Explainable AI for COVID-19 prognosis from early Chest X-ray and clinical data in the context of the COVID-CXR international hackathon

Although many AI-based scientific works regarding chest X-ray (CXR) interpretation focused on COVID-19 diagnosis, fewer papers focused on other relevant tasks, like severity estimation, deterioration, and prognosis. The same holds for explainable decisions to estimate COVID-19 prognosis as well. The international hackathon launched during Dubai Expo 2020, aimed at designing machine learning solutions to help physicians formulate COVID-19 patients' prognosis, was the occasion to develop a machine learning model capable of predicting such prognoses and justifying them through interpretable explanations. The large hackathon dataset comprised subjects characterized by their CXR and numerous clinical features collected during triage. To calculate the prognostic value, our model considered both patients' CXRs and clinical features. After automatic pre-processing to improve their quality, CXRs were processed by a Deep Learning model to estimate the lung compromise degree, which has been considered as an additional clinical feature. Original clinical parameters suffered from missing values that were adequately handled. We trained and evaluated multiple models to find the best one and fine-tune it before the inference process. Finally, we produced novel explanations, both visual and numerical, to justify the model predictions. Ultimately, our model processes a CXR and several clinical data to estimate a patient's prognosis related to the COVID-19 disease. It proved to be accurate and was ranked second in the final rankings with 75%, 73.9%, and 74.4% in sensitivity, specificity, and balanced accuracy, respectively. In terms of model explainability, it was ranked first since it was agreed to be the most interpretable by health professionals. © 2023 SPIE.

HANDLING SEVERE DATA IMBALANCE IN CHEST X-RAY IMAGE CLASSIFICATION WITH TRANSFER LEARNING USING SWAV SELF-SUPERVISED PRE-TRAINING

Ever since the COVID-19 outbreak, numerous researchers have attempted to train accurate Deep Learning (DL) models, especially Convolutional Neural Networks (CNN), to assist medical personnel in diagnosing COVID-19 infections from Chest X-Ray (CXR) images. However, data imbalance and small dataset sizes have been an issue in training DL models for medical image classification tasks. On the other hand, most researchers focused on complex novel methods instead and few explored this problem. In this research, we demonstrated how Self-Supervised Learning (SSL) can assist DL models during pre-training, and Transfer Learning (TL) can be used in training the models, which can produce models that are more robust to data imbalance. The Swapping Assignment between Views (SwAV) algorithm in particular has been known to be outstanding in enhancing the accuracy of CNN models for classification tasks after TL. By training a ResNet-50 model pre-trained using SwAV on a severely imbalanced CXR dataset, the model managed to greatly outperform its counterpart pre-trained in a standard supervised manner. The SwAV-TL ResNet-50 model attained 0.952 AUROC with 0.821 macro-averaged F1 score when trained on the imbalanced dataset. Hence, it was proven that TL using models pre-trained through SwAV can achieve better accuracy even when the dataset is severely imbalanced, which is usually the case in medical image datasets. © 2023, SCIK Publishing Corporation. All rights reserved.

Covid-19 Disease Detection with Improved Deep Learning Algorithms on X-Ray Data

The COVID-19 pandemic has brought human life to a startling halt around the world from the moment it emerged and took thousands of lives. The health system has come to the point of collapse, many people in the world have died from being infected, and many people who have survived the disease have had permanent lung damage with the spread of COVID-19 in 212 countries and regions. In this study, an answer is sought to diagnose the disease-causing virus through Artificial Intelligence Algorithms. The aim of the study is to accelerate the diagnosis and treatment process of COVID-19 disease. Enhancements were made using Deep Learning methods, including CNN, VGG16, DenseNet121, and ResNet50. For this study, the disease was detected by using X-Ray images of patients with and without COVID-19 disease, and then it was evaluated how to increase the accuracy rate with the limited available data. To increase the accuracy rate, the results of data augmentation on the image data were examined and the time complexity of the algorithms with different layers was evaluated. As a result of the study, it was seen that data augmentation increased the performance rate in all algorithms and the ResNet50 algorithm was more successful than other algorithms. © 2022 IEEE.

Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training

Federated learning, which shares the weights of the neural network across clients, is gaining attention in the healthcare sector as it enables training on a large corpus of decentralized data while maintaining data privacy. For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals. Unfortunately, the exchange of the weights quickly consumes the network bandwidth if highly expressive network architecture is employed. So-called split learning partially solves this problem by dividing a neural network into a client and a server part, so that the client part of the network takes up less extensive computation resources and bandwidth. However, it is not clear how to find the optimal split without sacrificing the overall network performance. To amalgamate these methods and thereby maximize their distinct strengths, here we show that the Vision Transformer, a recently developed deep learning architecture with straightforward decomposable configuration, is ideally suitable for split learning without sacrificing performance. Even under the non-independent and identically distributed data distribution which emulates a real collaboration between hospitals using CXR datasets from multiple sources, the proposed framework was able to attain performance comparable to data-centralized training. In addition, the proposed framework along with heterogeneous multi-task clients also improves individual task performances including the diagnosis of COVID-19, eliminating the need for sharing large weights with innumerable parameters. Our results affirm the suitability of Transformer for collaborative learning in medical imaging and pave the way forward for future real-world implementations. © 2021 Neural information processing systems foundation. All rights reserved.

Covid-19 Diagnosis: Comparative Approach Between Chest X-Ray and Blood Test Data

The Covid-19 virus has made a major impact on the world and is still spreading rapidly. A reliable solution to prevent further damage, early diagnosis of coronavirus patients are incredibly important. While chest X-Ray diagnosis is the easiest and fastest solution for this, an average radiologist has only a 75% to 85% accuracy when evaluating X-Ray data, thus it is desirable to achieve an accurate artificial network for this. Throughout this study, chest X-Ray data and blood routine test data are utilised and compared. X-Ray data consists of 5000 chest X-Ray images which are gathered from an open-source research and from a local hospital in which both have anonymous data. The blood test results were also taken from the same hospital. For the chest X-Ray diagnosis we utilised two of the popular convolutional neural networks, which are Resnet18 and Squeezenet and concluded that Resnet18 provided slightly more accurate results, while both having almost 98% accuracy. For blood test diagnosis, a feed-forward multi layer neural network was used. Even though it was worked on an insufficient dataset, 72% accuracy was obtained, thus making it a feasible option for further research. Hence, we concluded that in general chest X-Ray diagnosis is preferable over routine blood test diagnosis and the usage of AI yields better approximate results than humans. © 2021 IEEE

Requirement analysis for an artificial intelligence model for the diagnosis of the COVID-19 from chest X-ray data

There are multiple papers published about different AI models for the COVID-19 diagnosis with promising results. Unfortunately according to the reviews many of the papers do not reach the level of sophistication needed for a clinically usable model. In this paper I go through multiple review papers, guidelines, and other relevant material in order to generate more comprehensive requirements for the future papers proposing a AI based diagnosis of the COVID-19 from chest X-ray data (CXR). Main findings are that a clinically usable AI needs to have an extremely good documentation, comprehensive statistical analysis of the possible biases and performance, and an explainability module. © 2021 IEEE.