Artificial intelligence using deep learning analysis of endoscopic ultrasonography images for the differential diagnosis of pancreatic masses

Takamichi Kuwahara; Kazuo Hara; Nobumasa Mizuno; Shin Haba; Nozomi Okuno; Yasuhiro Kuraishi; Daiki Fumihara; Takafumi Yanaidani; Sho Ishikawa; Tsukasa Yasuda; Masanori Yamada; Sachiyo Onishi; Keisaku Yamada; Tsutomu Tanaka; Masahiro Tajika; Yasumasa Niwa; Rui Yamaguchi; Yasuhiro Shimizu

doi:10.1055/a-1873-7920

Endoscopy, Table of Contents

Endoscopy 2023; 55(02): 140-149
DOI: 10.1055/a-1873-7920

Original article

Artificial intelligence using deep learning analysis of endoscopic ultrasonography images for the differential diagnosis of pancreatic masses

Takamichi Kuwahara

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Kazuo Hara

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Nobumasa Mizuno

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Shin Haba

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Nozomi Okuno

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Yasuhiro Kuraishi

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Daiki Fumihara

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Takafumi Yanaidani

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Sho Ishikawa

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Tsukasa Yasuda

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Masanori Yamada

¹Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan

,

Sachiyo Onishi

²Department of Endoscopy, Aichi Cancer Center Hospital, Nagoya, Japan

,

Keisaku Yamada

²Department of Endoscopy, Aichi Cancer Center Hospital, Nagoya, Japan

,

Tsutomu Tanaka

²Department of Endoscopy, Aichi Cancer Center Hospital, Nagoya, Japan

,

Masahiro Tajika

²Department of Endoscopy, Aichi Cancer Center Hospital, Nagoya, Japan

,

Yasumasa Niwa

²Department of Endoscopy, Aichi Cancer Center Hospital, Nagoya, Japan

,

Rui Yamaguchi

³Division of Cancer Systems Biology, Aichi Cancer Center Research Institute, Nagoya, Japan

⁴Division of Cancer Informatics, Nagoya University Graduate School of Medicine, Nagoya, Japan

,

Yasuhiro Shimizu

⁵Department of Gastroenterological Surgery, Aichi Cancer Center Hospital, Nagoya, Japan

› Author Affiliations

Abstract

Background There are several types of pancreatic mass, so it is important to distinguish between them before treatment. Artificial intelligence (AI) is a mathematical technique that automates learning and recognition of data patterns. This study aimed to investigate the efficacy of our AI model using endoscopic ultrasonography (EUS) images of multiple types of pancreatic mass (pancreatic ductal adenocarcinoma [PDAC], pancreatic adenosquamous carcinoma [PASC], acinar cell carcinoma [ACC], metastatic pancreatic tumor [MPT], neuroendocrine carcinoma [NEC], neuroendocrine tumor [NET], solid pseudopapillary neoplasm [SPN], chronic pancreatitis, and autoimmune pancreatitis [AIP]).

Methods Patients who underwent EUS were included in this retrospective study. The included patients were divided into training, validation, and test cohorts. Using these cohorts, an AI model that can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions was developed using a deep-learning architecture and the diagnostic performance of the AI model was evaluated.

Results 22 000 images were generated from 933 patients. The area under the curve, sensitivity, specificity, and accuracy (95 %CI) of the AI model for the diagnosis of pancreatic carcinomas in the test cohort were 0.90 (0.84–0.97), 0.94 (0.88–0.98), 0.82 (0.68–0.92), and 0.91 (0.85–0.95), respectively. The per-category sensitivities (95 %CI) of each disease were PDAC 0.96 (0.90–0.99), PASC 1.00 (0.05–1.00), ACC 1.00 (0.22–1.00), MPT 0.33 (0.01–0.91), NEC 1.00 (0.22–1.00), NET 0.93 (0.66–1.00), SPN 1.00 (0.22–1.00), chronic pancreatitis 0.78 (0.52–0.94), and AIP 0.73 (0.39–0.94).

Conclusions Our developed AI model can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions, but external validation is needed.

Full Text

References

References
1 WHO Classification of Tumours Editorial Board. Digestive System Tumors. WHO classification of tumors. 5th edn.. Lyon: IARC Press; 2019
2 Fusaroli P, Napoleon B, Gincul R. et al. The clinical impact of ultrasound contrast agents in EUS: a systematic review according to the levels of evidence. Gastrointest Endosc 2016; 84: 587-596.e10
3 Kuwahara T, Hara K, Mizuno N. et al. Present status of ultrasound elastography for the diagnosis of pancreatic tumors: review of the literature. J Med Ultrason 2020; 47: 413-420
4 Hirooka Y, Kuwahara T, Irisawa A. et al. JSUM ultrasound elastography practice guidelines: pancreas. J Med Ultrasonics 2015; 42: 151-174
5 Wiresema MJ, Vilmann P, Giovannini M. et al. Endosonography-guided fine-needle aspiration biopsy: diagnostic accuracy and complication assessment. Gastroenterology 1997; 112: 1087-1095
6 Haba S, Yamao K, Bhatia V. et al. Diagnostic ability and factors affecting accuracy of endoscopic ultrasound-guided fine needle aspiration for pancreatic solid lesions: Japanese large single center experience. J Gastroenterol 2013; 48: 973-981
7 Hewitt MJ, McPhail MJ, Possamai L. et al. EUS-guided FNA for diagnosis of solid pancreatic neoplasms: a meta-analysis. Gastrointest Endosc 2012; 75: 319-331
8 Kurita Y, Kuwahara T, Hara K. et al. Features of chronic pancreatitis by endoscopic ultrasound influence the diagnostic accuracy of endoscopic ultrasound-guided fine-needle aspiration of small pancreatic lesions. Dig Endosc 2020; 32: 399-408
9 Hu DM, Gong TT, Zhu Q. Endoscopic ultrasound elastography for differential diagnosis of pancreatic masses: a meta-analysis. Dig Dis Sci 2013; 58: 1125-1131
10 LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521: 436-444
11 Kuwahara T, Hara K, Mizuno N. et al. Current status of artificial intelligence analysis for endoscopic ultrasonography. Dig Endosc 2021; 33: 298-305
12 Ting DSW, Cheung CY, Lim G. et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 2017; 318: 2211-2223
13 Gulshan V, Peng L, Coram M. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016; 316: 2402-2410
14 Byrne MF, Chapados N, Soudan F. et al. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut 2019; 68: 94-100
15 Hirasawa T, Aoyama K, Tanimoto T. et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 2018; 21: 653-660
16 Horie Y, Yoshio T, Aoyama K. et al. Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks. Gastrointest Endosc 2019; 89: 25-32
17 Hirai K, Kuwahara T, Furukawa K. et al. Artificial intelligence-based diagnosis of upper gastrointestinal subepithelial lesions on endoscopic ultrasonography images. Gastric Cancer 2022; 25: 382-391
18 Zhu M, Xu C, Yu J. et al. Differentiation of pancreatic cancer and chronic pancreatitis using computer-aided diagnosis of endoscopic ultrasound (EUS) images: A diagnostic test. PLoS One 2013; 8: e63820
19 Das A, Nguyen CC, Li F. et al. Digital image analysis of EUS images accurately differentiates pancreatic cancer from chronic pancreatitis and normal tissue. Gastrointest Endosc 2008; 67: 861-867
20 Ozkan M, Cakiroglu M, Kocaman O. et al. Age-based computer-aided diagnosis approach for pancreatic cancer on endoscopic ultrasound images. Endosc Ultrasound 2016; 5: 101-107
21 Săftoiu A, Vilmann P, Dietrich CF. et al. Quantitative contrast-enhanced harmonic EUS in differential diagnosis of focal pancreatic masses (with videos). Gastrointest Endosc 2015; 82: 59-69
22 Săftoiu A, Vilmann P, Gorunescu F. et al. Neural network analysis of dynamic sequences of EUS elastography used for the differential diagnosis of chronic pancreatitis and pancreatic cancer. Gastrointest Endosc 2008; 68: 1086-1094
23 Marya N, Powers P, Chari S. et al. Utilisation of artificial intelligence for the development of an EUS-convolutional neural network model trained to enhance the diagnosis of autoimmune pancreatitis. Gut 2021; 70: 1335-1344
24 Kuwahara T, Hara K, Mizuno N. et al. Usefulness of deep learning analysis for the diagnosis of malignancy in intraductal papillary mucinous neoplasms of the pancreas. Clin Transl Gastroenterol 2019; 10: 1-8
25 Wang S, Liu W, Wu L. et al. Training deep neural networks on imbalanced data sets. 2016 International Joint Conference on Neural Networks (IJCNN) 2016; 4368-4374
26 Lloyd RV, Osamura R, Kloppel G, Rosai J. WHO Classification of Tumours of Endocrine Organs. 4th edn. Lyon: IARC Press; 2017
27 Okazaki K, Chari ST, Frulloni L. et al. International consensus for the treatment of autoimmune pancreatitis. Pancreatology 2017; 17: 1-6
28 World Medical Association Inc. Declaration of Helsinki. Ethical principles for medical research involving human subjects. J Indian Med Assoc 2009; 107: 403-405
29 Goodfellow IJ, Pouget-Abadie J, Mirza M. et al. Generative adversarial nets. Adv Neural Inf Process Syst 2014; 27: 2672-2680
30 Tan M, Le QV. EffIicientNetV2: Smaller models and faster training. Proceedings of the 34th international conference on machine learning. PMLR 2021; 139: 10096-10106
31 Yao Y, Rosasco L, Caponnetto A. On early stopping in gradient descent learning. Constr Approx 2007; 26: 289-315
32 Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data 2019; 6: 60
33 He K, Zhang X, Ren S. et al. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2016; 770-778
34 Zhang J, Zhu L, Yao L. et al. Deep-learning-based pancreas segmentation and station recognition system in EUS: development and validation of a useful training tool (with video). Gastrointest Endosc 2020; 92: 874-885.e3
35 Tonozuka R, Itoi T, Nagata N. et al. Deep learning analysis for the detection of pancreatic cancer on endosonographic images: a pilot study. J Hepatobiliary Pancreat Sci 2021; 28: 95-104

Supplementary Material

Supplementary material