A Semi-supervised Learning for Segmentation of Gigapixel Histopathology Images from Brain Tissues

Lai, Zhengfeng; Wang, Chao; Hu, Zin; Dugger, Brittany N.; Cheung, Susan; Chuah, Chen-Nee

doi:10.1109/embc46164.2021.9629715

Cited by 15 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To move closer to clinical applicability, external validation of any DL system is paramount 13 . Recent technical benchmark studies have demonstrated that attentionbased multiple instance learning (attMIL) 14 and self-supervised learning (SSL) 15,16 for pre-training of feature extractors 17,18 can improve performance and generalizability for computational pathology biomarkers, but these technical advances have not yet been systematically applied to mutation prediction in a pancancer approach.…”

mentioning

confidence: 99%

Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology

et al. 2023

View full text Add to dashboard Cite

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from pathology slides, but it is unclear how well these predictions generalize to external datasets. We performed a systematic study on Deep-Learning-based prediction of genetic alterations from histology, using two large datasets of multiple tumor types. We show that an analysis pipeline that integrates self-supervised feature extraction and attention-based multiple instance learning achieves a robust predictability and generalizability.

show abstract

mentioning

confidence: 99%

Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Machine learning (ML) methods have been utilized to aid in other realms of neuropathology. This includes detection of amyloid deposits in AD and white matter/gray matter segmentation [ 48 , 67 , 68 ]. The Neuropathology and Machine Learning core seeks to adapt these pipelines and develop workflows to detect microinfarcts in postmortem human brain tissue.…”

Section: Thematic Approachmentioning

confidence: 99%

How cy pres promotes transdisciplinary convergence science: an academic health center for women’s cardiovascular and brain health

Villablanca,

Dugger,

Nuthikattu

et al. 2024

J. Clin. Trans. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…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). Similarly, perturbationbased self-ensembling and temporal ensembling, where average predictions from prior epochs are used as pseudo-labels for training the current epoch (Li et al, 2020;Perone et al, 2019), have been shown to perform well in segmentation tasks with minimal manual annotations for training.…”

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

A Semi-supervised Learning for Segmentation of Gigapixel Histopathology Images from Brain Tissues

Cited by 15 publications

References 13 publications

Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology

Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology

How cy pres promotes transdisciplinary convergence science: an academic health center for women’s cardiovascular and brain health

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

Contact Info

Product

Resources

About