Development of an acquisition system to monitoring asynchronous tele-ultrasound for lung patients

Lung ultrasound imaging allows the detection and evaluation of the lung damage generated by COVID-19. However, several infrastructure and logistical limitations prevent them from being carried out in isolated and remote areas. In this work, a system for the acquisition of medical images through asynchronous tele-ultrasounds was developed. The system is based on a graphical user interface, which records the three video cameras, the ultrasound image and the accelerometer simultaneously. The interface was developed according to the Volume Sweep Imaging acquisition protocol. The translational and rotational movement of the transducer are tracked and monitored by the accelerometer and the position of the transducer is obtained from the images acquired by the three video cameras. The results show a correct functioning of the system overall, being viable to be implemented for data acquisition and calculation of error, although in order to validate the error calculation there is still more research to be done. © 2023 SPIE.

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Biomedical image segmentation (BIS) task is challenging due to the variations in organ types, position, shape, size, scale, orientation, and image contrast. Conventional methods lack accurate and automated designs. Artificial intelligence (AI)-based UNet has recently dominated BIS. This is the first review of its kind that microscopically addressed UNet types by complexity, stratification of UNet by its components, addressing UNet in vascular vs. non-vascular framework, the key to segmentation challenge vs. UNet-based architecture, and finally interfacing the three facets of AI, the pruning, the explainable AI (XAI), and the AI-bias. PRISMA was used to select 267 UNet-based studies. Five classes were identified and labeled as conventional UNet, superior UNet, attention-channel UNet, hybrid UNet, and ensemble UNet. We discovered 81 variations of UNet by considering six kinds of components, namely encoder, decoder, skip connection, bridge network, loss function, and their combination. Vascular vs. non-vascular UNet architecture was compared. AP(ai)Bias 2.0-UNet was identified in these UNet classes based on (i) attributes of UNet architecture and its performance, (ii) explainable AI (XAI), and, (iii) pruning (compression). Five bias methods such as (i) ranking, (ii) radial, (iii) regional area, (iv) PROBAST, and (v) ROBINS-I were applied and compared using a Venn diagram. Vascular and non-vascular UNet systems dominated with sUNet classes with attention. Most of the studies suffered from a low interest in XAI and pruning strategies. None of the UNet models qualified to be bias-free. There is a need to move from paper-to-practice paradigms for clinical evaluation and settings.

A reliable and fully automated diagnosis of COVID-19 based on computed tomography

Coronavirus or COVID-19 is an infectious disease that has been identified in humans. The symptoms range from mild to extremely severe when a person infected with COVID-19 may suffer from pneumonia. Chest imaging that may include radiography, computed tomography (CT), and ultra-sound can be used for detecting thepresence of the virus. The certain distinctive factors that help differentiate COVID-19 from pneumonia are that COVID-19 affects both lungs as opposed to one and lungs may show a ground-glass appearance and abnormalities in liver et cetera. A drawback anyway about this method is that it requires an expert radiologist and provided the size of this pandemic, and the number of cases greatly outnumbers the radiologists. This paper aims to establish a proposal to a reliable, fully automated diagnosis powered by deep learning for diagnosis of COVID-19 from CT. The approach is divided into three phases. The first phase is to look out for abnormalities in lungs. The second phase is to determine the presence of pneumonia using OpenCV for pointingout the regions of interest. The third is to distinguish COVID-19 from pneumonia proceeding on the guidelines mentioned above, which are both the lungs affected as opposed to one, and using the regions that were obtained using OpenCV, endorsing the potential presence of COVID-19. The model, based on convolutional networks, takes advantage of TensorFlow 2.1 and Keras deep learning libraries since both were later integrated and can be used conjointly for the identification and the OpenCV library for image loading and preprocessing. Tenfold method is used for the division of training and test set, and the evaluation metric is accuracy. The model was trained against a dataset of a thousand images (owing to the lack of x-ray images of patients affected with coronavirus), with images of normal versus abnormal lungs in a ratio of 1:1, and was tested for accuracy using the confusion matrix. It provided an accuracyof 86% in pointing out the abnormalities in lungs. Then, the identification of images with normal pneumonia versus those infected with coronavirus was done with an accuracy of 75%. © 2022 Scrivener Publishing LLC.

Multi-modal lung ultrasound image classification by fusing image-based features and probe information

Lung ultrasound is a widely used portable, cheap, and non-invasive medical imaging technology that can be used to identify various lung pathologies. In this work, we propose a multi-modal approach for lung ultrasound image classification that combines image-based features with information about the type of ultrasound probe used to acquire the input image. Experiments on a large lung ultrasound image dataset that contains images acquired with a linear or a convex ultrasound probe demonstrated the superiority of the proposed approach for the task of classifying lung ultrasound images as "COVID-19”, "Normal”, "Pneumonia”, or "Other”, when compared to simply using image-based features. Classification accuracy reached 99.98% using the proposed combination of the Xception pre-trained CNN model with the ultrasound probe information, as opposed to 96.81% when only the pre-trained EfficientNetB4 CNN model was used. Furthermore, the experimental results demonstrated a consistent improvement in classification performance when combining the examined base CNN models with probe information, indicating the efficiency of the proposed approach. © 2022 IEEE.

Contrasting EfficientNet, ViT, and gMLP for COVID-19 Detection in Ultrasound Imagery.

A timely diagnosis of coronavirus is critical in order to control the spread of the virus. To aid in this, we propose in this paper a deep learning-based approach for detecting coronavirus patients using ultrasound imagery. We propose to exploit the transfer learning of a EfficientNet model pre-trained on the ImageNet dataset for the classification of ultrasound images of suspected patients. In particular, we contrast the results of EfficentNet-B2 with the results of ViT and gMLP. Then, we show the results of the three models by learning from scratch, i.e., without transfer learning. We view the detection problem from a multiclass classification perspective by classifying images as COVID-19, pneumonia, and normal. In the experiments, we evaluated the models on a publically available ultrasound dataset. This dataset consists of 261 recordings (202 videos + 59 images) belonging to 216 distinct patients. The best results were obtained using EfficientNet-B2 with transfer learning. In particular, we obtained precision, recall, and F1 scores of 95.84%, 99.88%, and 24 97.41%, respectively, for detecting the COVID-19 class. EfficientNet-B2 with transfer learning presented an overall accuracy of 96.79%, outperforming gMLP and ViT, which achieved accuracies of 93.03% and 92.82%, respectively.

Performance Analysis of Wiener filter in Restoration of Covid-19 Chest X-Ray Images, Ultrasound Images and Mammograms

Medical images such as X-Ray images, Mammograms and Ultrasound images are very useful diagnostic techniques used for understanding the functions of different internal organs, bones, tissues, etc. Most of the times these medical images are degraded by some noises and different kinds of blur. Image blurring and degradation leads to loss of quality of images which in hand causes difficulty in proper diagnosis. This paper emphases on the efficacy of Wiener filter in image de blurring and denoising Chest X-Ray of Covid-19 patients, ultrasound images of fetal abdominal cyst, umbilical cord cyst and Common Carotid Artery, Mammogram of both pathological and non-pathological breasts. Performance of Wiener filter is analyzed using image restoration parameters like Structural Similarity (SSIM), Histogram, Peak Signal to Noise Ratio and Mean Square Error. © 2022 IEEE.

Design of Deep Learning Based Covid 19 Diagnosis Framework Using Lung Ultrasound Images

The global health catastrophe caused by the Coronavirus disease pandemic (COVID-19) and related control efforts has impacted every aspect of human life. The most important requirement for COVID-19 diagnosis is early detection of the condition. The ML algorithm aids in the acceleration of the process while also conserving energy. Time-to-delivery and the availability of training data, on the other hand, are critical. Deep learning algorithms surpass covid 19-based lung ultrasound scans in diagnosing them, according to a thorough background analysis. As a result, this study shows how to develop a CNN-based framework for Lung Ultrasound indicators in COVID-19 in real time. This research looks into the roadmap of lung ultrasonography indicators in detail, with a focus on COVID-19. Finally, this article emphasizes the investigation of the covid19 problem in different domains. © 2022 IEEE.

A Comparative and Extensive Study of Covid 19 Diagnosis using Lung Ultrasound Images

The COVID-19 pandemic has resulted in a worldwide health crisis that has affected all facets of human existence and has brought the world to a halt. The most important pre-requisite for COVID-19 diagnosis is early detection. Machine learning algorithms can help in speeding up the process while saving money and effort. Following a comprehensive background study on the various medical imaging options available, it was discovered that there are few surveys focusing on COVID-19 identification based on Lung Ultrasound. The feasibility of lung ultrasound is visible from the survey. In this paper, huge efforts have been undertaken to study the road-map of lung ultrasound markers for detecting COVID-19. The detection of abnormal A lines, B lines and pleural lines or traces in ultrasound images will aid in the rapid identification and control of the ongoing COVID- 19 epidemic. The numerous deep learning models will make diagnosis easier and more accurate, assisting doctors and front-line employees in this pandemic emergency. © 2022 IEEE.

COVID-19 detection from lung ultrasound images

Early-stage detection of Coronavirus Disease 2019 (COVID-19) is crucial for patient medical attention. Since lungs are the most affected organs, monitoring them constantly is an effective way to observe sickness evolution. The most common technique for lung-imaging and evaluation is Computed Tomography (CT). However, its costs and effects over human health has made Lung Ultrasound (LUS) a good alternative. LUS does not expose the patient to radiation and minimizes the risk of contamination. Also, there is evidence of a relation between different artifacts on LUS and lung’s diseases coming from the pleura, whose abnormalities are related with most acute respiratory disorders. However, LUS often requires an expert clinical interpretation that may increase diagnosis time or decrease diagnosis performance. This paper describes and compares machine learning classification methods namely Naive Bayes (NB) Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) and Random Forest (RF) over several LUS images. They obtain a classification between lung images with COVID-19, pneumonia, and healthy patients, using image’s features previously extracted from Gray Level Co-Occurrence Matrix (GLCM) and histogram’s statistics. Furthermore, this paper compares the above classic methods with different Convolutional Neural Networks (CNN) that classifies the images in order to identify these lung’s diseases. © 2022 SPIE.

Early COVID-19 Diagnosis from Lung Ultrasound Images Combining RIULBP-TP and 3D-DenseNet

The pandemic of COVID-19 has affected the world with the high deaths rate. Early diagnosis of this disease is the bottleneck to the patient's health recovery. Its symptoms appear through the wide range of experiments especially accompany with the severe lung lesions. These lesions could be spotted on the lung ultrasound data. Being non-intrusive, low cost, portable, and accurate enough are among the main pros of ultrasound imaging. However, this imaging modality most often contain variety of noises. In order to overcome this challenge, we propose a novel approach combining Rotation Invariant Uniform LBP on 3 Planes (RIULBP-TP) and 3D-DenseNet. These methods are proved to be robust against various noises. Accordingly, our method reaches outstanding results comparing to related most state-of-the-art methods. © 2022 IEEE.

Detection of Covid-19 Based on Lung Ultrasound Image Using Convolutional Neural Network Architectures

The spread of Covid-19 is so fast that it has become a global pandemic. A fast, cheap, and guaranteed Covid-19 detection system is needed. Medical images such as CT scans and X-rays with biological sciences and deep learning techniques can be critical diagnostic tools. This study uses ultrasound images as an alternative to medical images that can diagnose Covid-19 using a deep learning method based on the Convolutional Neural Network (CNN) architectures. The dataset used is obtained from the Covid-19 Lung Ultrasound. This study shows the highest accuracy of detection covid-19 based on a lung ultrasound image using the VGG16 architecture compared to ResNet50 and InceptionV3architectures. VGG16 architecture with an Adam optimization and a learning rate of 0.0001 yielded 86% accuracy. ResNet50 and InceptionV3architectures produce 79% and 64% of accuracy. © 2021 IEEE.