2.5D U-Net with Depth Reduction for 3D CryoET Object Identification

Yusuke Uchida, Takaaki Fukui
2/19/2025
cs.CV

No official code found. Best implementation: yu4u/kaggle-czii-4th (16 stars, MIT, last commit 2025-03-07).

Abstract

Cryo-electron tomography (cryoET) is a crucial technique for unveiling the structure of protein complexes. Automatically analyzing tomograms captured by cryoET is an essential step toward understanding cellular structures. In this paper, we introduce the 4th place solution from the CZII - CryoET Object Identification competition, which was organized to advance the development of automated tomogram analysis techniques. Our solution adopted a heatmap-based keypoint detection approach, utilizing an ensemble of two different types of 2.5D U-Net models with depth reduction. Despite its highly unified and simple architecture, our method achieved 4th place, demonstrating its effectiveness.

View on arXivView PDF

Code Implementations(1)

yu4u/kaggle-czii-4thCommunity100%
MIT

This is the implementation of the 4th place solution (yu4u's part) for CZII - CryoET Object Identification at Kaggle.

160Python, DockerfileFeb 6, 20251 years agoMIT
computer-visioncziideep-learningkagglekaggle-competition+1 more

Similar Papers

SemiETPicker: Fast and Label-Efficient Particle Picking for CryoET Tomography Using Semi-Supervised Learning

79% match2025

MAESTER: Masked Autoencoder Guided Segmentation at Pixel Resolution for Accurate, Self-Supervised Subcellular Structure Recognition

78% match2026

Region of Interest Segmentation and Morphological Analysis for Membranes in Cryo-Electron Tomography

77% match2026

FFF: Fragment-Guided Flexible Fitting for Building Complete Protein Structures

77% match2026

GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction

77% match1 repo162025

CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks

76% match2025

Cite this paper

@article{uchida2025d,
  title  = {2.5D U-Net with Depth Reduction for 3D CryoET Object Identification},
  author = {Yusuke Uchida and Takaaki Fukui},
  year   = {2025},
  eprint = {2502.13484},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.13484v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.13484.svg)](https://codeofpaper.com/paper/2502.13484)

Discussion