Pattern Recognition Approaches for Breast Cancer DCE-MRI Classification: A Systematic Review.

We performed a systematic review of several pattern analysis approaches for classifying breast lesions using dynamic, morphological, and textural features in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Several machine learning approaches, namely artificial neural networks (ANN), support vector machines (SVM), linear discriminant analysis (LDA), tree-based classifiers (TC), and Bayesian classifiers (BC), and features used for classification are described. The findings of a systematic review of 26 studies are presented. The sensitivity and specificity are respectively 91 and 83 % for ANN, 85 and 82 % for SVM, 96 and 85 % for LDA, 92 and 87 % for TC, and 82 and 85 % for BC. The sensitivity and specificity are respectively 82 and 74 % for dynamic features, 93 and 60 % for morphological features, 88 and 81 % for textural features, 95 and 86 % for a combination of dynamic and morphological features, and 88 and 84 % for a combination of dynamic, morphological, and other features. LDA and TC have the best performance. A combination of dynamic and morphological features gives the best performance.

Early Assessment of Colorectal Cancer Patients with Liver Metastases Treated with Antiangiogenic Drugs: The Role of Intravoxel Incoherent Motion in Diffusion-Weighted Imaging.

PURPOSE: To assess the feasibility and effectiveness of quantitative intravoxel incoherent motion (IVIM) of Diffusion-weighted imaging (DWI) in the assessment of liver metastases treated with targeted chemotherapy agents. METHODS: 12 patients with unresectable liver metastases from colorectal cancer were enrolled and received neoadjuvant FOLFIRI (5-fluorouracil, leucovorin, irinotecan) plus bevacizumab therapy. DWI was performed for 36 metastases at baseline and after 14 days from starting the treatment. In addition to the basic IVIM metrics, the product between pseudo-diffusivity and perfusion fraction was considered as a descriptor roughly analogous to the flow. Median diffusion parameters of Region of Interest (ROI) were used as representative values for each lesion. Normalized parameters in comparison with the median value of spleen were also collected. The percentual change of the diffusion parameters was calculated. The response to chemotherapy was evaluated according the Response Evaluation Criteria in Solid Tumors (RECIST) as calculated on whole-body CT scan obtained three months after treatment. Mann Whitney test and Receiver operating characteristic (ROC) analysis were performed. RESULTS: 24 lesions were categorized as responding and 12 as not responding. There was no statistically significant difference among absolute and normalized diffusion parameters between the pretreatment and the post-treatment findings. Instead, the perfusion fraction (fp) values showed a statistical difference between responder and non-responder lesions: sensitivity and specificity of fp variation was 62% and 93%, respectively. CONCLUSIONS: IVIM parameters represent a valuable tool in the evaluation of the anti-angiogenic therapy in patients with liver metastases from colorectal cancer. A percentage change of fp represents the most effective DWI marker in the assessment of tumor response.

Integration of DCE-MRI and DW-MRI Quantitative Parameters for Breast Lesion Classification.

OBJECTIVE: The purpose of our study was to evaluate the diagnostic value of an imaging protocol combining dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted MRI (DW-MRI) in patients with suspicious breast lesions. MATERIALS AND METHODS: A total of 31 breast lesions (15 malignant and 16 benign proved by histological examination) in 26 female patients were included in this study. For both DCE-MRI and DW-MRI model free and model based parameters were computed pixel by pixel on manually segmented ROIs. Statistical procedures included conventional linear analysis and more advanced techniques for classification of lesions in benign and malignant. RESULTS: Our findings indicated no strong correlation between DCE-MRI and DW-MRI parameters. Results of classification analysis show that combining of DCE parameters or DW-MRI parameter, in comparison of single feature, does not yield a dramatic improvement of sensitivity and specificity of the two techniques alone. The best performance was obtained considering a full combination of all features. Moreover, the classification results combining all features are dominated by DCE-MRI features alone. CONCLUSION: The combination of DWI and DCE-MRI does not show a potential to dramatically increase the sensitivity and specificity of breast MRI. DCE-MRI alone gave the same performance as in combination with DW-MRI.

Risk management in magnetic resonance: failure mode, effects, and criticality analysis.

The aim of the study was to perform a risk management procedure in "Magnetic Resonance Examination" process in order to identify the critical phases and sources of radiological errors and to identify potential improvement projects including procedures, tests, and checks to reduce the error occurrence risk. In this study we used the proactive analysis "Failure Mode Effects Criticality Analysis," a qualitative and quantitative risk management procedure; has calculated Priority Risk Index (PRI) for each activity of the process; have identified, on the PRI basis, the most critical activities and, for them, have defined improvement projects; and have recalculated the PRI after implementation of improvement projects for each activity. Time stop and audits are performed in order to control the new procedures. The results showed that the most critical tasks of "Magnetic Resonance Examination" process were the reception of the patient, the patient schedule drafting, the closing examination, and the organization of activities. Four improvement projects have been defined and executed. PRI evaluation after improvement projects implementation has shown that the risk decreased significantly following the implementation of procedures and controls defined in improvement projects, resulting in a reduction of the PRI between 43% and 100%.