Combining MRF-based deformable registration and deep binary 3D-CNN descriptors for large lung motion estimation in COPD patients

Blendowski, Max; Heinrich, Mattias P.

doi:10.1007/s11548-018-1888-2

Cited by 35 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, 3D-CNN, convolutional layers extended to 3D filter that move 3-directions (x, y, z) extract spatiotemporal features from moving objects proposed as a method applied to motion image recognition (Ji et al, 2013; Blendowski and Heinrich, 2018; Lu et al, 2018). It has been successfully used to extract against the temporal change of the spatial structure data as a feature expression of 3D volume space such as cuboid output using the node locally connected to all the images within a certain time width (Ji et al, 2013; Maturana and Scherer, 2015).…”

Section: Resultsmentioning

confidence: 99%

“…Therefore, when recognizing an operation longer than the filter size, selection and combination processing of those features must be performed. As for chemical compounds, the 3D-CNN has been successfully shown to able to handle the data with spatial structure such as 3D-structures, on the choice of the data representation (Ji et al, 2013; Maturana and Scherer, 2015; Blendowski and Heinrich, 2018; Kuzminykh et al, 2018). If a suitable representation used, the most critical information efficiently captured.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of a Deep-Learning Method Based on the Classification of Images Generated by Parameterized Deep Snap a Novel Molecular-Image-Input Technique for Quantitative Structure–Activity Relationship (QSAR) Analysis

Matsuzaka

Uesawa

2019

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Numerous chemical compounds are distributed around the world and may affect the homeostasis of the endocrine system by disrupting the normal functions of hormone receptors. Although the risks associated with these compounds have been evaluated by acute toxicity testing in mammalian models, the chronic toxicity of many chemicals remains due to high cost of the compounds and the testing, etc. However, computational approaches may be promising alternatives and reduce these evaluations. Recently, deep learning (DL) has been shown to be promising prediction models with high accuracy for recognition of images, speech, signals, and videos since it greatly benefits from large datasets. Recently, a novel DL-based technique called DeepSnap was developed to conduct QSAR analysis using three-dimensional images of chemical structures. It can be used to predict the potential toxicity of many different chemicals to various receptors without extraction of descriptors. DeepSnap has been shown to have a very high capacity in tests using Tox21 quantitative qHTP datasets. Numerous parameters must be adjusted to use the DeepSnap method but they have not been optimized. In this study, the effects of these parameters on the performance of the DL prediction model were evaluated in terms of the loss in validation as an indicator for evaluating the performance of the DL using the toxicity information in the Tox21 qHTP database. The relations of the parameters of DeepSnap such as (1) number of molecules per SDF split into (2) zoom factor percentage, (3) atom size for van der waals percentage, (4) bond radius, (5) minimum bond distance, and (6) bond tolerance, with the validation loss following quadratic function curves, which suggests that optimal thresholds exist to attain the best performance with these prediction models. Using the parameter values set with the best performance, the prediction model of chemical compounds for CAR agonist was built using 64 images, at 105° angle, with AUC of 0.791. Thus, based on these parameters, the proposed DeepSnap-DL approach will be highly reliable and beneficial to establish models to assess the risk associated with various chemicals.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Optimization of a Deep-Learning Method Based on the Classification of Images Generated by Parameterized Deep Snap a Novel Molecular-Image-Input Technique for Quantitative Structure–Activity Relationship (QSAR) Analysis

Matsuzaka

Uesawa

2019

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…The results achieved by the approaches described in this section demonstrate that deep learning can be successfully applied to challenging registration tasks. However, the findings from [10] suggest that learned image similarity metrics may be best suited to complement existing similarity metrics in the unimodal case. Further, it is difficult to use these iterative techniques for real time registration.…”

Section: Discussion and Assessmentmentioning

confidence: 99%

“…Instead, Blendowski et al [10] proposed the combined use of both CNN-based descriptors and manually crafted MRF-based self-similarity descriptors for lung CT registration. Although the manually crafted descriptors outperformed the CNN-based descriptors, optimal performance was achieved using both sets of descriptors.…”

Section: Overview Of Workmentioning

confidence: 99%

Deep learning in medical image registration: a survey

Haskins

Krüger

Yan

2020

Machine Vision and Applications

487

320

View full text Add to dashboard Cite

The establishment of image correspondence through robust image registration is critical to many clinical tasks such as image fusion, organ atlas creation, and tumor growth monitoring, and is a very challenging problem. Since the beginning of the recent deep learning renaissance, the medical imaging research community has developed deep learning based approaches and achieved the stateof-the-art in many applications, including image registration. The rapid adoption of deep learning for image registration applications over the past few years necessitates a comprehensive summary and outlook, which is the main scope of this survey. This requires placing a focus on the different research areas as well as highlighting challenges that practitioners face. This survey, therefore, outlines the evolution of deep learning based medical image registration in the context of both research challenges and relevant innovations in the past few years. Further, this survey highlights future research directions to show how this field may be possibly moved forward to the next level.

show abstract

“…The model shows a performance improvement of 20% when compared to the structure based on handcrafted biochemical features. To deal with the memory issue and computational cost, Blendowski and Heinrich [ 105 ] suggested a combination of MRF-based deformable registration and 3D CNN descriptors for lung motion estimation on non-rigidly deformed chest CT images.…”

Section: Applications In 3d Medical Imagingmentioning

confidence: 99%

3D Deep Learning on Medical Images: A Review

Singh

Wang

Gupta

et al. 2020

Sensors

347

150

View full text Add to dashboard Cite

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field.

show abstract

Combining MRF-based deformable registration and deep binary 3D-CNN descriptors for large lung motion estimation in COPD patients

Cited by 35 publications

References 28 publications

Optimization of a Deep-Learning Method Based on the Classification of Images Generated by Parameterized Deep Snap a Novel Molecular-Image-Input Technique for Quantitative Structure–Activity Relationship (QSAR) Analysis

Optimization of a Deep-Learning Method Based on the Classification of Images Generated by Parameterized Deep Snap a Novel Molecular-Image-Input Technique for Quantitative Structure–Activity Relationship (QSAR) Analysis

Deep learning in medical image registration: a survey

3D Deep Learning on Medical Images: A Review

Contact Info

Product

Resources

About