A Unified Deep Learning Framework for ssTEM Image Restoration

Deng, Shiyu; Huang, Wei; Chen, Chang; Fu, Xueyang; Xiong, Zhiwei

doi:10.1109/tmi.2022.3194984

Cited by 3 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors also employ a multi-scale training strategy, dividing the training into two stages with progressively larger input images, first \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $256\times 256\times 32$\end{document} , and then \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $320\times 320\times 36$\end{document} . For pre-processing, the authors apply denoising using their own image restoration network [45] , which is trained on patches of size \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $256\times 256\times 3$\end{document} . During testing, coarse noisy regions in the test sets are manually selected and restored using the trained interpolation network before performing segmentation.…”

Section: Summary Of Segmentation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Current Progress and Challenges in Large-Scale 3D Mitochondria Instance Segmentation

Franco-Barranco,

Lin,

Jang

et al. 2023

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

In this paper, we present the results of the MitoEM challenge on mitochondria 3D instance segmentation from electron microscopy images, organized in conjunction with the IEEE-ISBI 2021 conference. Our benchmark dataset consists of two large-scale 3D volumes, one from human and one from rat cortex tissue, which are 1,986 times larger than previously used datasets. At the time of paper submission, 257 participants had registered for the challenge, 14 teams had submitted their results, and six teams participated in the challenge workshop. Here, we present eight top-performing approaches from the challenge participants, along with our own baseline strategies. Posterior to the challenge, annotation errors in the ground truth were corrected without altering the final ranking. Additionally, we present a retrospective evaluation of the scoring system which revealed that: 1) challenge metric was permissive with the false positive predictions; and 2) size-based grouping of instances did not correctly categorize mitochondria of interest. Thus, we propose a new scoring system that better reflects the correctness of the segmentation results. Although several of the top methods are compared favorably to our own baselines, substantial errors remain unsolved for mitochondria with challenging morphologies. Thus, the challenge remains open for submission and automatic evaluation, with all volumes available for download.

show abstract

Section: Summary Of Segmentation Methodsmentioning

confidence: 99%

“…• VIDAR (USTC) 6 For pre-processing, the authors apply denoising using their own image restoration network [45], which is trained on patches of size 256 × 256 × 3. During testing, coarse noisy regions in the test sets are manually selected and restored using the trained interpolation network before performing segmentation.…”

Section: B Participants' Methodsmentioning

confidence: 99%

Current Progress and Challenges in Large-Scale 3D Mitochondria Instance Segmentation

Franco-Barranco,

Lin,

Jang

et al. 2023

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, they used a weighted binary cross-entropy loss function to compensate for the class imbalance and deployed a multi-scale training strategy to train the network in two stages with progressively larger input images. For pre-processing, denoising was performed with their own image restoration network [41]. Finally, the semantic masks and instance boundaries are used to create a seed map to perform hierarchical agglomeration [42] and extract individual instances.…”

Section: A Participants' Methodsmentioning

confidence: 99%

Current Progress and Challenges in Large-scale 3D Mitochondria Instance Segmentation

Franco-Barranco¹,

Lin²,

Jang³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>In this paper, we present the results of the MitoEM challenge on mitochondria 3D instance segmentation from electron microscopy images, organized in conjunction with the IEEE-ISBI 2021 conference. Our benchmark dataset consists of two large-scale 3D volumes, one from human and one from rat cortex tissue, which are 3,600 times larger than previously used datasets. At the time of paper submission, 257 participants had registered for the challenge, 14 teams had submitted their results, and six teams participated in the challenge workshop. Here, we present eight top-performing approaches from the challenge participants, along with our own baseline strategies. Posterior to the challenge, annotation errors in the ground truth were corrected without altering the final ranking. Although several of the top methods are compared favorably to our own baselines, substantial errors remain unsolved for mitochondria with challenging morphologies. Thus, the challenge remains open for submission and automatic evaluation, with all volumes available for download. Additionally, we present a retrospective evaluation of the scoring system performed using TIMISE, our novel open-source evaluation toolbox, which revealed that (1) the challenge metric was permissive with the false positive predictions and (2) the size-based grouping of instances did not correctly categorize mitochondria of interest. Thus, we propose a new scoring system that better reflects the correctness of the segmentation results. </p>

show abstract

Two Stage Image Restoration based on Histogram Equalization and Edge Computation for Image

Kumar

Jayalakshmi

2022

2022 International Conference on Computer, Power and Communications (ICCPC)

View full text Add to dashboard Cite

A Unified Deep Learning Framework for ssTEM Image Restoration

Cited by 3 publications

References 43 publications

Current Progress and Challenges in Large-Scale 3D Mitochondria Instance Segmentation

Current Progress and Challenges in Large-Scale 3D Mitochondria Instance Segmentation

Current Progress and Challenges in Large-scale 3D Mitochondria Instance Segmentation

Two Stage Image Restoration based on Histogram Equalization and Edge Computation for Image

Contact Info

Product

Resources

About