Digital image correlation based on convolutional neural networks

Optics and Lasers in Engineering, Journal Year: 2022, Volume and Issue: 160, P. 107234 - 107234

Published: Aug. 29, 2022

Language: Английский

---

Development of a high-performance label-free electrochemical immunosensor for early cancer diagnosis using anti-CEA/Ag-MOF/GO/GCE nanocomposite

Environmental Research, Journal Year: 2023, Volume and Issue: 238, P. 117178 - 117178

Published: Sept. 20, 2023

Language: Английский

---

Label-free macrophage phenotype classification using machine learning methods

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: March 30, 2023

Abstract Macrophages are heterogeneous innate immune cells that functionally shaped by their surrounding microenvironment. Diverse macrophage populations have multifaceted differences related to morphology, metabolism, expressed markers, and functions, where the identification of different phenotypes is an utmost importance in modelling response. While markers most used signature classify phenotypes, multiple reports indicate morphology autofluorescence also valuable clues can be process. In this work, we investigated as a distinct feature for classifying six namely: M0, M1, M2a, M2b, M2c, M2d. The was based on extracted signals from multi-channel/multi-wavelength flow cytometer. To achieve identification, constructed dataset containing 152,438 cell events each having response vector 45 optical fingerprint. Based dataset, applied supervised machine learning methods detect phenotype specific fingerprint vector, fully connected neural network architecture provided highest classification accuracy 75.8% compared simultaneously. Furthermore, restricting number experiment, proposed framework produces higher accuracies, averaging 92.0%, 91.9%, 84.2%, 80.4% pool two, three, four, five respectively. These results potential intrinsic with method being quick, simple, cost-effective way accelerate discovery phenotypical diversity.

Language: Английский

---

IDRM: Brain tumor image segmentation with boosted RIME optimization

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 166, P. 107551 - 107551

Published: Sept. 30, 2023

Language: Английский

---

Beyond the beat: A pioneering investigation into exercise modalities for alleviating diabetic cardiomyopathy and enhancing cardiac health

Current Problems in Cardiology, Journal Year: 2023, Volume and Issue: 49(2), P. 102222 - 102222

Published: Nov. 23, 2023

Language: Английский

---