# Investigating the Visual Cues of CNNs for Vascular Segmentation: A Case Study in Microscopy and Fundus Imaging

arXiv: https://arxiv.org/abs/2607.23371 · HTML: https://mlsanity.com/paper/2607.23371/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 25 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [Explainable deep learning models in medical image analysis](https://mlsanity.com/paper/2005.13799/) (2020)
- [Shape or Texture: Understanding Discriminative Features in CNNs](https://mlsanity.com/paper/2101.11604/) (2021)
- [Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation](https://mlsanity.com/paper/2305.06568/) (2023)
- [Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion](https://mlsanity.com/paper/2402.09530/) (2024)
- [Understanding the Influence of Receptive Field and Network Complexity in Neural-Network-Guided TEM Image Analysis](https://mlsanity.com/paper/2204.04250/) (2022)
- [A new dataset for measuring the performance of blood vessel segmentation methods under distribution shifts](https://mlsanity.com/paper/2301.04517/) (2023)
- [Demystifying the Effect of Receptive Field Size in U-Net Models for Medical Image Segmentation](https://mlsanity.com/paper/2406.16701/) (2024)
- [Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation](https://mlsanity.com/paper/2503.12453/) (2025)
- [Decomposing and Revising What Language Models Generate](https://mlsanity.com/paper/2509.00765/) (2025)

## Abstract (arXiv)

Vascular segmentation is a standard procedure for clinical diagnosis, yet the specific visual features determining model decisions remain poorly understood. This paper investigates the visual cues Convolutional Neural Networks (CNNs) use to segment blood vessels across two distinct imaging domains: fluorescence microscopy and retinal fundus photography. We employ a series of experiments to quantify the influence of shape, texture, and receptive field on segmentation performance. First, we isolate texture and intensity by evaluating performance on patches subjected to pixel shuffling and normalization. Second, we assess global shape relevance by training models on sparse contours and centerlines. Lastly, we quantify the required spatial context by systematically varying the network's theoretical and effective receptive fields. Within the scope of the evaluated datasets, we found that pixel intensity is more relevant than texture, though networks maintain surprisingly high accuracy even when both cues are removed. Furthermore, CNNs struggle to extrapolate full vessel geometry from shape cues alone, typically relying on a relatively small effective receptive field of around 20 pixels, though global context provides a modest benefit for fundus images. While specific to the modalities studied, this methodology offers a quantitative foundation to audit and refine deep learning systems in vascular imaging.