REVIEW 5 cited by
Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
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
One of the biggest challenges for applying machine learning to histopathology is weak supervision: whole-slide images have billions of pixels yet often only one global label. The state of the art therefore relies on strongly-supervised model training using additional local annotations from domain experts. However, in the absence of detailed annotations, most weakly-supervised approaches depend on a frozen feature extractor pre-trained on ImageNet. We identify this as a key weakness and propose to train an in-domain feature extractor on histology images using MoCo v2, a recent self-supervised learning algorithm. Experimental results on Camelyon16 and TCGA show that the proposed extractor greatly outperforms its ImageNet counterpart. In particular, our results improve the weakly-supervised state of the art on Camelyon16 from 91.4% to 98.7% AUC, thereby closing the gap with strongly-supervised models that reach 99.3% AUC. Through these experiments, we demonstrate that feature extractors trained via self-supervised learning can act as drop-in replacements to significantly improve existing machine learning techniques in histology. Lastly, we show that the learned embedding space exhibits biologically meaningful separation of tissue structures.
Forward citations
Cited by 5 Pith papers
-
Current Pathology Foundation Models are unrobust to Medical Center Differences
Ten pathology foundation models encode medical center identity more strongly than cancer type in their embeddings, according to a new Robustness Index.
-
On the Generalizability of Iterative Patch Selection for Memory-Efficient High-Resolution Image Classification
The generalization threshold for Iterative Patch Selection on low object-to-image-ratio images depends on training set size and task, and smaller patches relative to the object improve low-data accuracy.
-
Understanding Synergistic Interactions among Pathology Foundation Models via Adaptive Fusion
A lightweight gating network that fuses frozen pathology foundation models improves several downstream benchmarks, but one headline metric is contradicted by the paper's own table.
-
Robustifying pathology foundation models via fine-tuning
A uniform fine-tuning step improves acquisition robustness and downstream performance across ten pathology foundation models, but the paper never discloses the fine-tuning recipe.
-
SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images
A weakly supervised pre-training scheme that propagates bag labels to patches improves downstream MIL classification and survival prediction on WSI datasets, but the comparison baselines are not trained on the same ta...
Discussion (0). Continue with ORCID to comment.