Can Color-Coded Parametric Maps Improve Dynamic Enhancement Pattern Analysis in MR Mammography?

Multiple Sclerosis lesions detection by a hybrid Watershed-Clustering algorithm

BACKGROUND

Computer Aided Diagnosis (CAD) systems have been developing in the last years with the aim of helping the diagnosis and monitoring of several diseases. We present a novel CAD system based on a hybrid Watershed-Clustering algorithm for the detection of lesions in Multiple Sclerosis.

METHODS

Magnetic Resonance Imaging scans (FLAIR sequences without gadolinium) of 20 patients affected by Multiple Sclerosis with hyperintense lesions were studied. The CAD system consisted of the following automated processing steps: images recording, automated segmentation based on the Watershed algorithm, detection of lesions, extraction of both dynamic and morphological features, and classification of lesions by Cluster Analysis.

RESULTS

The investigation was performed on 316 suspect regions including 255 lesion and 61 non-lesion cases. The Receiver Operating Characteristic analysis revealed a highly significant difference between lesions and non-lesions; the diagnostic accuracy was 87% (95% CI: 0.83-0.90), with an appropriate cut-off of 192.8; the sensitivity was 77% and the specificity was 87%.

CONCLUSIONS

In conclusion, we developed a CAD system by using a modified algorithm for automated image segmentation which may discriminate MS lesions from non-lesions. The proposed method generates a detection out-put that may be support the clinical evaluation.

Automated Semi-Quantitative Analysis of Breast MRI: Potential Imaging Biomarker for the Prediction of Tissue Response to Neoadjuvant Chemotherapy

BACKGROUND

We aimed to investigate an automated semi-quantitative software as an imaging biomarker for the prediction of tissue response (TR) after completion of neoadjuvant chemotherapy (NAC).

METHODS

Breast magnetic resonance imaging (MRI) (1.5T, protocol according to international recommendations) of 67 patients with biopsy-proven invasive breast cancer were examined before and after NAC. After completion of NAC, histopathologic assessments of TR were classified according to the Chevallier grading system (CG1/4: full/non-responder; CG2/C3: partial responder). A commercially available fully automatic software (CADstream) extracted MRI parameters of tumor extension (tumor diameter/volume: TD/TV). Pre- versus post-NAC values were compared (ΔTV and ΔTD). Additionally, the software performed volumetric analyses of vascularization (VAV) after NAC. Accuracy of MRI parameters to predict TR were identified (cross-tabs, ROC, AUC, Kruskal-Wallis).

RESULTS

There were 37 (34.3%) CG1, 7 (6.5%) CG2, 53 (49.1%) CG3, and 11 (10.2%) CG4 lesions. The software reached area under the curve levels of 79.5% (CG1/complete response: ΔTD), 68.6% (CG2, CG3/partial response: VAV), and 88.8% to predict TR (CG4/non-response: ΔTV).

CONCLUSION

Semi-quantitative automated analysis of breast MRI data enabled the prediction of tissue response to NAC.

4D co-registration of X-ray and MR-mammograms: initial clinical results and potential incremental diagnostic value

PURPOSE

4D co-registration of X-ray- and MR-mammograms (XM and MM) is a new method of image fusion. The present study aims to evaluate its clinical feasibility, radiological accuracy, and potential clinical value.

METHODS

XM and MM of 25 patients were co-registered. Results were evaluated by a blinded reader.

RESULTS

Precision of the 4D co-registration was "very good" (mean-score [ms]=7), and lesions were "easier to delineate" (ms=5). In 88.8%, "relevant additional diagnostic information" was present, accounting for a more "confident diagnosis" in 76% (ms=5).

CONCLUSION

4D co-registration is feasible, accurate, and of potential clinical value.

The necrosis sign in magnetic resonance-mammography: diagnostic accuracy in 1,084 histologically verified breast lesions

Necrosis sign (NS) is a new descriptor for differential diagnosis of breast lesions in magnetic resonance (MR)-mammography (MRM). This study was designed: (a) to analyze diagnostic accuracy of NS in 1,084 histologically verified breast lesions, (b) to assess performance of NS in subgroups. This study was approved by the local ethical committee. All histologically verified lesions having undergone MR-mammography at our institution over 12 years were evaluated by experienced radiologists (> 500 MRM) according to standard protocols and study design (T1w; 0.1 mmol/kg bw gadolinium diethylenetriamine penta-acetic acid; T2-turbo spin echo (TSE)). Patients with history of breast biopsy (surgically, minimal-invasive), radiation- or chemotherapy ≤ 1 year before MRM were excluded. NS was assessed on T2w-TSE sequences and was rated positive if a hyperintense center in a hypointense lesion could be visualized (chi-squared test). One thousand and eighty-four lesions were available for statistical analysis (648: malignant, 436: benign). NS was significantly associated with malignancy (p < 0.001), providing specificity and positive predictive value (PPV) of 96.1% and 78.8%. Malignant lesions > 20 mm presented significantly more often NS (p < 0.001) than neoplasias ≤ 20 mm. There was no difference regarding prevalence of NS in small versus advanced benign lesions (n.s.), leading to better performance of NS in lesions > 20 mm (PPV: 87.8%). Correlation between NS and Grading of invasive carcinomas was significant. In this study of 1,084 lesions necrosis sign was a specific and highly predictive feature for differential diagnosis in MRM (Specificity: 96.1%; PPV: 78.8%). This particularly counts for advanced lesions (PPV 87.8%). As this new descriptor correlates with Grading, it could be used as an initial estimate of patient's prognosis.