# Anatomical Positional Embeddings

arXiv: https://arxiv.org/abs/2409.10291 · HTML: https://mlsanity.com/paper/2409.10291/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 5 of 5)

- [AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation](https://mlsanity.com/paper/2206.08023/) (2022)
- [SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images](https://mlsanity.com/paper/2012.02383/) (2020)
- [nnDetection: A Self-configuring Method for Medical Object Detection](https://mlsanity.com/paper/2106.00817/) (2021)
- [vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical Images](https://mlsanity.com/paper/2307.14725/) (2023)
- [Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Images](https://mlsanity.com/paper/2012.07043/) (2020)

## Built on by (most cited first, 3 of 3)

- [RadiomicsRetrieval: A Customizable Framework for Medical Image Retrieval Using Radiomics Features](https://mlsanity.com/paper/2507.08546/) (2025)
- [Screener: Self-supervised Pathology Segmentation in Medical CT Images](https://mlsanity.com/paper/2502.08321/) (2025)
- [Weakly-supervised Kidney Tumor Classification from CT Scans with Multi-Instance Learning and Anatomical Filtering](https://mlsanity.com/paper/2609.07178/) (2026)

## Abstract (arXiv)

We propose a self-supervised model producing 3D anatomical positional embeddings (APE) of individual medical image voxels. APE encodes voxels' anatomical closeness, i.e., voxels of the same organ or nearby organs always have closer positional embeddings than the voxels of more distant body parts. In contrast to the existing models of anatomical positional embeddings, our method is able to efficiently produce a map of voxel-wise embeddings for a whole volumetric input image, which makes it an optimal choice for different downstream applications. We train our APE model on 8400 publicly available CT images of abdomen and chest regions. We demonstrate its superior performance compared with the existing models on anatomical landmark retrieval and weakly-supervised few-shot localization of 13 abdominal organs. As a practical application, we show how to cheaply train APE to crop raw CT images to different anatomical regions of interest with 0.99 recall, while reducing the image volume by 10-100 times. The code and the pre-trained APE model are available at https://github.com/mishgon/ape .