ABSTRACT
The benefits of m-RNA vaccines in immunosuppressed patients receiving anti-CD20 monoclonal antibodies such as patients with B-line haematological malignancies or multiple sclerosis (MS) are poor investigated. Several studies demonstrated that anti-CD20 therapies were associated with a reduction/absence of the humoral response but only few data are available on T-cell immunity. In our study, we evaluated the antibodies levels and the T-cellular response of 70 immunosuppressed patients receiving anti-CD20 monoclonal antibodies (45 haematological and 25 MS patients), after the administration of the third dose of BNT162b2 vaccine. We also enrolled 10 healthy individuals, as controls. Anti-CD20 therapies significantly reduced the vaccineinduced antibodies targeting the spike protein (anti-S antibodies) in most patients (both haematological and MS patients). When they were stratified based on time elapsed between therapy infusions and vaccination, the median of anti-S antibody levels showed significant differences: patients vaccinated during the treatment were seronegative;patients who began the therapy after one, two or three doses of vaccine generated increasing antibody titers (109 BAU/mL;484 BAU/mL;2532 BAU/mL, respectively);patients who started vaccination 6 months or more after the suspension of the therapy presented good antibody levels (9173 BAU/mL), slightly lower than those of controls (11914 BAU/mL). The magnitude of the T-cell response after vaccination was determined by an interferon (IFN)-gamma enzyme-linked immune absorbent spot (ELISPOT) analysis, stimulating peripheral blood mononuclear cells (PBMC) of patients and controls with overlapping peptide pools of the spike protein. The vaccination induced T cell immunity was partially preserved in patients receiving anti-CD20 monoclonal antibodies, even in those without detectable anti-S antibodies. There were important differences between haematological and MS patients: 97% of MS patients developed a good T-cell response after vaccination (with a median value of 96 spots forming units (SFU) per million of PBMC). Conversely, only 59% of haematological patients, treated in association with other cytostatic drugs, produced a protective T-cell response (with a median value of 40 SFU per million of PBMC).
ABSTRACT
Artificial intelligence-based analysis of lung ultrasound imaging has been demonstrated as an effective technique for rapid diagnostic decision support throughout the COVID-19 pandemic. However, such techniques can require days- or weeks-long training processes and hyper-parameter tuning to develop intelligent deep learning image analysis models. This work focuses on leveraging ‘off-the-shelf’ pre-trained models as deep feature extractors for scoring disease severity with minimal training time. We propose using pre-trained initializations of existing methods ahead of simple and compact neural networks to reduce reliance on computational capacity. This reduction of computational capacity is of critical importance in time-limited or resource-constrained circumstances, such as the early stages of a pandemic. On a dataset of 49 patients, comprising over 20,000 images, we demonstrate that the use of existing methods as feature extractors results in the effective classification of COVID-19-related pneumonia severity while requiring only minutes of training time. Our methods can achieve an accuracy of over 0.93 on a 4-level severity score scale and provides comparable per-patient region and global scores compared to expert annotated ground truths. These results demonstrate the capability for rapid deployment and use of such minimally-adapted methods for progress monitoring, patient stratification and management in clinical practice for COVID-19 patients, and potentially in other respiratory diseases. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Lung ultrasound imaging has been shown effective in detecting typical patterns for interstitial pneumonia, as a point-of-care tool for both patients with COVID-19 and other community-acquired pneumonia (CAP). In this work, we focus on the hyperechoic B-line segmentation task. Using deep neural networks, we automatically outline the regions that are indicative of pathology-sensitive artifacts and their associated sonographic patterns. With a real-world data-scarce scenario, we investigate approaches to utilize both COVID-19 and CAP lung ultrasound data to train the networks;comparing fine-tuning and unsupervised domain adaptation. Segmenting either type of lung condition at inference may support a range of clinical applications during evolving epidemic stages, but also demonstrates value in resource-constrained clinical scenarios. Adapting real clinical data acquired from COVID-19 patients to those from CAP patients significantly improved Dice scores from 0.60 to 0.87 (p <0.001) and from 0.43 to 0.71 (p <0.001), on independent COVID-19 and CAP test cases, respectively. It is of practical value that the improvement was demonstrated with only a small amount of data in both training and adaptation data sets, a common constraint for deploying machine learning models in clinical practice. Interestingly, we also report that the inverse adaptation, from labelled CAP data to unlabeled COVID-19 data, did not demonstrate an improvement when tested on either condition. Furthermore, we offer a possible explanation that correlates the segmentation performance to label consistency and data domain diversity in this point-of-care lung ultrasound application. © 2021, Springer Nature Switzerland AG.