# Multi-head automated segmentation by incorporating detection head into the contextual layer neural network

arXiv: https://arxiv.org/abs/2602.02471 · HTML: https://mlsanity.com/paper/2602.02471/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Annotation-efficient deep learning for automatic medical image segmentation](https://mlsanity.com/paper/2012.04885/) (2020)
- [AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy](https://mlsanity.com/paper/1808.05238/) (2018)
- [Loss Functions and Metrics in Deep Learning](https://mlsanity.com/paper/2307.02694/) (2023)
- [Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network](https://mlsanity.com/paper/2411.13873/) (2024)
- [UOLO - automatic object detection and segmentation in biomedical images](https://mlsanity.com/paper/1810.05729/) (2018)
- [HALOS: Hallucination-free Organ Segmentation after Organ Resection Surgery](https://mlsanity.com/paper/2303.07717/) (2023)
- [Deep-learning Segmentation of Small Volumes in CT images for Radiotherapy Treatment Planning](https://mlsanity.com/paper/2404.04202/) (2024)

## Abstract (arXiv)

Deep learning based auto segmentation is increasingly used in radiotherapy, but conventional models often produce anatomically implausible false positives, or hallucinations, in slices lacking target structures. We propose a gated multi-head Transformer architecture based on Swin U-Net, augmented with inter-slice context integration and a parallel detection head, which jointly performs slice-level structure detection via a multi-layer perceptron and pixel-level segmentation through a context-enhanced stream. Detection outputs gate the segmentation predictions to suppress false positives in anatomically invalid slices, and training uses slice-wise Tversky loss to address class imbalance. Experiments on the Prostate-Anatomical-Edge-Cases dataset from The Cancer Imaging Archive demonstrate that the gated model substantially outperforms a non-gated segmentation-only baseline, achieving a mean Dice loss of 0.013 ± 0.036 versus 0.732 ± 0.314, with detection probabilities strongly correlated with anatomical presence, effectively eliminating spurious segmentations. In contrast, the non-gated model exhibited higher variability and persistent false positives across all slices. These results indicate that detection-based gating enhances robustness and anatomical plausibility in automated segmentation applications, reducing hallucinated predictions without compromising segmentation quality in valid slices, and offers a promising approach for improving the reliability of clinical radiotherapy auto-contouring workflows.