A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images

The first step in the diagnosis of gastric abnormalities is the detection of various abnormalities in the human gastrointestinal tract. Manual examination of endoscopy images relies on a medical practitioner’s expertise to identify inflammatory regions on the inner surface of the gastrointestinal tract. The length of the alimentary canal and the large volume of images obtained from endoscopic procedures make traditional detection methods time consuming and laborious. Recently, deep learning architectures have achieved better results in the classification of endoscopy images. However, visual similarities between different portions of the gastrointestinal tract pose a challenge for effective disease detection. This work proposes a novel system for the classification of endoscopy images by focusing on feature mining through convolutional neural networks (CNN). The model presented is built by combining a state-of-the-art architecture (i.e., EfficientNet B0) with a custom-built CNN architecture named Effimix. The proposed Effimix model employs a combination of squeeze and excitation layers and self-normalising activation layers for precise classification of gastrointestinal diseases. Experimental observations on the HyperKvasir dataset confirm the effectiveness of the proposed architecture for the classification of endoscopy images. The proposed model yields an accuracy of 97.99%, with an F1 score, precision, and recall of 97%, 97%, and 98%, respectively, which is significantly higher compared to the existing works.

[1]  Yan Jin,et al.  Polyp segmentation with convolutional MLP , 2022, The Visual Computer.

[2]  Muzhou Hou,et al.  Three feature streams based on a convolutional neural network for early esophageal cancer identification , 2022, Multimedia Tools and Applications.

[3]  L. Gool,et al.  Video Polyp Segmentation: A Deep Learning Perspective , 2022, Machine Intelligence Research.

[4]  Mohamed El Ansari,et al.  Fine-tuned deep neural networks for polyp detection in colonoscopy images , 2022, Personal and Ubiquitous Computing.

[5]  Zonggui Li,et al.  Diagnosis of ulcerative colitis from endoscopic images based on deep learning , 2022, Biomed. Signal Process. Control..

[6]  Yi Shen,et al.  Endoscopic image recognition method of gastric cancer based on deep learning model , 2021, Expert Syst. J. Knowl. Eng..

[7]  G. Carneiro,et al.  Balanced-MixUp for Highly Imbalanced Medical Image Classification , 2021, MICCAI.

[8]  Qingmin Liao,et al.  AFA-RN: An Abnormal Feature Attention Relation Network for Multi-class Disease Classification in gastrointestinal endoscopic images , 2021, 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI).

[9]  Pål Halvorsen,et al.  A self-learning teacher-student framework for gastrointestinal image classification , 2021, 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS).

[10]  Yixuan Yuan,et al.  DSI-Net: Deep Synergistic Interaction Network for Joint Classification and Segmentation With Endoscope Images , 2021, IEEE Transactions on Medical Imaging.

[11]  Xiongxiong He,et al.  EFAG-CNN: Effectively fused attention guided convolutional neural network for WCE image classification , 2021, 2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS).

[12]  Feng Zeng,et al.  An image classification model based on transfer learning for ulcerative proctitis , 2021, Multimedia Systems.

[13]  Şaban Öztürk,et al.  Residual LSTM layered CNN for classification of gastrointestinal tract diseases , 2020, J. Biomed. Informatics.

[14]  Soo Young Shin,et al.  A Deep Convolutional Neural Network for the Detection of Polyps in Colonoscopy Images , 2020, Biomed. Signal Process. Control..

[15]  Mohammad Motiur Rahman,et al.  Computerized classification of gastrointestinal polyps using stacking ensemble of convolutional neural network , 2021 .

[16]  G. Carneiro,et al.  A Hierarchical Multi-task Approach to Gastrointestinal Image Analysis , 2021, ICPR Workshops.

[17]  Shokoufeh Hatami,et al.  Detection and classification of gastric precancerous diseases using deep learning , 2020, 2020 6th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS).

[18]  Mohamed El Ansari,et al.  GastroNet: Abnormalities Recognition in Gastrointestinal Tract through Endoscopic Imagery using Deep Learning Techniques , 2020, 2020 8th International Conference on Wireless Networks and Mobile Communications (WINCOM).

[19]  Shuguang Cui,et al.  Adaptive Context Selection for Polyp Segmentation , 2020, MICCAI.

[20]  Tatsuya Mikami,et al.  Anatomical classification of upper gastrointestinal organs under various image capture conditions using AlexNet , 2020, Comput. Biol. Medicine.

[21]  Duc Tien Dang Nguyen,et al.  HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy , 2019, Scientific Data.

[22]  R. Bhattacharjee,et al.  Efficient Detection of Lesions During Endoscopy , 2020, ICPR Workshops.

[23]  D. Stoyanov,et al.  Hybrid Loss with Network Trimming for Disease Recognition in Gastrointestinal Endoscopy , 2020, ICPR Workshops.

[24]  Pooja,et al.  Automated Gastrointestinal Disease Recognition for Endoscopic Images , 2019, 2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS).

[25]  Diganta Misra,et al.  Mish: A Self Regularized Non-Monotonic Neural Activation Function , 2019, ArXiv.

[26]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[27]  Rajeev Srivastava,et al.  Computer Aided Medical Image Analysis for Capsule Endoscopy using Multi-class Classifier , 2019, 2019 IEEE 5th International Conference for Convergence in Technology (I2CT).

[28]  Christoph Palm,et al.  Learning visual representations with optimum-path forest and its applications to Barrett’s esophagus and adenocarcinoma diagnosis , 2019, Neural Computing and Applications.

[29]  Hélder P. Oliveira,et al.  Lesions Multiclass Classification in Endoscopic Capsule Frames , 2019, CENTERIS/ProjMAN/HCist.

[30]  Dimitris K. Iakovidis,et al.  Detecting and Locating Gastrointestinal Anomalies Using Deep Learning and Iterative Cluster Unification , 2018, IEEE Transactions on Medical Imaging.

[31]  Elena De Momi,et al.  Learning-based classification of informative laryngoscopic frames , 2018, Comput. Methods Programs Biomed..

[32]  Mubashir Husain Rehmani,et al.  Computer Assisted Gastric Abnormalities Detection Using Hybrid Texture Descriptors for Chromoendoscopy Images , 2018, Comput. Methods Programs Biomed..

[33]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[34]  P. Sivakumar,et al.  A novel method to detect bleeding frame and region in wireless capsule endoscopy video , 2018, Cluster Computing.

[35]  Mohamed El Ansari,et al.  Computer-aided diagnosis system for colon abnormalities detection in wireless capsule endoscopy images , 2017, Multimedia Tools and Applications.

[36]  Joan Lu,et al.  University of Huddersfield Repository Examining applying high performance genetic data feature selection and classification algorithms for colon cancer diagnosis Examining Applying High Performance Genetic Data Feature Selection and Classification Algorithms for Colon Cancer Diagnosis , 2022 .

[37]  Ahnaf Rashik Hassan,et al.  Computer-aided gastrointestinal hemorrhage detection in wireless capsule endoscopy videos , 2015, Comput. Methods Programs Biomed..

[38]  Amy Wang,et al.  The role of endoscopy in the management of GERD. , 2015, Gastrointestinal endoscopy.