# Beyond Point Annotation: A Weakly Supervised Network Guided by Multi-Level Labels Generated from Four-Point Annotation for Thyroid Nodule Segmentation in Ultrasound Image

arXiv: https://arxiv.org/abs/2410.19332 · HTML: https://mlsanity.com/paper/2410.19332/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 25 Oct 2024.

## Builds on (most cited first, 4 of 4)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [BoxInst: High-Performance Instance Segmentation with Box Annotations](https://mlsanity.com/paper/2012.02310/) (2020)
- [Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple Clinical Annotation](https://mlsanity.com/paper/2404.14852/) (2024)
- [A Spatially Constrained Deep Convolutional Neural Network for Nerve Fiber Segmentation in Corneal Confocal Microscopic Images using Inaccurate Annotations](https://mlsanity.com/paper/2004.09443/) (2020)

## Built on by (most cited first, 2 of 2)

- [DEPT: Deep Extreme Point Tracing for Ultrasound Image Segmentation](https://mlsanity.com/paper/2503.15260/) (2025)
- [Uncertainty-Aware Extreme Point Tracing for Weakly Supervised Ultrasound Image Segmentation](https://mlsanity.com/paper/2510.15666/) (2025)

## Abstract (arXiv)

Weakly-supervised methods typically guided the pixel-wise training by comparing the predictions to single-level labels containing diverse segmentation-related information at once, but struggled to represent delicate feature differences between nodule and background regions and confused incorrect information, resulting in underfitting or overfitting in the segmentation predictions. In this work, we propose a weakly-supervised network that generates multi-level labels from four-point annotation to refine diverse constraints for delicate nodule segmentation. The Distance-Similarity Fusion Prior referring to the points annotations filters out information irrelevant to nodules. The bounding box and pure foreground/background labels, generated from the point annotation, guarantee the rationality of the prediction in the arrangement of target localization and the spatial distribution of target/background regions, respectively. Our proposed network outperforms existing weakly-supervised methods on two public datasets with respect to the accuracy and robustness, improving the applicability of deep-learning based segmentation in the clinical practice of thyroid nodule diagnosis.