EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A first explainable-AI-based workflow integrating forward-forward and backpropagation-trained networks of label-free multiphoton microscopy images to assess human biopsies of rare neuromuscular disease

Riccardo Scodellaro, Jana Zschüntzsch, Anna-Kathrin Hell, Frauke Alves

Computer Methods and Programs in Biomedicine · 2025

DOI: 10.1016/j.cmpb.2025.108733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2025. Verfasst von Riccardo Scodellaro und 3 weiteren Autor:innen. Beteiligte Einrichtung: Translational Molecular Imaging, Max-Planck-Institute for Multidisciplinary Sciences, Göttingen, Germany. Hauptthemen laut MEDLINE: Muscular Dystrophy, Duchenne, Neuromuscular Diseases, Microscopy, Fluorescence, Multiphoton. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovative Medicines Initiative, European Commission, European Federation of Pharmaceutical Industries and Associations.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE: Diagnosis of rare neuromuscular diseases often relies on muscle biopsy analysis, which varies based on the evaluator's experience. Advances in deep learning show promise in improving diagnostic accuracy by identifying standardized features and phenotypic expressions in biopsy images. Explainable artificial intelligence extracts these features from the neural network's "black box," ensuring compliance with European ethical standards for the use of clinical data in real-world applications. This study proposes a clinic-friendly workflow, based on explainable artificial intelligence. It combines forward-forward and backpropagation-trained convolutional networks to identify complementary features of Duchenne Muscular Dystrophy. Our proposal sets the forward-forward training, applied here for the first time on biomedical images, as a potential new standard for interpretable deep learning applications in clinics. METHODS: We analyzed a multiphoton microscopy dataset of 1600 images from 16 human muscle biopsies obtained during elective spinal surgery, combining autofluorescence, second and third harmonic generation signals. Class Activation Maps unveiled the dual decision-making process of the convolutional network, independently trained with both standard backpropagation and forward-forward algorithms. We evaluated the significance of the discovered features by using the Mann Whitney method. Entire biopsies were analyzed by providing an attention metric, computed as the weighted mean of all significant parameters. RESULTS: Backpropagation, gold standard for 35 years, and forward-forward achieved over 90 % accuracy in distinguishing healthy and diseased patients tissue. Class activation maps revealed that, when trained independently with both algorithms, the same network identifies Duchenne Muscular Dystrophy tissue by focusing on different features. Both methods identified intramuscular collagen as a key feature. Backpropagation also highlighted collagen waviness and fatty tissue. Forward-forward emphasized collagen density. We integrated these complementary insights, validated by significance analysis, into a standardized attention metric, allowing a multi-structural, quantitative assessment of tissue changes and highlighting areas for further clinical analysis. CONCLUSIONS: Our workflow, using clinically routine biopsies and transparent diagnostic features, demonstrates the unique potential of forward-forward in providing novel, reliable, interpretable results from biomedical images. This paves the way for its dual use with backpropagation, shifting benchmarks by enabling the discovery of features potentially overlooked by backpropagation across biomedical datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Muscular Dystrophy, DuchenneNeuromuscular DiseasesMicroscopy, Fluorescence, MultiphotonHumansBiopsyWorkflowNeural Networks, ComputerAlgorithmsArtificial IntelligenceDeep LearningImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Class activation mapsDuchenne muscular dystrophyExplainable artificial intelligenceForward-forwardLabel-free imagingMultiphoton microscopy

Autor:innen und Institutionen

  • Translational Molecular Imaging, Max-Planck-Institute for Multidisciplinary Sciences, Göttingen, Germany.
  • Department of Neurology, University Medical Center Göttingen, Göttingen, Germany.
  • Pediatric Orthopaedics, Department for Trauma Surgery, Orthopaedics and Plastic Surgery, University Medical Center Göttingen, Göttingen, Germany.
  • Translational Molecular Imaging, Max-Planck-Institute for Multidisciplinary Sciences, Göttingen, Germany; Institute for Diagnostic and Interventional Radiology, University Medical Center Göttingen, Göttingen, Germany; C…

Förderung

  • Innovative Medicines Initiative
  • European Commission
  • European Federation of Pharmaceutical Industries and Associations

Zitieren

APA

Scodellaro, R., Zschüntzsch, J., Hell, A. K., & Alves, F. (2025). A first explainable-AI-based workflow integrating forward-forward and backpropagation-trained networks of label-free multiphoton microscopy images to assess human biopsies of rare neuromuscular disease. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2025.108733

Vancouver

Scodellaro R, Zschüntzsch J, Hell AK, Alves F. A first explainable-AI-based workflow integrating forward-forward and backpropagation-trained networks of label-free multiphoton microscopy images to assess human biopsies of rare neuromuscular disease. Computer Methods and Programs in Biomedicine. 2025. doi:10.1016/j.cmpb.2025.108733

BibTeX
@article{Scodellaro2025,
  author = {Scodellaro, Riccardo and Zschüntzsch, Jana and Hell, Anna-Kathrin and Alves, Frauke},
  title = {A first explainable-AI-based workflow integrating forward-forward and backpropagation-trained networks of label-free multiphoton microscopy images to assess human biopsies of rare neuromuscular disease},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2025},
  doi = {10.1016/j.cmpb.2025.108733}
}
Kostenlos starten →