Integrating patient symptoms, clinical readings, and radiologist feedback with computer-aided diagnosis system for detection of infectious pulmonary disease: a feasibility study.

Automatic computer-aided diagnosis (CAD) system has been widely used as an assisting tool for mass screening and risk assessment of infectious pulmonary diseases (PDs). However, such a system still lacks clinical acceptability and trust due to the integration gap between the patient's metadata, radiologist feedback, and the CAD system. This paper proposed three integration frameworks, namely-direct integration (DI), rule-based integration (RBI), and weight-based integration (WBI). The proposed framework helps clinicians diagnose lung inflammation and provide an end-to-end robust diagnostic system. Initially, the feasibility of integrating patients' symptoms, clinical pathologies, and radiologist feedback with CAD system to improve the classification performance is investigated. Subsequently, the patient's metadata and radiologist feedback are integrated with the CAD system using the proposed integration frameworks. The proposed method's performance is evaluated using a private dataset consisting of 70 chest X-ray (CXR) images (31 COVID-19, 14 other diseases, and 25 normal). The obtained results reveal that the proposed WBI achieved the highest classification performance (accuracy = 98.18%, F1 score = 97.73%, and Matthew's correlation coefficient = 0.969) compared to DI and RI. The generalization capability of the proposed framework is also verified from an external validation set. Furthermore, the Friedman average ranking and Shaffer and Holm post hoc statistical methods reveal the obtained results' statistical significance. Methodological diagram of proposed integration frameworks.

Disease Localization and Severity Assessment in Chest X-Ray Images using Multi-Stage Superpixels Classification.

BACKGROUND AND OBJECTIVES: Chest X-ray (CXR) is a non-invasive imaging modality used in the prognosis and management of chronic lung disorders like tuberculosis (TB), pneumonia, coronavirus disease (COVID-19), etc. The radiomic features associated with different disease manifestations assist in detection, localization, and grading the severity of infected lung regions. The majority of the existing computer-aided diagnosis (CAD) system used these features for the classification task, and only a few works have been dedicated to disease-localization and severity scoring. Moreover, the existing deep learning approaches use class activation map and Saliency map, which generate a rough localization. This study aims to generate a compact disease boundary, infection map, and grade the infection severity using proposed multistage superpixel classification-based disease localization and severity assessment framework. METHODS: The proposed method uses a simple linear iterative clustering (SLIC) technique to subdivide the lung field into small superpixels. Initially, the different radiomic texture and proposed shape features are extracted and combined to train different benchmark classifiers in a multistage framework. Subsequently, the predicted class labels are used to generate an infection map, mark disease boundary, and grade the infection severity. The performance is evaluated using a publicly available Montgomery dataset and validated using Friedman average ranking and Holm and Nemenyi post-hoc procedures. RESULTS: The proposed multistage classification approach achieved accuracy (ACC)= 95.52%, F-Measure (FM)= 95.48%, area under the curve (AUC)= 0.955 for Stage-I and ACC=85.35%, FM=85.20%, AUC=0.853 for Stage-II using calibration dataset and ACC = 93.41%, FM = 95.32%, AUC = 0.936 for Stage-I and ACC = 84.02%, FM = 71.01%, AUC = 0.795 for Stage-II using validation dataset. Also, the model has demonstrated the average Jaccard Index (JI) of 0.82 and Pearson's correlation coefficient (r) of 0.9589. CONCLUSIONS: The obtained classification results using calibration and validation dataset confirms the promising performance of the proposed framework. Also, the average JI shows promising potential to localize the disease, and better agreement between radiologist score and predicted severity score (r) confirms the robustness of the method. Finally, the statistical test justified the significance of the obtained results.

Coronavirus disease (COVID-19) detection in Chest X-Ray images using majority voting based classifier ensemble.

Novel coronavirus disease (nCOVID-19) is the most challenging problem for the world. The disease is caused by severe acute respiratory syndrome coronavirus-2 (SARS-COV-2), leading to high morbidity and mortality worldwide. The study reveals that infected patients exhibit distinct radiographic visual characteristics along with fever, dry cough, fatigue, dyspnea, etc. Chest X-Ray (CXR) is one of the important, non-invasive clinical adjuncts that play an essential role in the detection of such visual responses associated with SARS-COV-2 infection. However, the limited availability of expert radiologists to interpret the CXR images and subtle appearance of disease radiographic responses remains the biggest bottlenecks in manual diagnosis. In this study, we present an automatic COVID screening (ACoS) system that uses radiomic texture descriptors extracted from CXR images to identify the normal, suspected, and nCOVID-19 infected patients. The proposed system uses two-phase classification approach (normal vs. abnormal and nCOVID-19 vs. pneumonia) using majority vote based classifier ensemble of five benchmark supervised classification algorithms. The training-testing and validation of the ACoS system are performed using 2088 (696 normal, 696 pneumonia and 696 nCOVID-19) and 258 (86 images of each category) CXR images, respectively. The obtained validation results for phase-I (accuracy (ACC) = 98.062%, area under curve (AUC) = 0.956) and phase-II (ACC = 91.329% and AUC = 0.831) show the promising performance of the proposed system. Further, the Friedman post-hoc multiple comparisons and z-test statistics reveals that the results of ACoS system are statistically significant. Finally, the obtained performance is compared with the existing state-of-the-art methods.