3D Ground Truth Annotations of Nuclei in 3D Microscopy Volumes

Chen, Alain; Wu, Liming; Winfree, Seth; Dunn, Kenneth W.; Salama, Paul; Delp, Edward J.

doi:10.1101/2022.09.26.509542

Cited by 6 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The source code cannot be used for commercial purposes. The test volumes are also available at [37].…”

Section: Acknowledgmentmentioning

confidence: 99%

“…We used four microscopy volumes in our experiments, denoted by V 1 -V 4 , having fluorescent-labeled (Hoechst 33342 stain) nuclei that were collected from cleared rat kidneys, shallow rat livers, and cleared mouse intestines using confocal microscopy, to both generate synthetic data as well as provide ground truth data. Datasets V 1 -V 4 are available at [37]. In particular, we use the 3D Nuclei Image Synthesis method described in Section 2.1 in conjunction with a subset of V 1 -V 4 (other than those used for validation and testing) to generate 950 volumes of corresponding synthetic microscopy volumes (250 volumes for V 1 , 250 volumes for V 2 , 250 volumes for V 3 , and 200 volumes for V 4 ), that NISNet3D were then used for training NISNet3D.…”

Section: Evaluation Datasetsmentioning

confidence: 99%

“…The source code cannot be used for commercial purposes. The test volumes are also available at [37]. Address all correspondence to Edward J. Delp, ace@ecn.purdue.edu…”

Section: The Authors Have No Conflicts Of Interestmentioning

confidence: 99%

See 2 more Smart Citations

NISNet3D: Three-Dimensional Nuclear Synthesis and Instance Segmentation for Fluorescence Microscopy Images

Chen

Salama

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The primary step in tissue cytometry is the automated distinction of individual cells (segmentation). Since cell borders are seldom labeled, researchers generally segment cells by their nuclei. While effective tools have been developed for segmenting nuclei in two dimensions, segmentation of nuclei in three-dimensional images remains a challenging task for which few tools have been developed. The lack of effective methods for three-dimensional segmentation represents a bottleneck in the realization of the potential of tissue cytometry, particularly as methods of tissue clearing present researchers with the opportunity to characterize entire organs. Methods based upon deep learning have shown enormous promise, but their implementation is hampered by the need for large amounts manually-annotated training data. Here we describe 3D Nuclei Instance Segmentation Network (NISNet3D), a deep learning-based approach in which training is accomplished using synthetic data, profoundly reducing the effort required for network training. We compare results obtained from NISNet3D with results obtained from eight existing techniques.

show abstract

“…The source code cannot be used for commercial purposes. The test volumes are also available at [37].…”

Section: Acknowledgmentmentioning

confidence: 99%

Section: Evaluation Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

NISNet3D: Three-Dimensional Nuclear Synthesis and Instance Segmentation for Fluorescence Microscopy Images

Chen

Salama

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our experiments, the microscopy volumes used to train SpCycleGAN are of rat kidney and liver. 38 After SpCycleGAN is trained, we can then generate 3D synthetic microscopy volumes with known ground truth. We do this by giving the trained SpCycleGAN binary segmentation masks with known nuclei location (Section 2.2.1).…”

Section: Synthetic Microscopy Volume Generationmentioning

confidence: 99%

UNETRIS: transformer-based nuclear instance segmentation for three-dimensional fluorescence microscopy images

Chen,

Wu,

Winfree

et al. 2024

Medical Imaging 2024: Image Processing

View full text Add to dashboard Cite

Automated cellular nuclei segmentation is often an important step for digital pathology and other analyses such as computer aided diagnosis. Most existing machine learning methods for microscopy image analysis require postprocessing such as watershed transform or connected component analysis to obtain instance segmentation from semantic segmentation results. This becomes prohibitively expensive computationally especially when used with 3D microscopy volumes. UNet Transformers for Instance Segmentation (UNETRIS) is proposed to eliminate the postprocessing steps necessary for nuclei instance segmentation in 3D microscopy images. UNETRIS, an extension of UNETR which utilizes a transformer as the encoder in the successful "U-shaped" network design for the encoder-decoder structure of U-Net, uses additional transformers to separate individual instances of cell nuclei directly during the inference step without the need for expensive postprocessing steps. UNETRIS does not require but can use manual ground truth annotations for training. UNETRIS was tested on a variety of microscopy volumes collected from multiple regions of organ tissues.

show abstract

“…Synthetic ground truth image generation methods are frequently used with deep learning nuclei segmentation methods to create more training samples. [21][22][23][24] Many segmentation methods for elliptical nuclei have been proposed, while approaches for segmenting nonelliptical nuclei are lacking. Due to the diverse shapes of nuclei abnormalities, existing segmentation methods exhibit poor performance when abnormal nuclei and elliptical nuclei are mixed together.…”

Section: Introductionmentioning

confidence: 99%

Ensemble processing and convexity measure for abnormally shaped nuclei segmentation

Han,

Lei,

Shkolnikov

et al. 2024

Medical Imaging 2024: Image Processing

View full text Add to dashboard Cite

Morphological abnormalities in biological cell nuclei are used as essential features for diagnosing diseases, determining cell cycle stages, and conducting other fundamental cell biological research. While many deep learning approaches have been proposed for segmenting normal elliptical nuclei, less work has been done on segmenting abnormally shaped nuclei. One issue is that acquiring a significant number of annotated nuclei data poses a challenge for many deep learning segmentation methods, particularly due to the generally high cost associated with obtaining annotated data. The lack of the use of shape analysis is another problem that causes segmentation to not perform well for abnormally shaped nuclei. To address these problems, we propose a system to segment abnormally shaped nuclei with limited training data. We generate synthetic ground truth images of abnormally shaped nuclei to supplement the limited amount of training images available. Six Mask R-CNNs are trained to segment abnormally shaped nuclei. We then introduce an ensemble strategy, known as Weighted Mask Fusion, to combine the segmentation results from the six Mask R-CNNs. We describe a shape analysis step, based on a convexity measure, that is used on the segmented nuclei in the ensemble result to further improve the segmentation performance. Our proposed system is compared with other segmentation methods for abnormally shaped nuclei. The evaluation demonstrates the effectiveness of the ensemble processing, fusion, and convexity measures for segmenting abnormally shaped nuclei.

show abstract

3D Ground Truth Annotations of Nuclei in 3D Microscopy Volumes

Cited by 6 publications

References 24 publications

NISNet3D: Three-Dimensional Nuclear Synthesis and Instance Segmentation for Fluorescence Microscopy Images

NISNet3D: Three-Dimensional Nuclear Synthesis and Instance Segmentation for Fluorescence Microscopy Images

UNETRIS: transformer-based nuclear instance segmentation for three-dimensional fluorescence microscopy images

Ensemble processing and convexity measure for abnormally shaped nuclei segmentation

Contact Info

Product

Resources

About