# TAPE: A two-stage parameter-efficient adaptation framework for foundation models in OCT-OCTA analysis

Source: [TAPE: A two-stage parameter-efficient adaptation framework for foundation models in OCT-OCTA analysis](<https://www.sota2.com/research/paper/69d48fb77d0172140ec74505>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-08T05:00:12.103Z

Authors: Xiaofei Su, Zengshuo Wang, Minghe Sun, Xin Zhao, Mingzhu Sun

Published: 2026-04-06T10:08:43.000Z

## Abstract

Automated analysis of optical coherence tomography (OCT) and OCT angiography (OCTA) images is critical for robust ophthalmic diagnosis. Existing mainstream methods trained from scratch rely heavily on massive data and model scale, thereby hindering their practical deployment in resource-constrained clinical settings. Although transfer learning based on foundation models (FMs) is promising, it still faces significant challenges: domain shift and task misalignment. To address these, we propose TAPE: A Two-stage Adaptation Framework via Parameter-Efficient Fine-tuning, which strategically decouples adaptation into domain alignment and task fitting for downstream segmentation. The domain adaptation stage notably applies parameter-efficient fine-tuning (PEFT) in the context of masked image modeling for medical image domain adaptation, a novel approach to the best of our knowledge. Applying TAPE to retinal layer segmentation on both universal (masked auto-encoder, MAE) and specialized (RETFound) FMs, it demonstrates superior parameter efficiency and achieves state-of-the-art generalization performance across diverse pathologies.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Retinal Layer Segmentation on OCTA-500 AMD](<https://www.sota2.com/research/sota/retinal-layer-segmentation-on-octa-500-amd.md>): Retinal Layer Segmentation; OCTA-500 AMD; mDice: 90.69.

- [Retinal Layer Segmentation on OCTA-500 DR](<https://www.sota2.com/research/sota/retinal-layer-segmentation-on-octa-500-dr.md>): Retinal Layer Segmentation; OCTA-500 DR; Dice Score: 93.12.

- [Retinal layer segmentation on OCTA-500 RVO](<https://www.sota2.com/research/sota/retinal-layer-segmentation-on-octa-500-rvo.md>): Retinal Layer Segmentation; OCTA-500 RVO; mDice: 89.13.

- [Retinal Layer Segmentation on OCTA-500 NORMAL](<https://www.sota2.com/research/sota/retinal-layer-segmentation-on-octa-500-normal.md>): Retinal Layer Segmentation; OCTA-500 NORMAL; mDice: 96.

- [Retinal layer segmentation on OCTA-500 ALL](<https://www.sota2.com/research/sota/retinal-layer-segmentation-on-octa-500-all.md>): Retinal Layer Segmentation; OCTA-500 ALL; mDice: 93.86.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.04571>)

[PDF](<https://arxiv.org/pdf/2604.04571.pdf>)
