No abstract

CEUS represents a useful method in clinical practice for differentiating between malignant and benign FLLs detected on standard ultrasonography, and the results of this study are in concordance with previous multicenter studies: DEGUM (Germany) and STIC (France).

BackgroundSecond-generation intravenous blood-pool ultrasound contrast agents are increasingly used in endoscopic ultrasound (EUS) for characterization of microvascularization, differential diagnosis of benign and malignant focal lesions, as well as improved staging and guidance of therapeutic procedures.MethodsThe aim of our study was to prospectively compare the vascularisation patterns in chronic pseudotumoral pancreatitis and pancreatic cancer using quantitative low mechanical index (MI) contrast-enhanced EUS. We included 51 patients with chronic pseudotumoral pancreatitis (n = 19) and pancreatic cancer (n = 32). Perfusion imaging started with a bolus injection of Sonovue (2.4 ml), followed by analysis in the early arterial (wash-in) and late venous (wash-out) phase. Perfusion analysis was performed by post-processing of the raw data (time intensity curve [TIC] analysis). TIC analysis was performed inside the tumor and the pancreatic parenchyma, with depiction of the dynamic vascular pattern generated by specific software. Statistical analysis was performed on raw data extracted from the TIC analysis. Final diagnosis was based on a combination of EUS-FNA, surgery and follow-up of minimum 6 months in negative cases.ResultsThe sensitivity and specificity of low MI contrast enhanced EUS using TIC were sensitivity and specificity of low MI contrast enhanced EUS using TIC analysis were 93.75% (95% CI = 77.77 - 98.91%) and 89.47% (95% CI = 65.46 - 98.15%), respectively. Pseudotumoral chronic pancreatitis showed in the majority of cases a hypervascular appearance in the early arterial phase of contrast-enhancement, with a dynamic enhancement pattern similar with the rest of the parenchyma. Statistical analysis of the resulting series of individual intensities revealed no statistically relevant differences (p = .78). Pancreatic adenocarcinoma was usually a hypovascular lesion, showing low contrast-enhancement during the early arterial and also during the late venous phase of contrast-enhancement, also lower than the normal surrounding parenchyma. We found statistically significant differences in values during TIC analysis (p < .001).ConclusionsLow MI contrast enhanced EUS technique is expected to improve the differential diagnosis of focal pancreatic lesions. However, further multicentric randomized studies will confirm the exact role of the technique and its place in imaging assessment of focal pancreatic lesions.

Neural network analysis of contrast-enhanced ultrasonography - obtained TICs seems a promising field of development for future techniques, providing fast and reliable diagnostic aid for the clinician.

IntroductionConfocal laser endomicroscopy (CLE) is becoming a popular method for optical biopsy of digestive mucosa for both diagnostic and therapeutic procedures. Computer aided diagnosis of CLE images, using image processing and fractal analysis can be used to quantify the histological structures in the CLE generated images. The aim of this study is to develop an automatic diagnosis algorithm of colorectal cancer (CRC), based on fractal analysis and neural network modeling of the CLE-generated colon mucosa images.Materials and MethodsWe retrospectively analyzed a series of 1035 artifact-free endomicroscopy images, obtained during CLE examinations from normal mucosa (356 images) and tumor regions (679 images). The images were processed using a computer aided diagnosis (CAD) medical imaging system in order to obtain an automatic diagnosis. The CAD application includes image reading and processing functions, a module for fractal analysis, grey-level co-occurrence matrix (GLCM) computation module, and a feature identification module based on the Marching Squares and linear interpolation methods. A two-layer neural network was trained to automatically interpret the imaging data and diagnose the pathological samples based on the fractal dimension and the characteristic features of the biological tissues.ResultsNormal colon mucosa is characterized by regular polyhedral crypt structures whereas malignant colon mucosa is characterized by irregular and interrupted crypts, which can be diagnosed by CAD. For this purpose, seven geometric parameters were defined for each image: fractal dimension, lacunarity, contrast correlation, energy, homogeneity, and feature number. Of the seven parameters only contrast, homogeneity and feature number were significantly different between normal and cancer samples. Next, a two-layer feed forward neural network was used to train and automatically diagnose the malignant samples, based on the seven parameters tested. The neural network operations were cross-entropy with the results: training: 0.53, validation: 1.17, testing: 1.17, and percent error, resulting: training: 16.14, validation: 17.42, testing: 15.48. The diagnosis accuracy error was 15.5%.ConclusionsComputed aided diagnosis via fractal analysis of glandular structures can complement the traditional histological and minimally invasive imaging methods. A larger dataset from colorectal and other pathologies should be used to further validate the diagnostic power of the method.