Automated identification of human gastrointestinal tract abnormalities based on deep convolutional neural network with endoscopic images

As a powerful analytic tool for medical image analysis, particularly for endoscopic image interpretation, deep convolutional neural network (DCNN) has gained remarkable attention due to its capacity to provide results comparable to or even exceeding those of medical experts. Automated identification of gastrointestinal abnormalities with endoscopic images is a challenging task even for experienced gastroenterologists which could greatly aid medical diagnosis and reduce the time and cost of investigational procedures. Nonetheless, in medical diagnosis, the human gastrointestinal tract findings are manually determined, and greatly depend on the prowess of the gastrointestinal endoscopist. In addition, this evaluation is laborious and onerous, and there is also a high degree of intra- and inter-laboratory discrepancy in the outcomes. With the aim of preventing these issues, a specialized DCNN architecture is proposed to accurately identify human gastrointestinal abnormalities with endoscopic images. It is meticulously designed with multiple routes, various image resolutions and several convolutional layers to improve the efficacy and performance. The results of our proposed deep learning-based method are presented in terms of specificity, recall, area under the receiver operating characteristics (AUROC) and other metrics in Kvasir dataset. The experimental results of the proposed algorithm outdo recent techniques, exhibiting 0.9743 Matthews correlation coefficient (MCC), and can be used to assist gastroenterologists for the classification of gastrointestinal tract abnormalities. Proposed model is also assessed on skewed Kvasir-Capsule dataset to show its genericity. Consequently, this approach offers an innovative and attainable way for accelerating and systematizing the classification of human gastrointestinal abnormalities along with saving time and exertion.