Accurate three-dimensional (3D) reconstruction of individual dendrites in serial block-face scanning electron microscopy (SBF-SEM) is essential for quantifying structural plasticity in the brain, yet manual annotation at scale is infeasible. We present a fully automatic pipeline for 3D dendrite instance segmentation that unifies YOLOv6-guided Segment Anything Model (SAM) prompting on downsampled slices, iterative two-dimensional mask refinement, random forest 3D instance linking, and instance-aware high-resolution refinement using nnU-Net at native resolution into a single system requiring no manual prompting at inference. Applied to hippocampal CA1 SBF-SEM datasets from a control rat and a pilocarpine- induced epileptic rat, our pipeline reconstructs coherent, well- separated dendrites with high semantic accuracy (Dice 0.93 and 0.91) and strong instance-level performance on control tissue, while analysis of the more challenging epileptic tissue identifies instance recognition in dense regions as the principal remaining limitation. The high-resolution refinement stage recovers thin dendritic protrusions, providing a basis for downstream spine- level analysis. Code is available at https://github.com/ ZE-WEN/dendrite-3d-instance-seg.
Figures & tables
Fig. 1: Overview of the proposed pipeline. The main branch (1–7) produces and links 2D instance masks from downsampled slices. The high-resolution branch (A–D) applies nnU-Net at original resolution for protrusion recovery, and the two branches merge at step 7.
Category
Metric
Dataset A
Dataset B
Instance-level
Sinst
0.63
0.38
Sinst@0.5
0.75
0.34
Sinst@0.75
0.44
0.11
Panoptic
PQ
0.70
0.37
SQ
0.82
0.72
DQ
0.86
0.51
TABLE I: Quantitative results on Dataset A (control) and Dataset B (epileptic).
Fig. 2: Qualitative results on Dataset A (control) and Dataset B (epileptic). The left panel of each pair overlays predicted dendrite instances, each in a distinct color, on a single original-resolution EM slice. The right panel shows the corresponding 3D instance reconstruction over the whole volume.
Dataset A
Dataset B
Metric
RF
IoU only
RF
IoU only
Sinst
0.63
0.33
0.38
0.25
Sinst@0.5
0.75
0.29
0.34
0.30
Sinst@0.75
0.44
0.29
0.11
0.08
TABLE II: Ablation of the inter-slice linking model.
Segmentation of cellular structures in electron microscopy (EM) images is fundamental to analyzing the morphology of neurons and glial cells in the healthy and diseased brain tissue. Current neuronal segmentation applications are based on convolutional neural networks (CNNs) and do not effectively capture global relationships within images. Here, we present DendriteSAM, a vision foundation model based on Segment Anything, for interactive and automatic segmentation of dendrites in EM images. The model is trained on high-resolution EM data from healthy rat hippocampus and is tested on diseased rat and human data. Our evaluation results demonstrate better mask quality compared to the original and other fine-tuned models, leveraging the features learned during training. This study introduces the first implementation of vision foundation models in dendrite segmentation, paving the path for computer-assisted diagnosis of neuronal anomalies.
Zewen Zhuo, Ilya Belevich, Ville Leinonen +4
A.I. Virtanen Institute for Molecular Sciences University of Eastern Finland Kuopio, Finland · Electron Microscopy Unit Institute of Biotechnology University of Helsinki Helsinki, Finland · Department of Medicine Faculty of Health Sciences University of Eastern Finland Kuopio, Finland
Soma instance segmentation, i.e., identifying and delineating individual cell somas as distinct instances, is crucial for cellular analysis and connectomic reconstruction. Three-dimensional electron microscopy (3D EM) provides nanometer-scale resolution for capturing fine-grained soma morphology. However, dense instance-level manual annotation is prohibitively costly, limiting the scalability of fully supervised methods. To address this challenge, we propose SomaNet, a weakly supervised framework for 3D EM soma instance segmentation under partial annotation constraints. SomaNet adopts a teacher--student learning paradigm tailored to partial labels. The teacher is trained using partially annotated data to generate pseudo-labels, while the student jointly learns from the partial ground-truth annotations and the generated pseudo-labels, progressively recovering dense instance segmentations. To accurately delineate cell somas under limited supervision with varying instance counts, SomaNet incorporates affinity learning, which encourages high similarity within instances and low similarity across instance boundaries. Semantic-guided affinity decoding and 2D-to-3D reconstruction then produce volumetrically consistent 3D soma instances while preserving the large receptive fields of 2D backbones. The framework is architecture-flexible and supports diverse backbones, including vision transformers and foundation models, enabling direct transfer of pretrained visual representations to volumetric EM segmentation. Experiments on 3D EM brain datasets demonstrate that SomaNet achieves accurate and robust soma instance segmentation across regions with diverse soma morphologies under partial annotation. Code is available at https://github.com/mkhateri/SomaNet.
Mohammad Khateri, Morteza Ghahremani, Jussi Tohka +1
A. I. Virtanen Institute for Molecular Sciences, Faculty of Health Sciences, University of Eastern Finland, Finland
2D visual foundation models, such as DINOv3, a self-supervised model trained on large-scale natural images, have demonstrated strong zero-shot generalization, capturing both rich global context and fine-grained structural cues. However, an analogous 3D foundation model for downstream volumetric neuroimaging remains lacking, largely due to the challenges of 3D image acquisition and the scarcity of high-quality annotations. To address this gap, we propose to adapt the 2D visual representations learned by DINOv3 to a 3D biomedical segmentation model, enabling more data-efficient and morphologically faithful neuronal reconstruction. Specifically, we design an inflation-based adaptation strategy that inflates 2D filters into 3D operators, preserving semantic priors from DINOv3 while adapting to 3D neuronal volume patches. In addition, we introduce a topology-aware skeleton loss to explicitly enforce structural fidelity of graph-based neuronal arbor reconstruction. Extensive experiments on four neuronal imaging datasets, including two from BigNeuron and two public datasets, NeuroFly and CWMBS, demonstrate consistent improvements in reconstruction accuracy over SoTA methods, with average gains of 2.9% in Entire Structure Average, 2.8% in Different Structure Average, and 3.8% in Percentage of Different Structure. Code: https://github.com/yy0007/NeurINO.