Tags

Type your tag names separated by a space and hit enter

Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus.
Esophagus 2019; 16(2):180-187E

Abstract

BACKGROUND AND AIMS

The endocytoscopic system (ECS) helps in virtual realization of histology and can aid in confirming histological diagnosis in vivo. We propose replacing biopsy-based histology for esophageal squamous cell carcinoma (ESCC) by using the ECS. We applied deep-learning artificial intelligence (AI) to analyse ECS images of the esophagus to determine whether AI can support endoscopists for the replacement of biopsy-based histology.

METHODS

A convolutional neural network-based AI was constructed based on GoogLeNet and trained using 4715 ECS images of the esophagus (1141 malignant and 3574 non-malignant images). To evaluate the diagnostic accuracy of the AI, an independent test set of 1520 ECS images, collected from 55 consecutive patients (27 ESCCs and 28 benign esophageal lesions) were examined.

RESULTS

On the basis of the receiver-operating characteristic curve analysis, the areas under the curve of the total images, higher magnification pictures, and lower magnification pictures were 0.85, 0.90, and 0.72, respectively. The AI correctly diagnosed 25 of the 27 ESCC cases, with an overall sensitivity of 92.6%. Twenty-five of the 28 non-cancerous lesions were diagnosed as non-malignant, with a specificity of 89.3% and an overall accuracy of 90.9%. Two cases of malignant lesions, misdiagnosed as non-malignant by the AI, were correctly diagnosed as malignant by the endoscopist. Among the 3 cases of non-cancerous lesions diagnosed as malignant by the AI, 2 were of radiation-related esophagitis and one was of gastroesophageal reflux disease.

CONCLUSION

AI is expected to support endoscopists in diagnosing ESCC based on ECS images without biopsy-based histological reference.

Authors+Show Affiliations

Department of Digestive Tract and General Surgery, Saitama Medical Center, Saitama Medical University, 1981 Kamoda, Kawagoe, Saitama, 350-8550, Japan. kuma7srg1@gmail.com.Research Team for Geriatric Pathology, Tokyo Metropolitan Institute of Gerontology, Tokyo, Japan.Department of Esophageal and General Surgery, Tokyo Medical and Dental University, Tokyo, Japan.AI Medical Service Inc., Tokyo, Japan.AI Medical Service Inc., Tokyo, Japan.Department of Surgery, Teikyo University Hospital, Tokyo, Japan. Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan.Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan. Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan.Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan. Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan.Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan. Surgery Department, Sanno Hospital, International University of Health and Welfare, Tokyo, Japan.Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.Department of Pathology, Saitama Medical Center, Saitama Medical University, Saitama, Japan.Department of Digestive Tract and General Surgery, Saitama Medical Center, Saitama Medical University, 1981 Kamoda, Kawagoe, Saitama, 350-8550, Japan.Department of Digestive Tract and General Surgery, Saitama Medical Center, Saitama Medical University, 1981 Kamoda, Kawagoe, Saitama, 350-8550, Japan.AI Medical Service Inc., Tokyo, Japan. Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan.

Pub Type(s)

Evaluation Studies
Journal Article

Language

eng

PubMed ID

30547352

Citation

Kumagai, Youichi, et al. "Diagnosis Using Deep-learning Artificial Intelligence Based On the Endocytoscopic Observation of the Esophagus." Esophagus : Official Journal of the Japan Esophageal Society, vol. 16, no. 2, 2019, pp. 180-187.
Kumagai Y, Takubo K, Kawada K, et al. Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus. Esophagus. 2019;16(2):180-187.
Kumagai, Y., Takubo, K., Kawada, K., Aoyama, K., Endo, Y., Ozawa, T., ... Tada, T. (2019). Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus. Esophagus : Official Journal of the Japan Esophageal Society, 16(2), pp. 180-187. doi:10.1007/s10388-018-0651-7.
Kumagai Y, et al. Diagnosis Using Deep-learning Artificial Intelligence Based On the Endocytoscopic Observation of the Esophagus. Esophagus. 2019;16(2):180-187. PubMed PMID: 30547352.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus. AU - Kumagai,Youichi, AU - Takubo,Kaiyo, AU - Kawada,Kenro, AU - Aoyama,Kazuharu, AU - Endo,Yuma, AU - Ozawa,Tsuyoshi, AU - Hirasawa,Toshiaki, AU - Yoshio,Toshiyuki, AU - Ishihara,Soichiro, AU - Fujishiro,Mitsuhiro, AU - Tamaru,Jun-Ichi, AU - Mochiki,Erito, AU - Ishida,Hideyuki, AU - Tada,Tomohiro, Y1 - 2018/12/13/ PY - 2018/08/31/received PY - 2018/12/10/accepted PY - 2018/12/14/pubmed PY - 2018/12/14/medline PY - 2018/12/15/entrez KW - Artificial intelligence KW - Convolutional neural network KW - Deep learning KW - Endocytoscopy system KW - Esophagus SP - 180 EP - 187 JF - Esophagus : official journal of the Japan Esophageal Society JO - Esophagus VL - 16 IS - 2 N2 - BACKGROUND AND AIMS: The endocytoscopic system (ECS) helps in virtual realization of histology and can aid in confirming histological diagnosis in vivo. We propose replacing biopsy-based histology for esophageal squamous cell carcinoma (ESCC) by using the ECS. We applied deep-learning artificial intelligence (AI) to analyse ECS images of the esophagus to determine whether AI can support endoscopists for the replacement of biopsy-based histology. METHODS: A convolutional neural network-based AI was constructed based on GoogLeNet and trained using 4715 ECS images of the esophagus (1141 malignant and 3574 non-malignant images). To evaluate the diagnostic accuracy of the AI, an independent test set of 1520 ECS images, collected from 55 consecutive patients (27 ESCCs and 28 benign esophageal lesions) were examined. RESULTS: On the basis of the receiver-operating characteristic curve analysis, the areas under the curve of the total images, higher magnification pictures, and lower magnification pictures were 0.85, 0.90, and 0.72, respectively. The AI correctly diagnosed 25 of the 27 ESCC cases, with an overall sensitivity of 92.6%. Twenty-five of the 28 non-cancerous lesions were diagnosed as non-malignant, with a specificity of 89.3% and an overall accuracy of 90.9%. Two cases of malignant lesions, misdiagnosed as non-malignant by the AI, were correctly diagnosed as malignant by the endoscopist. Among the 3 cases of non-cancerous lesions diagnosed as malignant by the AI, 2 were of radiation-related esophagitis and one was of gastroesophageal reflux disease. CONCLUSION: AI is expected to support endoscopists in diagnosing ESCC based on ECS images without biopsy-based histological reference. SN - 1612-9067 UR - https://www.unboundmedicine.com/medline/citation/30547352/Diagnosis_using_deep_learning_artificial_intelligence_based_on_the_endocytoscopic_observation_of_the_esophagus_ L2 - https://medlineplus.gov/esophagealcancer.html DB - PRIME DP - Unbound Medicine ER -