A 3D Convolutional Neural Network for Volumetric Image Semantic Segmentation

Lu, Hongya; Wang, Haifeng; Zhang, Qianqian; Yoon, Sang Won; Won, Daehan

doi:10.1016/j.promfg.2020.01.386

Cited by 38 publications

(25 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In brain MR segmentation, approaches such as VoxResNet [28] and various 3D U-Net based architectures [29] [30] [31] have proven successful. [32] achieve results surpassing the 2D slice-based approach by using 3D convolutional neural networks to classify volumetric thyroid images.…”

Section: Related Workmentioning

confidence: 96%

Residue Assignment in Crystallographic Protein Electron Density Maps With 3D Convolutional Networks

Godo¹,

Aoki

Nakagawa

et al. 2022

IEEE Access

View full text Add to dashboard Cite

This work proposes a neural network architecture, called 3D FC-DenseNet, for assigning amino acid labels to X-ray crystallographic electron density maps without relying on the amino acid sequence of proteins. The 3DFC-DenseNet is able to treat the task as a 3D semantic segmentation problem, assigning amino acid labels directly to protein electron density maps. By creating dedicated data sets and models for high, medium and low resolution samples, our method matches the performance of crystallographic toolkits for primary structure assignment at high resolutions. Furthermore, it outperforms them at medium resolution and functions at low resolutions where current toolkits and human ability fails.

show abstract

Section: Related Workmentioning

confidence: 96%

Residue Assignment in Crystallographic Protein Electron Density Maps With 3D Convolutional Networks

Godo¹,

Aoki

Nakagawa

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In [9,10] the long skip connections have residual form, adding the activity of encoder layers to the output of decoder layers, allowing a faster training. Hu et al [11] developed this approach further to successfully perform volumetric segmentation on three-dimensional medical recordings. In this study, fully convolutional encoder-decoder type networks are trained to automatically perform two-and three-dimensional segmentations on CT data.…”

Section: Machine-learning-based Segmentationmentioning

confidence: 99%

A machine-learning-based method for automatizing lattice-Boltzmann simulations of respiratory flows

et al. 2022

View full text Add to dashboard Cite

Many simulation workflows require to prepare the data for the simulation manually. This is time consuming and leads to a massive bottleneck when a large number of numerical simulations is requested. This bottleneck can be overcome by an automated data processing pipeline. Such a novel pipeline is developed for a medical use case from rhinology, where computer tomography recordings are used as input and flow simulation data define the results. Convolutional neural networks are applied to segment the upper airways and to detect and prepare the in- and outflow regions for accurate boundary condition prescription in the simulation. The automated process is tested on three cases which have not been used to train the networks. The accuracy of the pipeline is evaluated by comparing the network-generated output surfaces to those obtained from a semi-automated procedure performed by a medical professional. Except for minor deviations at interfaces between ethmoidal sinuses, the network-generated surface is sufficiently accurate. To further analyze the accuracy of the automated pipeline, flow simulations are conducted with a thermal lattice-Boltzmann method for both cases on a high-performace computing system. The comparison of the results of the respiratory flow simulations yield averaged errors of less than 1% for the pressure loss between the in- and outlets, and for the outlet temperature. Thus, the pipeline is shown to work accurately and the geometrical deviations at the ethmoidal sinuses to be negligible.

show abstract

“…A 3D-CNN, a 3D space implementation of convolution and pooling operation, is practiced to overcome spatial voxel information loss as in the 2D-CNNs. The image becomes scalable in the spatial direction using a 3D-CNN, allowing accurate image detection with different frame sizes [64]. Therefore, we propose a classifier based on 3D-CNN to identify COVID-19 from the volumetric CT scans.…”

Section: Architecturementioning

confidence: 99%

COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing

Hasan¹,

Jawad²,

Hasan³

et al. 2021

Preprint

View full text Add to dashboard Cite

The novel COVID-19 is a global pandemic disease overgrowing worldwide. Computer-aided screening tools with greater sensitivity is imperative for disease diagnosis and prognosis as early as possible. It also can be a helpful tool in triage for testing and clinical supervision of COVID-19 patients. However, designing such an automated tool from non-invasive radiographic images is challenging as many manually annotated datasets are not publicly available yet, which is the essential core requirement of supervised learning schemes. This article proposes a 3D Convolutional Neural Network (CNN)-based classification approach considering both the inter-and intra-slice spatial voxel information. The proposed system is trained in an end-to-end manner on the 3D patches from the whole volumetric CT images to enlarge the number of training samples, performing the ablation studies on patch size determination. We integrate progressive resizing, segmentation, augmentations, and class-rebalancing to our 3D network. The segmentation is a critical prerequisite step for COVID-19 diagnosis enabling the classifier to learn prominent lung features while excluding the outer lung regions of the CT scans. We evaluate all the extensive experiments on a publicly available dataset, named MosMed, having binary-and multi-class chest CT image partitions. Our experimental results are very encouraging, yielding areas under the ROC curve of 0.914 ± 0.049 and 0.893 ± 0.035 for the binary-and multi-class tasks, respectively, applying 5-fold cross-validations. Our method's promising results delegate it as a favorable 1

show abstract

A 3D Convolutional Neural Network for Volumetric Image Semantic Segmentation

Cited by 38 publications

References 10 publications

Residue Assignment in Crystallographic Protein Electron Density Maps With 3D Convolutional Networks

Residue Assignment in Crystallographic Protein Electron Density Maps With 3D Convolutional Networks

A machine-learning-based method for automatizing lattice-Boltzmann simulations of respiratory flows

COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing

Contact Info

Product

Resources

About