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

TL;DR

SemiETPicker introduces a semi-supervised particle picking method for CryoET that significantly reduces manual labeling effort while improving detection accuracy by leveraging unlabeled data with innovative training strategies.

Contribution

The paper presents a novel semi-supervised framework combining heatmap-based detection and teacher-student co-training tailored for CryoET particle picking, enhancing efficiency and accuracy.

Findings

Improves F1 score by 10% over supervised methods.

Effectively utilizes unlabeled CryoET data.

Introduces CryoET-specific augmentation techniques.

Abstract

Cryogenic Electron Tomography (CryoET) combined with sub-volume averaging (SVA) is the only imaging modality capable of resolving protein structures inside cells at molecular resolution. Particle picking, the task of localizing and classifying target proteins in 3D CryoET volumes, remains the main bottleneck. Due to the reliance on time-consuming manual labels, the vast reserve of unlabeled tomograms remains underutilized. In this work, we present a fast, label-efficient semi-supervised framework that exploits this untapped data. Our framework consists of two components: (i) an end-to-end heatmap-supervised detection model inspired by keypoint detection, and (ii) a teacher-student co-training mechanism that enhances performance under sparse labeling conditions. Furthermore, we introduce multi-view pseudo-labeling and a CryoET-specific DropBlock augmentation strategy to further boost performance. Extensive evaluations on the large-scale CZII dataset show that our approach improves F1 by 10% over supervised baselines, underscoring the promise of semi-supervised learning for leveraging unlabeled CryoET data.