Derin öğrenme tabanlı topluluk sınıflandırıcı yaklaşımı ile gastrointestinal anomalilerin tespiti

Öz

Gastrointestinal bölgede yer alan anomalilerin teşhisi güncel bir araştırma alanıdır. Bu bölgenin incelenmesi için kablosuz kapsül endoskopi (WCE), geleneksel endoskopinin risklerini önlemek ve ağrısız bir süreç sağlamak amacıyla tercih edilen alternatif bir teknolojidir. Fakat birçok avantaja sahip bu teknoloji, düşük çerçeve yoğunluğu sunmaktadır. Verilerin kalitesini etkileyen bu durum, teşhis doğruluk oranının düşmesine neden olmaktadır. Bu çalışmada KID Atlas Veri kümesi 2’den elde edilen WCE endoskopi görüntüleri kullanılmış ve gatrointestinal bölgedeki inflammatory anomali, vascular anomali, polypoid anomali ve normal görüntü kategorilerinin tespiti için üç aşamalı yapay zeka destekli bir tanı süreci geliştirilmiştir. İlk aşama için 5 farklı yaklaşım kullanılarak görüntüler üzerindeki kritik noktalar belirginleştirilmiştir. İyileştirilen bu görüntüler, bölge öneri temelli bir nesne tanıma algoritması ile sınıflandırılmıştır ve kullanılan yaklaşımlara göre performans karşılaştırması yapılmıştır. İkinci aşamada, ilk aşamada maksimum performans gösteren iyileştirilmiş verilere görüntü çoğaltma tekniği uygulanmıştır. Böylece dengeli ve yeterli sayıda görüntü içeren bir veri kümesi oluşturulmuştur. Üçüncü aşamada bu güncel veri kümesi beş ayrı nesne tanıma algoritması ile sınıflandırılmıştır. Ancak her bir algoritmanın sahip olduğu bireysel başarı farklıdır. Bu nedenle her bir kategori için kararlı çıktılar elde etmek ve kategoriler arasında dengeli bir tespit süreci oluşturmak için topluluk öğrenme yaklaşımı kullanılmıştır. Son olarak inşa edilen bu hibrit yapı ile kategoriler arasında dengeli ve kararlı bir tahmin işlevi sağlanmıştır.

Anahtar Kelimeler

• Gastrointestinal anomaliler
• Kablosuz kapsül endoskopi
• Derin öğrenme
• Topluluk öğrenme

Detection of gastrointestinal anomalies with a deep learning-based ensemble classifier approach

Abstract

Diagnosis of anomalies in the gastrointestinal tract is a current research area. Wireless capsule endoscopy (WCE) for the evaluation of this region is a preferred alternative technology to avoid the risks of traditional endoscopy and to provide a painless process. But this technology, which has many advantages, offers low frame density. This situation affects the quality of the data and causes to a decrease in the diagnostic accuracy rate. In this study, WCE endoscopy images obtained from KID Atlas Dataset 2 were used and a three-stage artificial intelligence-supported diagnostic process was developed for the detection of the inflammatory anomaly, vascular anomaly, polypoid anomaly and normal image categories in the gastrointestinal tract. For the first stage, critical points on the images were clarified using 5 different approaches. These improved images were classified with a region proposal-based object recognition algorithm and performance comparison was made according to the approaches used. In the second stage, the data augmentation technique was applied to the improved images that showed maximum performance in the first stage. Thus, a dataset with a balanced and sufficient number of images was created. In the third stage, this current dataset was classified with five different object recognition algorithms. However, the individual success of each algorithm is different. For this reason, the ensemble learning approach was used to obtain stable outputs for each category and to create a balanced detection process among the categories. Finally, a balanced and stable estimation function was provided between categories with this hybrid structure.

Keywords

• Gastrointestinal anomalies
• Wireless capsule endoscopy
• Deep learning
• Ensemble learning

Kaynakça

1. [1] Öner RY. Sindirim Sistemi Rahatsızlıklarında Kullanılan Tıbbi Çay Formülleri. Yüksek Lisans Tezi, İstanbul Üniversitesi, İstanbul, Türkiye, 2019.
2. [2] Sushma B, Aparna P. “Recent developments in wireless capsule endoscopy imaging: Compression and summarization techniques”. Computers in Biology and Medicine, 149, 1-15, 2022.
3. [3] Iakovidis DK, Georgakopoulos SV, Vasilakakis M, Koulaouzidis A, Plagianakos VP. “Detecting and Locating Gastrointestinal Anomalies Using Deep Learning and Iterative Cluster Unification”. IEEE Transactıons on Medical Imaging, 37(10), 2196-2210, 2018.
4. [4] Du W, Rao N, Liu D, Jiang H, Luo C, Li Z, Gan T, Zeng B. “Review on the Applications of Deep Learning in the Analysis of Gastrointestinal Endoscopy Images”. IEEE Access, 7, 142053-142069, 2019.
5. [5] Akalın F, Yumuşak N. İnce Bağırsak Görüntüleri Üzerinde Sezgisel Algoritma Teknikleri ile Polip Teşhisi. Yüksek Lisans Tezi, Sakarya üniversitesi, Sakarya, Türkiye, 2020.
6. [6] Muhammad K, Khan S, Kumar N, Del Ser J, Mirjalili S. “Vision-based personalized Wireless Capsule Endoscopy for smart healthcare: Taxonomy, literature review, opportunities and challenges”. Future Generation Computer Systems, 113, 266-280, 2020.
7. [7] Jain S, Seal A, Ojha A, Yazidi A, Bures J, Tacheci I, Krejcar O. “A deep CNN model for anomaly detection and localization in wireless capsule endoscopy images”. Computers in Biology and Medicine, 137, 1-14, 2021.
8. [8] Xing, X, Yuan Y, Meng MQH. “Zoom in Lesions for Better Diagnosis: Attention Guided Deformation Network for WCE Image Classification”. IEEE Transactions on Medical Imaging, 39(12), 4047-4059, 2020.

9. [9] Iqbal I, Walayat K, Kakar MU, Ma J. “Automated identification of human gastrointestinal tract abnormalities based on deep convolutional neural network with endoscopic images”. Intelligent Systems with Applications, 16, 1-14, 2022.
10. [10] Shin Y, Qadir HA, Aabakken L, Bergsland J, Balasingham I. “Automatic colon polyp detection using region based deep CNN and post learning approaches”. IEEE Access, 6, 40950-40962, 2018.
11. [11] Byrne MF, Chapados N, Soudan F, Oertel C, Perez ML, Kelly R, Iqbal N, Chandelier F, Rex DK. “Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model”. Endoscopy, 68, 94-100, 2019.
12. [12] Jia X, Meng MQH. “A deep convolutional neural network for bleeding detection in Wireless Capsule Endoscopy images”. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 639-642, 2016.
13. [13] Liu X, Wang C, Hu Y, Zeng Z, Bai J, Liao G. “Transfer Learning with Convolutional Neural Network for Early Gastric Cancer Classification on Magnifiying Narrow-Band Imaging Images”. 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, 07-10 October 2018.
14. [14] Yu L, Chen H, Dou Q, Qin J, Heng PA. “Integrating online and offline three-dimensional deep learning for automated polyp detection in colonoscopy videos”. IEEE Journal of Biomedical and Health Informatics, 21(1), 65-75, 2017.
15. [15] Ali H, Sharif M, Yasmin M, Rehmani MH, Riaz F. “A survey of feature extraction and fusion of deep learning for detection of abnormalities in video endoscopy of gastrointestinal-tract”. Artificial Intelligence Review, 53(4), 2635-2707, 2020.
16. [16] Xing X, Yuan Y, Jia X, Max QHM. “A saliency-aware hybrid dense network for bleeding detection in wireless capsule endoscopy images”. International Symposium on Biomedical Imaging (ISBI), Venice, Italy, 08-11 April 2019.
17. [17] Muruganantham P, Balakrishnan SM. “A survey on deep learning models for wireless capsule endoscopy image analysis”. International Journal of Cognitive Computing in Engineering, 2, 83-92, 2021.
18. [18] Aliyi S, Dese K, Raj H. “Detection of gastrointestinal tract disorders using deep learning methods from colonoscopy ımages and videos”. Scientific African, 20, 1-17, 2023.
19. [19] Pannala R. Krishnan K, Melson J, Parsi MA, Schulman A, Sullivan S, Trikudanathan G, Trindade A, Watson R, Maple J, Lichtenstein DR. “Artificial intelligence in gastrointestinal endoscopy”, Artificial Intelligence in Gastrointestinal Endoscopy, 5(12), 598-613, 2020.
20. [20] Koulaouzidis A, Iakovidis DK, Yung DE, Rondonotti E, Kopylov U, Plevris, Toth E, Eliakim A, Johansson GW, Marlicz W, Mavrogenis G, Nemeth A, Thorlacius H, Tontini GE. “KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes”. Endoscopy International Open, 05, E477-E483, 2017.
21. [21] Akalın F, Yumuşak N. “DNA genom dizilimi üzerinde dijital sinyal işleme teknikleri kullanılarak elde edilen ekson ve intron bölgelerinin EfficientNetB7 mimarisi ile sınıflandırılması”. Journal of the Faculty of Engineering and Architecture of Gazi University, 37(3), 1355-1371, 2022.
22. [22] Pérez-García F, Sparks R, Ourselin S. “TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning”. Computer Methods and Programs in Biomedicine, 208, 1-12, 2021.
23. [23] Akalın F, Yumuşak N. “Özellik seçim algoritmaları ve derin öğrenme tabanlı mimarilerin hibrit kullanımıyla akut lösemilerin sınıflandırılması”. Pamukkale University Journal of Engineering Sciences, 29(3), 256-263, 2023.
24. [24] Bilginer O, Tunga B, Demirer RM. “Classification of skin lesions using convolutional neural networks”. Pamukkale University Journal of Engineering Sciences, 28(2), 208-214, 2022.
25. [25] Dheir IM, Naser SSA. “Classification of Anomalies in Gastrointestinal Tract Using Deep Learning”. International Journal of Academic Engineering Research (IJAER), 6(3), 15-28, 2022.
26. [26] Akalın F, Yumuşak N. “Detection and classification of white blood cells with an improved deep learning-based approach”. Turkish Journal of Electrical Engineering and Computer Sciences. 30(7), 2725-2739, 2022.
27. [27] Georgakopoulos SV, Iakovidis DK, Vasilakakis M, Plagianakos VP, Koulaouzidis A. “Weakly-supervised Convolutional learning for detection of inflammatory gastrointestinal lesions”. IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings, Chania, Greece, 04-06 October 2016.
28. [28] Zhao Q, Yang W, Liao Q. “AFA-RN: An Abnormal Feature Attention Relation Network for Multi-class Disease Classification in gastrointestinal endoscopic images”. EMBS International Conference on Biomedical and Health Informatics (BHI), Athens, Greece, 27-30 July 2021.
29. [29] Raut V, Gunjan R, Shete VV, Eknath UD. “Gastrointestinal tract disease segmentation and classification in wireless capsule endoscopy using intelligent deep learning model”, Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization, 2022. https://doi.org/10.1080/21681163.2022.2099298.
30. [30] Jain S, Seal A, Ojha A. “A Hybrid Convolutional Neural Network with Meta Feature Learning for Abnormality Detection in Wireless Capsule Endoscopy Images". Arxiv, 2022. https://doi.org/10.48550/arXiv.2207.09769
31. [31] Yuan Y, Li B, Meng MQH. “Improved Bag of Feature for Automatic Polyp Detection in Wireless Capsule Endoscopy Images”. IEEE Transactions on Automation Science and Engineering, 13(2), 529-535, 2016.
32. [32] Sasmal P, Bhuyan MK, Dutta S, Iwahori Y. “An unsupervised approach of colonic polyp segmentation using adaptive markov random fields”. Pattern Recognition Letters, 154, 7-15, 2022.