Scholarlink

<p>Tauopathies are characterised by a progressive accumulation of hyperphosphorylated tau. However, early and intermediate stages remain challenging to quantify due to subtle and heterogeneous morphological characteristics. This study evaluates a deep learning framework for classifying multiple temporal stages of tauopathy progression using AT8 (anti-phospho-tau antibody)-stained cortical micrographs in a controlled traumatic brain injury mouse model – an underexplored application. Three convolutional neural network (CNN) architectures were examined: a custom CNN and two transfer-learning models (InceptionV3 and DenseNet). Images were grouped into four post-injury stages: 1&#xa0;day, 1&#xa0;week, 1&#xa0;month and 3&#xa0;months. Preprocessing included normalisation, augmentation and oversampling to address imbalance. Performance was assessed using stratified k-fold cross-validation with accuracy, macro-F1, per-class F1, and one-vs-rest area under the receiver operating characteristic curve (AUC). DenseNet achieved the best overall performance (accuracy = 70.9%, macro-F1 = 0.68) with strong discrimination for the 1-week stage (F1 = 0.95). All models showed limited separability in the earliest post-injury stage (1&#xa0;day), while intermediate to late stages (1–3&#xa0;months) exhibited partial overlap, consistent with the progressive nature of tau accumulation. These results indicate that deep learning, particularly transfer learning, offers a scalable approach for automated temporal staging of tauopathy in preclinical histology. Although the results are based on internal cross-validation without independent animal-level identifiers or external cohorts, the proposed framework provides a reliable foundation for incorporating CNN-based analysis into digital neuropathology workflows. Larger multi-centre datasets and slide-level modelling will be required to assess generalisation and support applications in early detection, longitudinal tracking, and treatment evaluation of tau-related neurodegeneration.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning-Based Classification of Temporal Stages of AT8-Labeled Tau Pathology After Experimental Traumatic Brain Injury

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月19日

查看全文
  • Guilherme José de Antunes e Sousa,
  • Rodrigo Afonso Sá,
  • Marcos António Spínola Monteiro Gomes,
  • George A. Edwards III,
  • Ines Moreno-González,
  • Ricardo José Alves de Sousa

摘要

Tauopathies are characterised by a progressive accumulation of hyperphosphorylated tau. However, early and intermediate stages remain challenging to quantify due to subtle and heterogeneous morphological characteristics. This study evaluates a deep learning framework for classifying multiple temporal stages of tauopathy progression using AT8 (anti-phospho-tau antibody)-stained cortical micrographs in a controlled traumatic brain injury mouse model – an underexplored application. Three convolutional neural network (CNN) architectures were examined: a custom CNN and two transfer-learning models (InceptionV3 and DenseNet). Images were grouped into four post-injury stages: 1 day, 1 week, 1 month and 3 months. Preprocessing included normalisation, augmentation and oversampling to address imbalance. Performance was assessed using stratified k-fold cross-validation with accuracy, macro-F1, per-class F1, and one-vs-rest area under the receiver operating characteristic curve (AUC). DenseNet achieved the best overall performance (accuracy = 70.9%, macro-F1 = 0.68) with strong discrimination for the 1-week stage (F1 = 0.95). All models showed limited separability in the earliest post-injury stage (1 day), while intermediate to late stages (1–3 months) exhibited partial overlap, consistent with the progressive nature of tau accumulation. These results indicate that deep learning, particularly transfer learning, offers a scalable approach for automated temporal staging of tauopathy in preclinical histology. Although the results are based on internal cross-validation without independent animal-level identifiers or external cohorts, the proposed framework provides a reliable foundation for incorporating CNN-based analysis into digital neuropathology workflows. Larger multi-centre datasets and slide-level modelling will be required to assess generalisation and support applications in early detection, longitudinal tracking, and treatment evaluation of tau-related neurodegeneration.