Search Results (42)

Objective: Esophageal carcinoma (EC) is the eighth most prevalent cancer and the sixth leading cause of cancer-related mortality worldwide. Early detection is vital for improving prognosis, particularly for dysplasia and squamous cell carcinoma (SCC). Methods: This study evaluates a hyperspectral imaging conversion method, the Spectrum-Aided Vision Enhancer (SAVE), for its efficacy in enhancing esophageal cancer detection compared to conventional white-light imaging (WLI). Five deep learning models (YOLOv9, YOLOv10, YOLO-NAS, RT-DETR, and Roboflow 3.0) were trained and evaluated on a dataset comprising labeled endoscopic images, including normal, dysplasia, and SCC classes. Results: Across all five evaluated deep learning models, the SAVE consistently outperformed conventional WLI in detecting esophageal cancer lesions. For SCC, the F1 score improved from 84.3% to 90.4% in regard to the YOLOv9 model and from 87.3% to 90.3% in regard to the Roboflow 3.0 model when using the SAVE. Dysplasia detection also improved, with the precision increasing from 72.4% (WLI) to 76.5% (SAVE) in regard to the YOLOv9 model. Roboflow 3.0 achieved the highest F1 score for dysplasia of 64.7%. YOLO-NAS exhibited balanced performance across all lesion types, with the dysplasia precision rising from 75.1% to 79.8%. Roboflow 3.0 also recorded the highest SCC sensitivity of 85.7%. In regard to SCC detection with YOLOv9, the WLI F1 score was 84.3% (95% CI: 71.7–96.9%) compared to 90.4% (95% CI: 80.2–100%) with the SAVE (p = 0.03). For dysplasia detection, the F1 score increased from 60.3% (95% CI: 51.5–69.1%) using WLI to 65.5% (95% CI: 57.0–73.8%) with SAVE (p = 0.04). These findings demonstrate that the SAVE enhances lesion detectability and diagnostic performance across different deep learning models. Conclusions: The amalgamation of the SAVE with deep learning algorithms markedly enhances the detection of esophageal cancer lesions, especially squamous cell carcinoma and dysplasia, in contrast to traditional white-light imaging. This underscores the SAVE’s potential as an essential clinical instrument for the early detection and diagnosis of cancer. Full article

Capsule endoscopy (CE) has revolutionized gastrointestinal (GI) diagnostics by providing a non-invasive, patient-centered approach to observing the digestive tract. Conceived in 2000 by Gavriel Iddan, CE employs a diminutive, ingestible capsule containing a high-resolution camera, LED lighting, and a power supply. It specializes in visualizing the small intestine, a region frequently unreachable by conventional endoscopy. CE helps detect and monitor disorders, such as unexplained gastrointestinal bleeding, Crohn’s disease, and cancer, while presenting a lower procedural risk than conventional endoscopy. Contrary to conventional techniques that necessitate anesthesia, CE reduces patient discomfort and complications. Nonetheless, its constraints, specifically the incapacity to conduct biopsies or therapeutic procedures, have spurred technical advancements. Five primary types of capsule endoscopes have emerged: steerable, magnetic, robotic, tethered, and hybrid. Their performance varies substantially. For example, the image sizes vary from 256 × 256 to 640 × 480 pixels, the fields of view (FOV) range from 140° to 360°, the battery life is between 8 and 15 h, and the frame rates fluctuate from 2 to 35 frames per second, contingent upon motion-adaptive capture. This study addresses a significant gap by methodically evaluating CE platforms, outlining their clinical preparedness, and examining the underexploited potential of artificial intelligence in improving diagnostic precision. Through the examination of technical requirements and clinical integration, we highlight the progress made in overcoming existing CE constraints and outline prospective developments for next-generation GI diagnostics. Full article

Early detection of early-stage esophageal cancer (ECA) is crucial for timely intervention and improved treatment outcomes. Hyperspectral imaging (HSI) and artificial intelligence (AI) technologies offer promising avenues for enhancing diagnostic accuracy in this context. This study utilized a dataset comprising 3984 white light images (WLIs) and 3666 narrow-band images (NBIs). We employed the Yolov5 model, a state-of-the-art object detection algorithm, to predict early ECA based on the provided images. The dataset was divided into two subsets: RGB-WLIs and NBIs, and four distinct models were trained using these datasets. The experimental results revealed that the prediction performance of the training model was notably enhanced when using HSI compared to general NBI training. The HSI training model demonstrated an 8% improvement in accuracy, along with a 5–8% enhancement in precision and recall measures. Notably, the model trained with WLIs exhibited the most significant improvement. Integration of HSI with AI technologies improves the prediction performance for early ECA detection. This study underscores the potential of deep learning identification models to aid in medical detection research. Integrating these models with endoscopic diagnostic systems in healthcare settings could offer faster and more accurate results, thereby improving overall detection performance. Full article

Background/Objectives: The study aims to analyse the factors associated with positive margins and endoscopic understaging in laryngeal carcinoma. It also aims to assess the diagnostic accuracy of Narrow Band Imaging (NBI) in comparison to White Light Endoscopy (WLE) and other diagnostic methods. Methods: In this retrospective comparative cohort analysis, 206 patients who underwent endoscopic laser surgery for T1 and T2a glottic squamous cell carcinoma between 1 January 2016 and 30 April 2023 were included. The data were collected from endoscopy, CT, histopathology, and NBI images. Statistical analysis was performed and associations between variables were analysed using binary logistic regression and receiver operating characteristic analysis. Results: The types of cordectomy performed included type III (51 patients), type IV (40 patients), and type VI (23 patients). Positive margins were found in 14.01% of patients, with significant correlations observed between positive margins and bilateral laryngeal carcinoma, right-sided laryngeal carcinoma, higher clinical and histopathologic T categories, and higher NBI grade. Endoscopic understaging versus histopathologic T category correlated with various factors, including cordectomy type, tumour size, and clinical T category. The NBI findings correlated with positive margins but did not correlate with endoscopic understaging. Conclusions: The study highlights several clinical and pathological factors associated with positive margins and endoscopic understaging in laryngeal carcinoma. NBI demonstrated high diagnostic accuracy, correlating with histopathological results and serving as an independent predictive factor for positive margins. Recognizing these factors is crucial for improving preoperative assessments, refining treatment strategies, and enhancing patient care. Full article

Background: Endoscopic assessment for the diagnosis of gastric cancer is limited by interoperator variability and lack of real-time capability. Recently, Raman spectroscopy-based artificial intelligence (AI) has been proposed as a solution to overcome these limitations. Objective: To compare the performance of the AI-enabled Raman spectroscopy with that of high-definition white light endoscopy (HD-WLE) for the risk classification of gastric lesions. Methods: This was a randomized double-arm feasibility proof-of-concept trial in which participants with suspected gastric neoplasia underwent endoscopic assessment using either the Raman spectroscopy-based AI (SPECTRA IMDx™) or HD-WLE performed by expert endoscopists. Identified lesions were classified in real time as having either low or high risk for neoplasia. Diagnostic outcomes were compared between the two groups using histopathology as the reference. Results: A total of 20 patients with 25 lesions were included in the study. SPECTRA, in real-time, performed at a statistically similar level to that of HD-WLE performed by expert endoscopists, achieving an overall sensitivity, specificity, and accuracy of 100%, 80%, and 89.0%, respectively, by patient; and 100%, 80%, and 92%, respectively, by lesion, while expert endoscopists using HD-WLE attained a sensitivity, specificity, and accuracy of 100%, 80%, and 90%, respectively, by patient; and 100%, 83.3%, and 91.7%, respectively, by lesion, in differentiating high-risk from low-risk gastric lesions. Conclusions: The SPECTRA’s comparable performance with that of HD-WLE suggests that it can potentially be a valuable adjunct for less experienced endoscopists to attain accurate and real-time diagnoses of gastric lesions. Larger-scale prospective randomized trials are recommended to validate these promising results further. Full article

Background: Narrow-band imaging is an advanced endoscopic technology used to detect changes on the laryngeal tissue surface, employing a comparative approach alongside white-light endoscopy to facilitate histopathological examination. Objective: This study aimed to assess the utility and advantages of NBI (narrow-band imaging) in identifying malignant laryngeal lesions through a comparative analysis with histopathological examination. Methods: We conducted a systematic literature review, utilizing databases such as PubMed, the CNKI database, and Embase for our research. Results: We analyzed the articles by reviewing their titles and abstracts, selecting those we considered relevant based on determined criteria; in the final phase, we examined the relevant studies according to the specific eligibility criteria. Conclusions: Narrow-band imaging is an advanced endoscopic technology that demonstrates its efficacy as a tool for diagnosing malignant laryngeal lesions and comparing them to premalignant lesions. The European Society of Laryngology has implemented a standardized classification system for laryngeal lesions to enhance data correlation and organization. Full article

Background: Fluorescence visualization of pathologies, primarily neoplasms in human internal cavities, is one of the most popular forms of diagnostics during endoscopic examination in medical practice. Currently, visualization can be performed in the augmented reality mode, which allows to observe areas of increased fluorescence directly on top of a usual color image. Another no less informative form of endoscopic visualization in the future can be mapping (creating a mosaic) of the acquired image sequence into a single map covering the area under study. The originality of the present contribution lies in the development of a new 3D bimodal experimental bladder model and its validation as an appropriate phantom for testing the combination of bimodal cystoscopy and image mosaicking. Methods: An original 3D real bladder-based phantom (physical model) including cancer-like fluorescent foci was developed and used to validate the combination of (i) a simultaneous white light and fluorescence cystoscopy imager with augmented reality mode and (ii) an image mosaicking algorithm superimposing both information. Results: Simultaneous registration and real-time visualization of a color image as a reference and a black-and-white fluorescence image with an overlay of the two images was made possible. The panoramic image build allowed to precisely visualize the relative location of the five fluorescent foci along the trajectory of the endoscope tip. Conclusions: The method has broad prospects and opportunities for further developments in bimodal endoscopy instrumentation and automatic image mosaicking. Full article

Current standard methods for evaluating benign vocal lesions, including white light laryngoscopy and video laryngostroboscopy, may struggle to identify smaller lesions. While histopathological results obtained from laryngeal microsurgery provide definitive results, their invasiveness can lead to scarring and impaired phonological outcomes. Intralesional steroid injection has recently gained acceptance, but it lacks pathological diagnostic capabilities. Therefore, there is a growing need for a simple examination that can enhance the diagnosis of benign vocal lesions. NBI, from Olympus Corporation, has shown promising outcomes in detecting and characterizing laryngeal lesions. The i-scan technology by PENTAX, while providing the ability to improve visual clarity during endoscopic procedures, has been addressed less in this field. Our study aims to further investigate the application of i-scan imaging in benign vocal lesions, enrolling patients diagnosed with vocal cysts, polyps, and nodules. We conducted i-scan imaging prior to office-based intralesional steroid injection, assessing the possibility of its providing additional diagnostic information for benign vocal lesions without additional burden. Full article

Endoscopy is a commonly used clinical method for gastrointestinal disorders. However, the complexity of the gastrointestinal environment can lead to artifacts. Consequently, the artifacts affect the visual perception of images captured during endoscopic examinations. Existing methods to assess image quality with no reference display limitations: some are artifact-specific, while others are poorly interpretable. This study presents an improved cascade region-based convolutional neural network (CNN) for detecting gastrointestinal artifacts to quantitatively assess the quality of endoscopic images. This method detects eight artifacts in endoscopic images and provides their localization, classification, and confidence scores; these scores represent image quality assessment results. The artifact detection component of this method enhances the feature pyramid structure, incorporates the channel attention mechanism into the feature extraction process, and combines shallow and deep features to improve the utilization of spatial information. The detection results are further used for image quality assessment. Experimental results using white light imaging, narrow-band imaging, and iodine-stained images demonstrate that the proposed artifact detection method achieved the highest average precision (62.4% at a 50% IOU threshold). Compared to the typical networks, the accuracy of this algorithm is improved. Furthermore, three clinicians validated that the proposed image quality assessment method based on the object detection of endoscopy artifacts achieves a correlation coefficient of 60.71%. Full article

Artificial intelligence (AI) presents a novel platform for improving disease diagnosis. However, the clinical utility of AI remains limited to discovery studies, with poor translation to clinical practice. Current data suggests that 26% of diminutive pre-malignant lesions and 3.5% of colorectal cancers are missed during colonoscopies. The primary aim of this study was to explore the role of artificial intelligence in real-time histological prediction of colorectal lesions during colonoscopy. A systematic search using MeSH headings relating to “AI”, “machine learning”, “computer-aided”, “colonoscopy”, and “colon/rectum/colorectal” identified 2290 studies. Thirteen studies reporting real-time analysis were included. A total of 2958 patients with 5908 colorectal lesions were included. A meta-analysis of six studies reporting sensitivities (95% CI) demonstrated that endoscopist diagnosis was superior to a computer-assisted detection platform, although no statistical significance was reached (p = 0.43). AI applications have shown encouraging results in differentiating neoplastic and non-neoplastic lesions using narrow-band imaging, white light imaging, and blue light imaging. Other modalities include autofluorescence imaging and elastic scattering microscopy. The current literature demonstrates that despite the promise of new endoscopic AI models, they remain inferior to expert endoscopist diagnosis. There is a need to focus developments on real-time histological predictions prior to clinical translation to demonstrate improved diagnostic capabilities and time efficiency. Full article

Colorectal cancer is one of the leading death causes worldwide, but, fortunately, early detection highly increases survival rates, with the adenoma detection rate being one surrogate marker for colonoscopy quality. Artificial intelligence and deep learning methods have been applied with great success to improve polyp detection and localization and, therefore, the adenoma detection rate. In this regard, a comparison with clinical experts is required to prove the added value of the systems. Nevertheless, there is no standardized comparison in a laboratory setting before their clinical validation. The ClinExpPICCOLO comprises 65 unedited endoscopic images that represent the clinical setting. They include white light imaging and narrow band imaging, with one third of the images containing a lesion but, differently to another public datasets, the lesion does not appear well-centered in the image. Together with the dataset, an expert clinical performance baseline has been established with the performance of 146 gastroenterologists, who were required to locate the lesions in the selected images. Results shows statistically significant differences between experience groups. Expert gastroenterologists’ accuracy was 77.74, while sensitivity and specificity were 86.47 and 74.33, respectively. These values can be established as minimum values for a DL method before performing a clinical trial in the hospital setting. Full article

Neuroendocrine neoplasms (NENs), also called neuroendocrine tumors (NETs), are relatively uncommon, heterogenous tumors primarily originating in the gastrointestinal tract. With the improvement in technology and increasing use of cross-sectional imaging and endoscopy, they are being discovered with increasing frequency. Although traditionally considered indolent tumors with good prognoses, some NENs exhibit aggressive behavior. Timely diagnosis, risk stratification, and management can often be a challenge. In general, small NENs without local invasion or lymphovascular involvement can often be managed using minimally invasive advanced endoscopic techniques, while larger lesions and those with evidence of lymphovascular invasion require surgery, systemic therapy, or a combination thereof. Ideal management requires a comprehensive and accurate understanding of the stage and grade of the tumor. With the recent advancements, a therapeutic advanced endoscopist can play a pivotal role in diagnosing, staging, and managing this rare condition. High-definition white light imaging and digital image enhancing technologies like narrow band imaging (NBI) in the newer endoscopes have improved the diagnostic accuracy of traditional endoscopy. The refinement of endoscopic ultrasound (EUS) over the past decade has revolutionized the role of endoscopy in diagnosing and managing various pathologies, including NENs. In addition to EUS-directed diagnostic biopsies, it also offers the ability to precisely assess the depth of invasion and lymphovascular involvement and thus stage NENs accurately. EUS-directed locoregional ablative therapies are increasingly recognized as highly effective, minimally invasive treatment modalities for NENs, particularly pancreatic NENs. Advanced endoscopic resection techniques like endoscopic submucosal dissection (ESD), endoscopic submucosal resection (EMR), and endoscopic full-thickness resection (EFTR) have been increasingly used over the past decade with excellent results in achieving curative resection of various early-stage gastrointestinal luminal lesions including NENs. In this article, we aim to delineate NENs of the different segments of the gastrointestinal (GI) tract (esophagus, gastric, pancreatic, and small and large intestine) and their management with emphasis on the endoscopic management of these tumors. Full article

Precision glass molding (PGM) is an efficient process used for manufacturing high-precision micro lenses with aspheric surfaces, which are key components in high-resolution systems, such as endoscopes. In PGM, production costs are significantly influenced by the lifetimes of elaborately manufactured molding tools. Protective coatings are applied to the molding tools to withstand severe cyclic thermochemical and thermomechanical loads in the PGM process and, in this way, extend the life of the molding tools. This research focuses on a new method which combines metallographic analysis and finite element method (FEM) simulation to study the interaction of three protective coatings—diamond-like carbon (DLC), PtIr and CrAlN—each in contact with the high Abbe number glass material S-FPM3 in a precision glass molding process. Molding tools are analyzed metallographically using light microscopy, white light interferometry, scanning electron microscopy (SEM), and energy dispersive X-ray spectroscopy (EDX). The results show that the DLC coating improved process durability more than the PtIr and CrAlN coatings, in which the phenomenon of coating delamination and glass adhesion can be observed. To identify potential explanations for the metrological results, FEM is applied to inspect the stress state and stress distribution in the molding tools during the molding process. Full article

Early detection of esophageal cancer through endoscopic imaging is pivotal for effective treatment. However, the intricacies of endoscopic diagnosis, contingent on the physician’s expertise, pose challenges. Esophageal cancer features often manifest ambiguously, leading to potential confusions with other inflammatory esophageal conditions, thereby complicating diagnostic accuracy. In recent times, computer-aided diagnosis has emerged as a promising solution in medical imaging, particularly within the domain of endoscopy. Nonetheless, contemporary AI-based diagnostic models heavily rely on voluminous data sources, limiting their applicability, especially in scenarios with scarce datasets. To address this limitation, our study introduces novel data training strategies based on transfer learning, tailored to optimize performance with limited data. Additionally, we propose a hybrid model integrating EfficientNet and Vision Transformer networks to enhance prediction accuracy. Conducting rigorous evaluations on a carefully curated dataset comprising 1002 endoscopic images (comprising 650 white-light images and 352 narrow-band images), our model achieved exceptional outcomes. Our combined model achieved an accuracy of 96.32%, precision of 96.44%, recall of 95.70%, and f1-score of 96.04%, surpassing state-of-the-art models and individual components, substantiating its potential for precise medical image classification. The AI-based medical image prediction platform presents several advantageous characteristics, encompassing superior prediction accuracy, a compact model size, and adaptability to low-data scenarios. This research heralds a significant stride in the advancement of computer-aided endoscopic imaging for improved esophageal cancer diagnosis. Full article

Temperature sensors, such as Fiber Bragg Grating (FBG) and thermocouple (TC), have been widely used for monitoring the interstitial tissue temperature during laser irradiation. The aim of the current study was to compare the performance of both FBG and TC in real-time temperature monitoring during endoscopic and circumferential laser treatment on tubular tissue structure. A 600-µm core-diameter diffusing applicator was employed to deliver 980-nm laser light (30 W for 90 s) circumferentially for quantitative evaluation. The tip of the TC was covered with a white tube (W-TC) in order to prevent direct light absorption and to minimize temperature overestimation. The temperature measurements in air demonstrated that the measurement difference in the temperature elevations was around 3.5 °C between FBG and W-TC. Ex vivo porcine liver tests confirmed that the measurement difference became lower (less than 1 °C). Ex vivo porcine esophageal tissue using a balloon-integrated catheter exhibited that both FBG and W-TC consistently showed a comparable trend of temperature measurements during laser irradiation (~2 °C). The current study demonstrated that the white tube-covered TC could be a feasible sensor to monitor interstitial tissue temperature with minimal overestimation during endoscopic laser irradiation. Further in vivo studies on gastroesophageal reflux disease will investigate the performance of the W-TC to monitor the temperature of the esophageal mucosa surface in real-time mode to warrant the safety of endoscopic laser treatment. Full article