Bayesian Optimization for Design Parameters of 3D Image Data Analysis
Preprint
Abstract
Deep learning-based segmentation and classification are crucial to large-scale biomedical imaging, particularly for 3D data, where manual analysis is impractical. Although many methods exist, selecting suitable models and tuning parameters remains a major bottleneck in practice. Hence, we introduce the 3D data Analysis Optimization Pipeline, a method designed to facilitate the design and parameterization of segmentation and classification using two Bayesian Optimization stages. First, the pipeline selects a segmentation model and optimizes postprocessing parameters using a domain-adapted syntactic benchmark dataset. To ensure a concise evaluation of segmentation performance, we introduce a segmentation quality metric that serves as the objective function. Second, the pipeline optimizes design choices of a classifier, such as encoder and classifier head architectures, incorporation of prior knowledge, and pretraining strategies. To reduce manual annotation effort, this stage includes an assisted class-annotation workflow that extracts predicted instances from the segmentation results and sequentially presents them to the operator, eliminating the need for manual tracking. In four case studies, the 3D data Analysis Optimization Pipeline efficiently identifies effective model and parameter configurations for individual datasets.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- CellSAM: a foundation model for cell segmentationNature Methods, 2025
- U-Net-based architecture with attention mechanisms and Bayesian Optimization for brain tumor segmentation using MR imagesComputers in Biology and Medicine, 2025
- Automatic head and neck tumor segmentation through deep learning and Bayesian optimization on three-dimensional medical imagesComputers in Biology and Medicine, 2025
- 3D reconstruction of skin and spatial mapping of immune cell density, vascular distance and effects of sun exposure and agingCommunications Biology, 2023
- The Cell Tracking Challenge: 10 years of objective benchmarkingNature Methods, 2023
- DeepSynth: Three-dimensional nuclear segmentation of biological images using neural networks trained with synthetic dataScientific Reports, 2019
- Rapid 3-D delineation of cell nuclei for high-content screening platformsComputers in Biology and Medicine, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Lipschitzian optimization without the Lipschitz constantJournal of Optimization Theory and Applications, 1993
- Automated basin delineation from digital elevation models using mathematical morphologySignal Processing, 1990