What does this research mean for the field?

For automated inflammatory bowel disease (IBD) classification using multimodal microscopy, ResNet50 with partial fine-tuning and augmentation provides the most efficient and robust baseline, while training from scratch can match transfer-learning performance due to domain differences from ImageNet. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Assessing the effectiveness of various convolutional neural network architectures for classifying IBD using multimodal microscopy data.

March 26, 2026Open Access

Comparative analysis of transfer learning architectures for multimodal microscopy based IBD histopathology

Puntos clave

Assessing the effectiveness of various convolutional neural network architectures for classifying IBD using multimodal microscopy data.
Evaluated nine CNN architectures for IBD classification using three training regimes.
Implemented partial and full fine-tuning, as well as training from scratch methods.
Applied patch-level augmentation and performed patient-level cross-validation.
Quantified uncertainty using bootstrap confidence intervals.
ResNet architectures consistently performed best, with ResNet50 showing optimal accuracy and stability.
Training from scratch achieved performance comparable to transfer learning, demonstrating effective learning from random initialization.
Partial fine-tuning with augmentation yielded near-perfect accuracy at the patient level.
Lightweight models required augmentation for stable performance.

Resumen

Assessment of inflammatory bowel disease (IBD) activity is limited by the need for biopsy processing and manual histological review. Multimodal microscopy combining coherent anti-Stokes Raman scattering (CARS), two-photon excited autofluorescence (TPEF), and second-harmonic generation (SHG) provides label-free images of colonic tissue with subcellular resolution. Earlier analyses using classical machine learning required annotated masks and handcrafted features, introducing dependence on manual input and limiting scalability. In this work, nine convolutional neural network (CNN) architectures were evaluated for IBD classification under three training regimes: partial fine-tuning, full fine-tuning, and training from scratch. Models were trained with and without patch-level augmentation and assessed using patient-level cross-validation at both patch and patient levels and uncertainty quantified using bootstrap confidence intervals. ResNet architectures showed the most consistent performance, with ResNet50 providing the best balance between accuracy, stability, and parameter efficiency. Training from scratch often matched transfer-learning performance, indicating that ImageNet features do not always align well with multimodal microscopy data. DenseNet121, in particular, learned effectively from random initialization, highlighting the role of architectural connectivity in domain-specific learning. Partial fine-tuning with augmentation achieved near-perfect patient-level accuracy, while deeper ResNets offered no additional benefit. Lightweight models such as EfficientNetB0 and MobileNet depended on augmentation and complete retraining for stable convergence. Overall, these results show that architecture choice, adaptation capacity, and augmentation must be considered jointly. For practical transfer-learning setups in multimodal IBD histopathology, ResNet50 with partial fine-tuning and augmentation provides an efficient and robust baseline, while suitably structured architectures can still learn effectively from scratch on limited datasets.

Me gusta

Guardar

Ver artículo completo