# Spatial Aggregation of Holistically-Nested Convolutional Neural Networks for Automated Pancreas Localization and Segmentation

arXiv: https://arxiv.org/abs/1702.00045 · HTML: https://mlsanity.com/paper/1702.00045/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2017.

## Built on by (most cited first, 18 of 18)

- [Medical Image Segmentation with 3D Convolutional Neural Networks: A Survey](https://mlsanity.com/paper/2108.08467/) (2021)
- [Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation](https://mlsanity.com/paper/2203.08964/) (2022)
- [Hierarchical 3D Feature Learning for Pancreas Segmentation](https://mlsanity.com/paper/2109.01667/) (2021)
- [Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation](https://mlsanity.com/paper/2204.01712/) (2022)
- [Implicit U-Net for volumetric medical image segmentation](https://mlsanity.com/paper/2206.15217/) (2022)
- [Deep Learning for Pancreas Segmentation: a Systematic Review](https://mlsanity.com/paper/2407.16313/) (2024)
- [Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network](https://mlsanity.com/paper/2111.04733/) (2021)
- [Recurrent Feature Propagation and Edge Skip-Connections for Automatic Abdominal Organ Segmentation](https://mlsanity.com/paper/2201.00317/) (2022)
- [Generalizable Pancreas Segmentation via a Dual Self-Supervised Learning Framework](https://mlsanity.com/paper/2505.07165/) (2025)
- [Diffusion Probabilistic Multi-cue Level Set for Reducing Edge Uncertainty in Pancreas Segmentation](https://mlsanity.com/paper/2404.07620/) (2024)
- [Multi-organ Segmentation Network with Adversarial Performance Validator](https://mlsanity.com/paper/2204.07850/) (2022)
- [CV-Attention UNet: Attention-based UNet for 3D Cerebrovascular Segmentation of Enhanced TOF-MRA Images](https://mlsanity.com/paper/2311.10224/) (2023)
- [Detection and Segmentation of Pancreas using Morphological Snakes and Deep Convolutional Neural Networks](https://mlsanity.com/paper/2302.06356/) (2023)
- [Curriculum Knowledge Switching for Pancreas Segmentation](https://mlsanity.com/paper/2306.12651/) (2023)
- [M3BUNet: Mobile Mean Max UNet for Pancreas Segmentation on CT-Scans](https://mlsanity.com/paper/2401.10419/) (2024)
- [DMC-Net: Lightweight Dynamic Multi-Scale and Multi-Resolution Convolution Network for Pancreas Segmentation in CT Images](https://mlsanity.com/paper/2410.02129/) (2024)
- [Deep Learning-Based Automatic Delineation of Liver Domes in kV Triggered Images for Online Breath-hold Reproducibility Verification of Liver Stereotactic Body Radiation Therapy](https://mlsanity.com/paper/2411.15322/) (2024)
- [A Unified Framework for the Detection and Classification of Fatty Pancreas in Ultrasound Images](https://mlsanity.com/paper/2605.07466/) (2026)

## Abstract (arXiv)

Accurate and automatic organ segmentation from 3D radiological scans is an important yet challenging problem for medical image analysis. Specifically, the pancreas demonstrates very high inter-patient anatomical variability in both its shape and volume. In this paper, we present an automated system using 3D computed tomography (CT) volumes via a two-stage cascaded approach: pancreas localization and segmentation. For the first step, we localize the pancreas from the entire 3D CT scan, providing a reliable bounding box for the more refined segmentation step. We introduce a fully deep-learning approach, based on an efficient application of holistically-nested convolutional networks (HNNs) on the three orthogonal axial, sagittal, and coronal views. The resulting HNN per-pixel probability maps are then fused using pooling to reliably produce a 3D bounding box of the pancreas that maximizes the recall. We show that our introduced localizer compares favorably to both a conventional non-deep-learning method and a recent hybrid approach based on spatial aggregation of superpixels using random forest classification. The second, segmentation, phase operates within the computed bounding box and integrates semantic mid-level cues of deeply-learned organ interior and boundary maps, obtained by two additional and separate realizations of HNNs. By integrating these two mid-level cues, our method is capable of generating boundary-preserving pixel-wise class label maps that result in the final pancreas segmentation. Quantitative evaluation is performed on a publicly available dataset of 82 patient CT scans using 4-fold cross-validation (CV). We achieve a Dice similarity coefficient (DSC) of 81.27+/-6.27% in validation, which significantly outperforms previous state-of-the art methods that report DSCs of 71.80+/-10.70% and 78.01+/-8.20%, respectively, using the same dataset.