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

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.

Download Full-text

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

10.21203/rs.3.rs-126656/v1 ◽

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.

Download Full-text

Comparison of performances of artificial intelligence versus expert endoscopists for real-time assisted diagnosis of esophageal squamous cell carcinoma (with video)

Gastrointestinal Endoscopy ◽

10.1016/j.gie.2020.05.043 ◽

2020 ◽

Vol 92 (4) ◽

pp. 848-855 ◽

Cited By ~ 1

Author(s):

Hiromu Fukuda ◽

Ryu Ishihara ◽

Yusuke Kato ◽

Takashi Matsunaga ◽

Tsutomu Nishida ◽

...

Keyword(s):

Artificial Intelligence ◽

Squamous Cell Carcinoma ◽

Esophageal Squamous Cell Carcinoma ◽

Cell Carcinoma ◽

Real Time ◽

Squamous Cell ◽

Assisted Diagnosis

Download Full-text

Endoscopic Detection of Early Esophageal Squamous Cell Carcinoma in Patients with Achalasia: Narrow-Band Imaging versus Lugol's Staining

Journal of Oncology ◽

10.1155/2013/736756 ◽

2013 ◽

Vol 2013 ◽

pp. 1-6 ◽

Cited By ~ 3

Author(s):

Edson Ide ◽

Fred Olavo Aragão Andrade Carneiro ◽

Mariana Souza Varella Frazão ◽

Dalton Marques Chaves ◽

Rubens Antônio Aissar Sallum ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Esophageal Squamous Cell Carcinoma ◽

Cell Carcinoma ◽

Negative Predictive Value ◽

Squamous Cell ◽

Predictive Value ◽

Narrow Band ◽

Narrow Band Imaging ◽

Standard Technique ◽

High Sensitivity

Chromoendoscopy with Lugol's staining remains the gold standard technique for detecting superficial SCC. An alternative technique, such as narrow-band imaging (NBI), for “optical staining” would be desirable, since NBI is a simpler technique and has no known complications. In this study, we compare NBI without magnification and chromoendoscopy with Lugol's staining for detecting high-grade dysplasia and intramucosal esophageal squamous cell carcinoma (SCC) in patients with achalasia. This was a prospective observational study of 43 patients with achalasia referred to the Gastrointestinal Endoscopy Unit of the Hospital of Clinics, São Paulo, University Medical School, Brazil, from October 2006 to February 2007. Conventional examinations with white light, NBI, and Lugol staining were consecutively performed, and the suspected lesions were mapped, recorded, and sent for biopsy. The results of the three methods were compared regarding sensitivity, specificity, accuracy, positive predictive value, negative predictive value, positive likelihood value, and negative likelihood value. Of the 43 patients, one was diagnosed with esophageal squamous cell carcinoma, and it was detected by all of the methods. NBI technology without magnification has high sensitivity and negative predictive value for detecting superficial esophageal squamous cell carcinoma, and it has comparable results with those obtained with Lugol's staining.

Download Full-text