Automatic deep learning-based consolidation/collapse classification in lung ultrasound images for COVID-19 induced pneumonia

The prognostic role of lung ultrasound in hospitalised patients with COVID-19. Correlation with chest CT findings and clinical markers of severity

BACKGROUND

The use of lung ultrasound (LUS) has recently become vital in the diagnosis and prognosis of various respiratory diseases. Its role in COVID-19 requires further investigation.

RESEARCH DESIGN AND METHODS

Twenty-five consecutive, non-ICU hospitalized COVID-19 patients were included. LUS was performed on admission and sequentially every 3 days at 8 points in the chest. Based on the LUS findings a score was designed. Logarithmic regression models and ROC curve analysis were applied.

RESULTS

A statistically significant positive correlation was found between LUS score at admission and the severity of SARS-COV-2 infection. Higher LUS score was significantly associated with lower PaO2/FiO2 ratio, use of HFNC, longer hospitalization and greater extent of chest CT infiltrates. A significant association between LUS score and risk of death or intubation or HFNC was found. For one point of increase in the score, risk of death or intubation or HFNC increased 1.93-fold (95% CI 1.02 to 3.65). The predictive role of the score was very satisfactory (area under the ROC curve = 0.87).

CONCLUSIONS

Lung ultrasound findings were significantly positively associated with clinical and radiological markers of severity of SARS-CoV-2 pneumonia. It therefore constitutes a promising and reliable technique for assessing pneumonia, comparable to chest CT.

Artificial Intelligence-Guided Lung Ultrasound by Nonexperts

Importance

Lung ultrasound (LUS) aids in the diagnosis of patients with dyspnea, including those with cardiogenic pulmonary edema, but requires technical proficiency for image acquisition. Previous research has demonstrated the effectiveness of artificial intelligence (AI) in guiding novice users to acquire high-quality cardiac ultrasound images, suggesting its potential for broader use in LUS.

Objective

To evaluate the ability of AI to guide acquisition of diagnostic-quality LUS images by trained health care professionals (THCPs).

Design, Setting, and Participants

In this multicenter diagnostic validation study conducted between July 2023 and December 2023, participants aged 21 years or older with shortness of breath recruited from 4 clinical sites underwent 2 ultrasound examinations: 1 examination by a THCP operator using Lung Guidance AI and the other by a trained LUS expert without AI. The THCPs (including medical assistants, respiratory therapists, and nurses) underwent standardized AI training for LUS acquisition before participation.

Interventions

Lung Guidance AI software uses deep learning algorithms guiding LUS image acquisition and B-line annotation. Using an 8-zone LUS protocol, the AI software automatically captures images of diagnostic quality.

Main Outcomes and Measures

The primary end point was the proportion of THCP-acquired examinations of diagnostic quality according to a panel of 5 masked expert LUS readers, who provided remote review and ground truth validation.

Results

The intention-to-treat analysis included 176 participants (81 female participants [46.0%]; mean [SD] age, 63 [14] years; mean [SD] body mass index, 31 [8]). Overall, 98.3% (95% CI, 95.1%-99.4%) of THCP-acquired studies were of diagnostic quality, with no statistically significant difference in quality compared to LUS expert-acquired studies (difference, 1.7%; 95% CI, -1.6% to 5.0%).

Conclusions and Relevance

In this multicenter validation study, THCPs with AI assistance achieved LUS images meeting diagnostic standards compared with LUS experts without AI. This technology could extend access to LUS to underserved areas lacking expert personnel.

Trial Registration

ClinicalTrials.gov Identifier: NCT05992324.

Active learning based on multi-enhanced views for classification of multiple patterns in lung ultrasound images

There are several main patterns in lung ultrasound (LUS) images, including A-lines, B-lines, consolidation and pleural effusion. LUS images of healthy lungs typically only exhibit A-lines, while other patterns may emerge or coexist in LUS images associated with different lung diseases. The accurate categorization of these primary patterns is pivotal for effective lung disease screening. However, two challenges complicate the classification task: the first is the inherent blurring of feature differences between main patterns due to ultrasound imaging properties; and the second is the potential coexistence of multiple patterns in a single case, with only the most dominant pattern being clinically annotated. To address these challenges, we propose the active learning based on multi-enhanced views (MEVAL) method to achieve more precise pattern classification in LUS. To accentuate feature differences between multiple patterns, we introduce a feature enhancement module by applying vertical linear fitting and k-means clustering. The multi-enhanced views are then employed in parallel with the original images, thus enhancing MEVAL's awareness of feature differences between multiple patterns. To tackle the patterns coexistence issue, we propose an active learning strategy based on confidence sets and misclassified sets. This strategy enables the network to simultaneously recognize multiple patterns by selectively labeling of a small number of images. Our dataset comprises 5075 LUS images, with approximately 4% exhibiting multiple patterns. Experimental results showcase the effectiveness of the proposed method in the classification task, with accuracy of 98.72%, AUC of 0.9989, sensitivity of 98.76%, and specificity of 98.16%, which outperforms than the state-of-the-art deep learning-based methods. A series of comprehensive ablation studies suggest the effectiveness of each proposed component and show great potential in clinical application.

Multi-modal deep learning methods for classification of chest diseases using different medical imaging and cough sounds

Chest disease refers to a wide range of conditions affecting the lungs, such as COVID-19, lung cancer (LC), consolidation lung (COL), and many more. When diagnosing chest disorders medical professionals may be thrown off by the overlapping symptoms (such as fever, cough, sore throat, etc.). Additionally, researchers and medical professionals make use of chest X-rays (CXR), cough sounds, and computed tomography (CT) scans to diagnose chest disorders. The present study aims to classify the nine different conditions of chest disorders, including COVID-19, LC, COL, atelectasis (ATE), tuberculosis (TB), pneumothorax (PNEUTH), edema (EDE), pneumonia (PNEU). Thus, we suggested four novel convolutional neural network (CNN) models that train distinct image-level representations for nine different chest disease classifications by extracting features from images. Furthermore, the proposed CNN employed several new approaches such as a max-pooling layer, batch normalization layers (BANL), dropout, rank-based average pooling (RBAP), and multiple-way data generation (MWDG). The scalogram method is utilized to transform the sounds of coughing into a visual representation. Before beginning to train the model that has been developed, the SMOTE approach is used to calibrate the CXR and CT scans as well as the cough sound images (CSI) of nine different chest disorders. The CXR, CT scan, and CSI used for training and evaluating the proposed model come from 24 publicly available benchmark chest illness datasets. The classification performance of the proposed model is compared with that of seven baseline models, namely Vgg-19, ResNet-101, ResNet-50, DenseNet-121, EfficientNetB0, DenseNet-201, and Inception-V3, in addition to state-of-the-art (SOTA) classifiers. The effectiveness of the proposed model is further demonstrated by the results of the ablation experiments. The proposed model was successful in achieving an accuracy of 99.01%, making it superior to both the baseline models and the SOTA classifiers. As a result, the proposed approach is capable of offering significant support to radiologists and other medical professionals.

Qualitative and semi-quantitative ultrasound assessment in delta and Omicron Covid-19 patients: data from high volume reference center

OBJECTIVE

to evaluate the efficacy of US, both qualitatively and semi-quantitatively, in the selection of treatment for the Covid-19 patient, using patient triage as the gold standard.

METHODS

Patients admitted to the Covid-19 clinic to be treated with monoclonal antibodies (mAb) or retroviral treatment and undergoing lung ultrasound (US) were selected from the radiological data set between December 2021 and May 2022 according to the following inclusion criteria: patients with proven Omicron variant and Delta Covid-19 infection; patients with known Covid-19 vaccination with at least two doses. Lung US (LUS) was performed by experienced radiologists. The presence, location, and distribution of abnormalities, such as B-lines, thickening or ruptures of the pleural line, consolidations, and air bronchograms, were evaluated. The anomalous findings in each scan were classified according to the LUS scoring system. Nonparametric statistical tests were performed.

RESULTS

The LUS score median value in the patients with Omicron variant was 1.5 (1-20) while the LUS score median value in the patients with Delta variant was 7 (3-24). A difference statistically significant was observed for LUS score values among the patients with Delta variant between the two US examinations (p value = 0.045 at Kruskal Wallis test). There was a difference in median LUS score values between hospitalized and non-hospitalized patients for both the Omicron and Delta groups (p value = 0.02 on the Kruskal Wallis test). For Delta patients groups the sensitivity, specificity, positive and negative predictive values, considering a value of 14 for LUS score for the hospitalization, were of 85.29%, 44.44%, 85.29% and 76.74% respectively.

CONCLUSIONS

LUS is an interesting diagnostic tool in the context of Covid-19, it could allow to identify the typical pattern of diffuse interstitial pulmonary syndrome and could guide the correct management of patients.