Clinically Available Optical Imaging Technologies in Endoscopic Lesion Detection: Current Status and Future Perspective

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.

Comprehensive advancement in endoscopy: optical design, algorithm enhancement, and clinical validation for merged WLI and CBI imaging

As endoscopic imaging technology advances, there is a growing clinical demand for enhanced imaging capabilities. Although conventional white light imaging (WLI) endoscopy offers realistic images, it often cannot reveal detailed characteristics of the mucosa. On the other hand, optical staining endoscopy, such as Compound Band Imaging (CBI), can discern subtle structures, serving to some extent as an optical biopsy. However, its image brightness is low, and the colors can be abrupt. These two techniques, commonly used in clinical settings, have complementary advantages. Nonetheless, they require different lighting conditions, which makes it challenging to combine their imaging strengths on living tissues. In this study, we introduce a novel endoscopic imaging technique that effectively combines the advantages of both WLI and CBI. Doctors don't need to manually switch between these two observation modes, as they can obtain the image information of both modes in one image. We calibrated an appropriate proportion for simultaneous illumination with the light required for WLI and CBI. We designed a new illumination spectrum tailored for gastrointestinal examination, achieving their fusion at the optical level. Using a new algorithm that focuses on enhancing specific hemoglobin tissue features, we restored narrow-band image characteristics lost due to the introduction of white light. Our hardware and software innovations not only boost the illumination brightness of the endoscope but also ensure the narrow-band feature details of the image. To evaluate the reliability and safety of the new endoscopic system, we conducted a series of tests in line with relevant international standards and validated the design parameters. For clinical trials, we collected a total of 256 sets of images, each set comprising images of the same lesion location captured using WLI, CBI, and our proposed method. We recruited four experienced clinicians to conduct subjective evaluations of the collected images. The results affirmed the significant advantages of our method. We believe that the novel endoscopic system we introduced has vast potential for clinical application in the future.

Deep learning-based anatomical position recognition for gastroscopic examination

BACKGROUND

The gastroscopic examination is a preferred method for the detection of upper gastrointestinal lesions. However, gastroscopic examination has high requirements for doctors, especially for the strict position and quantity of the archived images. These requirements are challenging for the education and training of junior doctors.

OBJECTIVE

The purpose of this study is to use deep learning to develop automatic position recognition technology for gastroscopic examination.

METHODS

A total of 17182 gastroscopic images in eight anatomical position categories are collected. Convolutional neural network model MogaNet is used to identify all the anatomical positions of the stomach for gastroscopic examination The performance of four models is evaluated by sensitivity, precision, and F1 score.

RESULTS

The average sensitivity of the method proposed is 0.963, which is 0.074, 0.066 and 0.065 higher than ResNet, GoogleNet and SqueezeNet, respectively. The average precision of the method proposed is 0.964, which is 0.072, 0.067 and 0.068 higher than ResNet, GoogleNet, and SqueezeNet, respectively. And the average F1-Score of the method proposed is 0.964, which is 0.074, 0.067 and 0.067 higher than ResNet, GoogleNet, and SqueezeNet, respectively. The results of the t-test show that the method proposed is significantly different from other methods (p< 0.05).

CONCLUSION

The method proposed exhibits the best performance for anatomical positions recognition. And the method proposed can help junior doctors meet the requirements of completeness of gastroscopic examination and the number and position of archived images quickly.

Value of needle confocal laser microendoscopy combined with endobronchial ultrasound bronchoscopy in the diagnosis of hilar and mediastinal lymph node lesions

Endobronchial ultrasound bronchoscopy (EBUS) and needle confocal laser endomicroscopy (nCLE) are techniques for screening benign and malignant lesions of the hilar and mediastinal lymph node (HMLN). This study investigated the diagnostic potential of EBUS, nCLE, and combined EBUS and nCLE in HMLN lesions. We recruited 107 patients with HMLN lesions who were examined by EBUS and nCLE. A pathological examination was performed, and the diagnostic potential of EBUS, nCLE, and combined EBUS-nCLE approach was analyzed according to the results. Among the 107 cases of HMLN lesions, 43 cases were benign and 64 cases were malignant on pathological examination, 41 cases were benign and 66 cases were malignant on EBUS examination; 42 cases were benign and 65 cases were malignant on nCLE examination; 43 cases were benign and 64 cases were malignant on combined EBUS-nCLE examination. The combination approach had 93.8% sensitivity, 90.7% specificity, and 0.922 area under the curve, which was higher than those of EBUS (84.4%, 72.1%, and 0.782, respectively) and nCLE diagnosis (90.6%, 83.7%, and 0.872, respectively). The combination approach had a higher positive predictive value (0.908), negative predictive value (0.881), and positive likelihood ratio (10.09) than that of EBUS (0.813, 0.721, and 3.03, respectively) and nCLE (0.892, 0.857, and 5.56, respectively), whereas, the negative likelihood ratio was lower than that for EBUS (0.22) and nCLE (0.11). No serious complications occurred in patients with HMLN lesions. To summarize, the diagnostic efficacy of nCLE was better than EBUS. The EBUS-nCLE combination is a suitable approach for diagnosing HMLN lesions.

Systematic meta-analysis of computer-aided detection to detect early esophageal cancer using hyperspectral imaging

One of the leading causes of cancer deaths is esophageal cancer (EC) because identifying it in early stage is challenging. Computer-aided diagnosis (CAD) could detect the early stages of EC have been developed in recent years. Therefore, in this study, complete meta-analysis of selected studies that only uses hyperspectral imaging to detect EC is evaluated in terms of their diagnostic test accuracy (DTA). Eight studies are chosen based on the Quadas-2 tool results for systematic DTA analysis, and each of the methods developed in these studies is classified based on the nationality of the data, artificial intelligence, the type of image, the type of cancer detected, and the year of publishing. Deeks' funnel plot, forest plot, and accuracy charts were made. The methods studied in these articles show the automatic diagnosis of EC has a high accuracy, but external validation, which is a prerequisite for real-time clinical applications, is lacking.

The development and clinical application of microscopic endoscopy for in vivo optical biopsies: Endocytoscopy and confocal laser endomicroscopy

Endoscopies are crucial for detecting and diagnosing diseases in gastroenterology, pulmonology, urology, and other fields. To accurately diagnose diseases, sample biopsies are indispensable and are currently considered the gold standard. However, random 4-quadrant biopsies have sampling errors and time delays. To provide intraoperative real-time microscopic images of suspicious lesions, microscopic endoscopy for in vivo optical biopsy has been developed, including endocytoscopy and confocal laser endomicroscopy. This article reviews recent advances in technology and clinical applications, as well as their shortcomings and future directions.

Role of Macroscopic Image Enhancement in Diagnosis of Non-Muscle-Invasive Bladder Cancer: An Analytical Review

Early diagnosis of non-muscle-invasive bladder cancer (NMIBC) is of paramount importance to prevent morbidity and mortality due to bladder cancer. Although white light imaging (WLI) cystoscopy has long been considered the gold standard in the diagnosis of bladder cancer, it can miss lesions in a substantial percentage of patients and is very likely to miss carcinoma in situ and dysplasia. Tumor margin detection by WLI can be inaccurate. Moreover, WLI could, sometimes, be inadequate in distinguishing inflammation and malignancy. To improve the diagnostic efficacy of cystoscopy, various optical image enhancement modalities have been studied. These image enhancement modalities have been classified as macroscopic, microscopic, or molecular. Photodynamic diagnosis (PDD), narrow band imaging (NBI), and Storz image 1 S enhancement (formerly known as SPIES) are macroscopic image enhancement modalities. A relevant search was performed for literature describing macroscopic image enhancement modalities like PDD, NBI, and image 1 S enhancement. The advantages, limitations, and usefulness of each of these in the diagnosis of bladder cancer were studied. Photodynamic diagnosis requires intravesical instillation of a photosensitizing agent and a special blue light cystoscope system. PDD has been shown to be more sensitive than WLI in the detection of bladder cancer. It is superior to WLI in the detection of flat lesions. Bladder tumor resection (TURBT) by PDD results in more complete resection and reduced recurrence rates. PDD-guided TURBT may have some role in reducing the risk of progression. Narrow band imaging provides increased contrast between normal and abnormal tissues based on neovascularization, thereby augmenting WLI. NBI requires a special light source. There is no need for intravesical contrast instillation. NBI is superior to WLI in the detection of bladder cancer. The addition of NBI to WLI improves the detection of flat lesions like carcinoma in situ. NBI is not useful in predicting invasive tumors or grades of tumors. NBI-directed TURBT reduces recurrence rates and recurrence free survival. But its efficacy in retarding progression is unproven. Image 1 S-enhancement utilizes software-based image enhancement modes without the need for a special light source or intravesical contrast instillation. This system provides high-quality images and identifies additional abnormal-looking areas. Another advantage of this system is simultaneous side-by-side visualization of WLI and enhanced image, providing WLI images as the control for comparison. As with PDD, S-enhancement produces a lower rate of a missed bladder cancer diagnosis. The system significantly improves the diagnosis of NMIBC. The sensitivity and negative predictive value of image 1 S enhancement increase with the increase in cancer grade. A negative test by S-enhancement effectively rules out NMIBC. All the image enhancement modalities have proven their utility in improving detection and short-term cancer control. But none of these modalities have proven their utility in delaying progression, or in long-term cancer control. Cancer progression and long-term control are governed by the biological nature of cancer cells. Early detection by optical enhancement may not be of utility in this regard. Well-designed studies are needed to establish the efficacy of these modalities in the evaluation of patients with bladder cancer. The last word, in this regard, is yet to be written.