Chandra Suda | Searcharxiv

arXiv2023

Using Deep Learning to Predict Neural Stem Cell Differentiation in Regenerative Medicine

Over one in three people are affected by neurodegenerative disorders. Neural stem cells, which are multipotent regenerative cells with the potential to differentiate into any of the neural cell types, have immense therapeutic potential for treating neurological disorders. However, lengthy differentiation protocols hinder clinical applications and research. In this study, we present a deep learning approach using convolutional neural networks (CNNs) to predict the fate of neural stem cell differentiation at an early stage. We trained a CNN model on a dataset of cellular images from neural stem cell cultures. Our models achieved impressive results in predicting neuron and glial cell differentiation, with a 93.3% testing accuracy for a multiclass Resnet50 model (and 99.7% accuracy for a binary Resnet50 model). In addition, we developed and published a web tool to give stem cell researchers access to this technology to allow for efficient prediction of stem cell cell differentiation. Our work demonstrates the feasibility of and builds tooling for using CNNs for rapid, early differentiation outcome prediction from simple microscopy images, which could greatly accelerate neural stem cell research and therapies.

eess.IV↗

arXiv2023

Early Detection of Tuberculosis with Machine Learning Cough Audio Analysis: Towards More Accessible Global Triaging Usage

Tuberculosis (TB), a bacterial disease mainly affecting the lungs, is one of the leading infectious causes of mortality worldwide. To prevent TB from spreading within the body, which causes life-threatening complications, timely and effective anti-TB treatment is crucial. Cough, an objective biomarker for TB, is a triage tool that monitors treatment response and regresses with successful therapy. Current gold standards for TB diagnosis are slow or inaccessible, especially in rural areas where TB is most prevalent. In addition, current machine learning (ML) diagnosis research, like utilizing chest radiographs, is ineffective and does not monitor treatment progression. To enable effective diagnosis, an ensemble model was developed that analyzes, using a novel ML architecture, coughs' acoustic epidemiologies from smartphones' microphones to detect TB. The architecture includes a 2D-CNN and XGBoost that was trained on 724,964 cough audio samples and demographics from 7 countries. After feature extraction (Mel-spectrograms) and data augmentation (IR-convolution), the model achieved AUROC (area under the receiving operator characteristic) of 88%, surpassing WHO's requirements for screening tests. The results are available within 15 seconds and can easily be accessible via a mobile app. This research helps to improve TB diagnosis through a promising accurate, quick, and accessible triaging tool.

eess.AS↗