# Nested Radially Monotone Polar Occupancy Estimation: Clinically-Grounded Optic Disc and Cup Segmentation for Glaucoma Screening

Source: [Nested Radially Monotone Polar Occupancy Estimation: Clinically-Grounded Optic Disc and Cup Segmentation for Glaucoma Screening](<https://www.sota2.com/research/paper/69dc78657d0172140ec78945>)

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

Data updated: 2026-04-14T05:00:04.234Z

Authors: Rimsa Goperma, Rojan Basnet, Liang Zhao

Published: 2026-04-10T07:40:25.000Z

## Abstract

Valid segmentation of the optic disc (OD) and optic cup (OC) from fundus photographs is essential for glaucoma screening. Unfortunately, existing deep learning methods do not guarantee clinical validness including star-convexity and nested structure of OD and OC, resulting corruption in diagnostic metric, especially under cross-dataset domain shift. To adress this issue, this paper proposed NPS-Net (Nested Polar Shape Network), the first framework that formulates the OD/OC segmentation as nested radially monotone polar occupancy estimation.This output representation can guarantee the aforementioned clinical validness and achieve high accuracy. Evaluated across seven public datasets, NPS-Net shows strong zero-shot generalization. On RIM-ONE, it maintains 100% anatomical validity and improves Cup Dice by 12.8% absolute over the best baseline, reducing vCDR MAE by over 56%. On PAPILA, it achieves Disc Dice of 0.9438 and Disc HD95 of 2.78 px, an 83% reduction over the best competing method.

## 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.

- [Optic Disc and Cup Segmentation on RIM-ONE Zero-Shot 64 samples](<https://www.sota2.com/research/sota/optic-disc-and-cup-segmentation-on-rim-one-zero-shot-64-samples.md>): Optic disc and cup segmentation; RIM-ONE Zero-Shot 64 samples; Dice (Cup): 80.64.

- [Optic Disc and Cup Segmentation on PAPILA Zero-shot 488 samples](<https://www.sota2.com/research/sota/optic-disc-and-cup-segmentation-on-papila-zero-shot-488-samples.md>): Optic disc and cup segmentation; PAPILA Zero-shot 488 samples; Dice (Cup): 60.63.

- [Optic Disc and Cup Segmentation on DRISHTI-GS + REFUGE (combined test)](<https://www.sota2.com/research/sota/optic-disc-and-cup-segmentation-on-drishti-gs-plus-refuge-combined-test.md>): Optic disc and cup segmentation; DRISHTI-GS + REFUGE (combined test); Dice (Cup): 85.63.

- [Optic Disc and Cup Segmentation on Internal 275 samples (test)](<https://www.sota2.com/research/sota/optic-disc-and-cup-segmentation-on-internal-275-samples-test.md>): Optic disc and cup segmentation; Internal 275 samples (test); Dice (Cup): 89.33.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.09062>)

[PDF](<https://arxiv.org/pdf/2604.09062.pdf>)
