventional Doppler technique such as power and color Doppler and found an improvement in vascularity detection with SMI. The main variations were in sample size, evaluated parameters and vascularity interpretation methods. Inter-observer agreement for SMI ranged from moderate to excellent. CONCLUSIONS: SMI is a promising tool for the diagnosis and treatment planning of different musculoskeletal disorders. Future investigations should include larger samples of patients with long-term follow-up.

Contrast agents in diagnostic imaging: Present and future.

Specific contrast agents have been developed for x ray examinations (mainly CT), sonography and Magnetic Resonance Imaging. Most of them are extracellular agents which create different enhancement on basis of different vascularization or on basis of different interstitial network in tissues, but some can be targeted to a particular cell line (e.g. hepatocyte). Microbubbles can be used as carrier for therapeutic drugs which can be released in specific targets under sonographic guidance, decreasing systemic toxicity and increasing therapeutic effect. Radiologists have to choose a particular contrast agent knowing its physical and chemical properties and the possibility of adverse reactions and balancing them with the clinical benefits of a more accurate diagnosis. As for any drug, contrast agents can cause adverse events, which are more frequent with Iodine based CA, but also with Gd based CA and even with sonographic contrast agents hypersensitivity reaction can occur.