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.

The development of endoscopic ultrasound (EUS) has had a significant impact for patients with digestive diseases, enabling enhanced diagnostic and therapeutic procedures, with most of the available evidence focusing on upper gastrointestinal (GI) and pancreatico-biliary diseases. For the lower GI tract the main application of EUS has been in staging rectal cancer, as a complementary technique to other cross-sectional imaging methods. EUS can provide highly accurate in-depth assessments of tumour infiltration, performing best in the diagnosis of early rectal tumours. In the light of recent developments other EUS applications for colorectal diseases have been also envisaged and are currently under investigation, including beyond-rectum tumour staging by means of the newly developed forward-viewing radial array echoendoscope. Due to its high resolution, EUS might be also regarded as an ideal method for the evaluation of subepithelial lesions. Their differential diagnosis is possible by imaging the originating wall layer and the associated echostructure, and cytological and histological confirmation can be obtained through EUS-guided fine needle aspiration or trucut biopsy. However, reports on the use of EUS in colorectal subepithelial lesions are currently limited. EUS allows detailed examination of perirectal and perianal complications in Crohn's disease and, as a safe and less expensive investigation, can be used to monitor therapeutic response of fistulae, which seems to improve outcomes and reduce the need for additional surgery. Furthermore, EUS image enhancement techniques, such as the use of contrast agents or elastography, have recently been evaluated for colorectal indications as well. Possible applications of contrast enhancement include the assessment of tumour angiogenesis in colorectal cancer, the monitoring of disease activity in inflammatory bowel disease based on quantification of bowel wall vascularization, and differentiating between benign and malignant subepithelial tumours. Recent reports suggest that EUS elastography enables highly accurate discrimination of colorectal adenocarcinomas from adenomas, while inflammatory bowel disease phenotypes can be distinguished based on the strain ratio calculation. Among EUS-guided therapies, the drainage of abdominal and pelvic collections has been regarded as a safe and effective procedure to be used as an alternative for the transcutaneous route, while the placing of fiducial markers under EUS guidance for targeted radiotherapy in rectal cancer or the use of contrast microbubbles as drug-delivery vehicles represent experimental therapeutic applications that could greatly impact the forthcoming management of patients with colorectal diseases, pending on further investigations.

No abstract

No abstract