Confocal Laser Endomicroscopy Research Articles

Ultra-minimally invasive endoscopic techniques and colorectal diseases: Current status and its future

Colorectal diseases are increasing due to altered lifestyle, genetic, and environmental factors. Colonoscopy plays an important role in diagnosis. Advances in colonoscope (ultrathin scope, magnetic scope, capsule) and technological gadgets (Balloon assisted scope, third eye retroscope, NaviAid G-EYE, dye-based chromoendoscopy, virtual chromoendoscopy, narrow band imaging, i-SCAN, etc. ) have made colonoscopy more comfortable and efficient. Now in-vivo microscopy can be performed using confocal laser endomicroscopy, optical coherence tomography, spectroscopy, etc. Besides developments in diagnostic colonoscopy, therapeutic colonoscopy has improved to manage lower gastrointestinal tract bleeding, obstruction, perforations, resection polyps, and early colorectal cancers. The introduction of combined endo-laparoscopic surgery and robotic endoscopic surgery has made these interventions feasible. The role of artificial intelligence in the diagnosis and management of colorectal diseases is also increasing day by day. Hence, this article is to review cutting-edge developments in endoscopic principles for the management of colorectal diseases.

Confocal laser endomicroscopy for the diagnosis of gastric adenocarcinoma of the fundic gland type

Confocal laser endomicroscopy for the diagnosis of gastric adenocarcinoma of the fundic gland type

Emerging Technologies in Endoscopy for Gastrointestinal Neoplasms: A Comprehensive Overview.

Gastrointestinal neoplasms are a growing global health concern, requiring prompt identification and treatment. Endoscopic procedures have revolutionized the detection and treatment of gastrointestinal tumors by providing accurate, minimally invasive methods. Early-stage malignancies can be treated with endoscopic excision, leading to improved outcomes and increased survival rates. Precancerous lesions, like adenomatous polyps, can be prevented by removing them, reducing cancer occurrence and death rates. Advanced techniques like chromoendoscopy, narrow-band imaging, and confocal laser endomicroscopy improve the ability to see the mucosa surface and diagnose conditions. Artificial Intelligence (AI) applications in endoscopy can enhance diagnostic accuracy and predict histology outcomes. However, challenges remain in accurately defining lesions and ensuring precise diagnosis and treatment selection. Molecular imaging approaches and therapeutic modalities like photodynamic therapy and endoscopic ultrasonography-guided therapies hold potential but require further study and clinical confirmation. This study examines the future prospects and obstacles in endoscopic procedures for the timely identification and treatment of gastrointestinal cancers. The focus is on developing technology, limits, and prospective effects on clinical practice.

Distance Regression Enhanced with Temporal Information Fusion and Adversarial Training for Robot-Assisted Endomicroscopy.

Probe-based confocal laser endomicroscopy (pCLE) has a role in characterising tissue intraoperatively to guide tumour resection during surgery. To capture good quality pCLE data which is important for diagnosis, the probe-tissue contact needs to be maintained within a working range of micrometre scale. This can be achieved through micro-surgical robotic manipulation which requires the automatic estimation of the probe-tissue distance. In this paper, we propose a novel deep regression framework composed of the Deep Regression Generative Adversarial Network (DR-GAN) and a Sequence Attention (SA) module. The aim of DR-GAN is to train the network using an enhanced image-based supervision approach. It extents the standard generator by using a well-defined function for image generation, instead of a learnable decoder. Also, DR-GAN uses a novel learnable neural perceptual loss which combines for the first time spatial and frequency domain features. This effectively suppresses the adverse effects of noise in the pCLE data. To incorporate temporal information, we've designed the SA module which is a cross-attention module, enhanced with Radial Basis Function based encoding (SA-RBF). Furthermore, to train the regression framework, we designed a multi-step training mechanism. During inference, the trained network is used to generate data representations which are fused along time in the SA-RBF module to boost the regression stability. Our proposed network advances SOTA networks by addressing the challenge of excessive noise in the pCLE data and enhancing regression stability. It outperforms SOTA networks applied on the pCLE Regression dataset (PRD) in terms of accuracy, data quality and stability.

Intraoperative in vivo confocal endomicroscopy of the glioma margin: performance assessment of image interpretation by neurosurgeon users.

Confocal laser endomicroscopy (CLE) is an intraoperative real-time cellular resolution imaging technology that images brain tumor histoarchitecture. Previously, we demonstrated that CLE images may be interpreted by neuropathologists to determine the presence of tumor infiltration at glioma margins. In this study, we assessed neurosurgeons' ability to interpret CLE images from glioma margins and compared their assessments to those of neuropathologists. In vivo CLE images acquired at the glioma margins that were previously reviewed by CLE-experienced neuropathologists were interpreted by four CLE-experienced neurosurgeons. A numerical scoring system from 0 to 5 and a dichotomous scoring system based on pathological features were used. Scores from assessments of hematoxylin and eosin (H&E)-stained sections and CLE images by neuropathologists from a previous study were used for comparison. Neurosurgeons' scores were compared to the H&E findings. The inter-rater agreement and diagnostic performance based on neurosurgeons' scores were calculated. The concordance between dichotomous and numerical scores was determined. In all, 4275 images from 56 glioma margin regions of interest (ROIs) were included in the analysis. With the numerical scoring system, the inter-rater agreement for neurosurgeons interpreting CLE images was moderate for all ROIs (mean agreement, 61%), which was significantly better than the inter-rater agreement for the neuropathologists (mean agreement, 48%) (p < 0.01). The inter-rater agreement for neurosurgeons using the dichotomous scoring system was 83%. The concordance between the numerical and dichotomous scoring systems was 93%. The overall sensitivity, specificity, positive predictive value, and negative predictive value were 78%, 32%, 62%, and 50%, respectively, using the numerical scoring system and 80%, 27%, 61%, and 48%, respectively, using the dichotomous scoring system. No statistically significant differences in diagnostic performance were found between the neurosurgeons and neuropathologists. Neurosurgeons' performance in interpreting CLE images was comparable to that of neuropathologists. These results suggest that CLE could be used as an intraoperative guidance tool with neurosurgeons interpreting the images with or without assistance of the neuropathologists. The dichotomous scoring system is robust yet simple and may streamline rapid, simultaneous interpretation of CLE images during imaging.

A look inside the gut as a clue to nutritional status.

Malabsorption and malnutrition are common gastrointestinal manifestations clinicians face, requiring diagnostic workup for effective diagnosis and management of the underlying cause. This review discusses recent advances in diagnostic approaches to malabsorption and maldigestion of macronutrients - lipids, proteins, and carbohydrates. We highlight underrecognized causes, available testing modalities, and ongoing diagnostic unmet needs. Innovations in the diagnostic landscape are enhancing our understanding of malabsorption syndromes. Stool collection and handling is uncomfortable and commonly avoided. The objective quantification of stool lipids, bile acids, and gut enzymes is therefore underused in the diagnosis and management of common disorders such as exocrine pancreatic insufficiency, bile acid diarrhea, protein-losing enteropathy, and more. We review the recent advancements in spot quantification of stool fat and bile acid content, endoscopic imaging techniques such as endocytoscopy, confocal laser endomicroscopy, and optical coherence tomography and the future place in clinical practice. Malabsorption and maldigestion represent significant challenges in clinical nutrition and gastroenterology. Through the integration of advanced diagnostic techniques, clinicians will be better equipped to tailor therapy and monitor treatment response, ultimately improving patient health outcomes. This review underscores the critical role of innovative diagnostic tools in accurately detecting and effectively managing gastrointestinal disorders linked to nutritional status.

Feasibility of Optical Biopsy During Endoscopic Sinus Surgery With Confocal Laser Endomicroscopy: A Pilot Study.

Confocal laser endomicroscopy (CLE) is an optical imaging technique that allows in vivo, real-time, microscope-like assessment of superficial lesions. Although there is substantial data on CLE use in the upper GI tract, there is limited information regarding its application in the nasal cavity and paranasal sinuses. This study aims to assess the feasibility and diagnostic metrics of CLE in the nasal cavity and paranasal sinuses regarding differentiation between healthy/benign and malignant tissue. These structures show, however, a wider variety of frequent and concomitant benign and malignant pathologies, which could pose an increased challenge for optical biopsy by CLE. We performed CLE on a case series of six patients with various findings in the nose (three chronic rhinosinusitis, adenocarcinoma, meningoenzephalozele, esthesionneuroblastoma). Forty-two sequences (3792 images) from various structures in the nasal cavity and/or paranasal sinuses were acquired. Biopsies were taken at corresponding locations and analyzed in hematoxylin and eosin staining as a standard of reference. Three independent examiners blinded to the histopathology assessed the sequences. Healthy and inflamed mucosa could be distinguished from malignant lesions with an accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 84.1%, 85.4%, 83.1%, 72.5%, and 92.1%, respectively, with a substantial agreement between raters (Fleiss κ = 0.62). This technique shows, despite its limitations, potential as an adjunctive imaging technique during sinus surgery; however, the creation of a scoring system based on reproducible and defined characteristics in a larger more diverse population should be the focus of further research to improve its diagnostic value and clinical utility. NA Laryngoscope, 134:4217-4224, 2024.

Gastrointestinal adverse reaction to food (GARF) and endoscopic confocal laser endomicroscopy (eCLE).

Gastrointestinal adverse reaction to food (GARF) is reported frequently in the general population and even more in patients with disorders of the gut brain axis. However, there is a significant difference between self-reported and objective proven GARF. The aim of the study was to characterize a mucosal correlate of GARF by endoscopic confocal laser endomicroscopy (eCLE) with duodenal food challenge (DFC). In an observational and proof of concept study we evaluated 71 patients with disorders of the gut brain axis without (group I, n=19) and with (group II, n=52) GARF by eCLE and DFC. Spontaneous and food induced transfer of fluorescein into duodenal lumen was detected 10 minutes following intravenously application of fluorescein and 10 minutes after DFC. According to Rom IV, the patients (group I/II) could be classified as irritable bowel syndrome (IBS) 32%/31%, functional abdominal pain without changes in bowel movement 47 %/48 %, functional abdominal bloating/distension 0 %/10 %, functional diarrhea 5 %/ 2 %, and unspecified functional bowel disorder 16 %/10 %, respectively. 21 %/27 % of the patients responded with a fluorescein leakage into the duodenal lumen before and 74 %/69 % following to DFC. Frequency rank order of food components that induced a response were soy (55.5 %/60 %), wheat (60 %/45.5 %), egg (35.7 %/8.3), milk (30 %/18.2 %) and yeast (10 %/6.6 %), respectively. Histology of duodenal biopsies, number, form and distribution of intraepithelial lymphocytes and mucosal mast cells as well as mast cell function were normal. Overall, 14 %/79 % reported main symptom benefit following a food exclusion therapy according to eCLE and DFC that was significant different between the groups. The results of our study indicate that eCLE with DFC is a technique to clinically evaluate patients with disorders of the gut brain axis and GARF resulting in a high proportion of patients reporting symptom benefit upon food exclusion dietary advice focussed on the results of eCLE.

Advancements in Neurosurgical Intraoperative Histology.

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.

Clustering-Guided Twin Contrastive Learning for Endomicroscopy Image Classification.

Learning better representations is essential in medical image analysis for computer-aided diagnosis. However, learning discriminative semantic features is a major challenge due to the lack of large-scale well-annotated datasets. Thus, how can we learn a well-structured categorizable embedding space in limited-scale and unlabeled datasets? In this paper, we proposed a novel clustering-guided twin-contrastive learning framework (CTCL) that learns the discriminative representations of probe-based confocal laser endomicroscopy (pCLE) images for gastrointestinal (GI) tumor classification. Compared with traditional contrastive learning, in which only two randomly augmented views of the same instance are considered, the proposed CTCL aligns more semantically related and class-consistent samples by clustering, which improved intra-class tightness and inter-class variability to produce more informative representations. Furthermore, based on the inherent properties of CLE (geometric invariance and intrinsic noise), we proposed to regard CLE images with any angle rotation and CLE images with different noises as the same instance, respectively, for increased variability and diversity of samples. By optimizing CTCL in an end-to-end expectation-maximization framework, comprehensive experimental results demonstrated that CTCL-based visual representations achieved competitive performance on each downstream task as well as more robustness and transferability compared with existing state-of-the-art SSL and supervised methods. Notably, CTCL achieved 75.60%/78.45% and 64.12%/77.37% top-1 accuracy on the linear evaluation protocol and few-shot classification downstream tasks, respectively, which outperformed the previous best results by 1.27%/1.63% and 0.5%/3%, respectively. The proposed method holds great potential to assist pathologists in achieving an automated, fast, and high-precision diagnosis of GI tumors and accurately determining different stages of tumor development based on CLE images.

Basic Principles and Role of Endoscopic Ultrasound in Diagnosis and Differentiation of Pancreatic Cancer from Other Pancreatic Lesions: A Comprehensive Review of Endoscopic Ultrasound for Pancreatic Cancer.

Pancreatic cancer is one of the leading causes of cancer-related deaths worldwide. Pancreatic lesions consist of both neoplastic and non-neoplastic lesions and often pose a diagnostic and therapeutic challenge due to similar clinical and radiological features. In recent years, pancreatic lesions have been discovered more frequently as incidental findings due to the increased utilization and widespread availability of abdominal cross-sectional imaging. Therefore, it becomes imperative to establish an early and appropriate diagnosis with meticulous differentiation in an attempt to balance unnecessary treatment of benign pancreatic lesions and missing the opportunity for early intervention in malignant lesions. Endoscopic ultrasound (EUS) has become an important diagnostic modality for the identification and risk stratification of pancreatic lesions due to its ability to provide detailed imaging and acquisition of tissue samples for analysis with the help of fine-needle aspiration/biopsy. The recent development of EUS-based technology, including contrast-enhanced endoscopic ultrasound, real-time elastography-endoscopic ultrasound, miniature probe ultrasound, confocal laser endomicroscopy, and the application of artificial intelligence has significantly augmented the diagnostic accuracy of EUS as it enables better evaluation of the number, location, dimension, wall thickness, and contents of these lesions. This article provides a comprehensive overview of the role of the different types of EUS available for the diagnosis and differentiation of pancreatic cancer from other pancreatic lesions while discussing their key strengths and important limitations.

Oral mucosa - an examination map for confocal laser endomicroscopy within the oral cavity: an experimental clinical study

ObjectivesConfocal laser endomicroscopy (CLE) is an optical method that enables microscopic visualization of oral mucosa. Previous studies have shown that it is possible to differentiate between physiological and malignant oral mucosa. However, differences in mucosal architecture were not taken into account. The objective was to map the different oral mucosal morphologies and to establish a “CLE map” of physiological mucosa as baseline for further application of this powerful technology.Materials and methodsThe CLE database consisted of 27 patients. The following spots were examined: (1) upper lip (intraoral) (2) alveolar ridge (3) lateral tongue (4) floor of the mouth (5) hard palate (6) intercalary line. All sequences were examined by two CLE experts for morphological differences and video quality.ResultsAnalysis revealed clear differences in image quality and possibility of depicting tissue morphologies between the various localizations of oral mucosa: imaging of the alveolar ridge and hard palate showed visually most discriminative tissue morphology. Labial mucosa was also visualized well using CLE. Here, typical morphological features such as uniform cells with regular intercellular gaps and vessels could be clearly depicted. Image generation and evaluation was particularly difficult in the area of the buccal mucosa, the lateral tongue and the floor of the mouth.ConclusionA physiological “CLE map” for the entire oral cavity could be created for the first time.Clinical relevanceThis will make it possible to take into account the existing physiological morphological features when differentiating between normal mucosa and oral squamous cell carcinoma in future work.

FF-ViT: probe orientation regression for robot-assisted endomicroscopy tissue scanning

PurposeProbe-based confocal laser endomicroscopy (pCLE) enables visualization of cellular tissue morphology during surgical procedures. To capture high-quality pCLE images during tissue scanning, it is important to maintain close contact between the probe and the tissue, while also keeping the probe perpendicular to the tissue surface. Existing robotic pCLE tissue scanning systems, which rely on macroscopic vision, struggle to accurately place the probe at the optimal position on the tissue surface. As a result, the need arises for regression of longitudinal distance and orientation via endomicroscopic vision.MethodThis paper introduces a novel method for automatically regressing the orientation between a pCLE probe and the tissue surface during robotic scanning, utilizing the fast Fourier vision transformer (FF-ViT) to extract local frequency representations and use them for probe orientation regression. Additionally, the FF-ViT incorporates a blur mapping attention (BMA) module to refine latent representations, which is combined with the pyramid angle regressor (PAR) to precisely estimate probe orientation.ResultA first of its kind dataset for pCLE probe-tissue orientation (pCLE-PTO) has been created. The performance evaluation demonstrates that our proposed network surpasses other top regression networks in accuracy, stability, and generalizability, while maintaining low computational complexity (1.8G FLOPs) and high inference speed (90 fps).ConclusionThe performance evaluation study verifies the clinical value of the proposed framework and its potential to be integrated into surgical robotic platforms for intraoperative tissue scanning.

Confocal laser endomicroscopy as predictive biomarker of clinical and endoscopic efficacy of vedolizumab in ulcerative colitis: The DETECT study.

In patients with ulcerative colitis (UC), no biomarker is available to help the physician to choose the most suitable biotherapy. The primary objective of this pilot study was to assess the feasibility of identification of α4β7- and TNF-expressing cells, to predict the response to vedolizumab using confocal laser endoscopy (CLE). Patients with moderate-to-severe UC, naïve of biotherapy, received vedolizumab. Clinical evaluation was performed at each infusion. Endoscopic evaluation was performed before inclusion and at week 22. Fresh colonic biopsies were stained using FITC-labelled vedolizumab and Alexa fluor-labelled adalimumab and ex vivo dual-band CLE images were acquired. Blood samples were collected to measure trough concentrations of vedolizumab and to determine absolute counts of T and B cells subpopulations, NK cells and monocytes. Nineteen patients were enrolled in the study and received at least one dose of vedolizumab. Clinical remission and endoscopic improvement were observed in 58% of whom 5 patients (45%) had an endoscopic subscore of 0. In terms of clinical response and remission, endoscopic improvement and histologic response, FITC-conjugated vedolizumab staining tended to be higher in responder patients compared to non-responders at week 22. A threshold value of 6 positive FITC-vedolizumab staining areas detected by CLE seemed informative to discriminate the responders and non-responders. The results were similar in terms of clinical remission and endoscopic improvement with a sensitivity of 78% and a specificity of 85% (p = 0.05). Trough concentrations and blood immune cells were not associated with responses to vedolizumab. This pilot study demonstrate that dual-band CLE is feasible to detect α4β7- and TNF-expressing cells. Positive α4β7 staining seems to be associated with clinical and endoscopic remission in UC patients treated by anti-α4β7-integrin, subject to validation by larger-scale studies. Clinical-trial.gov: NCT02878083.

292 Intraoperative Confocal Laser Endomicroscopy During 5-ALA Guided Glioma Surgery: Significant Considerations for Resection at the Tumor Margins

INTRODUCTION: Fluorescence-guided surgery using 5-aminolevulinic acid (5-ALA) has proven effective in aiding the detection of glioma marginal zones and enhancing maximal safe resection. FDA-cleared confocal laser endomicroscopy is another imaging modality for intraoperative brain tissue discrimination on cellular level that could improve visualization at the glioma margin. METHODS: 5-ALA wide-field imaging and CLE were used in 9 patients with gliomas (6 enhancing, 3 non-enhancing). CLE imaging was enhanced by the use of a telesurgical pathology software platform to enable real-time conversation between neurosurgeons and pathologists located remotely. CLE was used for imaging tumor regions subjectively regarded as tumor margins under normal visualization with the operative microscope. After CLE imaging, 5-ALA wide-field imaging was performed in the same regions. A tissue was harvested at imaging locations, and interpretations of CLE and 5-ALA wide-field imaging were compared to permanent histological sections. RESULTS: Overall, 20 deep and superficial margin regions of interest (ROI) were imaged with CLE and 5-ALA imaging. Most of the ROIs interpreted by the neuropathologist as infiltrative glioma based on CLE imaging lacked 5-ALA-induced fluorescence. Permanent histological sections from the corresponding regions were concordant with the interpretation of CLE images in 15 of 20 (75%) ROIs and with the interpretation of 5-ALA imaging in 11 of 20 (55%) ROIs. Sensitivity/specificity of CLE and 5-ALA for interpretation of tumor margins were 79%/67%, and 50%/67%, respectively. Positive/negative predictive values for CLE and 5-ALA were 85%/57%, and 78%/37%, respectively. CONCLUSIONS: Conventional intraoperative understanding of tumor margins based on wide-field fluorescence could underestimate the invasiveness of gliomas. The ongoing study demonstrates that CLE shows higher accuracy in detecting regions with infiltrating tumor than intraoperative 5-ALA imaging.

Role of confocal laser endomicroscopy compared with high definition i-scan video bronchoscopy in patients with suspected lung cancer

Abstract Background Lung cancer is the one of the most important leading cause of mortality related to cancer worldwide. The 5-year survival is not optimistic with a percentage of 15% with mild improvement along the past 20 years (1.59 million deaths). The best effective and sensitive strategies of prevention is avoiding the common risk factor; tobacco smoking. The mortality of lung cancer can be reduced by early detection and treatment of the cases. Bronchial carcinoma in situ is one of the important stages to detect since over 40% of these can develop into invasive cancer. Sputum cytology and chest imaging have been used as a screening tests with limited success. Objective To study the diagnostic performance of confocal laser endomicroscopy in comparison to high definition i-scan videobronchoscopy in patients with suspected lung cancer. Patients and methods The study was performed at pulmonary diseases hospital in Kobry Elkobba military complex for 2 years since January 2018 to December 2019. The study included 25 patients all had chest CT findings suspicious of lung cancer. Results i-scan findings showed 68% accuracy and 73.3% specificity, and findings of confocal laser endomicroscopy were 92% accuracy and 90% specificity. Conclusion This was a study including patient characteristics in Egypt as a comparison between two methods of diagnosis of lung cancer. The study showed the higher sensitivity of confocal laser endomicroscopy in the diagnosis of lung cancer approved by the results of the pathological specimens optioned under the visual of confocal laser endomicroscopy in comparison with i-scan method.

XRelevanceCAM: towards explainable tissue characterization with improved localisation of pathological structures in probe-based confocal laser endomicroscopy

PurposeProbe-based confocal laser endomicroscopy (pCLE) enables intraoperative tissue characterization with improved resection rates of brain tumours. Although a plethora of deep learning models have been developed for automating tissue characterization, their lack of transparency is a concern. To tackle this issue, techniques like Class Activation Map (CAM) and its variations highlight image regions related to model decisions. However, they often fall short of providing human-interpretable visual explanations for surgical decision support, primarily due to the shattered gradient problem or insufficient theoretical underpinning.MethodsIn this paper, we introduce XRelevanceCAM, an explanation method rooted in a better backpropagation approach, incorporating sensitivity and conservation axioms. This enhanced method offers greater theoretical foundation and effectively mitigates the shattered gradient issue when compared to other CAM variants.ResultsQualitative and quantitative evaluations are based on ex vivo pCLE data of brain tumours. XRelevanceCAM effectively highlights clinically relevant areas that characterize the tissue type. Specifically, it yields a remarkable 56% improvement over our closest baseline, RelevanceCAM, in the network’s shallowest layer as measured by the mean Intersection over Union (mIoU) metric based on ground-truth annotations (from 18 to 28.07%). Furthermore, a 6% improvement in mIoU is observed when generating the final saliency map from all network layers.ConclusionWe introduce a new CAM variation, XRelevanceCAM, for precise identification of clinically important structures in pCLE data. This can aid introperative decision support in brain tumour resection surgery, as validated in our performance study.

A prospective multicenter assessor blinded pilot study using confocal laser endomicroscopy for intraoperative brain tumor diagnosis

In this multi-center, assessor-blinded pilot study, the diagnostic efficacy of cCeLL-Ex vivo, a second-generation confocal laser endomicroscopy (CLE), was compared against the gold standard frozen section analysis for intraoperative brain tumor diagnosis. The study was conducted across three tertiary medical institutions in the Republic of Korea. Biopsy samples from newly diagnosed brain tumor patients were categorized based on location and divided for permanent section analysis, frozen section analysis, and cCeLL-Ex vivo imaging. Of the 74 samples from 55 patients, the majority were from the tumor core (74.3%). cCeLL-Ex vivo exhibited a relatively higher diagnostic accuracy (89.2%) than frozen section analysis (86.5%), with both methods showing a sensitivity of 92.2%. cCeLL-Ex vivo also demonstrated higher specificity (70% vs. 50%), positive predictive value (PPV) (95.2% vs. 92.2%), and negative predictive value (NPV) (58.3% vs. 50%). Furthermore, the time from sample preparation to diagnosis was notably shorter with cCeLL-Ex vivo (13 min 17 s) compared to frozen section analysis (28 min 28 s) (p-value < 0.005). These findings underscore cCeLL-Ex vivo's potential as a supplementary tool for intraoperative brain tumor diagnosis, with future studies anticipated to further validate its clinical utility.

Endoscopic Ultrasound-Guided Needle-Based Confocal Endomicroscopy as a Diagnostic Imaging Biomarker for Intraductal Papillary Mucinous Neoplasms.

Pancreatic cancer is on track to become the second leading cause of cancer-related deaths by 2030, yet there is a lack of accurate diagnostic tests for early detection. Intraductal papillary mucinous neoplasms (IPMNs) are precursors to pancreatic cancer and are increasingly being detected. Despite the development and refinement of multiple guidelines, diagnosing high-grade dysplasia or cancer in IPMNs using clinical, radiologic, endosonographic, and cyst fluid features still falls short in terms of accuracy, leading to both under- and overtreatment. EUS-guided needle-based confocal laser endomicroscopy (nCLE) is a novel technology that allows real-time optical biopsies of pancreatic cystic lesions. Emerging data has demonstrated that EUS-nCLE can diagnose and risk stratify IPMNs more accurately than conventional diagnostic tools. Implementing EUS-nCLE in clinical practice can potentially improve early diagnosis of pancreatic cancer, reduce unnecessary surgeries of IPMNs with low-grade dysplasia, and advance the field of digital pathomics. In this review, we summarize the current evidence that supports using EUS-nCLE as a diagnostic imaging biomarker for diagnosing IPMNs and for risk stratifying their degree of neoplasia. Moreover, we will present emerging data on the role of adding artificial intelligence (AI) algorithms to nCLE and integrating novel fluid biomarkers into nCLE.

A novel Dual-Branch Asymmetric Encoder–Decoder Segmentation Network for accurate colonic crypt segmentation

Colorectal cancer (CRC) is a leading cause of cancer-related deaths, with colonic crypts (CC) being crucial in its development. Accurate segmentation of CC is essential for decisions CRC and developing diagnostic strategies. However, colonic crypts’ blurred boundaries and morphological diversity bring substantial challenges for automatic segmentation. To mitigate this problem, we proposed the Dual-Branch Asymmetric Encoder–Decoder Segmentation Network (DAUNet), a novel and efficient model tailored for confocal laser endomicroscopy (CLE) CC images. In DAUNet, we crafted a dual-branch feature extraction module (DFEM), employing Focus operations and dense depth-wise separable convolution (DDSC) to extract multiscale features, boosting semantic understanding and coping with the morphological diversity of CC. We also introduced the feature fusion guided module (FFGM) to adaptively combine features from both branches using cross-group spatial and channel attention to improve the model representation in focusing on specific lesion features. These modules are seamlessly integrated into the encoder for effective multiscale information extraction and fusion, and DDSC is further introduced in the decoder to provide rich representations for precise segmentation. Moreover, the local multi-layer perceptron (LMLP) module is designed to decouple and recalibrate features through a local linear transformation that filters out the noise and refines features to provide edge-enriched representation. Experimental evaluations on two datasets demonstrate that the proposed method achieves Intersection over Union (IoU) scores of 81.54% and 84.83%, respectively, which are on par with state-of-the-art methods, exhibiting its effectiveness for CC segmentation. The proposed method holds great potential in assisting physicians with precise lesion localization and region analysis, thereby improving the diagnostic accuracy of CRC.