Deep Learning-Assisted Microscopy Reveals Progressive Supramolecular Remodeling and Colloidal Reorganization of Bovine Milk Induced by Centrifugation
Authors:
- Kamila PuppelKPKamila Puppel
- Dawid NiemiecDNDawid Niemiec
- Grzegorz GrodkowskiGGGrzegorz Grodkowski
- Piotr KostusiakPKPiotr Kostusiak
- Wojciech MendelowskiWMWojciech Mendelowski
- Jan SlósarzJSJan Slósarz
- Marcin GołęBiewskiMGMarcin GołęBiewski
- Kosma JagodzińskiKJKosma Jagodziński
- Krzysztof GwardysKGKrzysztof Gwardys
Open Access
- 29 June 2026
- journal article
- research article
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 27 (13) , 5868
Abstract
Bovine milk represents a highly complex colloidal system whose physicochemical stability depends on the organization of milk fat globules, casein micelles, membrane-associated phospholipids, and somatic cellular components. Mechanical separation procedures such as centrifugation induce redistribution of dispersed colloidal fractions and structural perturbations within the milk matrix, potentially enabling fraudulent reduction of somatic cell count while preserving bulk compositional parameters. In the present study, we investigated whether advanced deep learning architectures could identify centrifugation-associated structural alterations in bovine milk using microscopy image representations. A total of 16,472 microscopy images obtained from centrifuged and non-centrifuged milk samples were analyzed using Swin Transformer V2 and ConvNeXt-Base architectures. Both models successfully detected centrifugation-associated structural perturbations and substantially outperformed the previously analyzed InceptionC baseline. ConvNeXt-Base achieved 87.30% classification accuracy together with 86.85% balanced accuracy and 86.59% harmonic average of recalls following totalogit aggregation. Importantly, Swin Transformer V2 demonstrated strong monotonic relationships between logit metrics and centrifugation ratio (r = 0.640–0.651, p < 0.01), indicating sensitivity to progressive image-level changes associated with increasing centrifugation ratio. Collectively, the obtained findings demonstrate that microscopy-derived deep learning representations capture structural information associated with centrifugation-induced changes in bovine milk, supporting the applicability of AI-assisted microscopy for detecting processing-related alterations in complex dairy systems.Keywords
Funding Information
- Narodowe Centrum Badań i Rozwoju (POIR.01.01.01-00-2162/20-02)
This publication has 25 references indexed in Scilit:
- Recognition of bovine milk somatic cells based on multi-feature extraction and a GBDT-AdaBoost fusion modelMathematical Biosciences and Engineering, 2022
- Variation in milk fat globule size and composition: A source of bioactives for human healthCritical Reviews in Food Science and Nutrition, 2021
- Short communication: A decrease in diameter of milk fat globules accompanies milk fat depression induced by conjugated linoleic acid supplementation in lactating dairy cowsJournal of Dairy Science, 2020
- Characterization of difference in structure and function of fresh and mastitic bovine milk fat globulesPLOS ONE, 2019
- Prevalence and Comparing of Some Microbiological Properties, Somatic Cell Count and Antibiotic Residue of Organic and Conventional Raw Milk Produced in TurkeyFood Science of Animal Resources, 2017
- Structure–function relationship of the milk fat globuleCurrent Opinion in Clinical Nutrition and Metabolic Care, 2015
- The relationship between size and lipid composition of the bovine milk fat globule is modulated by lactation stageFood Chemistry, 2014
- Casein Micelles: Size Distribution in Milks from Individual CowsJournal of Agricultural and Food Chemistry, 2012
- Using Confocal Laser Scanning Microscopy To Probe the Milk Fat Globule Membrane and Associated ProteinsJournal of Agricultural and Food Chemistry, 2010
- Influence of Mastitis on Properties of Milk. VIII. Distribution of Soluble and Micellar CaseinJournal of Dairy Science, 1974