![]() This study is applied on a vehicle dataset. In this work, we presented the evolution of effects of image resizing on model training time and performance. A larger input image requires the neural network to learn from four times as many pixels, and this increase the training time for the architecture. Principally, deep learning models train faster on small images. Resizing images is a critical pre-processing step in computer vision. ![]() To the best of our knowledge, this is the first time that various applications of interpretability methods for disease diagnosis have been summarized. ![]() In addition, the challenges of interpretability and future research directions are also discussed here. ![]() Therefore, in this paper, we comprehensively review the interpretability of deep learning in medical diagnosis based on the current literature, including some common interpretability methods used in the medical domain, various applications with interpretability for disease diagnosis, prevalent evaluation metrics, and several disease datasets. To overcome this problem, several studies on interpretability have been proposed. This creates a barrier to the application of deep learning models in clinical practice due to lack of interpretability, trust, and transparency. However, it has a significant problem that these models are “black-box” structures, which means they are opaque, non-intuitive, and difficult for people to understand. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.ĭeep learning has demonstrated remarkable performance in the medical domain, with accuracy that rivals or even exceeds that of human experts. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient’s symptoms and/or an examination. In the medical field, any judgment or decision is fraught with risk. Furthermore, the Explainable AI technique provides additional insights into the model's decision-making process, which can be used to improve the quality of care for patients.Īrtificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. The results show that our approach achieves superior performance in terms of accuracy (91.40%), precision, recall, and F1 score compared to several state-of-the-art methods. An Explainable AI technique is incorporated to make the model more interpretable and explainable, allowing clinicians to understand the model's decision-making process and provide insights into the underlying factors driving the diagnosis. The model is then optimized using a hyper-parameter tuning technique to improve its accuracy and generalization performance. The method is built on a state-of-the-art Vision Transformer architecture that has been fine-tuned on a diverse dataset of medical images. The proposed method aims to accurately diagnose eye diseases from medical images, improving patient outcomes and reducing the burden on ophthalmologists. Hence, this research presents a novel eye disease detection and classification approach using a hyper-tuned Vision Transformer model with Explainable AI techniques. Current research focuses on systems that identify eye diseases using artificial intelligence. Timely and accurate detection and classification of eye diseases are crucial for effective treatment and management. Eye disease is a significant health issue that affects millions of people worldwide.
0 Comments
Leave a Reply. |