Coarse-Refined Consistency Learning Using Pixel-Level Features for Semi-Supervised Medical Image Segmentation

Du, Jie; Zhang, Xiaoci; Liu, Peng; Wang, Tianfu

doi:10.1109/jbhi.2023.3278741

Cited by 3 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We seek to overcome the above challenges with the use of semi-/self-supervised segmentation approaches that can extract maximal information from limited training data, while being sufficiently generalizable in the presence of typical variation across datasets from different brains and injection sites. Semi-/self-supervised methods have been shown to work well on generic noisy data and limited labels with uncertainties (Dinsdale et al, 2022;Chen et al, 2020;Feyjie et al, 2020;Perone et al, 2019;Sundaresan et al, 2022;Fischer et al, 2023;Du et al, 2023). In particular, contrastive learning, which aims to learn image features that are similar or different between segmentation classes (Chen et al, 2020;Zhao et al, 2023), has been used to segment histopathological images (Wu et al, 2022;Lai et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Self-supervised segmentation and characterization of fiber bundles in anatomic tracing data

Sundaresan,

Lehman,

Maffei

et al. 2023

Preprint

View full text Add to dashboard Cite

Anatomic tracing is the gold standard tool for delineating brain connections and for validating more recently developed imaging approaches such as diffusion MRI tractography. A key step in the analysis of data from tracer experiments is the careful, manual charting of fiber trajectories on histological sections. This is a very time-consuming process, which limits the amount of annotated tracer data that are available for validation studies. Thus, there is a need to accelerate this process by developing a method for computer-assisted segmentation. Such a method must be robust to the common artifacts in tracer data, including variations in the intensity of stained axons and background, as well as spatial distortions introduced by sectioning and mounting the tissue. The method should also achieve satisfactory performance using limited manually charted data for training. Here we propose the first deep-learning method, with a self-supervised loss function, for segmentation of fiber bundles on histological sections from macaque brains that have received tracer injections. We address the limited availability of manual labels with a semi-supervised training technique that takes advantage of unlabeled data to improve performance. We also introduce anatomic and across-section continuity constraints to improve accuracy. We show that our method can be trained on manually charted sections from a single case and segment unseen sections from different cases, with a true positive rate of∼0.80. We further demonstrate the utility of our method by quantifying the density of fiber bundles as they travel through different white-matter pathways. We show that fiber bundles originating in the same injection site have different levels of density when they travel through different pathways, a finding that can have implications for microstructure-informed tractography methods. The code for our method is available athttps://github.com/v-sundaresan/fiberbundle_seg_tracing.

show abstract