REVIEW 6 cited by
Transfusion: Understanding Transfer Learning for Medical Imaging
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Transfer learning from natural image datasets, particularly ImageNet, using standard large models and corresponding pretrained weights has become a de-facto method for deep learning applications to medical imaging. However, there are fundamental differences in data sizes, features and task specifications between natural image classification and the target medical tasks, and there is little understanding of the effects of transfer. In this paper, we explore properties of transfer learning for medical imaging. A performance evaluation on two large scale medical imaging tasks shows that surprisingly, transfer offers little benefit to performance, and simple, lightweight models can perform comparably to ImageNet architectures. Investigating the learned representations and features, we find that some of the differences from transfer learning are due to the over-parametrization of standard models rather than sophisticated feature reuse. We isolate where useful feature reuse occurs, and outline the implications for more efficient model exploration. We also explore feature independent benefits of transfer arising from weight scalings.
Forward citations
Cited by 6 Pith papers
-
Fine-Tuning Regimes Define Distinct Continual Learning Problems
The relative rankings of continual learning methods are not preserved across different fine-tuning regimes defined by trainable parameter depth.
-
Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification
Source-dataset selection for medical transfer learning is driven by community practice and perceived similarity, and 'more similar is better' does not consistently hold.
-
Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks
On MIMIC-III mortality and length-of-stay tasks, temporal evaluation shows raw-feature models lose up to 0.29 AUROC across the 2008 EHR switch, while expert-defined clinical concept features cut the drop to 0.06.
-
Robustness of transferability estimation metrics for medical imaging
Transferability estimation metric rankings in medical imaging are unstable to target resampling and to the evaluation metric used for the reference ranking.
-
XAI-Guided Analysis of Residual Networks for Interpretable Pneumonia Detection in Paediatric Chest X-rays
A fine-tuned ResNet-50 with Grad-CAM and Monte Carlo dropout reports 95.94% accuracy and 98.91% AUC for pediatric pneumonia on the Kermany chest X-ray dataset.
-
Analysis of Big Data Technology for Health Care Services
A literature review that summarizes known deep learning applications in health care without contributing any new results.
Discussion (0). Continue with ORCID to comment.