Explore more content after your registration

Lavender Color in Linked Color Imaging Enables Noninvasive Detection of Gastric Intestinal Metaplasia.

Ono S1, Kato M1, Tsuda M1, Miyamoto S1, Abiko S1, Shimizu Y1, Sakamoto N1

Digestion. 2018 Jul 25;98(4):222-230. doi: 10.1159/000489454

Background and aims: Recently, there have been some reports that image-enhanced endoscopy may improve detection of gastric intestinal metaplasia (GIM). Our aim was to determine the usefulness of linked color imaging (LCI) for detection of GIM.

Methods: In prospectively recruited patients, the whole antrum was observed by white light imaging (WLI) followed by LCI. When a whitish flat elevation (WFE) in WLI and a lavender color sign (LCS) in LCI were detected, target biopsies were performed after LCI. Random biopsies were performed in patients who had neither WFE nor LCS. The primary endpoint was the diagnostic accuracy of GIM per patient in WLI and LCI and the secondary endpoints were that of GIM per biopsy and interobserver agreement.

Results: Data from 128 patients were analyzed and 58 patients (45.3%) had histological GIM in the antrum. The per-patient yields of WLI and LCI to detect GIM were 19.0% (11/58) and 91.4% (53/58) respectively. Diagnostic accuracies of target biopsies for GIM were 23.7% in WLI and 84.2% in LCI. Kappa values among 3 doctors were 0.60 for WFE and 0.78 for LCS respectively.

Conclusion: LCI could be a new diagnostic tool for detecting GIM during routine endoscopy.

1 Division of Endoscopy, Hokkaido University Hospital, Sapporo, Japan

Artificial intelligence diagnosis of Helicobacter pylori infection using blue laser imaging-bright and linked color imaging: a single-center prospective study.

Nakashima H1, Kawahira H2, Kawachi H3, Sakaki N1.

Ann Gastroenterol. 2018 Jul-Aug;31(4):462-468. doi: 10.20524/aog.2018.0269. Epub 2018 May 3.

Background: Deep learning is a type of artificial intelligence (AI) that imitates the neural network in the brain. We generated an AI to diagnose Helicobacter pylori (H. pylori) infection using blue laser imaging (BLI)-bright and linked color imaging (LCI). The aim of this pilot study was to establish an AI diagnosing system that predicts H. pylori infection status using endoscopic images to improve the accuracy and productivity of endoscopic examination.

Methods: A total of 222 enrolled subjects (105 H. pylori-positive) underwent esophagogastroduodenoscopy and a serum test for H. pylori IgG antibodies. During esophagogastroduodenoscopy, an endoscopist sequentially took 3 still images of the lesser curvature of the stomach using white light imaging (WLI), BLI-bright, and LCI. EG-L580NW endoscopic equipment (FUJIFILM Co., Japan) was used for the study. The specifications of the AI were as follows: operating system, Linux; neural network, GoogLeNet; framework, Caffe; graphic processor unit, Geforce GTX TITAN X (NVIDIA Co., USA).

Results: The area under the curve (AUC) on receiver operating characteristics analysis was 0.66 for WLI. In contrast, the AUCs of BLI-bright and LCI were 0.96 and 0.95, respectively. The AUCs obtained for BLI-bright and LCI were significantly larger than those for WLI (P<0.01).

Conclusion: The results demonstrate that the developed AI has an excellent ability to diagnose H. pylori infection using BLI-bright and LCI. AI technology with image-enhanced endoscopy is likely to become a useful image diagnostic tool.

1 Foundation for Detection of Early Gastric Carcinoma, Tokyo (Hirotaka Nakashima, Nobuhiro Sakaki)
2 Center for Frontier Medical Engineering, Chiba University, Chiba (Hiroshi Kawahira)
3 Department of Pathology, The Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo (Hiroshi Kawachi), Japan

Ability of blue laser imaging with magnifying endoscopy for the diagnosis of gastric intestinal metaplasia.

Chen H1, Liu Y1, Lu Y1, Lin X1, Wu Q1, Sun J1, Li C1.

Lasers Med Sci. 2018 May 18. doi: 10.1007/s10103-018-2536-3. [Epub ahead of print]

We aimed to determine the utility of blue laser imaging (BLI) with magnifying endoscopy (BLI-ME) for the prediction and diagnosis of gastric intestinal metaplasia (GIM). Participants, aged between 40 and 75 years, undergoing gastroscopy from January to April 2017 were included in this study. The ability of BLI-ME and white light endoscopy (WLE) to detect GIM was assessed by comparing the endoscopic findings with the histological findings. The correlation between the grades of light blue crest (LBC) appearance and histology grade of GIM was calculated. We included 100 participants in this study. GIM was diagnosed in 27 participants; 20 participants were detected by both BLI and WLE, four by BLI only, and three exclusively by random biopsies. The values of sensitivity, specificity, positive predictive values, and negative predictive values for detecting GIM were 34.9, 38.9, 25.4, and 57.1%, respectively, for WLE and 88.9, 96.7, 94.1, and 93.3%, respectively, for BLI-ME. The diagnostic accuracy for GIM was 43% for WLE and 94.0% for BLI-ME. A good correlation between the grades of LBC and the grades of GIM on histology was observed (P < 0.01). BLI-ME achieved a good diagnostic efficiency for detection of GIM. LBC seen on BLI-ME is a typical indicator of GIM.

1 Department of Gastrointestinal Endoscopy, Guangdong Provincial Key Laboratory ofColorectal and Pelvic Floor Diseases, the Sixtli Affiliated Hospital, Sun Yat-sen University, No.26 Yuancun Er Heng Rd, Tianhe Dishict, Guangzhou 510655, Guangdong Province, People’s Republic of China

Linked color imaging can help gastric Helicobacter pylori infection diagnosis during endoscopy.

Chen TH1,2, Hsu CM1, Cheng HT1, Chu YY1, Su MY1, Hsu JT3, Yeh TS3, Kuo CF4, Chiu CT1.

J Chin Med Assoc. 2018 May 16. pii: S1726-4901(18)30096-0. doi: 10.1016/j.jcma.2018.03.006. [Epub ahead of print]

Background: Esophagogastroduodenoscopy (EGD) is a standard tool for detection of mucosal and submucosal lesions. However, identification of Helicobacter pylori (H. P) infection using EGD alone is limited in accuracy. Linked color imaging (LCI) is a novel tool to capture real-time image with sufficient contrast to observe mucosal microstructure.

Methods: This study aims to evaluate the applicability of LCI in the identification of H. pylori infection. Consecutive 122 patients scheduled for EGD were included. They were examined with LCI and magnifying endoscopy. The classification of H. pylori was based on pathology results of biopsy and rapid urease test or urea breath test.

Results: We compared the results based on LCI or magnifying endoscopy to reference classification. Of 122 patients, 36 had H. pylori infection (29.51%). The level of accuracy of diagnosis of H. pylori infections by LCI, magnifying endoscopy, and both LCI and magnifying endoscopy was 78.38%, 81.98%, and 78.38%, respectively. The sensitivity and specificity of each group were 70.97%, 81.25%, and 80.65% and 82.5%, 83.87%, and 76.25%, respectively. The positive predictive values were 59.46%, 64.10%, and 57.78%, respectively, and the negative predictive values were 87.84%, 91.67%, and 92.42%, respectively.

Conclusion: LCI could be playing a valuable initial screen tool for real-time diagnosis of H. pylori infections. It has a high accuracy of diagnosis of H. pylori infections. Therefore, in patients suspected to have H. pylori infections using LCI, the infections need to be carefully diagnosed using appropriate methods because, as per the consensus, they should be eradicated as soon as possible before precancerous lesions develop.

1 Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital- Linkou and Chang Gung University College of Medicine, Taoyuan, Taiwan, ROC
2 Graduate Institute of Clinical Medical Sciences, Chang Gung University, Taoyuan, Taiwan, ROC
3 Department of Surgery, Chang Gung Memorial Hospital-Linkou and Chang Gung University College of Medicine, Taoyuan, Taiwan, ROC
4 Division of Rheumatology, Allergy, and Immunology, Chang Gung Memorial Hospital- Linkou and Chang Gung University College of Medicine, Taoyuan,Taiwan, ROC

Diagnostic ability of blue laser imaging combined with magnifying endoscopy for early esophageal cancer.

Diao W1, Huang X1, Shen L1, Zeng Z2.

Dig Liver Dis. 2018 Mar 30. pii: S1590-8658(18)30668-6. doi: 10.1016/j.dld.2018.03.027. [Epub ahead of print]

Background: Blue laser imaging (BLI) is a new image-enhanced endoscopy technique that utilizes a laser light source developed for narrow-band light observation.

Aims: To evaluate the value of BLI combined with magnifying endoscopy (M-BLI) for the diagnosis of early esophageal cancers (EECs).

Methods: This single-center prospective study analyzed 149 patients with focal esophageal lesions detected with white light endoscopy (WLE) at Renmin Hospital of Wuhan University between April 2015 and June 2017. In this study, patients were examined sequentially with narrow-band imaging combined with magnifying endoscopy (M-NBI), M-BLI and 1.25% Lugol’s iodine chromoendoscopy. The concordance between endoscopic diagnosis and pathological diagnosis was evaluated using the agreement (kappa) test. The paired chi-square test was used to compare the concordance of M-NBI, M-BLI and Lugol’s iodine chromoendoscopy.

Results: This study analyzed 153 lesions (four patients had two lesions each). The sensitivity, specificity, accuracy, concordance rates and kappa value of M-BLI were 95.2%, 91.9%, 85.7%, 92.8% and 0.891, respectively; those of M-NBI were 95.2%, 92.8%, 87.5%, 93.5% and 0.906; and those of Lugol’s iodine chromoendoscopy were 95.2%, 94.6%, 91.3%, 94.8% and 0.936.

Conclusion: M-BLI has a diagnostic profile similar to that of M-NBI and could improve the accuracy of EEC diagnosis.

1 Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
2 Department of Pathology, Renmin Hospital of Wuhan University. Wuhan, China

Classification of atrophic mucosal patterns on Blue LASER Imaging for endoscopic diagnosis of Helicobacter pylori-related gastritis: A retrospective, observational study.

Nishikawa Y1, Ikeda Y2, Murakami H3, Hori SI4, Hino K4, Sasaki C3, Nishikawa M4.

PLoS One. 2018 Mar 29;13(3):e0193197. doi: 10.1371/journal.pone.0193197. eCollection 2018.

Background: Atrophic gastritis can be classified according to characteristic mucosal patterns observed by Blue LASER Imaging (BLI) in a medium-range to distant view.

Aims: To facilitate the endoscopic diagnosis of Helicobacter pylori (HP)-related gastritis, we investigated whether atrophic mucosal patterns correlated with HP infection based on the image interpretations of three endoscopists blinded to clinical features.

Methods: This study included 441 patients diagnosed as having atrophic gastritis by upper gastrointestinal endoscopy at Nishikawa Gastrointestinal Clinic between April 1, 2015 and March 31, 2016. The presence/absence of HP infection was not taken into consideration. Endoscopy was performed using a Fujifilm EG-L580NW scope. Atrophic mucosal patterns observed by BLI were classified into Spotty, Cracked and Mottled. Image interpretation results were that 89, 122 and 228 patients had the Spotty, Cracked and Mottled patterns, respectively, and 2 patients an undetermined pattern. Further analyses were performed on 439 patients, excluding the 2 with undetermined patterns.

Results: The numbers of patients testing negative/positive for HP infection in the Spotty, Cracked and Mottled pattern groups were 12/77, 105/17, and 138/90, respectively. The specificity, positive predictive value and positive likelihood ratio for endoscopic diagnosis with positive HP infection based on the Spotty pattern were 95.3%, 86.5% and 8.9, respectively. In all patients with the Spotty pattern before HP eradication, the Cracked pattern was observed on subsequent post-eradication endoscopy.

Conclusions: The Spotty pattern may represent the presence of HP infection, the Cracked pattern, a post-inflammatory change as seen after HP eradication, and the Mottled pattern, intestinal metaplasia.

1 Nishikawa Gastrointestinal Clinic, Matsuyama, Ehime, Japan
2 Endoscopy Center, Ehime University Hospital, Toon, Ehime, Japan
3 Department of Internal Medicine, Saiseikai Matsuyama Hospital Matsuyama, Ehime, Japan
4 Department of Gastroenterology, National Hospital Organization Shikoku Cancer Center, Matsuyama, Ehime, Japan