Person:

Gruionu, Gabriel

The tumor microcirculation is characterized by an abnormal vascular network with dilated, tortuous and saccular vessels. Therefore, imaging the tumor vasculature and determining its morphometric characteristics represent a critical goal for optimizing the cancer treatment that targets the blood vessels (i.e. antiangiogenesis therapy). The aim of this study was to evaluate new vascular morphometric parameters in colorectal cancer, difficult to achieve through conventional immunohistochemistry, by using the confocal laser endomicroscopy method. Fresh biopsies from tumor and normal tissue were collected during colonoscopy from five patients with T3 colorectal carcinoma without metastasis and were marked with fluorescently labeled anti-CD31 antibodies. A series of optical slices spanning 250 µm inside the tissue were immediately collected for each sample using a confocal laser endomicroscope. All measurements were expressed as the mean ± standard error. The mean diameter of tumor vessels was significantly larger than the normal vessels (9.46±0.4 µm vs. 7.60±0.3 µm, p = 0.0166). The vessel density was also significantly higher in the cancer vs. normal tissue samples (5541.05±262.81 vs. 3755.79±194.96 vessels/mm3, p = 0.0006). These results were confirmed by immunohistochemistry. In addition, the tortuosity index and vessel lengths were not significantly different (1.05±0.016 and 28.30±3.27 µm in normal tissue, vs. 1.07±0.008 and 26.49±3.18 µm in tumor tissue respectively, p = 0.5357 and p = 0.7033). The daughter/mother ratio (ratio of the sum of the squares of daughter vessel radii over the square of the mother vessel radius) was 1.15±0.09 in normal tissue, and 1.21±0.08 in tumor tissue (p = 0.6531). The confocal laser endomicroscopy is feasible for measuring more vascular parameters from fresh tumor biopsies than conventional immunohistochemistry alone. Provided new contrast agents will be clinically available, future in vivo use of CLE could lead to identification of novel biomarkers based on the morphometric characteristics of tumor vasculature.

Introduction: Confocal 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 Methods We 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. Results: Normal 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%. Conclusions: Computed 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.