StomachNet: Optimal Deep Learning Features Fusion for Stomach Abnormalities Classification

A fully automated design is proposed in this work employing optimal deep learning features for classifying gastrointestinal infections. Here, three prominent infections– ulcer, bleeding, polyp and a healthy class are considered as class labels. In the initial stage, the contrast is improved by fusing bi-directional histogram equalization with top-hat filtering output. The resultant fusion images are then passed to ResNet101 pre-trained model and trained once again using deep transfer learning. However, there are challenges involved in extracting deep learning features including impertinent information and redundancy. To mitigate this problem, we took advantage of two metaheuristic algorithms– Enhanced Crow Search and Differential Evolution. These algorithms are implemented in parallel to obtain optimal feature vectors. Following this, a maximum correlation-based fusion approach is applied to fuse optimal vectors from the previous step to obtain an enhanced vector. This final vector is given as input to Extreme Learning Machine (ELM) classifier for final classification. The proposed method is evaluated on a combined database. It accomplished an accuracy of 99.46%, which shows significant improvement over preceding techniques and other neural network architectures.

[1]  Shaikh Anowarul Fattah,et al.  Least Square Saliency Transformation of Capsule Endoscopy Images for PDF Model Based Multiple Gastrointestinal Disease Classification , 2020, IEEE Access.

[2]  Muhammad Attique Khan,et al.  Medical Imaging Fusion Techniques: A Survey Benchmark Analysis, Open Challenges and Recommendations , 2020, J. Medical Imaging Health Informatics.

[3]  Salima Ouadfel,et al.  Enhanced Crow Search Algorithm for Feature Selection , 2020, Expert Syst. Appl..

[4]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[5]  Muhammad Sharif,et al.  Stomach Deformities Recognition Using Rank-Based Deep Features Selection , 2019, Journal of Medical Systems.

[6]  Panos Liatsis,et al.  Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images , 2019, Sensors.

[7]  P. Swain,et al.  Wireless capsule endoscopy. , 2002, The Israel Medical Association journal : IMAJ.

[8]  Muhammad Rashid,et al.  Classification of gastrointestinal diseases of stomach from WCE using improved saliency-based method and discriminant features selection , 2019, Multimedia Tools and Applications.

[9]  Muhammad Rashid,et al.  Deep CNN and geometric features-based gastrointestinal tract diseases detection and classification from wireless capsule endoscopy images , 2019, J. Exp. Theor. Artif. Intell..

[10]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[11]  Muhammad Shaheen,et al.  Importance of Features Selection, Attributes Selection, Challenges and Future Directions for Medical Imaging Data: A Review , 2020, Computer Modeling in Engineering & Sciences.

[12]  Yeong-Taeg Kim,et al.  Contrast enhancement using brightness preserving bi-histogram equalization , 1997 .

[13]  Suresh Chandra Satapathy,et al.  Gastrointestinal diseases segmentation and classification based on duo-deep architectures , 2020, Pattern Recognit. Lett..

[14]  Jamal Hussain Shah,et al.  AUTOMATED ULCER AND BLEEDING CLASSIFICATION FROM WCE IMAGES USING MULTIPLE FEATURES FUSION AND SELECTION , 2018, Journal of Mechanics in Medicine and Biology.

[15]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Aymeric Histace,et al.  Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer , 2014, International Journal of Computer Assisted Radiology and Surgery.

[17]  Fernando Vilariño,et al.  WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians , 2015, Comput. Medical Imaging Graph..

[18]  Gavriel Salomon,et al.  T RANSFER OF LEARNING , 1992 .

[19]  Abdul Majid,et al.  Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection , 2020, Microscopy research and technique.

[20]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[22]  Muhammad Attique Khan,et al.  Gastric Tract Infections Detection and Classification from Wireless Capsule Endoscopy using Computer Vision Techniques: A Review. , 2020, Current medical imaging.

[23]  Khan Muhammad,et al.  Three-dimensional reconstruction of CT image features based on multi-threaded deep learning calculation , 2020, Pattern Recognit. Lett..

[24]  Javier Del Ser,et al.  Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Y Kopelman,et al.  Diagnosing small bowel Crohn’s disease with wireless capsule endoscopy , 2003, Gut.

[26]  Sung Wook Baik,et al.  An efficient computerized decision support system for the analysis and 3D visualization of brain tumor , 2018, Multimedia Tools and Applications.

[27]  Junaid Ali Khan,et al.  Human action recognition using fusion of multiview and deep features: an application to video surveillance , 2020, Multimedia Tools and Applications.

[28]  Wei Zhang,et al.  Computer-Aided Bleeding Detection in WCE Video , 2014, IEEE Journal of Biomedical and Health Informatics.

[29]  R. Spiller,et al.  Intestinal Disorders , 2012, Clinical Veterinary Advisor.

[30]  Muhammad Attique Khan,et al.  Automated design for recognition of blood cells diseases from hematopathology using classical features selection and ELM , 2020, Microscopy research and technique.

[31]  Rafal Scherer,et al.  Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists , 2020, Diagnostics.

[32]  Thomas de Lange,et al.  Kvasir-SEG: A Segmented Polyp Dataset , 2019, MMM.

[33]  Seifedine Kadry,et al.  Computer-Aided Gastrointestinal Diseases Analysis From Wireless Capsule Endoscopy: A Framework of Best Features Selection , 2020, IEEE Access.

[34]  Tai-Hsi Wu,et al.  Bleeding and Ulcer Detection Using Wireless Capsule Endoscopy Images , 2014 .

[35]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[36]  Tanzila Saba,et al.  Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture , 2020, Microscopy research and technique.

[37]  Tallha Akram,et al.  Skin lesion segmentation and recognition using multichannel saliency estimation and M-SVM on selected serially fused features , 2018, Journal of Ambient Intelligence and Humanized Computing.

[38]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[39]  Chung-Feng Jeffrey Kuo,et al.  Gaussian probability bi‐histogram equalization for enhancement of the pathological features in medical images , 2019, Int. J. Imaging Syst. Technol..

[40]  A. Jemal,et al.  Cancer statistics, 2016 , 2016, CA: a cancer journal for clinicians.

[41]  Fernando Vilariño,et al.  Towards automatic polyp detection with a polyp appearance model , 2012, Pattern Recognit..

[42]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).