# A Bottom-up Approach for Pancreas Segmentation using Cascaded Superpixels and (Deep) Image Patch Labeling

arXiv: https://arxiv.org/abs/1505.06236 · HTML: https://mlsanity.com/paper/1505.06236/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2015.

## Built on by (most cited first, 4 of 4)

- [Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation](https://mlsanity.com/paper/2109.13841/) (2021)
- [Deep Learning for Pancreas Segmentation: a Systematic Review](https://mlsanity.com/paper/2407.16313/) (2024)
- [Curriculum Knowledge Switching for Pancreas Segmentation](https://mlsanity.com/paper/2306.12651/) (2023)
- [Generalized Shortest Path-based Superpixels for 3D Spherical Image Segmentation](https://mlsanity.com/paper/2509.19895/) (2025)

## Abstract (arXiv)

Robust automated organ segmentation is a prerequisite for computer-aided diagnosis (CAD), quantitative imaging analysis and surgical assistance. For high-variability organs such as the pancreas, previous approaches report undesirably low accuracies. We present a bottom-up approach for pancreas segmentation in abdominal CT scans that is based on a hierarchy of information propagation by classifying image patches at different resolutions; and cascading superpixels. There are four stages: 1) decomposing CT slice images as a set of disjoint boundary-preserving superpixels; 2) computing pancreas class probability maps via dense patch labeling; 3) classifying superpixels by pooling both intensity and probability features to form empirical statistics in cascaded random forest frameworks; and 4) simple connectivity based post-processing. The dense image patch labeling are conducted by: efficient random forest classifier on image histogram, location and texture features; and more expensive (but with better specificity) deep convolutional neural network classification on larger image windows (with more spatial contexts). Evaluation of the approach is performed on a database of 80 manually segmented CT volumes in six-fold cross-validation (CV). Our achieved results are comparable, or better than the state-of-the-art methods (evaluated by "leave-one-patient-out"), with Dice 70.7% and Jaccard 57.9%. The computational efficiency has been drastically improved in the order of 6~8 minutes, comparing with others of ~10 hours per case. Finally, we implement a multi-atlas label fusion (MALF) approach for pancreas segmentation using the same datasets. Under six-fold CV, our bottom-up segmentation method significantly outperforms its MALF counterpart: (70.7 +/- 13.0%) versus (52.5 +/- 20.8%) in Dice. Deep CNN patch labeling confidences offer more numerical stability, reflected by smaller standard deviations.