Autonomous Scanning Target Localization for Robotic Lung Ultrasound Imaging.

Under the ceaseless global COVID-19 pandemic, lung ultrasound (LUS) is the emerging way for effective diagnosis and severeness evaluation of respiratory diseases. However, close physical contact is unavoidable in conventional clinical ultrasound, increasing the infection risk for health-care workers. Hence, a scanning approach involving minimal physical contact between an operator and a patient is vital to maximize the safety of clinical ultrasound procedures. A robotic ultrasound platform can satisfy this need by remotely manipulating the ultrasound probe with a robotic arm. This paper proposes a robotic LUS system that incorporates the automatic identification and execution of the ultrasound probe placement pose without manual input. An RGB-D camera is utilized to recognize the scanning targets on the patient through a learning-based human pose estimation algorithm and solve for the landing pose to attach the probe vertically to the tissue surface; A position/force controller is designed to handle intraoperative probe pose adjustment for maintaining the contact force. We evaluated the scanning area localization accuracy, motion execution accuracy, and ultrasound image acquisition capability using an upper torso mannequin and a realistic lung ultrasound phantom with healthy and COVID-19-infected lung anatomy. Results demonstrated the overall scanning target localization accuracy of 19.67 ± 4.92 mm and the probe landing pose estimation accuracy of 6.92 ± 2.75 mm in translation, 10.35 ± 2.97 deg in rotation. The contact force-controlled robotic scanning allowed the successful ultrasound image collection, capturing pathological landmarks.

Anatomical Feature-Based Lung Ultrasound Image Quality Assessment Using Deep Convolutional Neural Network.

Lung ultrasound (LUS) has been used for point-of-care diagnosis of respiratory diseases including COVID-19, with advantages such as low cost, safety, absence of radiation, and portability. The scanning procedure and assessment of LUS are highly operator-dependent, and the appearance of LUS images varies with the probe's position, orientation, and contact force. Karamalis et al. introduced the concept of ultrasound confidence maps based on random walks to assess the ultrasound image quality algorithmically by estimating the per-pixel confidence in the image data. However, these confidence maps do not consider the clinical context of an image, such as anatomical feature visibility and diagnosability. This work proposes a deep convolutional network that detects important anatomical features in an LUS image to quantify its clinical context. This work introduces an Anatomical Feature-based Confidence (AFC) Map, quantifying an LUS image's clinical context based on the visible anatomical features. We developed two U-net models, each segmenting one of the two classes crucial for analyzing an LUS image, namely 1) Bright Features: Pleural and Rib Lines and 2) Dark Features: Rib Shadows. Each model takes the LUS image as input and outputs the segmented regions with confidence values for the corresponding class. The evaluation dataset consists of ultrasound images extracted from videos of two sub-regions of the chest above the anterior axial line from three human subjects. The feature segmentation models achieved an average Dice score of 0.72 on the model's output for the testing data. The average of non-zero confidence values in all the pixels was calculated and compared against the image quality scores. The confidence values were different between different image quality scores. The results demonstrated the relevance of using an AFC Map to quantify the clinical context of an LUS image.

Lung Ultrasound Score as a Predictor of Mortality in Patients With COVID-19.

Background: Lung injury is a common condition among hospitalized patients with coronavirus disease 2019 (COVID-19). However, whether lung ultrasound (LUS) score predicts all-cause mortality in patients with COVID-19 is unknown. The aim of the present study was to explore the predictive value of lung ultrasound score for mortality in patients with COVID-19. Methods: Patients with COVID-19 who underwent lung ultrasound were prospectively enrolled from three hospitals in Wuhan, China between February 2020 and March 2020. Demographic, clinical, and laboratory data were collected from digital patient records. Lung ultrasound scores were analyzed offline by two observers. Primary outcome was in-hospital mortality. Results: Of the 402 patients, 318 (79.1%) had abnormal lung ultrasound. Compared with survivors (n = 360), non-survivors (n = 42) presented with more B2 lines, pleural line abnormalities, pulmonary consolidation, and pleural effusion (all p < 0.05). Moreover, non-survivors had higher global and anterolateral lung ultrasound score than survivors. In the receiver operating characteristic analysis, areas under the curve were 0.936 and 0.913 for global and anterolateral lung ultrasound score, respectively. A cutoff value of 15 for global lung ultrasound score had a sensitivity of 92.9% and specificity of 85.3%, and 9 for anterolateral score had a sensitivity of 88.1% and specificity of 83.3% for prediction of death. Kaplan-Meier analysis showed that both global and anterolateral scores were strong predictors of death (both p < 0.001). Multivariate Cox regression analysis showed that global lung ultrasound score was an independent predictor (hazard ratio, 1.08; 95% confidence interval, 1.01-1.16; p = 0.03) of death together with age, male sex, C-reactive protein, and creatine kinase-myocardial band. Conclusion: Lung ultrasound score as a semiquantitative tool can be easily measured by bedside lung ultrasound. It is a powerful predictor of in-hospital mortality and may play a crucial role in risk stratification of patients with COVID-19.

Modality alignment contrastive learning for severity assessment of COVID-19 from lung ultrasound and clinical information.

The outbreak of COVID-19 around the world has caused great pressure to the health care system, and many efforts have been devoted to artificial intelligence (AI)-based analysis of CT and chest X-ray images to help alleviate the shortage of radiologists and improve the diagnosis efficiency. However, only a few works focus on AI-based lung ultrasound (LUS) analysis in spite of its significant role in COVID-19. In this work, we aim to propose a novel method for severity assessment of COVID-19 patients from LUS and clinical information. Great challenges exist regarding the heterogeneous data, multi-modality information, and highly nonlinear mapping. To overcome these challenges, we first propose a dual-level supervised multiple instance learning module (DSA-MIL) to effectively combine the zone-level representations into patient-level representations. Then a novel modality alignment contrastive learning module (MA-CLR) is presented to combine representations of the two modalities, LUS and clinical information, by matching the two spaces while keeping the discriminative features. To train the nonlinear mapping, a staged representation transfer (SRT) strategy is introduced to maximumly leverage the semantic and discriminative information from the training data. We trained the model with LUS data of 233 patients, and validated it with 80 patients. Our method can effectively combine the two modalities and achieve accuracy of 75.0% for 4-level patient severity assessment, and 87.5% for the binary severe/non-severe identification. Besides, our method also provides interpretation of the severity assessment by grading each of the lung zone (with accuracy of 85.28%) and identifying the pathological patterns of each lung zone. Our method has a great potential in real clinical practice for COVID-19 patients, especially for pregnant women and children, in aspects of progress monitoring, prognosis stratification, and patient management.

Prognostic value of bedside lung ultrasound score in patients with COVID-19.

BACKGROUND: Bedside lung ultrasound (LUS) has emerged as a useful and non-invasive tool to detect lung involvement and monitor changes in patients with coronavirus disease 2019 (COVID-19). However, the clinical significance of the LUS score in patients with COVID-19 remains unknown. We aimed to investigate the prognostic value of the LUS score in patients with COVID-19. METHOD: The LUS protocol consisted of 12 scanning zones and was performed in 280 consecutive patients with COVID-19. The LUS score based on B-lines, lung consolidation and pleural line abnormalities was evaluated. RESULTS: The median time from admission to LUS examinations was 7 days (interquartile range [IQR] 3-10). Patients in the highest LUS score group were more likely to have a lower lymphocyte percentage (LYM%); higher levels of D-dimer, C-reactive protein, hypersensitive troponin I and creatine kinase muscle-brain; more invasive mechanical ventilation therapy; higher incidence of ARDS; and higher mortality than patients in the lowest LUS score group. After a median follow-up of 14 days [IQR, 10-20 days], 37 patients developed ARDS, and 13 died. Patients with adverse outcomes presented a higher rate of bilateral involvement; more involved zones and B-lines, pleural line abnormalities and consolidation; and a higher LUS score than event-free survivors. The Cox models adding the LUS score as a continuous variable (hazard ratio [HR]: 1.05, 95% confidence intervals [CI] 1.02 ~ 1.08; P < 0.001; Akaike information criterion [AIC] = 272; C-index = 0.903) or as a categorical variable (HR 10.76, 95% CI 2.75 ~ 42.05; P = 0.001; AIC = 272; C-index = 0.902) were found to predict poor outcomes more accurately than the basic model (AIC = 286; C-index = 0.866). An LUS score cut-off > 12 predicted adverse outcomes with a specificity and sensitivity of 90.5% and 91.9%, respectively. CONCLUSIONS: The LUS score devised by our group performs well at predicting adverse outcomes in patients with COVID-19 and is important for risk stratification in COVID-19 patients.