Patho AI: Automated Medical Image Analysis for the Identification of Gastrointestinal Disorders
##plugins.themes.bootstrap3.article.main##
Abstract
Artificial intelligence (AI) has the potential to significantly improve diagnostic procedures in modern healthcare, especially in pathology. This work presents PathoAI, a project to automate pathology picture processing with emphasis on gastrointestinal illness detection. By utilizing the Kvasir dataset, which offers a wide range of endoscopic pictures, this study aims to provide an extensive record of the project's goals, processes, execution, and assessment. PathoAI seeks to advance the creation of a reliable system for computer-aided diagnosis in gastrointestinal pathology by utilizing state-of-the-art deep learning algorithms for multi-class picture classification. Many illnesses can have an impact on the digestive tract in humans. Endoscopy is the most effective method for inspecting the GI tract. Since it influences decisions about therapy and follow-up, accurately identifying underlying issues in endoscopic images is crucial. In areas where medical professionals are few, automated recognition of these kinds of problems functions independently as a decision support system for the experts. In order to automate the process with neural networks, an expert-labeled dataset must be utilized for training the networks. Anatomical landmarks, pathological findings, and endoscopic operations in the GI tract are all shown in the publicly accessible dataset Kvasir [1]. There are 4000 photos in everything, 500 images in each of the 8- classes. Found image classes
##plugins.themes.bootstrap3.article.details##
References
[2]. Alaskar, H., Al-Mallah, M., & Al-Ahmad, H. (2020). Gastrointestinal polyp detection in wireless capsule endoscopy using deep learning convolutional neural networks. Future Generation Computer Systems, 105, 802-809
[3]. Qaiser, F., Younis, M. H., & Khan, M. A. (2019). Kvasir: A Multi-Class Image Dataset for Computer-Aided Gastrointestinal Disease Detection. arXiv preprint arXiv:1904.06487.
[4]. Wang, H., Li, L., & Li, W. Q. (2019). Capsule network for automated classification of gastrointestinal ulcer images. IEEE Access, 7, 30302-30310.
[5]. Byrne MF, Chapados N, Soudan F, Oertel C, Linares Pérez M, 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. Gut. 2019
[6]. Park, S., Yang, S., & Won, J. (2018). Support Vector Machine-Based Classification for and Malignant Colorectal Lesions Using Endoscopic Images. International Journal of Environmental Research and Public Health, 15(11), 2524.
[7]. Iakovidis, D. K. (2017). Automated gastrointestinal disease classification from endoscopic images: A review on deep learning methods. Computer Methods and Programs in Biomedicine, 152, 133-143.
[8]. Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2016). Convolutional neural networks for medical image analysis: Full training or fine tuning?. IEEE Transactions on Medical Imaging, 35(5), 1299-1312.
[9]. Li B, Meng MQ. Automatic polyp detection for wireless capsule endoscopy images. Expert Syst Applications. 2012 Sep;39 (12): 10952 – 10958. Doi :10. 1016 /j.eswa.2012.03.029