Using deep learning and explainable artificial intelligence to assess the severity of gastroesophageal reflux disease according to the Los Angeles Classification System

References

• Gyawali CP, Kahrilas PJ, Savarino E, et al. Modern diagnosis of GERD: the Lyon consensus. Gut. 2018;67(7):1351–1362.
   PubMed Web of Science ®Google Scholar
• ASGE Standards of Practice Committee, et al. The role of endoscopy in the management of GERD. Gastrointest Endosc. 2015;81(6):1305–1310.
   PubMed Web of Science ®Google Scholar
• Genta RM, Spechler SJ, Kielhorn AF, et al. The Los Angeles and Savary–Miller systems for grading esophagitis: utilization and correlation with histology. Dis Esophagus. 2011;24(1):10–17.
   PubMed Web of Science ®Google Scholar
• Kuribayashi S, Hosaka H, Nakamura F, et al. The role of endoscopy in the management of gastroesophageal reflux disease. DEN Open. 2022;2(1):e86.
   PubMedGoogle Scholar
• Liu L, Li S, Zhu K, et al. Relationship between esophageal motility and severity of gastroesophageal reflux disease according to the Los Angeles classification. Medicine. 2019;98(19):e15543.
   PubMed Web of Science ®Google Scholar
• Sugiura T, Iwakiri K, Kotoyori M, et al. Relationship between severity of reflux esophagitis according to the Los Angeles classification and esophageal motility. J Gastroenterol. 2001;36(4):226–230.
   PubMed Web of Science ®Google Scholar
• Ghoshal UC, Chourasia D, Tripathi S, et al. Relationship of severity of gastroesophageal reflux disease with gastric acid secretory profile and esophageal acid exposure during nocturnal acid breakthrough: a study using 24-h dual-channel pH-metry. Scand J Gastroenterol. 2008;43(6):654–661.
   PubMed Web of Science ®Google Scholar
• Lundell LR, Dent J, Bennett JR, et al. Endoscopic assessment of oesophagitis: clinical and functional correlates and further validation of the Los Angeles classification. Gut. 1999;45(2):172–180.
   PubMed Web of Science ®Google Scholar
• Kaushik AC, Raj U. AI-driven drug discovery: a boon against COVID-19? AI Open. 2020;1:1–4.
   Google Scholar
• Alafif T, Tehame AM, Bajaba S, et al. Machine and deep learning towards COVID-19 diagnosis and treatment: survey, challenges, and future directions. IJERPH. 2021;18(3):1117–1127.
   Web of Science ®Google Scholar
• Hann A, Meining A. Artificial intelligence in endoscopy. Visc Med. 2021;37(6):471–475.
   PubMed Web of Science ®Google Scholar
• Tziortziotis I, Laskaratos F-M, Coda S, et al. Role of artificial intelligence in video capsule endoscopy. Diagnostics. 2021;11(7):1130–1192.
   Web of Science ®Google Scholar
• Ikenoyama Y, Hirasawa T, Ishioka M, et al. Detecting early gastric cancer: comparison between the diagnostic ability of convolutional neural networks and endoscopists. Dig Endosc. 2021;33(1):141–150.
   PubMed Web of Science ®Google Scholar
• 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. 2020;91(1):41–51.
   PubMed Web of Science ®Google Scholar
• LeCun Y, Bengio Y, Hinton G, et al. Deep learning. Nature. 2015;521(7553):436–444.
   PubMed Web of Science ®Google Scholar
• Yamashita R, Nishio M, Do RKG, et al. Convolutional neural networks: an overview and application in radiology. Insights Imag. 2018;9(4):611–629.
   PubMed Web of Science ®Google Scholar
• Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Boston, MA, USA; 2015. p. 1–9.
   Google Scholar
• Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115–118.
   PubMed Web of Science ®Google Scholar
• Li L, Verma M, Nakashima Y, et al. IterNet: retinal image segmentation utilizing structural redundancy in vessel networks. 2020 IEEE Winter Conference on Applications of Computer Vision (WACV); Snowmass, CO, USA; 2020. p. 3645–3654.
   Google Scholar
• Wang B, Takeda T, Sugimoto K, et al. Automatic creation of annotations for chest radiographs based on the positional information extracted from radiographic image reports. Comput Methods Programs Biomed. 2021;209(2021):106331.
   PubMed Web of Science ®Google Scholar
• Ting DSW, Cheung CY-L, 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(22):2211–2223.
   PubMed Web of Science ®Google Scholar
• Huang C-R, Chen Y-T, Chen W-Y, et al. Gastroesophageal reflux disease diagnosis using hierarchical heterogeneous descriptor fusion support vector machine. IEEE Trans Biomed Eng. 2016;63(3):588–599.
   PubMed Web of Science ®Google Scholar
• Wang C-C, Chiu Y-C, Chen W-L, et al. A deep learning model for classification of endoscopic gastroesophageal reflux disease. IJERPH. 2021;18(5):2428–2422 Mar.
   Web of Science ®Google Scholar
• Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556; 2015.
   Google Scholar
• He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA; 2016. p. 770–778.
   Google Scholar
• Zhang H, Wu C, Zhang Z, et al. Resnest: Split-attention networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2022:2736–2746.
   Google Scholar
• Huang G, Liu Z, Maaten Lvd, et al. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI, USA; 2017. p. 2261–2269.
   Google Scholar
• Tan M, Quoc VL. EfficientNet: rethinking model scaling for convolutional neural networks. International conference on machine learning. PMLR. 2019:6105–6114.
   Google Scholar
• Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning. AAAI. 2017. p. 4278–4284.
   Google Scholar
• McInnes L, Healy J. UMAP: uniform manifold approximation and projection for dimension reduction. The Journal of Open Source Software. 2018;3(29):861.
   Google Scholar
• Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA; 2016. p. 2921–2929.
   Google Scholar
• Selvaraju RR, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis. 2020;128(2):336–359.
   Web of Science ®Google Scholar
• Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, Cham, 2014. p. 818–833.
   Google Scholar
• Petsiuk V, Das A, Saenko K. RISE: randomized input sampling for explanation of Black-box models. British Machine Vision Conference (BMVC); 2018.
   Google Scholar
• Li L, Wang B, Verma M, et al. SCOUTER: slot attention-based classifier for explainable image recognition. 2021 IEEE/CVF International Conference on Computer Vision (ICCV); Montreal, QC, Canada, 2021. p. 1026–1035.
   Google Scholar
• Wang B, Li L, Verma M, et al. MTUNet: few-shot image classification with visual explanations. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); Nashville, TN, USA; 2021. p. 2294–2298.
   Google Scholar
• Schulz K, Sixt L, Tombari F, et al. Restricting the flow: information bottlenecks for attribution. ArXiv abs/2001.00396; 2020. n. pag.
   Google Scholar
• McInnes L, Healy J, Saul N, et al. UMAP: uniform manifold approximation and projection. JOSS. 2018;3(29):861.
   Google Scholar
• Xu Y, Tan Y, Wang Y, et al. A gratifying step forward for the application of artificial intelligence in the field of endoscopy: a narrative review. Surg Laparosc Endosc Percutan Tech. 2020;31(2):254–263.
   PubMed Web of Science ®Google Scholar
• Song Y-Q, Mao X-L, Zhou X-B, et al. Use of artificial intelligence to improve the quality control of gastrointestinal endoscopy. Front Med (Lausanne). 2021;8:709322–709347.
   Google Scholar
• Yu C, Helwig EJ. Artificial intelligence in gastric cancer: a translational narrative review. Ann Transl Med. 2021;9(3):269.
   PubMed Web of Science ®Google Scholar
• Visaggi P, Barberio B, Ghisa M, et al. Modern diagnosis of early esophageal cancer: from blood biomarkers to advanced endoscopy and artificial intelligence. Cancers. 2021;13(13):3124–3162.
   PubMed Web of Science ®Google Scholar
• Pace F, Riegler G, de Leone A, EMERGE Study Group, et al. Is it possible to clinically differentiate erosive from nonerosive reflux disease patients? A study using an artificial neural networks-assisted algorithm. Eur J Gastroenterol Hepatol. 2010;22(10):1163–1168.
   PubMed Web of Science ®Google Scholar
• Xiao Y, Zhang S, Dai N, et al. Phase III, randomised, double-blind, multicentre study to evaluate the efficacy and safety of vonoprazan compared with lansoprazole in Asian patients with erosive oesophagitis. Gut. 2020;69(2):224–230.
   PubMed Web of Science ®Google Scholar
• Iwakiri K, Fujiwara Y, Manabe N, et al. Evidence-based clinical practice guidelines for gastroesophageal reflux disease 2021. J Gastroenterol. 2022;57(4):267–285.
   PubMed Web of Science ®Google Scholar
• Zerbib F, Bredenoord AJ, Fass R, et al. ESNM/ANMS consensus paper: diagnosis and management of refractory gastro-esophageal reflux disease. Neurogastroenterol Motil. 2021;33(4):e14075.
   PubMed Web of Science ®Google Scholar
• Pauwels A, Boecxstaens V, Andrews CN, et al. How to select patients for antireflux surgery? The ICARUS guidelines (international consensus regarding preoperative examinations and clinical characteristics assessment to select adult patients for antireflux surgery). Gut. 2019;68(11):1928–1941.
   PubMed Web of Science ®Google Scholar
• Katz PO, Dunbar KB, Schnoll-Sussman FH, et al. ACG clinical guideline for the diagnosis and management of gastroesophageal reflux disease. Am J Gastroenterol. 2022;117(1):27–56.
   PubMed Web of Science ®Google Scholar