AI-enabled radiologist in the loop: novel AI-based framework to augment radiologist performance for COVID-19 chest CT medical image annotation and classification from pneumonia.

A SARS-CoV-2 virus-specific reverse transcriptase-polymerase chain reaction (RT-PCR) test is usually used to diagnose COVID-19. However, this test requires up to 2 days for completion. Moreover, to avoid false-negative outcomes, serial testing may be essential. The availability of RT-PCR test kits is currently limited, highlighting the need for alternative approaches for the precise and rapid diagnosis of COVID-19. Patients suspected to be infected with SARS-CoV-2 can be assessed using chest CT scan images. However, CT images alone cannot be used for ruling out SARS-CoV-2 infection because individual patients may exhibit normal radiological results in the primary phases of the disease. A machine learning (ML)-based recognition and segmentation system was developed to spontaneously discover and compute infection areas in CT scans of COVID-19 patients. The computable assessment exhibited suitable performance for automatic infection region allocation. The ML models developed were suitable for the direct detection of COVID-19 (+). ML was confirmed to be a complementary diagnostic technique for diagnosing COVID-19(+) by forefront medical specialists. The complete manual delineation of COVID-19 often requires up to 225.5 min; however, the proposed RILML method decreases the delineation time to 7 min after four iterations of model updating.

Computer-aided diagnosis systems: a comparative study of classical machine learning versus deep learning-based approaches.

The diagnostic phase of the treatment process is essential for patient guidance and follow-up. The accuracy and effectiveness of this phase can determine the life or death of a patient. For the same symptoms, different doctors may come up with different diagnoses whose treatments may, instead of curing a patient, be fatal. Machine learning (ML) brings new solutions to healthcare professionals to save time and optimize the appropriate diagnosis. ML is a data analysis method that automates the creation of analytical models and promotes predictive data. There are several ML models and algorithms that rely on features extracted from, for example, a patient's medical images to indicate whether a tumor is benign or malignant. The models differ in the way they operate and the method used to extract the discriminative features of the tumor. In this article, we review different ML models for tumor classification and COVID-19 infection to evaluate the different works. The computer-aided diagnosis (CAD) systems, which we referred to as classical, are based on accurate feature identification, usually performed manually or with other ML techniques that are not involved in classification. The deep learning-based CAD systems automatically perform the identification and extraction of discriminative features. The results show that the two types of DAC have quite close performances but the use of one or the other type depends on the datasets. Indeed, manual feature extraction is necessary when the size of the dataset is small; otherwise, deep learning is used.

Contactless non-invasive method to identify abnormal tongue area using K-mean and problem identification in COVID-19 scenario

Due to the spread of COVID-19 all around the world, there is a need of automatic system for primary tongue ulcer cancerous cell detection since everyone do not go to hospital due to the panic and fear of virus spread. These diseases if avoided may spread soon. So, in such a situation, there is global need of improvement in disease sensing through remote devices using non-invasive methods. Automatic tongue analysis supports the examiner to identify the problem which can be finally verified using invasive methods. In automated tongue analysis image quality, segmentation of the affected region plays an important role for disease identification. This paper proposes mobile-based image sensing and sending the image to the examiner, if examiner finds an issue in the image, the examiner may guide the user to go for further treatment. For segmentation of abnormal area, K-mean clustering is used by varying its parameters.Copyright © 2022 Inderscience Enterprises Ltd.

Android Application for Human Respiratory System Diagnosis: A Systematic Review

This paper presents a systematic review of android app respiratory system on smartphone. For some diseases, doctors have succeeded in inventing the necessary treatments that lasts for a short period, but in several cases, the treatment can stay for a lifetime. The goal of this system is to detect if a patient has any respiratory disease(s) by specifying the symptoms the patient encounters, schedules an appointement in the hospital for patient through the system to the linked specialist doctors to avoid contact in the case of Covid-19 patient. This research will help raise patient's awareness of the high risk of late discovery of having respiratory diseases (like Lung Cancer. corona virus etc), and also to develop a model that will help detect this disease early through mobile application. The focus of this review is to encourage medical institutions to adopt the health android app that can help patients in self-managing behavioral activities such as physical activities, using symptoms to determine the stage(early or critical) of the disease and drug suggestions with research evaluation using the app, this could help patients monitor and manage their health conditions. © 2022 IEEE.

Improving Robustness of Medical Image Diagnosis System by Using Multi-loss Hybrid Adversarial Function with Heuristic Projection

Medical image diagnosis system by using deep neural networks (DNN) can improve the sensitivity and speed of interpretation of chest CT for COVID-19 screening. However, DNN based medical image diagnosis is known to be influenced by the adversarial perturbations. In order to improve the robustness of medical image diagnosis system, this paper proposes an adversarial attack training method by using multi-loss hybrid adversarial function with heuristic projection. Firstly, the effective adversarial attacks which contain the noise style that can puzzle the network are created with a multi-loss hybrid adversarial function (MLAdv). Then, instead of adding these adversarial attacks to the training data directly, we consider the similarity between the original samples and adversarial attacks by using an adjacent loss during the training process, which can improve the robustness and the generalization of the network for unanticipated noise perturbations. Experiments are finished on COVID-19 dataset. The average attack success rate of this method for three DNN based medical image diagnosis systems is 63.9%, indicating that the created adversarial attack has strong attack transferability and can puzzle the network effectively. In addition, with the adversarial attack training, the augmented networks by using adversarial attacks can improve the diagnosis accuracy by 4.75%. Therefore, the augmented network based on MLAdv adversarial attacks can improve the robustness of medical image diagnosis system. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

DeepChestNet: Artificial intelligence approach for COVID-19 detection on computed tomography images

The conventional approach for identifying ground glass opacities (GGO) in medical imaging is to use a convolutional neural network (CNN), a subset of artificial intelligence, which provides promising performance in COVID-19 detection. However, CNN is still limited in capturing structured relationships of GGO as the texture and shape of the GGO can be confused with other structures in the image. In this paper, a novel framework called DeepChestNet is proposed that leverages structured relationships by jointly performing segmentation and classification on the lung, pulmonary lobe, and GGO, leading to enhanced detection of COVID-19 with findings. The performance of DeepChestNet in terms of dice similarity coefficient is 99.35%, 99.73%, and 97.89% for the lung, pulmonary lobe, and GGO segmentation, respectively. The experimental investigations on DeepChestNet-Lung, DeepChestNet-Lobe and DeepChestNet-COVID datasets, and comparison with several state-of-the-art approaches reveal the great potential of DeepChestNet for diagnosis of COVID-19 disease. © 2023 Wiley Periodicals LLC.

Fusion Based Self Diagnosis Expert System Empowered with Leven-berg Marquardt Algorithm

COVID-19 coronavirus disease is the latest virus in the new century. The World Health Organization- WHO organization announced that COVID-19 disease is a pandemic that leads to thousands of death in short time of spam. A quick and accurate diagnosis of COVID-19 shows an important role in its prevention. This study is based on a fusion-based Self-Diagnosis Expert System Empowered by the Leven-berg Marquardt Algorithm for the diagnosis of diseases. Leven-berg Marquardt has been implemented for the classification of different symptoms of the diseases and relates the results for their diagnosis. The MatLab software was used for the simulation purpose. The proposed fusion-based LB increased the accuracy in the training and validation process to be 10 times more efficient than the existing. The fusion technique achieved an overall accuracy of 98.86%, and 99.09% in all performance metrics which included TNR, precision, and FPR statistical parameters. © 2022 IEEE.

Research on several major diseases based on machine learning models

Due to the continuous growth of disease types and past cases, it is more and more difficult to diagnose diseases only by manpower. Machine learning is a model mechanism that is sensitive to data and relies on a large amount of data to complete training. It is very suitable for medical diagnosis. Many scholars have tried to use ML to develop medical diagnosis systems, but they are basically not used in the real world at this stage. This article reviews the work related to medical detection of three major diseases (heart disease, cancer, and COVID-19), aiming to summarize previous experiences to help future scholars conduct research. Specifically, this paper summarizes the research status of the prediction of these three types of diseases based on machine learning methods, evaluate the accuracy and universality of the corresponding prediction models based on time as a clue, and use a comparative method to find out the progress researchers have made in this area and limitations still exist at this stage. And at the end of the article, the results and some potential work fields of the future in these studies are summarized. © 2022 IEEE.

D-Cov19Net: A DNN based COVID-19 detection system using lung sound.

The limitations of proper detectors for COVID-19 for the proliferating number of patients provoked us to build an auto-diagnosis system to detect COVID-19 infection using only one parameter. Our designed model is based on Deep Convolution Neural Network and considers lung/respiratory sound as the deterministic input for our approach. 'D-Cov19Net' has been trained with 23,592 recordings, begetting an AUC of 0.972 and sensitivity of 0.983 after 100 epochs. The model can be of immense utility in biomedical technology due to its significant accuracy, simplicity, user convenience, feasibility, and faster detection while maintaining social distancing.

Contactless non-invasive method to identify abnormal tongue area using K-mean and problem identification in COVID-19 scenario

Due to the spread of COVID-19 all around the world, there is a need of automatic system for primary tongue ulcer cancerous cell detection since everyone do not go to hospital due to the panic and fear of virus spread. These diseases if avoided may spread soon. So, in such a situation, there is global need of improvement in disease sensing through remote devices using non-invasive methods. Automatic tongue analysis supports the examiner to identify the problem which can be finally verified using invasive methods. In automated tongue analysis image quality, segmentation of the affected region plays an important role for disease identification. This paper proposes mobile-based image sensing and sending the image to the examiner, if examiner finds an issue in the image, the examiner may guide the user to go for further treatment. For segmentation of abnormal area, K-mean clustering is used by varying its parameters.

Application of Convolutional Neural Network in COVID-19 Diagnosis

Since the outbreak and spread of COVID-19 in large areas of the world, the importance of rapid diagnosis of COVID-19 has increased. In the first week after the onset of COVID-19, the density of lesions is uneven, and chest CT is often difficult to show local subpleural ground-glass shadows, resulting in missed diagnosis. The COVID-19 intelligent diagnosis system based on the convolutional neural network algorithm can not only accurately identify the feature points, reduce the workload of doctors and improve the diagnosis efficiency, but also reduce the rate of missed diagnosis and misdiagnosis, which is conducive to epidemic control. © 2022 ACM.

Radiographic Image Processing Analysis for Lung Infection - A Review

This paper presents a brief review on the developments of computer aided diagnosis system using image processing approaches. The rapid increase in lung infections which was in multiple during the current Corona virus infection has outcome with the need of automation system for an early detection of lung infection. Early detection of lung infection can avoid the spread of infection further and also act as an alarming intimation under critical cases. The need of such system has outcome with many researches in recent past towards developing new approaches toward improving the decision accuracy to reducing the system response time. This article review the past developments made in the area of developing automation systems with an analysis of attainted accuracy and methodology of image processing and classification system for automated lung infection detection. © 2022 IEEE.

Covid-19 Symptoms Periods Detection Using Transfer-Learning Techniques

The inflationary illness caused by extreme acute respiratory syndrome coronavirus in 2019 (COVID-19) is an infectious and deadly disease. COVID-19 was first found in Wuhan, China, in December 2019, and has since spread worldwide. Globally, there have been more than 198 M cases and over 4.22 M deaths, as of the first of Augest, 2021. Therefore, an automated and fast diagnosis system needs to be introduced as a simple, alternative diagnosis choice to avoid the spread of COVID-19. The main contributions of this research are 1) the COVID-19 Period Detection System (CPDS), that used to detect the symptoms periods or classes, i.e., healthy period, which mean the no COVID19, the period of the first six days of symptoms (i.e., COVID-19 positive cases from day 1 to day 6), and the third period of infection more than six days of symptoms (i.e., COVID-19 positive cases from day 6 and more): 2) the COVID19 Detection System (CDS) that used to determine if the X-ray images normal, i.e., healthy case or infected, i.e., COVID-19 positive cases;3) the collection of database consists of three different categories or groups based on the basis of time interval of offset of Symptoms. For CPDS, the VGG-19 perform to 96% accuracy, 90% Fl score, 91% average precision, and 91% average recall. For CDS, the VGG-19 perform to 100% accuracy, 99% F1 score, 100% average precision, and 99% average recall.