Consistent and effective method to define the mouse estrous cycle stage by a deep learning-based model.

The mouse estrous cycle is divided into four stages: proestrus (P), estrus (E), metestrus (M), and diestrus (D). The estrous cycle affects reproductive hormone levels in a wide variety of tissues. Therefore, to obtain reliable results from female mice, it is important to know the estrous cycle stage during sampling. The stage can be analyzed from a vaginal smear under a microscope. However, it is time-consuming, and the results vary between evaluators. Here, we present an accurate and reproducible method for staging the mouse estrous cycle in digital whole-slide images (WSIs) of vaginal smears. We developed a model using a deep convolutional neural network (CNN) in a cloud-based platform, Aiforia Create. The CNN was trained by supervised pixel-level multiclass semantic segmentation of image features from 171 hematoxylin-stained samples. The model was validated by comparing the results obtained by CNN with those of four independent researchers. The validation data included three separate studies comprising altogether 148 slides. The total agreement attested by the Fleiss kappa value between the validators and the CNN was excellent (0.75), and when D, E, and P were analyzed separately, the kappa values were 0.89, 0.79, and 0.74, respectively. The M stage is short and not well defined by the researchers. Thus, identification of the M stage by the CNN was challenging due to the lack of proper ground truth, and the kappa value was 0.26. We conclude that our model is reliable and effective for classifying the estrous cycle stages in female mice.

The prognostic utility of serum thyrotropin in hospitalized Covid-19 patients: statistical and machine learning approaches.

PURPOSE: To assess the prognostic value of serum TSH in Greek patients with COVID-19 and compare it with that of commonly used prognostic biomarkers. METHODS: Retrospective study of 128 COVID-19 in patients with no history of thyroid disease. Serum TSH, albumin, CRP, ferritin, and D-dimers were measured at admission. Outcomes were classified as "favorable" (discharge from hospital) and "adverse" (intubation or in-hospital death of any cause). The prognostic performance of TSH and other indices was assessed using binary logistic regression, machine learning classifiers, and ROC curve analysis. RESULTS: Patients with adverse outcomes had significantly lower TSH compared to those with favorable outcomes (0.61 versus 1.09 mIU/L, p < 0.001). Binary logistic regression with sex, age, TSH, albumin, CRP, ferritin, and D-dimers as covariates showed that only albumin (p < 0.001) and TSH (p = 0.006) were significantly predictive of the outcome. Serum TSH below the optimal cut-off value of 0.5 mIU/L was associated with an odds ratio of 4.13 (95% C.I.: 1.41-12.05) for adverse outcome. Artificial neural network analysis showed that the prognostic importance of TSH was second only to that of albumin. However, the prognostic accuracy of low TSH was limited, with an AUC of 69.5%, compared to albumin's 86.9%. A Naïve Bayes classifier based on the combination of serum albumin and TSH levels achieved high prognostic accuracy (AUC 99.2%). CONCLUSION: Low serum TSH is independently associated with adverse outcome in hospitalized Greek patients with COVID-19 but its prognostic utility is limited. The integration of serum TSH into machine learning classifiers in combination with other biomarkers enables outcome prediction with high accuracy.

A pressure-sensitive palatograph for speech analysis.

Electropalatography (EPG) is a clinical technique used to monitor contacts between the tongue and the hard palate, thus promoting correct articulation mechanisms. Currently, employed commercial tools have a good resolution but they do not provide contact pressure information. In this work, textile-based sensing technologies were employed to realize an innovative EPG tool able to both maintain the proper spatial resolution and perform quantitative pressure detection. The single sensing unit was developed using a thin polymeric sheet with a central hole, sandwiched between two piezoresistive fabric layers. Under load application, the two textile layers come into contact and the resistance of the sensor reduces significantly, measuring pressure in the range from 0 to 30 kPa. The complete prototype is composed of 62 sensing units disposed in a matrix structure: the dielectric layer contains all the sites arranged in rows and columns, according to the topography of the traditional tools, and this layer presents on both sides strips of piezoresistive textile. The entire system was covered with a thin latex membrane and fixed on a hard custom acrylic palate for the experimental characterization. The system was tested on a healthy subject, confirming the adequacy and effectiveness of the soft sensing technologies for the measuring of the tongue pressure during speech.

A biorobotic model of the human larynx.

This work focuses on a physical model of the human larynx that replicates its main components and functions. The prototype reproduces the multilayer vocal folds and the ab/adduction movements. In particular, the vocal folds prototype is made with soft materials whose mechanical properties have been obtained to be similar to the natural tissue in terms of viscoelasticity. A computational model was used to study fluid-structure interaction between vocal folds and the airflow. This tool allowed us to make a comparison between theoretical and experimental results. Measurements were performed with this prototype in an experimental platform comprising a controlled air flow, pressure sensors and a high-speed camera for measuring vocal fold vibrations. Data included oscillation frequency at the onset pressure and glottal width. Results show that the combination between vocal fold geometry, mechanical properties and dimensions exhibits an oscillation frequency close to that of the human vocal fold. Moreover, computational results show a high correlation with the experimental one.