Bayesian Optimization for Design Parameters of 3D Image Data Analysis

TL;DR

The 3D data Analysis Optimization Pipeline is introduced, a method designed to facilitate the design and parameterization of segmentation and classification using two Bayesian Optimization stages, and a segmentation quality metric is introduced that serves as the objective function.

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.

Figures (8)

• Figure 1: Progression of the introduced pipeline. 3D data (1) is used for data synthesis (2), combining instance simulation and domain adaptation. The synthetic data serves as input for segmentation optimization (3), where a pretrained model and postprocessing parameters are optimized with respect to the ipq metric. The optimized segmentation model (4) predicts instances, which are annotated by an operator (5). Classifier optimization (6) selects encoder and classifier head architectures, preprocessing, and pretraining strategies based on validation accuracy. The optimized classifier (7) predicts class labels, enabling the final analysis (8), which yields statistics such as class counts and instance volume distributions.
• Figure 2: Examples of idealized error types quantified by the ipq metric. rq detects hallucinations, iq captures instance splitting, and sq reflects oversegmentation.
• Figure 3: 3D depiction of the synthetic segmentation benchmark. a) Original reference, b) synthetic image, and c) synthetic image after domain adaptation via cycleGAN.
• Figure 4: ipq results of every experiment. Full bars present the baseline, thick-striped bars the random search, and thin-striped bars the model optimized by the pipe.
• Figure 5: 2D projection of a subset of the parameter space with resulting ipq values. The dots denote exploration steps, and the cross denotes the found optimum. Red numbers next to dots indicate that a specific parameter value combination was evaluated multiple times.