Assessment of Narrow-Band Imaging Algorithm for Video Capsule Endoscopy Based on Decorrelated Color Space for Esophageal Cancer: Part II, Detection and Classification of Esophageal Cancer.

Esophageal carcinoma (EC) is a prominent contributor to cancer-related mortality since it lacks discernible features in its first phases. Multiple studies have shown that narrow-band imaging (NBI) has superior accuracy, sensitivity, and specificity in detecting EC compared to white light imaging (WLI). Thus, this study innovatively employs a color space linked to décor to transform WLIs into NBIs, offering a novel approach to enhance the detection capabilities of EC in its early stages. In this study a total of 3415 WLI along with the corresponding 3415 simulated NBI images were used for analysis combined with the YOLOv5 algorithm to train the WLI images and the NBI images individually showcasing the adaptability of advanced object detection techniques in the context of medical image analysis. The evaluation of the model's performance was based on the produced confusion matrix and five key metrics: precision, recall, specificity, accuracy, and F1-score of the trained model. The model underwent training to accurately identify three specific manifestations of EC, namely dysplasia, squamous cell carcinoma (SCC), and polyps demonstrates a nuanced and targeted analysis, addressing diverse aspects of EC pathology for a more comprehensive understanding. The NBI model effectively enhanced both its recall and accuracy rates in detecting dysplasia cancer, a pre-cancerous stage that might improve the overall five-year survival rate. Conversely, the SCC category decreased its accuracy and recall rate, although the NBI and WLI models performed similarly in recognizing the polyp. The NBI model demonstrated an accuracy of 0.60, 0.81, and 0.66 in the dysplasia, SCC, and polyp categories, respectively. Additionally, it attained a recall rate of 0.40, 0.73, and 0.76 in the same categories. The WLI model demonstrated an accuracy of 0.56, 0.99, and 0.65 in the dysplasia, SCC, and polyp categories, respectively. Additionally, it obtained a recall rate of 0.39, 0.86, and 0.78 in the same categories, respectively. The limited number of training photos is the reason for the suboptimal performance of the NBI model which can be improved by increasing the dataset.

Artificial intelligence predicts direct-acting antivirals failure among hepatitis C virus patients: A nationwide hepatitis C virus registry program.

BACKGROUND/AIMS: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1-3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy. METHODS: We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment. RESULTS: The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset. CONCLUSION: Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.

An algorithm for simplified hepatitis C virus treatment with non-specialist care based on nation-wide data from Taiwan.

BACKGROUND: Both European Association for the Study of the Liver (EASL) and American Association for the Study of Liver Diseases and the Infectious Diseases Society of America (AASLD-IDSA) guidelines recommend simplified hepatitis C virus (HCV) treatment with pan-genotypic sofosbuvir/velpatasvir or glecaprevir/pibrentasvir for eligible patients. This observational study used real-world data to assess these regimens' safety in eligible patients and develop an algorithm to identify patients suitable for simplified treatment by non-specialists. METHODS: 7,677 HCV-infected patients from Taiwan Hepatitis C Registry (TACR) who received at least one dose of sofosbuvir/velpatasvir or glecaprevir/pibrentasvir, and fulfilled the EASL/AASLD-IDSA criteria for simplified treatment were analyzed. Multivariate analysis was conducted on patient characteristics and safety data. RESULTS: Overall, 92.8% (7,128/7,677) of patients achieved sustained virological response and only 1.9% (146/7,677) experienced Grades 2-4 laboratory abnormalities in key liver function parameters (alanine aminotransferase, aspartate aminotransferase, and total bilirubin), with only 18 patients (0.23%) experiencing Grades 3-4 abnormalities. Age > 70 years old, presence of hepatocellular carcinoma, total bilirubin > 1.2 mg/dL, estimated glomerular filtration rate < 60 mL/min/1.73 m2, and Fibrosis-4 > 3.25 were associated with higher risks of Grades 2-4 abnormalities. Patients with any of these had an odds of 4.53 times than that of those without in developing Grades 2-4 abnormalities (p < 0.01). CONCLUSIONS: Real-world data from Taiwan confirmed that simplified HCV treatment for eligible patients with pan-genotypic regimens is effective and well tolerated. The TACR algorithm, developed based on this study's results, can further identify patients who can be safely managed by non-specialist care.

Assessment of hyperspectral imaging and CycleGAN-simulated narrowband techniques to detect early esophageal cancer.

The clinical signs and symptoms of esophageal cancer (EC) are often not discernible until the intermediate or advanced phases. The detection of EC in advanced stages significantly decreases the survival rate to below 20%. This study conducts a comparative analysis of the efficacy of several imaging techniques, including white light image (WLI), narrowband imaging (NBI), cycle-consistent adversarial network simulated narrowband image (CNBI), and hyperspectral imaging simulated narrowband image (HNBI), in the early detection of esophageal cancer (EC). In conjunction with Kaohsiung Armed Forces General Hospital, a dataset consisting of 1000 EC pictures was used, including 500 images captured using WLI and 500 images captured using NBI. The CycleGAN model was used to generate the CNBI dataset. Additionally, a novel method for HSI imaging was created with the objective of generating HNBI pictures. The evaluation of the efficacy of these four picture types in early detection of EC was conducted using three indicators: CIEDE2000, entropy, and the structural similarity index measure (SSIM). Results of the CIEDE2000, entropy, and SSIM analyses suggest that using CycleGAN to generate CNBI images and HSI model for creating HNBI images is superior in detecting early esophageal cancer compared to the use of conventional WLI and NBI techniques.

Assessment of Narrow Band Imaging Algorithm for Video Capsule Endoscopy Based on Decorrelated Color Space for Esophageal Cancer.

Video capsule endoscopy (VCE) is increasingly used to decrease discomfort among patients owing to its small size. However, VCE has a major drawback of not having narrow band imaging (NBI) functionality. The current VCE has the traditional white light imaging (WLI) only, which has poor performance in the computer-aided detection (CAD) of different types of cancer compared to NBI. Specific cancers, such as esophageal cancer (EC), do not exhibit any early biomarkers, making their early detection difficult. In most cases, the symptoms are unnoticeable, and EC is diagnosed only in later stages, making its 5-year survival rate below 20% on average. NBI filters provide particular wavelengths that increase the contrast and enhance certain features of the mucosa, thereby enabling early identification of EC. However, VCE does not have a slot for NBI functionality because its size cannot be increased. Hence, NBI image conversion from WLI can presently only be achieved in post-processing. In this study, a complete arithmetic assessment of the decorrelated color space was conducted to generate NBI images from WLI images for VCE of the esophagus. Three parameters, structural similarity index metric (SSIM), entropy, and peak-signal-to-noise ratio (PSNR), were used to assess the simulated NBI images. Results show the good performance of the NBI image reproduction method with SSIM, entropy difference, and PSNR values of 93.215%, 4.360, and 28.064 dB, respectively.

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.

Preparing Well for Esophageal Endoscopic Detection Using a Hybrid Model and Transfer Learning.

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.

IgG4-Related Disease Mimicking Unilateral Urothelial Carcinoma: A Rare Case Report and Literature Review.

Immunoglobulin G4-related disease (IgG4-RD) is an autoimmune-mediated disorder with heterogeneous multiorgan manifestations. Early identification and treatment of IgG4-RD are crucial for organ function recovery. Rarely, IgG4-RD manifests as a unilateral renal pelvic soft tissue mass that may be misdiagnosed as urothelial malignancy, resulting in invasive surgical intervention and organ damage. Here we present a 73-year-old man who had a right ureteropelvic mass with hydronephrosis detected by enhanced computed tomography. Right upper tract urothelial carcinoma and lymph node metastasis was highly suggested based on the image findings. However, IgG4-RD was suspected due to his past history of bilateral submandibular lymphadenopathy, nasolacrimal duct obstruction, as well as a high serum IgG4 level of 861 mg/dL. The ureteroscopy with tissue biopsy showed no evidence of urothelial malignancy. His lesions and symptoms improved after glucocorticoid treatment. Hence, a diagnosis of IgG4-RD was made, with the phenotype of classic Mikulicz syndrome with systemic involvement. The manifestation of IgG4-RD as a unilateral renal pelvic mass is rare and should be kept in mind. A ureteroscopic biopsy and serum IgG4 level measurement can help in the diagnosis of IgG4-RD in patients with a unilateral renal pelvic lesion.

Treatment effectiveness and side effects of patients with hepatitis C in the prisons of Southern Taiwan: a real-life retrospective analysis.

OBJECTIVE: Hepatitis C is an important risk factor for cirrhosis and liver cancer in the Taiwanese population. Domestic prisons reported a higher rate of hepatitis C infection than the national average. Efficient and effective treatment of patients with hepatitis C in prisons is required to decrease the number of infections. This study analysed the effectiveness of hepatitis C treatment and its side effects in prison patients. DESIGN: This retrospective analysis included adult patients with hepatitis C who received direct-acting antiviral agents between 2018 and 2021. SETTING: The special hepatitis C clinics in the two prisons were run by a medium-sized hepatitis C treatment hospital in Southern Taiwan. Three direct-acting antiviral agents, sofosbuvir/ledipasvir for 12 weeks, glecaprevir/pibrentasvir for 8 or 12 weeks and sofosbuvir/velpatasvir for 12 weeks, were adopted based on patient characteristics. PARTICIPANTS: 470 patients were included. OUTCOME MEASURE: The sustained virological response at 12 weeks after the end of treatment was compared between the different groups. RESULTS: Most of the patients were men (70.0%) with a median age of 44 years. The most prevalent hepatitis C virus genotype was genotype 1 (44.26%). A total of 240 patients (51.06%) had a history of injectable drug use; 44 (9.36%) and 71 (15.11%) patients were coinfected with hepatitis B virus and HIV, respectively. Only 51 patients (10.85%) had liver cirrhosis. Most patients (98.30%) had normal renal function or no history of kidney disease. The patients had a sustained virological response achievement rate of 99.2%. The average incidence of adverse reactions during treatment was approximately 10%. Many of the adverse reactions were mild and resolved spontaneously. CONCLUSION: Direct-acting antiviral agents are effective for treating hepatitis C in Taiwanese prisoners. These therapeutics were well-tolerated by the patient population.

Tensins in Kidney Function and Diseases.

Tensins are focal adhesion proteins that regulate various biological processes, such as mechanical sensing, cell adhesion, migration, invasion, and proliferation, through their multiple binding activities that transduce critical signals across the plasma membrane. When these molecular interactions and/or mediated signaling are disrupted, cellular activities and tissue functions are compromised, leading to disease development. Here, we focus on the significance of the tensin family in renal function and diseases. The expression pattern of each tensin in the kidney, their roles in chronic kidney diseases, renal cell carcinoma, and their potentials as prognostic markers and/or therapeutic targets are discussed in this review.

Trends in the incidence of urothelial carcinoma in Taiwan after the ban on aristolochic acid-containing Chinese herbal preparations, 2001-2018: a national population-based cohort study.

PURPOSE: Urothelial carcinoma (UC) of the bladder (BUC) and the upper urinary tract (UTUC) are the two most common UCs. The incidence of UTUC in Taiwan is the highest worldwide. Aristolochic acid (AA) was identified as the main cause of UTUC in Taiwan. To explore trends in the incidence of UC in Taiwan after the ban on Chinese herbal preparations containing AA in 2003. METHODS: We used data from the Taiwanese National Health Insurance Research Database-linked Taiwanese National Cancer Registry for 2001-2018. UC was defined in accordance with the International Classification of Disease for Oncology. The age-standardized incidence was calculated on the basis of the World Health Organization standard population. Trends in the incidence were calculated as the annual percent change (APC) by using the Joinpoint regression program. RESULTS: Over the investigated period, the incidence of UC decreased at an average annual percent change (AAPC) of - 1.19% (95% CI - 1.47 ~ - 0.91, P < 0.001). However, the incidence in UTUC significantly increased, with the AAPC being 1.47% (95% CI 1.03 ~ 1.90, P < 0.001). In contrast, the incidence of BUC significantly decreased, with the overall AAPC being - 1.92% (95% CI - 2.3 ~ - 1.54, P < 0. 001). From 2001 to 2018, the overall incidence of UCs and BUC decreased in Taiwan, but the incidence of UTUC significantly increased. CONCLUSION: We suggest to apply the same review standards of new drug development process to herbal preparations and incorporate them into the adverse drug reaction or poison surveillance system. Most importantly, raise public awareness of the potential toxicity of phytotherapy.

Characterization of polysulfides in Saccharomyces cerevisiae cells and finished wine from a cysteine-supplemented model grape medium.

Polysulfide degradation in wine can result in hydrogen sulfide (H2S) release, imparting a rotten-egg smell that is detrimental to wine quality. Although the presence of wine polysulfides has been demonstrated, their biogenesis remains unclear. This study investigated the role of Saccharomyces cerevisiae in polysulfide formation during fermentation, with and without 5 mM cysteine supplementation as an H2S source. Using an established liquid chromatography-tandem mass spectrometry method, monobromobimane derivatives of hydropolysulfides, including CysSSSH, CysSSSSH and GSSSSH, and two oxidized polysulfides, GSSG and GSSSSG, were detected in yeast cells at the end of fermentation in a grape juice-like medium. Polysulfide production by four S. cerevisiae single deletion mutants (BY4743 Δcys3, Δcys4, Δmet17 and Δtum1) showed no significant differences compared to BY4743, suggesting that uncharacterized pathways maintain cellular polysulfide homeostasis. Five mM cysteine addition increased the formation of shorter sulfur chain species, including GSS-bimane and GSSG, but did not elevate levels of longer sulfur chain species. Additionally, polysulfides with even numbers of sulfur atoms tended to predominate in cellular lysates. Oxidized polysulfides and longer chain hydropolysulfides were not detected in finished wines. This evidence suggests that these polysulfides are unstable in wine-like environments or not transported extracellularly. Collectively, our data illustrate the complexity of yeast polysulfide metabolism under fermentation conditions.

Infectious complications in adult patients with idiopathic minimal change nephrotic syndrome undergoing immunosuppressive therapy.

BACKGROUND: Patients with idiopathic minimal change nephrotic syndrome (MCNS) undergoing immunosuppressive therapy are susceptible to infectious complications. Study specifically focusing on adult population's infectious complications is lacking. METHODS: We retrospectively collected 101 adult patients with biopsy-proven idiopathic MCNS and analysed for the infectious complications. Published literatures were also reviewed aiming to evaluate the feasibility of prophylactic antibiotic treatment. RESULTS: Infectious complications developed in 17 of 101 (16.8%) patients, with pneumonia (n = 4), cellulitis/fasciitis (n = 4) and urinary tract infection (UTI) (n = 4) being the dominant diseases, and Gram-negative bacilli the main cause. AKI stage ≥2 (Hazard ratio = 6.1; 95% CI: 1.2-31.9, p = 0.031) and non-remission by treatment (Hazard ratio = 4.4; 95% CI: 1.2-15.6, p = .023) were the two independent risk factors relevant to developing infectious complications. Review of 16 published literatures and our data showed that even no prophylactic antibiotic therapy, only one case of Pneumocystis jirovecii pneumonia developed among the 1787 accumulative cases of MCNS. In contrast, 16 (44%) of acute flare cases were reported among the 36 patients with positive hepatitis B surface antigen that did not receive antiviral prophylactic therapy. CONCLUSIONS: Advanced acute kidney injury and non-remission by treatment are the risk factors toward developing infectious complications in adult MCNS undergoing immunosuppressive therapy. It appears unnecessary to use prophylactic antibiotic for Pneumocystis jirovecii pneumonia or other bacterial infections, while screening and prophylactic therapy for hepatitis B and latent tuberculosis are critical for patients in prevalent area.

Intelligent Identification of Early Esophageal Cancer by Band-Selective Hyperspectral Imaging.

In this study, the combination of hyperspectral imaging (HSI) technology and band selection was coupled with color reproduction. The white-light images (WLIs) were simulated as narrow-band endoscopic images (NBIs). As a result, the blood vessel features in the endoscopic image became more noticeable, and the prediction performance was improved. In addition, a single-shot multi-box detector model for predicting the stage and location of esophageal cancer was developed to evaluate the results. A total of 1780 esophageal cancer images, including 845 WLIs and 935 NBIs, were used in this study. The images were divided into three stages based on the pathological features of esophageal cancer: normal, dysplasia, and squamous cell carcinoma. The results showed that the mean average precision (mAP) reached 80% in WLIs, 85% in NBIs, and 84% in HSI images. This study's results showed that HSI has more spectral features than white-light imagery, and it improves accuracy by about 5% and matches the results of NBI predictions.

Identification of Early Esophageal Cancer by Semantic Segmentation.

Early detection of esophageal cancer has always been difficult, thereby reducing the overall five-year survival rate of patients. In this study, semantic segmentation was used to predict and label esophageal cancer in its early stages. U-Net was used as the basic artificial neural network along with Resnet to extract feature maps that will classify and predict the location of esophageal cancer. A total of 75 white-light images (WLI) and 90 narrow-band images (NBI) were used. These images were classified into three categories: normal, dysplasia, and squamous cell carcinoma. After labeling, the data were divided into a training set, verification set, and test set. The training set was approved by the encoder-decoder model to train the prediction model. Research results show that the average time of 111 ms is used to predict each image in the test set, and the evaluation method is calculated in pixel units. Sensitivity is measured based on the severity of the cancer. In addition, NBI has higher accuracy of 84.724% when compared with the 82.377% accuracy rate of WLI, thereby making it a suitable method to detect esophageal cancer using the algorithm developed in this study.

Erythropoiesis-stimulating agents and incident malignancy in chronic kidney and end-stage renal disease: A population-based study.

Research investigating incident malignancy risk in erythropoiesis-stimulating agent (ESA) users with chronic kidney disease (CKD) is lacking. We aimed to compare the incident cancer risk between ESA and non-ESA users with CKD or end-stage renal disease (ESRD). In this retrospective cohort study, all adults newly diagnosed with CKD or ESRD between 2000 and 2012 were enrolled. The study population included 98,748 patients. After case-control matching, 7115 patients were included. The defined daily dose (DDD) of ESA was used as the unit for measuring the amount of ESA prescribed. The primary outcome was the risk of incident malignancy. The secondary outcomes were incident malignancy risk in different tertiles of cumulative ESA doses and the risk of different types of cancers. The risk of incident malignancy was 1.84 times higher with ESA treatment than without ESA treatment (hazard ratio, 1.84; 95% confidence interval, 1.43-2.36; p < 0.001). The malignancy risk was positively correlated with the cumulative dose of ESA (p-for-trend = 0.001) and a significant difference in the high annual cumulative DDD cohort (hazard ratio [HR], 2.39; 95% confidence interval [CI], 1.76-3.25; p < 0.001). The risk of genitourinary malignancy was 12.55 times higher with ESA treatment than without ESA treatment (HR, 12.55; 95% CI, 5.78-27.24; p < 0.001). ESA usage is associated with an increased risk of malignancy, particularly genitourinary cancers, in patients with CKD or ESRD. Clinicians should be aware of the occurrence of malignancy, and keep ESA dosage as low as possible.

Adenine Inhibits the Invasive Potential of DLD-1 Human Colorectal Cancer Cell via the AMPK/FAK Axis.

Tumor metastasis is a major cause of death of patients with colorectal cancer (CRC). Our previous findings show that adenine has antiproliferation activity against tumor cells. However, whether adenine reduces the invasiveness of DLD-1 and SW480 CRC cells has not been thoroughly explored. In this study, we aimed to explore the effects of adenine on the invasion potential of DLD-1 cells. Our findings showed that adenine at concentrations of ≤200 µM did not influence the cell viability of DLD-1 and SW480 CRC cells. By contrast, adenine reduced the migratory potential of the CRC cells. Moreover, it decreased the invasion capacity of the CRC cells in a dose-dependent manner. We further observed that adenine downregulated the protein levels of tissue plasminogen activator, matrix metalloproteinase-9, Snail, TWIST, and vimentin, but upregulated the tissue inhibitor of metalloproteinase-1 expression in DLD-1 cells. Adenine decreased the integrin αV level and reduced the activation of integrin-associated signaling components, including focal adhesion kinase (FAK), paxillin, and Src in DLD-1 cells. Further observations showed that adenine induced AMP-activated protein kinase (AMPK) activation and inhibited mTOR phosphorylation in DLD-1 cells. The knockdown of AMPK restored the reduced integrin αV level and FAK/paxillin/Src signaling inhibited by adenine in DLD-1 cells. Collectively, these findings reveal that adenine reduces the invasion potential of DLD-1 cells through the AMPK/integrin/FAK axis, suggesting that adenine may have anti-metastatic potential in CRC cells.

Hyperspectral Imaging Combined with Artificial Intelligence in the Early Detection of Esophageal Cancer.

This study uses hyperspectral imaging (HSI) and a deep learning diagnosis model that can identify the stage of esophageal cancer and mark the locations. This model simulates the spectrum data from the image using an algorithm developed in this study which is combined with deep learning for the classification and diagnosis of esophageal cancer using a single-shot multibox detector (SSD)-based identification system. Some 155 white-light endoscopic images and 153 narrow-band endoscopic images of esophageal cancer were used to evaluate the prediction model. The algorithm took 19 s to predict the results of 308 test images and the accuracy of the test results of the WLI and NBI esophageal cancer was 88 and 91%, respectively, when using the spectral data. Compared with RGB images, the accuracy of the WLI was 83% and the NBI was 86%. In this study, the accuracy of the WLI and NBI was increased by 5%, confirming that the prediction accuracy of the HSI detection method is significantly improved.