Deep learning (DL) has proved successful in medical imaging and, in the wake of the recent COVID-19 pandemic, some works have started to investigate DLbased solutions for the assisted diagnosis of lung diseases. While existing works focus on CT scans, this paper studies the application of DL techniques for the analysis of lung ultrasonography (LUS) images. Specifically, we present a novel fully-annotated dataset of LUS images collected from several Italian hospitals, with labels indicating the degree of disease severity at a frame-level, videolevel, and pixel-level (segmentation masks). Leveraging these data, we introduce several deep models that address relevant tasks for the automatic analysis of LUS images. In particular, we present a novel deep network, derived from Spatial Transformer Networks, which simultaneously predicts the disease severity score associated to a input frame and provides localization of pathological artefacts in a weakly-supervised way. Furthermore, we introduce a new method based on uninorms for effective frame score aggregation at a video-level. Finally, we benchmark state of the art deep models for estimating pixel-level segmentations of COVID-19 imaging biomarkers. Experiments on the proposed dataset demonstrate satisfactory results on all the considered tasks, paving the way to future research on DL for the assisted diagnosis of COVID-19 from LUS data.
30 March 2020 in Journal of Ultrasound in Medicine
Growing evidence is showing the usefulness of lung ultrasound in patients with the 2019 new coronavirus disease (COVID‐19). Severe acute respiratory syndrome coronavirus 2 has now spread in almost every country in the world. In this study, we share our experience and propose a standardized approach to optimize the use of lung ultrasound in patients with COVID‐19. We focus on equipment, procedure, classification, and data sharing.
20 March 2020 in Journal of Ultrasound in Medicine
Recent works highlighted the significant potential of Lung Ultrasound (LUS) imaging in the management of subjects affected by COVID-19. In general, the development of objective, fast, and accurate automatic methods for LUS data evaluation is still at an early stage. This is particularly true for COVID- 19 diagnostic. In this paper, we propose an automatic and unsupervised method for the detection and localization of the pleural line in LUS data based on the Hidden Markov Model and Viterbi Algorithm. The pleural line localization step is followed by a supervised classification procedure based on the Support Vector Machine (SVM). The classifier evaluates the healthiness level of a patient and, if present, the severity of the pathology, i.e., the score value for each image of a given LUS acquisition. The experiments performed on a variety of LUS data acquired in Italian hospitals with both linear and convex probes highlight the effectiveness of the proposed method. The average overall accuracy in detecting the pleura is 84% and 94% for convex and linear probes, respectively. The accuracy of the SVM classification in correctly evaluating the severity of COVID-19 related pleural line alterations is about 88% and 94% for convex and linear probes, respectively. The results as well as the visualization of the detected pleural line and the predicted score chart, provide a significant support to medical staff for further evaluating the patient condition.
4 October 2021 in IEEE Transactions on Medical Imaging
Lung ultrasound (LUS) is a cheap, safe and non-invasive imaging modality that can be performed at patient bed-side. However, to date LUS is not widely adopted due to lack of trained personnel required for interpreting the acquired LUS frames. In this work we propose a framework for training deep artificial neural networks for interpreting LUS, which may promote broader use of LUS. When using LUS to evaluate a patient’s condition, both anatomical phenomena (e.g., the pleural line, presence of consolidations), as well as sonographic artifacts (such as A- and B-lines) are of importance. In our framework, we integrate domain knowledge into deep neural networks by inputting anatomical features and LUS artifacts in the form of additional channels containing pleural and vertical artifacts masks along with the raw LUS frames. By explicitly supplying this domain knowledge, standard off-the-shelf neural networks can be rapidly and efficiently finetuned to accomplish various tasks on LUS data, such as frame classification or semantic segmentation. Our framework allows for a unified treatment of LUS frames captured by either convex or linear probes. We evaluated our proposed framework on the task of COVID-19 severity assessment using the ICLUS dataset. In particular, we finetuned simple image classification models to predict per-frame COVID-19 severity score. We also trained a semantic segmentation model to predict per-pixel COVID-19 severity annotations. Using the combined raw LUS frames and the detected lines for both tasks, our off-the-shelf models performed better than complicated models specifically designed for these tasks, exemplifying the efficacy of our framework.
27 July 2020 in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
The application of ultrasound imaging to the diagnosis of lung diseases is nowadays receiving growing interest. However, Lung Ultrasound (LUS) is mainly limited to the analysis of imaging artifacts, such as B-lines, which correlate with a wide variety of diseases. Therefore, the results of LUS investigations remain qualitative and subjective, and specificity is obviously suboptimal. Focusing on the development of a quantitative method dedicated to the lung, in this work we present the first clinical results obtained with Quantitative LUS Spectroscopy when applied to the differentiation of pulmonary fibrosis. A previously-developed specific multi-frequency ultrasound imaging technique was utilized to acquire ultrasound images from 26 selected patients. The multi-frequency imaging technique was implemented on the ULA-OP platform, and a LA533® (Esaote, Florence, Italy) linear-array probe was utilized. RF-data obtained at different imaging frequencies (3, 4, 5 and 6 MHz) were acquired and processed in order to characterize B-lines based on their frequency content. In particular, B-line native frequencies (the frequency at which a B-line exhibits the highest intensity) and bandwidth (the range of frequencies over which a B-line shows intensities within -6 dB from its highest intensity), as well as B-line intensity, were analyzed. Results show how the analysis of these features allows (in this group of patients) the differentiation of fibrosis with a sensitivity and specificity equal to 92% and 92%, respectively. These promising results strongly motivate towards the extension of the clinical study, aiming at analyzing a larger cohort of patients and including a broader range of pathologies.