The NOVA project: maximizing beam time efficiency through synergistic analyses of SRμCT data

Schmelzle, Sebastian; Heethoff, Michael; Heuveline, Vincent; Lösel, Philipp; Becker, Jürgen; Beckmann, Felix; Schluenzen, Frank; Hammel, Jörg U.; Kopmann, A.; Mexner, W.; Vogelgesang, Matthias; Jerome, Nicholas Tan; Betz, Oliver; Beutel, Rolf G.; Wipfler‍, Benjamin; Blanke, Alexander; Harzsch, Steffen; Hörnig, Marie K.; Baumbach, Tilo; Kamp, Thomas van de

doi:10.1117/12.2275959

Cited by 8 publications

(8 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tachinid fly Gymnosoma nudifrons (Herting, 1966) had been fixed and stored in 70% EtOH. The unstained sample was scanned using SRµCT at the ANKA synchrotron radiation facility [27], [28]. We used a beam energy of 20 keV and 3000 projections at 250 projections per second.…”

Section: Ct Data and 3d Visualisationmentioning

confidence: 99%

Real-Time Local Noise Filter in 3-D Visualization of CT Data

Jerome

Ateyev

Schmelzle

et al. 2019

IEEE Trans. Nucl. Sci.

Self Cite

View full text Add to dashboard Cite

Removing noise in computer tomography (CT) data for real-time 3D visualization is vital to improving the quality of the final display. However, the CT noise cannot be removed by straight averaging because the noise has a broadband spatial frequency that is overlapping with the interesting signal frequencies. To improve the display of structures and features contained in the data, we present spatially variant filtering that performs averaging of sub-regions around a central region. We compare our filter with four other similar spatially variant filters regarding entropy and processing time. The results demonstrate significant improvement of the visual quality with processing time still within the millisecond range.

show abstract

Section: Ct Data and 3d Visualisationmentioning

confidence: 99%

Real-Time Local Noise Filter in 3-D Visualization of CT Data

Jerome

Ateyev

Schmelzle

et al. 2019

IEEE Trans. Nucl. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The most common segmentation method is manual processing, which is extremely time-consuming and compromises reproducibility [6]. This limits the number of samples that can be included in a given study, and thus the scientific applications of 3D scanning.…”

Section: Introductionmentioning

confidence: 99%

Automated Segmentation of Insect Anatomy from Micro-CT Images Using Deep Learning

Toulkeridou

Gutierrez

Baum

et al. 2023

Preprint

View full text Add to dashboard Cite

Three-dimensional (3D) imaging, such as micro-computed tomography (micro-CT), is increasingly being used by organismal biologists for precise and comprehensive anatomical characterization. However, the segmentation of anatomical structures remains a bottleneck in research, often requiring tedious manual work. Here, we propose a pipeline for the fully-automated segmentation of anatomical structures in micro-CT images utilizing state-of-the-art deep learning methods, selecting the ant brain as a test case. We implemented the U-Net architecture for 2D image segmentation for our convolutional neural network (CNN), combined with pixel-island detection. For training and validation of the network, we assembled a dataset of semi-manually segmented brain images of 76 ant species. The trained network predicted the brain area in ant images fast and accurately; its performance tested on validation sets showed good agreement between the prediction and the target, scoring 80% Intersection over Union (IoU) and 90% Dice Coefficient (F1) accuracy. While manual segmentation usually takes many hours for each brain, the trained network takes only a few minutes. Furthermore, our network is generalizable for segmenting the whole neural system in full-body scans, and works in tests on distantly related and morphologically divergent insects (e.g., fruit flies). The latter suggests that methods like the one presented here generally apply across diverse taxa. Our method makes the construction of segmented maps and the morphological quantification of different species more efficient and scalable to large datasets, a step toward a big data approach to organismal anatomy.

show abstract

“…In particular, while 3D images are reconstructed shortly after scanning, segmentation of the images into specific body parts is often a necessary step for quantification and visualization of particular structures. The most common segmentation method to date is by manual processing, which is extremely time-consuming and compromises reproducibility [6]. This limits the number of samples that can be included in a given study, and thus the scientific applications of 3D scanning.…”

Section: Introductionmentioning

confidence: 99%

Automated segmentation of insect anatomy from micro-CT images using deep learning

Toulkeridou

Baum

et al. 2021

Preprint

View full text Add to dashboard Cite

Three-dimensional (3D) imaging, such as micro-computed tomography (micro-CT), is increasingly being used by organismal biologists for precise and comprehensive anatomical characterization. However, the segmentation of anatomical structures remains a bottleneck in research, often requiring tedious manual work. Here, we propose a pipeline for the fully-automated segmentation of anatomical structures in micro-CT images utilizing state-of-the-art deep learning methods, selecting the ant brain as a testcase. We implemented the U-Net architecture for 2D image segmentation for our convolutional neural network (CNN), combined with pixel-island detection. For training and validation of the network, we assembled a dataset of semi-manually segmented brain images of 94 ant species. The trained network predicted the brain area in ant images fast and accurately; its performance tested on validation sets showed good agreement between the prediction and the target, scoring 80% Intersection over Union(IoU) and 90% Dice Coefficient (F1) accuracy. While manual segmentation usually takes many hours for each brain, the trained network takes only a few minutes.Furthermore, our network is generalizable for segmenting the whole neural system in full-body scans, and works in tests on distantly related and morphologically divergent insects (e.g., fruit flies). The latter suggest that methods like the one presented here generally apply across diverse taxa. Our method makes the construction of segmented maps and the morphological quantification of different species more efficient and scalable to large datasets, a step toward a big data approach to organismal anatomy.

show abstract

The NOVA project: maximizing beam time efficiency through synergistic analyses of SRμCT data

Cited by 8 publications

References 58 publications

Real-Time Local Noise Filter in 3-D Visualization of CT Data

Real-Time Local Noise Filter in 3-D Visualization of CT Data

Automated Segmentation of Insect Anatomy from Micro-CT Images Using Deep Learning

Automated segmentation of insect anatomy from micro-CT images using deep learning

Contact Info

Product

Resources

About