Convolutional Neural Networks for the evaluation of cancer in Barrett's esophagus: Explainable AI to lighten up the black-box

Lagergren, 2010, Oesophageal cancer, BMJ, 341, 10.1136/bmj.c6280 Dent, 2011, Barret's esophagus: a historical perspective, an update on core practicalities and predictions on future evolutions of management, J. Gastroenterol. Hepatol., 26, 11, 10.1111/j.1440-1746.2010.06535.x Lepage, 2008, Continuing rapid increase in esophageal adenocarcinoma in England and Wales, Am. J. Gastroenterol., 103, 2694, 10.1111/j.1572-0241.2008.02191.x Sharma, 2016, Development and validation of a classification system to identify high-grade dysplasia and esophageal adenocarcinoma in barrett's esophagus using narrow-band imaging, Gastroenterology, 150, 591, 10.1053/j.gastro.2015.11.037 Phoa, 2016, Multimodality endoscopic eradication for neoplastic Barrett's oesophagus: results of an European multicentre study (Euro-II), Gut, 65, 555, 10.1136/gutjnl-2015-309298 Sharma, 2015, White paper AGA: advanced imaging in barrett's esophagus, Clin. Gastroenterol. Hepatol., 13, 2209, 10.1016/j.cgh.2015.09.017 Abrams, 2009, Adherence to biopsy guidelines for barrett's esophagus surveillance in the community setting in the United States, Clin. Gastroenterol. Hepatol., 7, 736, 10.1016/j.cgh.2008.12.027 van der Sommen, 2014, Supportive automatic annotation of early esophageal cancer using local gabor and color features, Neurocomputing, 144, 92, 10.1016/j.neucom.2014.02.066 Shaheen, 2009, Radiofrequency ablation in barrett's esophagus with dysplasia, N. Engl. J. Med., 360, 2277, 10.1056/NEJMoa0808145 H Johnston, 2006, Cryoablation of Barrett's esophagus: a pilot study, Gastrointest. Endosc., 62, 842, 10.1016/j.gie.2005.05.008 Overholt, 2003, Photodynamic therapy for Barret's esophagus with dysplasia and/or early stage carcinoma: long-term results, Gastrointest. Endosc., 58, 183, 10.1067/mge.2003.327 Mirniaharikandehei, 2021, Applying a random projection algorithm to optimize machine learning model for predicting peritoneal metastasis in gastric cancer patients using ct images, Comput. Methods Progr. Biomed., 200, 105937, 10.1016/j.cmpb.2021.105937 Tsochatzidis, 2021, Integrating segmentation information into cnn for breast cancer diagnosis of mammographic masses, Comput. Methods Progr. Biomed., 200, 105913, 10.1016/j.cmpb.2020.105913 Souza, 2018, A survey on Barrett's esophagus analysis using machine learning, Comput. Biol. Med., 96, 203, 10.1016/j.compbiomed.2018.03.014 Souza, 2019, Learning visual representations with Optimum-Path Forest and its applications to Barrett's esophagus and adenocarcinoma diagnosis, Neural Comput. Appl., 32, 759, 10.1007/s00521-018-03982-0 Souza, 2017, Barrett's esophagus Analysis using SURF features, 141 Souza, 2018, Barrett's esophagus identification using color Co-occurrence matrices, 166 Souza, 2017, Barrett's esophagus identification using optimum-path forest, 308 Souza, 2020, Assisting barrett's esophagus identification using endoscopic data augmentation based on generative adversarial networks, Comput. Biol. Med., 104029, 10.1016/j.compbiomed.2020.104029 Souza, 2021, Fine-tuning generative adversarial networks using metaheuristics, 205 Mendel, 2017, Barrett's esophagus analysis using convolutional neural networks, 80 Ebigbo, 2020, Real-time use of artificial intelligence in the evaluation of cancer in Barrett's oesophagus, Gut, 69, 615, 10.1136/gutjnl-2019-319460 Ebigbo, 2019, Computer-aided diagnosis using deep learning in the evaluation of early oesophageal adenocarcinoma, Gut, 68, 1143, 10.1136/gutjnl-2018-317573 de Groof, 2020, Deep-learning system detects neoplasia in patients with Barrett's esophagus with higher accuracy than endoscopists in a Multistep Training and Validation study with benchmarking, Gastroenterology, 158, 915, 10.1053/j.gastro.2019.11.030 van der Putten, 2020, Deep principal dimension encoding for the classification of early neoplasia in Barrett's esophagus with volumetric laser endomicroscopy, Comput. Med. Imag. Graph., 80, 101701, 10.1016/j.compmedimag.2020.101701 Ma, 2020, Diagnostic classification of cancers using extreme gradient boosting algorithm and multi-omics data, Comput. Biol. Med., 121, 103761, 10.1016/j.compbiomed.2020.103761 Ellis, 2020, Impact of hybrid supervision approaches on the performance of artificial intelligence for the classification of chest radiographs, Comput. Biol. Med., 120, 103699, 10.1016/j.compbiomed.2020.103699 Passos, 2019, Barrett's esophagus analysis using infinity Restricted Boltzmann Machines, J. Vis. Commun. Image Represent., 59, 475, 10.1016/j.jvcir.2019.01.043 Bay, 2008, Speeded-up robust features (SURF), Comput Vis Image Und, 110, 346, 10.1016/j.cviu.2007.09.014 Lowe, 2004, Distinctive image features from scale-invariant keypoints, Int J Comput Vision, 60, 91, 10.1023/B:VISI.0000029664.99615.94 Papa, 2009, Supervised pattern classification based on Optimum-Path Forest, Int J Imag Syst Tech, 19, 120, 10.1002/ima.20188 Papa, 2012, Efficient supervised Optimum-Path Forest classification for large datasets, Pattern Recogn., 45, 512, 10.1016/j.patcog.2011.07.013 Peng, 2018, On better training the infinite Restricted Boltzmann Machines, Mach. Learn., 107, 943, 10.1007/s10994-018-5696-2 van der Putten, 2020, Multi-stage domain-specific pretraining for improved detection and localization of Barrett's neoplasia: a comprehensive clinically validated study, Artif. Intell. Med., 107, 101914, 10.1016/j.artmed.2020.101914 Y. Xie, G. Gao, X. A. Chen, Outlining the Design Space of Explainable Intelligent Systems for Medical Diagnosis, CoRR abs/1902.06019. arXiv:1902.06019. URL http://arxiv.org/abs/1902.06019. Cassel, 1981, Dementia in the elderly: an analysis of medical responsibility, Ann. Intern. Med., 94, 802, 10.7326/0003-4819-94-6-802 E. Tjoa, C. Guan, A Survey on Explainable Artificial Intelligence (XAI): towards Medical XAI, CoRR abs/1907.07374. arXiv:1907.07374. URL http://arxiv.org/abs/1907.07374. Doshi-Velez, 2017 Tonekaboni, 2019, 359 Lapuschkin, 2019, Unmasking clever hans predictors and assessing what machines really learn, Nat. Commun., 10, 10.1038/s41467-019-08987-4 Zucco, 2018, Explainable sentiment analysis with applications in medicine, 1740 Kallianos, 2019, How far have we come? artificial intelligence for chest radiograph interpretation, Clin. Radiol., 74, 338, 10.1016/j.crad.2018.12.015 Lamy, 2019, Explainable artificial intelligence for breast cancer: a visual case-based reasoning approach, Artif. Intell. Med., 94, 42, 10.1016/j.artmed.2019.01.001 Codella, 1805, 12234 Ribeiro, 2016, Why should I trust you?”: explaining the predictions of any classifier, 1135 L. H. Gilpin, D. Bau, B. Z. Yuan, A. Bajwa, M. Specter, L. Kagal, Explaining Explanations: an Approach to Evaluating Interpretability of Machine Learning, CoRR abs/1806.00069. arXiv:1806.00069. URL http://arxiv.org/abs/1806.00069. Barredo Arrieta, 2020, Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI, Inform Fusion, 58, 82, 10.1016/j.inffus.2019.12.012 A. D. Preece, D. Harborne, D. Braines, R. Tomsett, S. Chakraborty, Stakeholders in Explainable AI, CoRR Abs/1810.00184. arXiv:1810.00184. URL http://arxiv.org/abs/1810.00184. K. Simonyan, A. Vedaldi, A. Zisserman, Deep inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, CoRR Abs/1312.6034. arXiv:1312.6034. URL https://arxiv.org/abs/1312.6034. Springenberg, 2015, Striving for simplicity: the all convolutional net Zeiler, 2013 A. Shrikumar, P. Greenside, A. Shcherbina, A. Kundaje, Not Just a Black Box: Learning Important Features through Propagating Activation Differences, CoRR Abs/1605.01713. arXiv:1605.01713. URL http://arxiv.org/abs/1605.01713. M. Sundararajan, A. Taly, Q. Yan, Axiomatic Attribution for Deep Networks, CoRR abs/1703.01365. arXiv:1703.01365. URL http://arxiv.org/abs/1703.01365. Shrikumar, 2017, Learning important features through propagating activation differences, 3145 Yu, 2010, Otsu's thresholding method based on gray level-gradient two-dimensional histogram, vol. 3, 282 McHugh, 2012, Interrater reliability: the kappa statistic, Biochemia medica : časopis Hrvatskoga društva medicinskih biokemičara/, HDMB, 22, 276 Krizhevsky, 2012, Imagenet classification with deep convolutional neural networks, 1097 Iandola He, 2016, Deep residual learning for image recognition, 770 Simonyan, 2015, Very deep convolutional networks for large-scale image recognition Kingma, 2015, A method for stochastic optimization Kingma, 2015, A method for stochastic optimization Lovie, 1995, Who discovered Spearman's rank correlation?, Br. J. Math. Stat. Psychol., 48, 255, 10.1111/j.2044-8317.1995.tb01063.x Wilcoxon, 1945, Individual comparisons by ranking methods, Biometrics Bull., 1, 80, 10.2307/3001968 Gu, 2020, A case-based ensemble learning system for explainable breast cancer recurrence prediction, Artif. Intell. Med., 107, 101858, 10.1016/j.artmed.2020.101858 Moncada-Torres, 2021, Explainable machine learning can outperform cox regression predictions and provide insights in breast cancer survival, Sci. Rep., 11, 6968, 10.1038/s41598-021-86327-7 Sabol, 2020, Explainable classifier for improving the accountability in decision-making for colorectal cancer diagnosis from histopathological images, J. Biomed. Inf., 109, 103523, 10.1016/j.jbi.2020.103523 2008, Spearman rank correlation coefficient, 502