Automated cell differential count in sputum is feasible and comparable to manual cell count in identifying eosinophilia

Association between Eosinophil Count and Cortisol Concentrations in Equids Admitted in the Emergency Unit with Abdominal Pain

Stress leukogram includes eosinopenia as one of its main markers (neutrophilia, eosinopenia, lymphopenia, and mild monocytosis). Cortisol is the main stress biomarker, which is also strongly correlated with the severity of gastrointestinal diseases. This study aimed to determine the relationship between salivary cortisol and the eosinophil cell count (EC) in equids with abdominal pain. To do this, 39 horses with abdominal pain referred to an emergency service were included. All samples were taken on admission, and several parameters and clinical data were included. Equids were classified according to the outcome as survivors and non-survivors. Non-surviving equids presented higher salivary cortisol concentrations (Non-Survivors: 1.580 ± 0.816 µg/dL; Survivors 0.988 ± 0.653 µg/dL; p < 0.05) and lower EC (Non-Survivors: 0.0000 × 103/µL (0.000/0.0075); Survivors: 0.0450 × 103/µL (0.010/0.1825); p < 0.01). In addition, the relationship between salivary cortisol concentration, EC, and the WBC was determined. Only a strong correlation (negative) was observed between cortisol and EC (r = -0.523, p < 0.01). Since cortisol is not an analyte that can be measured routinely in clinical settings such as emergencies, the EC could be a good alternative. While the results are promising, further studies are needed before EC can be used confidently in routine practice to predict survival in cases of abdominal pain.

ICOSeg: Real-Time ICOS Protein Expression Segmentation from Immunohistochemistry Slides Using a Lightweight Conv-Transformer Network

Simple Summary

Inducible T-cell COStimulator (ICOS) is a biomarker of interest in checkpoint inhibitor therapy, and as a means of assessing T-cell regulation as part of a complex process of adaptive immunity. The aim of our study is to segment the ICOS positive cells using a lightweight deep-learning segmentation network. We aim to assess the potential of a convolutional neural network and transformer together that permits the capture of relevant features from immunohistochemistry images. The proposed study achieved remarkable results compared to the existing biomedical segmentation methods on our in-house dataset and surpassed our previous analysis by only utilizing the Efficient-UNet network.

Abstract

In this article, we propose ICOSeg, a lightweight deep learning model that accurately segments the immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS) protein in colon cancer from immunohistochemistry (IHC) slide patches. The proposed model relies on the MobileViT network that includes two main components: convolutional neural network (CNN) layers for extracting spatial features; and a transformer block for capturing a global feature representation from IHC patch images. The ICOSeg uses an encoder and decoder sub-network. The encoder extracts the positive cell’s salient features (i.e., shape, texture, intensity, and margin), and the decoder reconstructs important features into segmentation maps. To improve the model generalization capabilities, we adopted a channel attention mechanism that added to the bottleneck of the encoder layer. This approach highlighted the most relevant cell structures by discriminating between the targeted cell and background tissues. We performed extensive experiments on our in-house dataset. The experimental results confirm that the proposed model achieves more significant results against state-of-the-art methods, together with an 8× reduction in parameters.

Missing sputum samples are common in asthma intervention studies and successful collection at follow-up is related to improvement in clinical outcomes

With only modest agreement between airway and systemic eosinophilia, biomarkers directly assessing the level and type of airway inflammation are becoming increasingly important, both for targeting treatment to the individual patient and for assessing effect [1].

Several factors significantly impact ability to produce a sputum sample after an anti-inflammatory intervention and these authors argue that the widely used complete-case analysis is inappropriate for paired sputum-based outcome measureshttps://bit.ly/3qN2pk5

Response of upper and lower airway inflammation to bronchial challenge with house dust mite in Chinese asthmatics: a pilot study

Background

Allergen nasal challenge can induce increase of eosinophils in sputum, but report about eosinophilic inflammation in upper airway after allergen bronchial challenge in Chinese asthmatics was rare. The article aims to evaluate response of upper and lower airways to house dust mite (HDM) allergen bronchial challenge.

Methods

HDM allergen bronchial challenge was carried out in asthmatic patients with allergic rhinitis (AR). Bronchial methacholine challenge and blood test were performed before and at 24 hours after allergen challenge. Nasal lavage and induced sputum for differential cells count and fractional exhaled nitric oxide (FeNO) measurement were performed before, 7 and 24 hours after allergen challenge.

Results

Eighteen asthmatic patients with AR underwent HDM allergen bronchial challenge with no serious adverse events reported. Fifteen patients showed dual asthmatic response (DAR), while 2 patients showed early (EAR) and 1 late asthmatic response (LAR) only. At 24 hours after allergen bronchial challenge testing, average PC₂₀FEV₁ to methacholine significantly decreased (1.58 to 0.81 mg/mL, P=0.03), while both FeNO and the percentage of eosinophils in blood and sputum were significantly increased [52.0 (54.0) to 69.0 (56.0) ppb, P=0.01; 4.82% to 6.91%, P<0.001; 20.70% to 27.86%, P=0.03, respectively], but with no significant differences found in the percentage of eosinophils in nasal lavage (39.36% to 38.58%, P=0.89). However, at 7 hours after allergen challenge, the eosinophils in sputum were significant increased to 40.45% (P<0.001), but there was an increase (39.36% to 48.07%) with no statistical difference (P=0.167) found in nasal lavage.

Conclusions

HDM allergen bronchial challenge induced different response of airway inflammation in upper and lower airways.

Differential cell counts using center-point networks achieves human-level accuracy and efficiency over segmentation

Differential cell counts is a challenging task when applying computer vision algorithms to pathology. Existing approaches to train cell recognition require high availability of multi-class segmentation and/or bounding box annotations and suffer in performance when objects are tightly clustered. We present differential count network ("DCNet"), an annotation efficient modality that utilises keypoint detection to locate in brightfield images the centre points of cells (not nuclei) and their cell class. The single centre point annotation for DCNet lowered burden for experts to generate ground truth data by 77.1% compared to bounding box labeling. Yet centre point annotation still enabled high accuracy when training DCNet on a multi-class algorithm on whole cell features, matching human experts in all 5 object classes in average precision and outperforming humans in consistency. The efficacy and efficiency of the DCNet end-to-end system represents a significant progress toward an open source, fully computationally approach to differential cell count based diagnosis that can be adapted to any pathology need.