Advances in medical imaging to evaluate acute respiratory distress syndrome

Abstract

Acute respiratory distress syndrome is a refractory respiratory syndrome with a high prevalence in the Intensive Care Unit. Though much improvement has been achieved over the last 50 decades, the disease continues to be under-recognized and under-treated, and its mortality remains high. Since the first report, the radiologic examination has been an essential part in evaluating this disease. Chest X-ray radiography and computed tomography are conventional imaging techniques in routine clinical practice. Other image modalities, including lung ultrasound, electrical impedance tomography, positron emission tomography, have demonstrated their respective advantages over recent years but have not yet been broadly applied in clinical practice. Among these modalities, computed tomography and its quantitative analysis have shown an irreplaceable power in diagnosis, intervention evaluation and prognostic prediction. In this review, we briefly introduced the basics of acute respiratory distress syndrome and summarized imaging advances. In addition, we focused on the computed tomography modality and highlighted the value of its quantitative assessment.

Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: efficient development of auditable risk prediction models via a fine-tuning approach

“…In the first step, CXRs obtained at the time of ED admission were applied to the CXR xAI model to identify abnormal radiographic features. A random forest model was then fitted using 7 infection-associated radiographic labels (pneumonia, atelectasis, other interstitial opacity, pulmonary edema, pleural effusion, cardiomegaly, and decreased lung volume) 8 – 12 , reflecting the severity and pathophysiological characteristics of respiratory infection, and 8 clinical parameters (age, gender, heart rate, body temperature, systolic blood pressure, respiratory rate, peripheral oxygen saturation, and initial oxygen requirement).…”

Correlation of mRALE Severity Scoring System and NLR Values in COVID-19 Patients Accompanied by Fungal Infection at Dr Soetomo Hospital Surabaya

“…This consolidation is believed to be formed by the spread of inflammation through the pores of Kohn or Lambert's canal s at the periphery of the lung. Thus , it usually appears in nonsegmental consolidation in the early stages of the disease (6).…”

Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study

“…Computed tomography (CT) plays a key role in the clinical classification and management of COVID-19 patients especially for its high sensitivity in identifying COVID-19 pneumonia (up to 97% when having RT-PCR as reference standard) [3] , [4] , [5] , [6] . Moreover, the quantitative analysis of the CT images for the extraction, analysis and interpretation of quantitative data has become widespread especially because of the experience acquired on ARDS [7] , [8] , [9] . Lung quantitative CT analysis embraces several techniques, for example the extraction of parameters from the intensity histogram [10] , [11] , [12] , [13] , [14] , texture-based parameters detailing spatial relationship between voxels [15] , [16] and also includes the development of predictive models based on AI tools [17] , [18] , [19] .…”