Artificial intelligence diagnostic system predicts multiple Lugol-voiding lesions in the esophagus and patients at high risk for esophageal squamous cell carcinoma

Endoscopy ◽  
2021 ◽  
Author(s):  
Yohei Ikenoyama ◽  
Toshiyuki Yoshio ◽  
Junki Tokura ◽  
Sakiko Naito ◽  
Ken Namikawa ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Esophageal Cancer ◽  
High Risk ◽  
Narrow Band Imaging ◽  
Diagnostic System ◽  
High Sensitivity ◽  
Endoscopic Examination ◽  
Validation Dataset ◽  
Iodine Staining ◽  
Experienced Endoscopists

Abstract Background It is known that an esophagus with multiple Lugol-voiding lesions (LVLs) after iodine staining is high risk for esophageal cancer; however, it is preferable to identify high-risk cases without staining because iodine causes discomfort and prolongs examination times. This study assessed the capability of an artificial intelligence (AI) system to predict multiple LVLs from images that had not been stained with iodine as well as patients at high risk for esophageal cancer. Methods We constructed the AI system by preparing a training set of 6634 images from white-light and narrow-band imaging in 595 patients before they underwent endoscopic examination with iodine staining. Diagnostic performance was evaluated on an independent validation dataset (667 images from 72 patients) and compared with that of 10 experienced endoscopists. Results The sensitivity, specificity, and accuracy of the AI system to predict multiple LVLs were 84.4 %, 70.0 %, and 76.4 %, respectively, compared with 46.9 %, 77.5 %, and 63.9 %, respectively, for the endoscopists. The AI system had significantly higher sensitivity than 9/10 experienced endoscopists. We also identified six endoscopic findings that were significantly more frequent in patients with multiple LVLs; however, the AI system had greater sensitivity than these findings for the prediction of multiple LVLs. Moreover, patients with AI-predicted multiple LVLs had significantly more cancers in the esophagus and head and neck than patients without predicted multiple LVLs. Conclusion The AI system could predict multiple LVLs with high sensitivity from images without iodine staining. The system could enable endoscopists to apply iodine staining more judiciously.

ID: 3526637 ARTIFICIAL INTELLIGENCE-ASSISTED DIAGNOSTIC SYSTEM FOR NARROW-BAND IMAGING FOR COLORECTAL LESIONS.

2021 ◽  
Vol 93 (6) ◽  
pp. AB198-AB199
Author(s):  
Masashi Misawa ◽  
Shinei Kudo ◽  
Yuichi Mori ◽  
Misaki Ishiyama ◽  
Yosuke Minegishi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Diagnostic System

scholarly journals Ability of artificial intelligence to detect T1 esophageal squamous cell carcinoma from endoscopic videos and the effects of real-time assistance

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Sho Shiroma ◽  
Toshiyuki Yoshio ◽  
Yusuke Kato ◽  
Yoshimasa Horie ◽  
Ken Namikawa ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Squamous Cell Carcinoma ◽  
Deep Learning ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Real Time ◽  
Squamous Cell ◽  
Narrow Band Imaging ◽  
High Sensitivity ◽  
Detection Accuracy

AbstractDiagnosis using artificial intelligence (AI) with deep learning could be useful in endoscopic examinations. We investigated the ability of AI to detect superficial esophageal squamous cell carcinoma (ESCC) from esophagogastroduodenoscopy (EGD) videos. We retrospectively collected 8428 EGD images of esophageal cancer to develop a convolutional neural network through deep learning. We evaluated the detection accuracy of the AI diagnosing system compared with that of 18 endoscopists. We used 144 EGD videos for the two validation sets. First, we used 64 EGD observation videos of ESCCs using both white light imaging (WLI) and narrow-band imaging (NBI). We then evaluated the system using 80 EGD videos from 40 patients (20 with superficial ESCC and 20 with non-ESCC). In the first set, the AI system correctly diagnosed 100% ESCCs. In the second set, it correctly detected 85% (17/20) ESCCs. Of these, 75% (15/20) and 55% (11/22) were detected by WLI and NBI, respectively, and the positive predictive value was 36.7%. The endoscopists correctly detected 45% (25–70%) ESCCs. With AI real-time assistance, the sensitivities of the endoscopists were significantly improved without AI assistance (p < 0.05). AI can detect superficial ESCCs from EGD videos with high sensitivity and the sensitivity of the endoscopist was improved with AI real-time support.

scholarly journals Ability of artificial intelligence to detect T1 esophageal squamous cell carcinoma from endoscopic videos: supportive effects of real-time assistance

2020 ◽  
Author(s):  
Sho Shiroma ◽  
Toshiyuki Yoshio ◽  
Yusuke Kato ◽  
Yoshimasa Horie ◽  
Ken Namikawa ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Squamous Cell Carcinoma ◽  
Deep Learning ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Real Time ◽  
Squamous Cell ◽  
Narrow Band Imaging ◽  
High Sensitivity ◽  
Detection Accuracy

Abstract Diagnosis using artificial intelligence (AI) with deep learning could be useful in endoscopic examinations. We investigated the ability of AI to detect superficial esophageal squamous cell carcinoma (ESCC) from esophagogastroduodenoscopy (EGD) videos. We retrospectively collected 8428 EGD images of esophageal cancer to develop a convolutional neural network through deep learning. We evaluated the detection accuracy of the AI diagnosing system compared with that of 18 endoscopists. We used 144 EGD videos for the two validation sets. First, we used 64 EGD observation videos of ESCC using both white light imaging (WLI) and narrow-band imaging (NBI). We then evaluated the system using 80 EGD videos from 40 patients (20 with superficial ESCC and 20 with non-ESCC). In the first set, the AI system correctly diagnosed 100% ESCCs. In the second set, it correctly detected 85% (17/20) ESCCs. Of these, 75% (15/20) and 55% (11/22) were detected by WLI and NBI, and the positive predictive value was 36.7%. The endoscopists correctly detected 45% (25-70%) ESCCs. With AI real-time assistance, the sensitivities of the endoscopists were significantly improved without AI assistance (p<0.05). AI can detect superficial ESCC from EGD videos with high sensitivity and improve endoscopists’ detection of ESCC with real-time support.

scholarly journals Utility of an Artificial Intelligence System for Classification of Esophageal Lesions when Simulating its Clinical use

2021 ◽  
Author(s):  
Ayaka Tajiri ◽  
Ryu ISHIHARA ◽  
Yusuke KATO ◽  
Takahiro INOUE ◽  
Katsunori MATSUEDA ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Narrow Band Imaging ◽  
Validation Dataset ◽  
Muscularis Mucosa ◽  
Still Images ◽  
Still Image ◽  
Intelligence System ◽  
System Diagnosis ◽  
Diagnostic Support

Abstract Background:Previous reports have shown favorable performance of artificial intelligence (AI) systems for diagnosing esophageal squamous cell carcinoma (ESCC) compared with endoscopists. However, these findings don’t reflect performance in clinical situations, as endoscopists classify lesions based on both magnified and non-magnified videos, while AI systems often use only a few magnified narrow band imaging (NBI) still images. We evaluated the performance of the AI system in simulated clinical situations.Methods:We used 25,048 images from 1,433 superficial ESCC and 4,746 images from 410 noncancerous esophagi to construct our AI system. For the validation dataset, we took NBI videos of suspected superficial ESCCs. The AI system diagnosis used one magnified still image taken from each video, while 19 endoscopists used whole videos. Results:We used 147 datasets including 83 superficial ESCC and 64 non-ESCC lesions. The accuracy, sensitivity and specificity for the classification of ESCC were, respectively, 80.9%, 85.5%, and 75.0% for the AI system and 69.2%, 67.5%, and 71.5% for the endoscopists. The AI system correctly classified all ESCCs invading the muscularis mucosa or submucosa and 96.8% of lesions ≥ 20 mm, whereas even the experts misdiagnosed some of them.Conclusions:Our AI system showed higher diagnostic ability for classifying ESCC and non-ESCC than endoscopists. It may provide valuable diagnostic support to endoscopists.

Artificial intelligence-based diagnostic system classifying gastric cancers and ulcers: comparison between the original and newly developed systems

Endoscopy ◽  
2020 ◽  
Vol 52 (12) ◽  
pp. 1077-1083 ◽  
Author(s):  
Ken Namikawa ◽  
Toshiaki Hirasawa ◽  
Kaoru Nakano ◽  
Yohei Ikenoyama ◽  
Mitsuaki Ishioka ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Gastric Cancer ◽  
Gastric Ulcer ◽  
Diagnostic System ◽  
Gastric Ulcers ◽  
Training Dataset ◽  
Validation Dataset ◽  
Gastric Cancers ◽  
Lesion Level ◽  
Sensitivity Specificity

Abstract Background We previously reported for the first time the usefulness of artificial intelligence (AI) systems in detecting gastric cancers. However, the “original convolutional neural network (O-CNN)” employed in the previous study had a relatively low positive predictive value (PPV). Therefore, we aimed to develop an advanced AI-based diagnostic system and evaluate its applicability for the classification of gastric cancers and gastric ulcers. Methods We constructed an “advanced CNN” (A-CNN) by adding a new training dataset (4453 gastric ulcer images from 1172 lesions) to the O-CNN, which had been trained using 13 584 gastric cancer and 373 gastric ulcer images. The diagnostic performance of the A-CNN in terms of classifying gastric cancers and ulcers was retrospectively evaluated using an independent validation dataset (739 images from 100 early gastric cancers and 720 images from 120 gastric ulcers) and compared with that of the O-CNN by estimating the overall classification accuracy. Results The sensitivity, specificity, and PPV of the A-CNN in classifying gastric cancer at the lesion level were 99.0 % (95 % confidence interval [CI] 94.6 %−100 %), 93.3 % (95 %CI 87.3 %−97.1 %), and 92.5 % (95 %CI 85.8 %−96.7 %), respectively, and for classifying gastric ulcers were 93.3 % (95 %CI 87.3 %−97.1 %), 99.0 % (95 %CI 94.6 %−100 %), and 99.1 % (95 %CI 95.2 %−100 %), respectively. At the lesion level, the overall accuracies of the O- and A-CNN for classifying gastric cancers and gastric ulcers were 45.9 % (gastric cancers 100 %, gastric ulcers 0.8 %) and 95.9 % (gastric cancers 99.0 %, gastric ulcers 93.3 %), respectively. Conclusion The newly developed AI-based diagnostic system can effectively classify gastric cancers and gastric ulcers.

The Efficacy of Virtual Chromoendoscopy in the Diagnosis of Portal Hypertensive Gastropathy

2016 ◽  
Vol 25 (3) ◽  
pp. 289-293
Author(s):  
Anda Carmen Achim ◽  
Stefan Cristian Vesa ◽  
Eugen Dumitru
Keyword(s):  
Diagnostic Criteria ◽  
White Light ◽  
Narrow Band Imaging ◽  
Endoscopic Examination ◽  
Kappa Statistics ◽  
Portal Hypertensive Gastropathy ◽  
Mosaic Pattern ◽  
White Light Endoscopy ◽  
A New Technique ◽  
Virtual Chromoendoscopy

Background: Diagnosis of portal hypertensive gastropathy (PHG) is based on endoscopic criteria. I-scan technology, a new technique of virtual chromoendoscopy, increases the diagnostic accuracy for lesions in the gastrointestinal tract. Aim: To establish the role of i-scan endoscopy in the diagnosis of PHG. Method: In this prospective study, endoscopic examination was conducted first by using white light and after that i-scan 1 and i-scan 2 technology in a group of 50 consecutive cirrhotic patients. The endoscopic diagnostic criteria for PHG followed the Baveno criteria. The interobserver agreement between white light endoscopy and i-scan endoscopy was determined using Cohen’s kappa statistics. Results: Forty-five of the 50 patients met the diagnostic criteria for PHG when examined by i-scan endoscopy and 39 patients were diagnosed with PHG by white light endoscopy. The strength of agreement between the two methods for the diagnosis of PHG was moderate (k=0.565; 95%CI 0.271-0.859; p<0.001). I-scan 1 classified the mosaic pattern better than classic endoscopy; i-scan 2 described better the red spots. Conclusion: I-scan examination increased the diagnostic sensitivity of PHG. The diagnostic criteria (mosaic pattern and red spots) were easier to observe endoscopically using i-scan than in white light.Abbreviations: FICE: Fuji Intelligent chromoendoscopy; GAVE: gastric antral vascular ectasia; NBI: narrow band imaging; PHG: portal hypertensive gastropathy; PHT: portal hypertension; UGIB: upper gastrointestinal bleeding.

Rare Primary Esophageal Paget’s Disease Diagnosed on a Large Bloc Specimen Obtained by Endoscopic Mucosal Resection

2017 ◽  
Vol 26 (4) ◽  
pp. 417-420 ◽  
Author(s):  
Hirohito Mori ◽  
Maki Ayaki ◽  
Hideki Kobara ◽  
Yasuhiro Goda ◽  
Noriko Nishiyama ◽  
...  
Keyword(s):  
Endoscopic Mucosal Resection ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Case Reports ◽  
Paget’S Disease ◽  
Paget's Disease ◽  
Endoscopic Examination ◽  
Capillary Loop ◽  
Mucosal Resection ◽  
Cap Method

Primary esophageal Paget’s disease is rare. Only a few case reports have described the intraepithelial papillary capillary loop (IPCL) pattern obtained by magnified Narrow Band Imaging (M-NBI) endoscopy in this rare pathology. This report highlights the usefulness of M-NBI and the successful diagnosis using a large bloc specimen obtained by endoscopic mucosal resection with the cap method (EMR−c). A 53-year-old man was referred to endoscopic examination for dysphagia. The endoscopic image revealed a ring-shaped scarring of the esophagus suggestive for eosinophilic esophagitis. The IPCL pattern by M-NBI endoscopy showed an inflammatory pattern, and the entire epithelium of the esophagus was not stained by Lugol iodine spraying. Based on six biopsies randomly performed, a poorly differentiated adenocarcinoma was diagnosed. Since the M-NBI pattern and the histology were completely different, EMR−c was performed to obtain large bloc specimens for a more detailed diagnosis. The pathological findings revealed extensive Paget’s cells infiltration into the epithelium and multifocal invasion from the mucosa to the submucosal layer with adenocarcinoma. In conclusion, a large bloc specimen by EMR-c might be more useful than a small biopsy for an accurate diagnosis of the rare esophageal Paget’s disease.Key words:  –  – .Abbreviations: EMR−c: endoscopic mucosal resection with cap method; IPCL: intraepithelial papillary capillary loop; LVLs: Lugol-voiding lesions; M-NBI: magnified Narrow Band Imaging; PET-CT: Positron-Emission Tomography and Computed Tomography.

Sign in / Sign up

Export Citation Format

Share Document