Search for: All records

This study develops a comprehensive framework that integrates computational fluid dynamics (CFD) and machine learning (ML) to predict milk flow behavior in lactating breasts. Utilizing CFD and other high-fidelity simulation techniques to tackle fluid flow challenges often entails significant computational resources and time investment. Artificial neural networks (ANNs) offer a promising avenue for grasping complex relationships among high-dimensional variables. This study leverages this potential to introduce an innovative data-driven approach to CFD. The initial step involved using CFD simulations to generate the necessary training and validation datasets. A machine learning pipeline was then crafted to train the ANN. Furthermore, various ANN architectures were explored, and their predictive performance was compared. The design of experiments method was also harnessed to identify the minimum number of simulations needed for precise predictions. This study underscores the synergy between CFD and ML methodologies, designated as ML-CFD. This novel integration enables a neural network to generate CFD-like results, resulting in significant savings in time and computational resources typically required for traditional CFD simulations. The models developed through this ML-CFD approach demonstrate remarkable efficiency and robustness, enabling faster exploration of milk flow behavior in individual lactating breasts compared to conventional CFD solvers. 

Abstract Two common hemoglobinopathies, sickle cell disease (SCD) and β-thalassemia, arise from genetic mutations within the β-globin gene. In this work, we identified a 500-bp motif (Fetal Chromatin Domain, FCD) upstream of human ϒ-globin locus and showed that the removal of this motif using CRISPR technology reactivates the expression of ϒ-globin. Next, we present two different cell morphology-based machine learning approaches that can be used identify human blood cells (KU-812) that harbor CRISPR-mediated FCD genetic modifications. Three candidate models from the first approach, which uses multilayer perceptron algorithm (MLP 20-26, MLP26-18, and MLP 30-26) and flow cytometry-derived cellular data, yielded 0.83 precision, 0.80 recall, 0.82 accuracy, and 0.90 area under the ROC (receiver operating characteristic) curve when predicting the edited cells. In comparison, the candidate model from the second approach, which uses deep learning (T2D5) and DIC microscopy-derived imaging data, performed with less accuracy (0.80) and ROC AUC (0.87). We envision that equivalent machine learning-based models can complement currently available genotyping protocols for specific genetic modifications which result in morphological changes in human cells. 

This descriptive study investigates breast thermal characteristics in females histologically diagnosed with unilateral breast cancer and in their contralateral normal breasts. The multi-institutional clinical pilot study was reviewed and approved by the Institutional Review Boards (IRBs) at participating institutions. Eleven female subjects with radiologic breast abnormalities were enrolled in the study between June 2019 and September 2019 after informed consent was obtained. Static infrared images were recorded for each subject. The Wilcoxon signed rank test was used to conduct paired comparisons in temperature data between breasts among the eight histologically diagnosed breast cancer subjects (n = 8). Localized temperatures of cancerous breast lesions were significantly warmer than corresponding regions in contralateral breasts (34.0 ± 0.9 °C vs. 33.2 ± 0.5 °C, p = 0.0142, 95% CI 0.25–1.5 °C). Generalized temperatures over cancerous breasts, in contrast, were not significantly warmer than corresponding regions in contralateral breasts (33.9 ± 0.8 °C vs. 33.4 ± 0.4 °C, p = 0.0625, 95% CI −0.05–1.45 °C). Among the breast cancers enrolled, breast cancers elevated temperatures locally at the site of the lesion (localized hyperthermia), but not over the entire breast (generalized hyperthermia). 

The influence of external factors, including temperature, storage, aging, time, and shear rate, on the general rheological behavior of raw human milk is investigated. Rotational and oscillatory experiments were performed. Human milk showed non-Newtonian, shear-thinning, thixotropic behavior with both yield and flow stresses. Storage and aging increased milk density and decreased viscosity. In general, increases in temperature lowered density and viscosity with periods of inconsistent behavior noted between 6–16 ∘ C and over 40 ∘ C. Non-homogeneous breakdown between the yield and flow stresses was found which, when coupled with thixotropy, helps identify the source of nutrient losses during tube feeding.