Automated Platelet Classification Under Different Solvent Conditions Through Deep Learning.
- 1Centre of Excellence for Data Science, Artificial Intelligence and Modelling, University of Hull, Hull HU6 7RX, UK.
- 2Centre for Biomedicine, Hull York Medical School, University of Hull, Hull HU6 7RX, UK.
- 3Tut-All Software GmbH, 76275 Ettlingen, Germany.
Abstract
Platelets undergo significant morphological transformations during activation influenced by chemical compounds such as zinc and milrinone. Manual classification methods are subjective, time-consuming, and prone to error. This research aimed to apply and evaluate the efficacy of different pre-trained deep learning Convolution Neural Networks, used for automated binary (treated vs untreated) and multiclass classification (control vs zinc vs milrinone vs combination) of platelet morphological changes induced by these solvents, addressing the limitations of manual classification methods. A dataset of 176 microscopic platelet images from Hull York Medical School was processed, comprising control (n = 43), zinc-treated (n = 45), milrinone-treated (n = 40), and combination treatment (n = 48) samples. Ten pre-trained CNN architectures were evaluated across 166 individual training iterations for both binary and multiclass classification tasks. Progressive optimisation strategies included contrast-limited adaptive histogram equalisation (CLAHE) enhancement, selective layer unfreezing, cross-validation, and hyperparameter tuning. For binary classification, Xception achieved optimal balanced performance (81% accuracy, 76% precision, 74% recall) with proper inter-class discrimination, despite higher numerical metrics (91% accuracy) showing classification bias. For multiclass classification, InceptionV3 and Xception demonstrated superior effectiveness with 72% accuracy. This study demonstrated that Xception and InceptionV3 architectures effectively capture subtle morphological features distinguishing treated platelets, offering reproducible alternatives to subjective manual methods.
Related
- Inflammation identity crisis: pathogenic nature of platelet-derived transforming growth factor β in chronic inflammatory conditions
- Identification and validation of stable reference genes for RT-qPCR analysis in blood samples from golden Syrian hamsters under different immunological conditions.
- Automated phytoplankton single‐cell counting from digital images with transfer learning for harmful algal bloom monitoring in the English Channel and North Sea
- Elicitor effects of silver nanoparticles (AgNPs) on secondary metabolite–related gene expression in different tissues and differentiation conditions of saffron (Crocus sativus L.)
- Automated spheroid and organoid image analysis from rule-based methods to deep learning
BibTeX
@article{daniel2026automated,
title = {{Automated Platelet Classification Under Different Solvent Conditions Through Deep Learning.}},
author = {Victor O Daniel and Charlie A Coupland and Nick Sander and Julius Mboli and Simon D J Calaminus and Eva Sousa},
journal = {Journal of imaging},
year = {2026},
month = oct,
doi = {10.3390/jimaging12100519},
url = {https://europepmc.org/article/MED/42930670},
note = {CC BY},
}
RIS
TY - JOUR
TI - Automated Platelet Classification Under Different Solvent Conditions Through Deep Learning.
AU - Victor O Daniel
AU - Charlie A Coupland
AU - Nick Sander
AU - Julius Mboli
AU - Simon D J Calaminus
AU - Eva Sousa
PY - 2026
DA - 2026/10/19
JO - Journal of imaging
DO - 10.3390/jimaging12100519
UR - https://europepmc.org/article/MED/42930670
AB - Platelets undergo significant morphological transformations during activation influenced by chemical compounds such as zinc and milrinone. Manual classification methods are subjective, time-consuming, and prone to error. This research aimed to apply and evaluate the efficacy of different pre-trained deep learning Convolution Neural Networks, used for automated binary (treated vs untreated) and multiclass classification (control vs zinc vs milrinone vs combination) of platelet morphological changes induced by these solvents, addressing the limitations of manual classification methods. A dataset of 176 microscopic platelet images from Hull York Medical School was processed, comprising control (n = 43), zinc-treated (n = 45), milrinone-treated (n = 40), and combination treatment (n = 48) samples. Ten pre-trained CNN architectures were evaluated across 166 individual training iterations for both binary and multiclass classification tasks. Progressive optimisation strategies included contrast-limited adaptive histogram equalisation (CLAHE) enhancement, selective layer unfreezing, cross-validation, and hyperparameter tuning. For binary classification, Xception achieved optimal balanced performance (81% accuracy, 76% precision, 74% recall) with proper inter-class discrimination, despite higher numerical metrics (91% accuracy) showing classification bias. For multiclass classification, InceptionV3 and Xception demonstrated superior effectiveness with 72% accuracy. This study demonstrated that Xception and InceptionV3 architectures effectively capture subtle morphological features distinguishing treated platelets, offering reproducible alternatives to subjective manual methods.
SN - 2313-433X
ER -