An Advanced Quantitative Echosound Methodology for Femoral Neck Densitometry.

The aim of this paper was to investigate the clinical feasibility and the accuracy in femoral neck densitometry of the Osteoporosis Score (O.S.), an ultrasound (US) parameter for osteoporosis diagnosis that has been recently introduced for lumbar spine applications. A total of 377 female patients (aged 61-70 y) underwent both a femoral dual X-ray absorptiometry (DXA) and an echographic scan of the proximal femur. Recruited patients were sub-divided into a reference database used for ultrasound spectral model construction and a study population for repeatability assessments and accuracy evaluations. Echographic images and radiofrequency signals were analyzed through a fully automatic algorithm that performed a series of combined spectral and statistical analyses, providing as a final output the O.S. value of the femoral neck. Assuming DXA as a gold standard reference, the accuracy of O.S.-based diagnoses resulted 94.7%, with k = 0.898 (p < 0.0001). Significant correlations were also found between O.S.-estimated bone mineral density and corresponding DXA values, with r(2) up to 0.79 and root mean square error = 5.9-7.4%. The reported accuracy levels, combined with the proven ease of use and very good measurement repeatability, provide the adopted method with a potential for clinical routine application in osteoporosis diagnosis.

Combination of computer-aided detection algorithms for automatic lung nodule identification.

PURPOSE: The aim of this work is to evaluate the potential of combining different computer-aided detection (CADe) methods to increase the actual support for radiologists of automated systems in the identification of pulmonary nodules in CT scans. METHODS: The outputs of three different CADe systems developed by researchers of the Italian MAGIC-5 collaboration were combined. The systems are: the CAMCADe (based on a Channeler-Ant-Model which segments vessel tree and nodule candidates and a neural classifier), the RGVPCADe (a Region-Growing- Volume-Plateau algorithm detects nodule candidates and a neural network reduces false positives); the VBNACADe (two dedicated procedures, based respectively on a 3D dot-enhancement algorithm and on intersections of pleura surface normals, identifies internal and juxtapleural nodules, and a Voxel-Based-Neural-Approach reduces false positives. A dedicated OsiriX plugin implemented with the Cocoa environments of MacOSX allows annotating nodules and visualizing singles and combined CADe findings. RESULTS: The combined CADe has been tested on thin slice (lower than 2 mm) CTs of the LIDC public research database and the results have been compared with those obtained by the single systems. The FROC (Free Receiver Operating Characteristic) curves show better results than the best of the single approaches. CONCLUSIONS: Has been demonstrated that the combination of different approaches offers better results than each single CADe system. A clinical validation of the combined CADe as second reader is being addressed by means of the dedicated OsiriX plugin.