Tags

Type your tag names separated by a space and hit enter

Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos).

Abstract

BACKGROUND AND AIMS

We developed a system for computer-assisted diagnosis (CAD) for real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinomas (ESCCs) to assist the diagnosis of esophageal cancer.

METHODS

A total of 6473 narrow-band imaging (NBI) images, including precancerous lesions, early ESCCs, and noncancerous lesions, were used to train the CAD system. We validated the CAD system using both endoscopic images and video datasets. The receiver operating characteristic curve of the CAD system was generated based on image datasets. An artificial intelligence probability heat map was generated for each input of endoscopic images. The yellow color indicated high possibility of cancerous lesion, and the blue color indicated noncancerous lesions on the probability heat map. When the CAD system detected any precancerous lesion or early ESCCs, the lesion of interest was masked with color.

RESULTS

The image datasets contained 1480 malignant NBI images from 59 consecutive cancerous cases (sensitivity, 98.04%) and 5191 noncancerous NBI images from 2004 cases (specificity, 95.03%). The area under curve was 0.989. The video datasets of precancerous lesions or early ESCCs included 27 nonmagnifying videos (per-frame sensitivity 60.8%, per-lesion sensitivity, 100%) and 20 magnifying videos (per-frame sensitivity 96.1%, per-lesion sensitivity, 100%). Unaltered full-range normal esophagus videos included 33 videos (per-frame specificity 99.9%, per-case specificity, 90.9%).

CONCLUSIONS

A deep learning model demonstrated high sensitivity and specificity for both endoscopic images and video datasets. The real-time CAD system has a promising potential in the near future to assist endoscopists in diagnosing precancerous lesions and ESCCs.

Authors+Show Affiliations

Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.Shanghai Wision AI Co Ltd, Shanghai, China.Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.Shanghai Wision AI Co Ltd, Shanghai, China.Shanghai Wision AI Co Ltd, Shanghai, China.Shanghai Wision AI Co Ltd, Shanghai, China.San Bernardino Gastroenterology Associates Inc and ACE Endoscopy and Surgery Center, Rialto, California, USA.Jaswant Rai Speciality Hospital, Meerut, India.Shanghai Wision AI Co Ltd, Shanghai, China.Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31445040

Citation

Guo, LinJie, et al. "Real-time Automated Diagnosis of Precancerous Lesions and Early Esophageal Squamous Cell Carcinoma Using a Deep Learning Model (with Videos)." Gastrointestinal Endoscopy, 2019.
Guo L, Xiao X, Wu C, et al. Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos). Gastrointest Endosc. 2019.
Guo, L., Xiao, X., Wu, C., Zeng, X., Zhang, Y., Du, J., ... Hu, B. (2019). Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos). Gastrointestinal Endoscopy, doi:10.1016/j.gie.2019.08.018.
Guo L, et al. Real-time Automated Diagnosis of Precancerous Lesions and Early Esophageal Squamous Cell Carcinoma Using a Deep Learning Model (with Videos). Gastrointest Endosc. 2019 Aug 21; PubMed PMID: 31445040.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos). AU - Guo,LinJie, AU - Xiao,Xiao, AU - Wu,ChunCheng, AU - Zeng,Xianhui, AU - Zhang,Yuhang, AU - Du,Jiang, AU - Bai,Shuai, AU - Xie,Jia, AU - Zhang,Zhiwei, AU - Li,Yuhong, AU - Wang,Xuedan, AU - Cheung,Onpan, AU - Sharma,Malay, AU - Liu,Jingjia, AU - Hu,Bing, Y1 - 2019/08/21/ PY - 2019/04/15/received PY - 2019/08/08/accepted PY - 2019/8/25/pubmed PY - 2019/8/25/medline PY - 2019/8/25/entrez JF - Gastrointestinal endoscopy JO - Gastrointest. Endosc. N2 - BACKGROUND AND AIMS: We developed a system for computer-assisted diagnosis (CAD) for real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinomas (ESCCs) to assist the diagnosis of esophageal cancer. METHODS: A total of 6473 narrow-band imaging (NBI) images, including precancerous lesions, early ESCCs, and noncancerous lesions, were used to train the CAD system. We validated the CAD system using both endoscopic images and video datasets. The receiver operating characteristic curve of the CAD system was generated based on image datasets. An artificial intelligence probability heat map was generated for each input of endoscopic images. The yellow color indicated high possibility of cancerous lesion, and the blue color indicated noncancerous lesions on the probability heat map. When the CAD system detected any precancerous lesion or early ESCCs, the lesion of interest was masked with color. RESULTS: The image datasets contained 1480 malignant NBI images from 59 consecutive cancerous cases (sensitivity, 98.04%) and 5191 noncancerous NBI images from 2004 cases (specificity, 95.03%). The area under curve was 0.989. The video datasets of precancerous lesions or early ESCCs included 27 nonmagnifying videos (per-frame sensitivity 60.8%, per-lesion sensitivity, 100%) and 20 magnifying videos (per-frame sensitivity 96.1%, per-lesion sensitivity, 100%). Unaltered full-range normal esophagus videos included 33 videos (per-frame specificity 99.9%, per-case specificity, 90.9%). CONCLUSIONS: A deep learning model demonstrated high sensitivity and specificity for both endoscopic images and video datasets. The real-time CAD system has a promising potential in the near future to assist endoscopists in diagnosing precancerous lesions and ESCCs. SN - 1097-6779 UR - https://www.unboundmedicine.com/medline/citation/31445040/Real_time_automated_diagnosis_of_precancerous_lesions_and_early_esophageal_squamous_cell_carcinoma_using_a_deep_learning_model__with_videos__ L2 - https://linkinghub.elsevier.com/retrieve/pii/S0016-5107(19)32187-X DB - PRIME DP - Unbound Medicine ER -