- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper investigates cross-modal failures in diabetic retinopathy classification from color fundus to near-infrared images. A normalization strategy combining channel adjustment and intensity alignment is proposed, with experiments across eight encoder architectures and additional analyses of feature shifts and lesion retention.
Critical strengths
-
The paper addresses an important practical challenge in transferring medical image classification models across imaging modalities
-
Extensive experiments across eight encoders, multiple random seeds, and an external dataset, together with uncertainty and feature analyses, provide strong empirical support.
Critical weaknesses
- The methodological novelty is limited to me, as the proposed normalization mainly combines established preprocessing techniques. Its differences from existing methods require further clarification. 2.The ablation studies demonstrate the effects of individual transformations but do not fully establish the claimed mechanisms of cross-modal failure.
- The comparisons with domain adaptation methods are insufficient, as recent cross-modal adaptation approaches are not adequately evaluated.
- The generalizability of the conclusions remains unclear, as experiments focus on a single cross-modal transfer scenario.
- Some lines overlap with graphical elements, affecting the clarity of module boundaries and information flow.
Questions for authors
- How are the effects of channel representation and intensity distribution distinguished from other changes introduced by the transformation?
- What are the main methodological contributions beyond existing preprocessing techniques?
- Why are recent cross-modal adaptation methods not included, and how is the competitiveness of the CycleGAN baseline ensured?