Qualitative Study on the Factors Influencing the Utilisation of Products Labelled "Food for Special Medicinal Use" (FSMP).

This study aimed to investigate Romanian physicians' awareness, recommendation practices, and opinions regarding the use of Foods for Special Medical Purposes (FSMPs) products. A total of ten physicians were interviewed using a structured questionnaire, and their responses were analysed using thematic content analysis. The study found that physicians were aware of FSMPs and recommended them to their patients based on nutritional deficits, weight loss, or deglutition impairments. In addition, disease stage, treatment scheme, taste, affordability, and availability were identified as factors influencing the recommendation and use of FSMPs. While physicians generally did not consult clinical trials, clinical experience was deemed essential for recommending FSMPs to patients. Patients' feedback regarding the usage and sourcing of FSMPs was generally positive, with some expressing concerns about the availability of different flavours and the costs of purchasing the products. This study concluded that physicians play a vital role in recommending FSMPs to patients and ensuring they have the necessary nutritional support during treatment. However, it may be imperative to consider the provision of additional patient education materials and fostering collaborative efforts with nutritionists in order to optimise the prospects of positive outcomes in oncology treatment, while simultaneously alleviating the financial burdens faced by patients.

Deep Learning Algorithm for the Confirmation of Mucosal Healing in Crohn's Disease, Based on Confocal Laser Endomicroscopy Images.

BACKGROUND AND AIMS: Mucosal healing (MH) is associated with a stable course of Crohn's disease (CD) which can be assessed by confocal laser endomicroscopy (CLE). To minimize the operator's errors and automate assessment of CLE images, we used a deep learning (DL) model for image analysis. We hypothesized that DL combined with convolutional neural networks (CNNs) and long short-term memory (LSTM) can distinguish between normal and inflamed colonic mucosa from CLE images. METHODS: The study included 54 patients, 32 with known active CD, and 22 control patients (18 CD patients with MH and four normal mucosa patients with no history of inflammatory bowel diseases). We designed and trained a deep convolutional neural network to detect active CD using 6,205 endomicroscopy images classified as active CD inflammation (3,672 images) and control mucosal healing or no inflammation (2,533 images). CLE imaging was performed on four colorectal areas and the terminal ileum. Gold standard was represented by the histopathological evaluation. The dataset was randomly split in two distinct training and testing datasets: 80% data from each patient were used for training and the remaining 20% for testing. The training dataset consists of 2,892 images with inflammation and 2,189 control images. The testing dataset consists of 780 images with inflammation and 344 control images of the colon. We used a CNN-LSTM model with four convolution layers and one LSTM layer for automatic detection of MH and CD diagnosis from CLE images. RESULTS: CLE investigation reveals normal colonic mucosa with round crypts and inflamed mucosa with irregular crypts and tortuous and dilated blood vessels. Our method obtained a 95.3% test accuracy with a specificity of 92.78% and a sensitivity of 94.6%, with an area under each receiver operating characteristic curves of 0.98. CONCLUSIONS: Using machine learning algorithms on CLE images can successfully differentiate between inflammation and normal ileocolonic mucosa and can be used as a computer aided diagnosis for CD. Future clinical studies with a larger patient spectrum will validate our results and improve the CNN-SSTM model.

Advanced Endoscopic Imaging Techniques for the Study of Colonic Mucosa in Patients with Inflammatory Bowel Disease.

BACKGROUND: Crohn's disease and ulcerative colitis are inflammatory bowel diseases (IBD) associated with colorectal cancer risk in long-standing diseases. In order to assess the colonic mucosa and to discover dysplastic or neoplastic lesions, advanced endoscopic techniques are needed. Such techniques are detailed in this review: chromoendoscopy, autofluorescence imaging (AFI), narrow band imaging (NBI), i-SCAN, Fujinon Intelligent Color Enhancement (FICE) and confocal laser endomicroscopy (CLE). AIM: The aim of the review is to describe and establish the clinical impact of advanced endoscopic techniques, that could be used in IBD patients'examination in order to assess mucosal healing, microscopic inflammation, dysplasia or neoplasia. MATERIALS AND METHODS: A literature research about new endoscopic approaches of patients with IBD was made. RESULTS: A lot of studies have been performed to reveal which imaging technique might be used for IBD surveillance. Regarding dysplasia or neoplasia detection and mucosal healing or inflammation assessment, CE proved to be superior to white light endoscopy (WLE), while NBI and AFI did not show an encouraging result. I-SCAN did not improve the colonoscopy quality while FICE has been used in a few studies. CLE could be used to characterize a lesion, providing the same results as conventional histology. CONCLUSION: At the moment, CE is the only technique which has been included in guidelines for IBD surveillance. CLE can be used to assess any lesion detected with WLE during surveillance, while the other imaging techniques require.more studies to determine their efficacy or inefficacy.

Computer Aided Diagnosis for Confocal Laser Endomicroscopy in Advanced Colorectal Adenocarcinoma.

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.

Needle-based confocal laser endomicroscopy in pancreatic cystic tumors assessment.

Pancreatic cystic tumors (PCT) are relatively common findings in general population due to the widespread use of cross-sectional imaging. PCT can be benign, with premalignant potential or malignant, a different management being applied for each type: benign cysts are usually referred for follow-up (based on imaging), while premalignant or malignant lesions should be surgically resected. The aim of this review is to describe the latest imaging technique that could be used for PCT diagnosis and to establish its clinical impact. Endoscopic ultrasound (EUS) is generally used to evaluate a pancreatic mass and to identify its characteristics. It offers a good visualization of the lesion. When combined with fine needle aspiration and cystic fluid analysis, the diagnosis potential is increased, although its accuracy for differentiating benign and malign tumors remains modest. EUS-guided needle-based confocal laser endomicroscopy (nCLE) is a new imaging technique that uses a miniprobe thin enough to be passed through a 19G needle. It provides in vivo images of the pancreas at a cellular level, offering the possibility to assess any changes that might have occurred. Several studies have shown that nCLE is feasible to use for PCT evaluation, imaging criteria being established with 100% specificity for intraductal papillary mucinous neoplasms (IPMN) and serous cystadenoma (SCA). Regarding the safety, more studies are needed. EUS-guided nCLE appears to be a new imaging technique that provides encouraging results for differential diagnosis between mucinous/non-mucinous cysts.