Search Results (59)

Introduction: Artificial intelligence (AI) is increasingly being applied to improve the diagnosis and management of inflammatory bowel disease (IBD). Aims and Methods: We conducted a narrative review of the literature on AI applications in IBD endoscopy, focusing on diagnosis, disease activity assessment, therapy prediction, and detection of dysplasia. Results: AI systems have demonstrated high accuracy in assessing endoscopic and histological disease activity in ulcerative colitis and Crohn’s disease, with performance comparable to expert clinicians. Machine learning models can predict response to biologics and risk of complications. AI-assisted technologies like confocal laser endomicroscopy enable real-time histological assessment. Computer-aided detection systems improve identification of dysplastic lesions during surveillance. Challenges remain, including need for larger datasets, external validation, and addressing potential biases. Conclusions: AI has significant potential to enhance IBD care by providing rapid, objective assessments of disease activity, predicting outcomes, and assisting in dysplasia surveillance. However, further validation in diverse populations and prospective studies are needed before widespread clinical implementation. With ongoing advances, AI is poised to become a valuable tool to support clinical decision-making and improve patient outcomes in IBD. Addressing methodological, regulatory, and cost barriers will be crucial for the successful integration of AI into routine IBD management. Full article

In prostate cancer (PCa) surgery, precise tumor margin identification remains challenging despite advances in surgical techniques. This study evaluates the combination of tumor-specific near-infrared imaging with the PSMA-targeting molecule PSMA-914 and optical endomicroscopy (NIR-pCLE) for single-cell-level tumor identification in a preclinical proof of concept. Methods: NIR-pCLE imaging of varying PSMA-914 concentrations was performed on PSMA-positive LNCaP and PSMA-negative PC-3 cells using Cellvizio^® 100 with pCLE Confocal Miniprobes™. To identify optimal PSMA-914 dosing for in vivo imaging, different doses (0–10 nmol) were evaluated using NIR-pCLE, Odyssey CLx imaging, and confocal microscopy in an LNCaP tumor-bearing xenograft model. A proof of concept mimicking a clinical workflow was performed using 5 nmol [⁶⁸Ga]Ga-PSMA-914 in LNCaP and PC-3 tumor xenografts, including PET/MRI, in/ex vivo NIR-pCLE imaging, and microscopic/macroscopic imaging. Results: NIR-pCLE detected PSMA-specific fluorescence at concentrations above 30 nM in vitro. The optimal dose was identified as 5 nmol PSMA-914 for NIR-pCLE imaging with cellular resolution in LNCaP xenografts. PET/MRI confirmed high tumor uptake and a favorable distribution profile of PSMA-914. NIR-pCLE imaging enabled real-time, single-cell-level detection of PSMA-positive tissue, visualizing tumor heterogeneity, confirmed by ex vivo microscopy and imaging. Conclusions: This preclinical proof of concept demonstrates the potential of intraoperative PSMA-specific NIR-pCLE imaging to visualize tissue structures in real time at cellular resolution. Clinical implementation could provide surgeons with valuable additional information, potentially advancing PCa patient care through improved surgical precision. Full article

Molecular endoscopy represents a transformative advance in the detection, diagnosis, and management of gastrointestinal diseases, addressing the critical limitations of conventional techniques. Current diagnostic standards, such as white light endoscopy (WLE), often fail to detect early-stage lesions, particularly in high-risk populations like Barrett’s esophagus or inflammatory bowel disease patients. To overcome these challenges, molecular endoscopy, using fluorescent molecular probes, may offer ultimate precision by targeting disease-specific biomarkers. Technologies like Confocal Laser Endomicroscopy (CLE) and Immunoendoscopy are revolutionizing in vivo diagnostics, enabling the real-time visualization of tissue microarchitecture and physiological mechanisms. Fluorescence molecular endoscopy (FME) enhances the detection of precancerous and cancerous lesions, even those undetectable by conventional methods, by highlighting subtle molecular changes. Clinical applications include early tumor detection, therapy response monitoring, and improved lesion characterization. Despite these advancements, challenges persist, including high costs, a lack of standardization, and the need for specialized training. Recent innovations, such as a multi-parametric rigid standard, aim to ensure the reliable performance assessment and quality control of FME systems, addressing subjective variability and improving reproducibility. In addition, the integration of artificial intelligence (AI) with molecular endoscopy offers the potential to further reduce detection errors and significantly enhance diagnostic accuracy. This advancement underscores the potential of molecular endoscopy for personalized GI disease management, while highlighting the need for ongoing research to refine the technology, validate its clinical utility, and overcome the barriers to routine clinical application. Full article

Currently, the focus of intraoperative imaging in brain tumor surgery is beginning to shift to optical methods such as optical coherence tomography (OCT), Raman spectroscopy, confocal laser endomicroscopy (CLE), and fluorescence lifetime imaging (FLIM). Optical imaging technologies provide in vivo and real-time high-resolution images of tissues. “Optical biopsy” can be considered as an alternative to traditional approaches for intraoperative histopathologic consultation. Intraoperative optical imaging can help to achieve precise intraoperative identification of tumor infiltrations within the surrounding brain parenchyma. Therefore, it can be considered as a complement to existing approaches based on wide-field imaging modalities such as MRI, US, or 5-ALA fluorescence. A promising future direction for intraoperative guidance during brain tumor surgery or stereotactic biopsy lies in the integration of optical imaging with machine learning techniques, enabling automated differentiation between tumor tissue and healthy brain parenchyma. We present this review to increase knowledge and form critical opinions in the field of using optical imaging in brain tumor surgery. Full article

Technological advances have greatly expanded the diagnostic and therapeutic capabilities of endoscopic ultrasound (EUS). The integration of cutting-edge imaging techniques, including tissue harmonic echo, contrast-enhanced harmonic EUS, elastography, and needle-based confocal laser endomicroscopy, have significantly enhanced lesion characterization and diagnostic accuracy. Additionally, developments in stent design and the introduction of new accessories have broadened the therapeutic applications of EUS. Ongoing innovations in clinical practice have transformed procedures such as drainage, tumor ablation, EUS-directed transgastric endoscopic retrograde cholangiopancreatography (ERCP), the placement of fiducial markers, advancements in endohepatology, lesion characterization, and treatment. These developments continue to expand the role of EUS in delivering precise and effective therapeutic interventions. Full article

Irritable bowel syndrome (IBS) is a gut–brain interaction disorder often associated with food-related triggers, yet the efficacy of common exclusion diets remains debated. Confocal laser endomicroscopy (CLE) offers real-time, high-resolution imaging of intestinal mucosal changes, allowing the visualization of food-induced barrier dysfunction. Early evidence indicates that a substantial subset of IBS patients exhibit acute mucosal reactions to specific foods, identified as fluorescein leakage and cell shedding on CLE, with over 70% showing symptom improvements after tailored exclusion diets. These findings suggest that localized immune responses and barrier defects may contribute to IBS symptoms beyond IgE-driven immunologic mechanisms. However, most CLE-based studies are small, unblinded, and heterogeneous, limiting definitive conclusions. Further research is needed to validate the diagnostic accuracy of CLE, refine protocols, and clarify how best to integrate CLE into personalized dietary management for difficult-to-treat IBS. Full article

Brain tumors, both primary and metastatic, represent a significant global health burden due to their high incidence, mortality, and the severe neurological deficits they frequently cause. Gliomas, especially high-grade gliomas (HGGs), rank among the most aggressive and lethal neoplasms, with only modest gains in long-term survival despite extensive molecular research and established standard therapies. In neurosurgical practice, maximizing the extent of safe resection is a principal strategy for improving clinical outcomes. Yet, the infiltrative nature of gliomas often complicates the accurate delineation of tumor margins. Confocal laser endomicroscopy (CLE), originally introduced in gastroenterology, has recently gained prominence in neuro-oncology by enabling real-time, high-resolution cellular imaging during surgery. This technique allows for intraoperative tumor characterization and reduces dependence on time-consuming frozen-section analyses. Recent technological advances, including device miniaturization and second-generation CLE systems, have substantially improved image quality and diagnostic utility. Furthermore, integration with deep learning algorithms and telepathology platforms fosters automated image interpretation and remote expert consultations, thereby accelerating surgical decision making and enhancing diagnostic consistency. Future work should address remaining challenges, such as mitigating motion artifacts, refining training protocols, and broadening the range of applicable fluorescent probes, to solidify CLE’s role as a critical intraoperative adjunct in neurosurgical oncology. Full article

Background/Objectives: Lung cancer remains the leading cause of cancer-related mortality, underscoring the need for improved diagnostic methods. This study seeks to enhance the classification accuracy of confocal laser endomicroscopy (pCLE) images for lung cancer by applying a dual transfer learning (TL) approach that incorporates histological imaging data. Methods: Histological samples and pCLE images, collected from 40 patients undergoing curative lung cancer surgeries, were selected to create 2 balanced datasets (800 benign and 800 malignant images each). Three CNN architectures—AlexNet, GoogLeNet, and ResNet—were pre-trained on ImageNet and re-trained on pCLE images (confocal TL) or using dual TL (first re-trained on histological images, then pCLE). Model performance was evaluated using accuracy and AUC across 50 independent runs with 10-fold cross-validation. Results: The dual TL approach statistically significant outperformed confocal TL, with AlexNet achieving a mean accuracy of 94.97% and an AUC of 0.98, surpassing GoogLeNet (91.43% accuracy, 0.97 AUC) and ResNet (89.87% accuracy, 0.96 AUC). All networks demonstrated statistically significant (p < 0.001) improvements in performance with dual TL. Additionally, dual TL models showed reductions in both false positives and false negatives, with class activation mappings highlighting enhanced focus on diagnostically relevant regions. Conclusions: Dual TL, integrating histological and pCLE imaging, results in a statistically significant improvement in lung cancer classification. This approach offers a promising framework for enhanced tissue classification. and with future development and testing, iy has the potential to improve patient outcomes. Full article

Patients with inflammatory bowel disease (IBD) face an elevated risk of developing colorectal cancer (CRC). Endoscopic surveillance is a cornerstone in CRC prevention, enabling early detection and intervention. However, despite recent advancements, challenges persist. Chromoendoscopy (CE), considered the gold standard for dysplasia detection, remains underutilized due to logistical constraints, prolonged procedural times, and the need for specialized training. New technologies, such as endomicroscopy, confocal laser endomicroscopy (CLE), and molecular endoscopy (ME), promise unprecedented precision in lesion characterization but are limited to specialized centers. Artificial intelligence (AI) can transform the field; however, barriers to widespread AI adoption include the need for robust datasets, real-time video integration, and seamless incorporation into existing workflows. Beyond technology, patient adherence to surveillance protocols, including bowel preparation and repeat procedures, remains a critical hurdle. This review aims to explore the advancements, ongoing challenges, and future prospects in CRC prevention for IBD patients, focusing on improving outcomes and expanding the implementation of advanced surveillance technologies. Full article

Abstract: Background/Objectives: Sinonasal malignancies are rare and highly diverse cancers that pose significant diagnostic challenges due to their variable histological features and complex anatomical locations. Accurate diagnosis is critical for guiding treatment, yet conventional methods often require multiple biopsies. This study aimed to evaluate the potential of confocal laser endomicroscopy (CLE) for real-time imaging of sinonasal tumors to characterize specific features of different entities and improve diagnostic precision. Methods: Ten patients with various sinonasal malignancies, including squamous cell carcinoma, adenocarcinoma, sinonasal undifferentiated carcinoma, olfactory neuroblastoma, sinonasal mucosal melanoma, and endonasal lymphoma, were examined using CLE during diagnostic endoscopy. CLE images were compared descriptively with histopathological cross-sections to identify unique imaging patterns for each tumor type. Results: CLE was feasible across all cases, with high-quality images obtained despite anatomical challenges in some cases. Characteristic features, such as vascular clusters in undifferentiated carcinoma, mucin-filled bubbles in adenocarcinoma, and small round cells in neuroblastoma, were identified and corresponded well with histopathological findings. CLE also helped guide biopsies by revealing areas with diagnostic relevance. Conclusions: CLE demonstrates promise as an adjunct diagnostic tool in sinonasal malignancies, offering real-time imaging that correlates with histopathological findings and aids in targeted biopsies. While this study provides preliminary insights into the utility of CLE, further research with larger cohorts and statistical validation is necessary to establish its diagnostic reliability and broader clinical application. Full article

Background/Objectives: Building upon the rising value of Confocal Laser Endomicroscopy (CLE) in squamous cell carcinoma of the head and neck, we present the first application of CLE during the resection of sinonasal malignant melanomas. This study aims to evaluate the potential of CLE to assist surgeons in intraoperative decision-making, with a particular focus on resection margin assessment within the constrained nasal cavity. Methods: Two cases of sinonasal malignant melanoma were included in this study. CLE was employed to examine visible tumors and their margins, both pre- and post-endoscopic resection. The findings were compared to histopathological results as well as data on squamous cell carcinoma, for which malignancy criteria had already been established in prior projects. Results: CLE provided the real-time visualization of sinonasal malignant melanomas and their margins, successfully differentiating between healthy and neoplastic tissue compared to histopathological findings. Conclusion: CLE offers the potential for real-time assessment, aiding surgeons in more precise tumor resection and potentially improving patient outcomes. This study demonstrates the feasibility of using CLE in the resection of sinonasal malignant melanoma, highlighting its ability to differentiate between healthy and neoplastic tissue intraoperatively. Full article

Diffuse low-grade gliomas are infiltrative tumors whose margins are not distinguishable from the adjacent healthy brain parenchyma. The aim was to precisely examine the results provided by the intraoperative use of macroscopic fluorescence in diffuse low-grade gliomas and to describe the new fluorescence-based techniques capable of guiding the resection of low-grade gliomas. Only about 20% and 50% of low-grade gliomas are macroscopically fluorescent after 5-amino-levulinic acid (5-ALA) or fluorescein sodium intake, respectively. However, 5-ALA is helpful for detecting anaplastic foci, and thus choosing the best biopsy targets in diffuse gliomas. Spectroscopic detection of 5-ALA-induced fluorescence can detect very low and non-macroscopically visible concentrations of protoporphyrin IX, a 5-ALA metabolite, and, consequently, has excellent performances for the detection of low-grade gliomas. Moreover, these tumors have a specific spectroscopic signature with two fluorescence emission peaks, which is useful for distinguishing them not only from healthy brain but also from high-grade gliomas. Confocal laser endomicroscopy can generate intraoperative optic biopsies, but its sensitivity remains limited. In the future, the coupled measurement of autofluorescence and induced fluorescence, and the introduction of fluorescence detection technologies providing a wider field of view could result in the development of operator-friendly tools implementable in the operative routine. Full article

Background: Chronic liver disease occurs throughout the world irrespective of region, age, sex, or race, and it is caused by a variety of liver conditions. One of the most frequent infectious complications in liver cirrhosis that severely reduces the median survival is spontaneous bacterial peritonitis. Current guidelines recommend a paracentesis before starting an antibiotic prophylaxis for this complication. Methods: Selective intestinal decontamination significantly lowers the rate of first or recurrent SBP in cirrhotic patients, so in this study we aimed to investigate and quantify the intestinal integrity of patients with liver cirrhosis and correlate a pathologically increased permeability with the incidence of SPB. We included 14 patients who met the inclusion criteria. No patient was excluded. For the CLE investigation, we use probe based confocal laser endomicroscopy techniques from Mauna Kea (Cellvizio), enabling in vivo surface imaging. The images (optical biopsies) were analyzed for functional and structural barrier defects after the procedure using Mauna Kea software (version 1.0.09). Results: Because of the small number of included patients and healthy controls, most results are lacking statistical relevance. We found that the CLE investigation showed an increased intestinal permeability in patients with liver cirrhosis, in concordance with previous published data, based on other assessment methods. Conclusions: This study confirms that previously published permeability scores can be applied for patients with liver cirrhosis and is, to our knowledge, the first to investigate the intestinal permeability in vivo in patients with liver cirrhosis. Further data are needed to identify patients at risk and help develop new and less invasive diagnostic criteria for cirrhotic patients who may profit from a prophylactic antibiotic treatment. Full article

Despite their relatively low incidence globally, central nervous system (CNS) tumors remain amongst the most lethal cancers, with only a few other malignancies surpassing them in 5-year mortality rates. Treatment decisions for brain tumors heavily rely on histopathological analysis, particularly intraoperatively, to guide surgical interventions and optimize patient outcomes. Frozen sectioning has emerged as a vital intraoperative technique, allowing for highly accurate, rapid analysis of tissue samples, although it poses challenges regarding interpretive errors and tissue distortion. Raman histology, based on Raman spectroscopy, has shown great promise in providing label-free, molecular information for accurate intraoperative diagnosis, aiding in tumor resection and the identification of neurodegenerative disease. Techniques including Stimulated Raman Scattering (SRS), Coherent Anti-Stokes Raman Scattering (CARS), Surface-Enhanced Raman Scattering (SERS), and Tip-Enhanced Raman Scattering (TERS) have profoundly enhanced the speed and resolution of Raman imaging. Similarly, Confocal Laser Endomicroscopy (CLE) allows for real-time imaging and the rapid intraoperative histologic evaluation of specimens. While CLE is primarily utilized in gastrointestinal procedures, its application in neurosurgery is promising, particularly in the context of gliomas and meningiomas. This review focuses on discussing the immense progress in intraoperative histology within neurosurgery and provides insight into the impact of these advancements on enhancing patient outcomes. Full article

Probe-based confocal laser endoscopy (pCLE) has emerged as a powerful tool for disease diagnosis, yet it faces challenges such as the formation of hexagonal patterns in images due to the inherent characteristics of fiber bundles. Recent advancements in deep learning offer promise in image denoising, but the acquisition of clean-noisy image pairs for training networks across all potential scenarios can be prohibitively costly. Few studies have explored training denoising networks on such pairs. Here, we propose an innovative self-supervised denoising method. Our approach integrates noise prediction networks, image quality assessment networks, and denoising networks in a collaborative, jointly trained manner. Compared to prior self-supervised denoising methods, our approach yields superior results on pCLE images and fluorescence microscopy images. In summary, our novel self-supervised denoising technique enhances image quality in pCLE diagnosis by leveraging the synergy of noise prediction, image quality assessment, and denoising networks, surpassing previous methods on both pCLE and fluorescence microscopy images. Full article