Objective and Impact Statement.We propose an automated method of predicting Normal Pressure Hydrocephalus(NPH)from CT scans.A deep convolutional network segments regions of interest from the scans.These regions are th...Objective and Impact Statement.We propose an automated method of predicting Normal Pressure Hydrocephalus(NPH)from CT scans.A deep convolutional network segments regions of interest from the scans.These regions are then combined with MRI information to predict NPH.To our knowledge,this is the first method which automatically predicts NPH from CT scans and incorporates diffusion tractography information for prediction.Introduction.Due to their low cost and high versatility,CT scans are often used in NPH diagnosis.No well-defined and effective protocol currently exists for analysis of CT scans for NPH.Evans’index,an approximation of the ventricle to brain volume using one 2D image slice,has been proposed but is not robust.The proposed approach is an effective way to quantify regions of interest and offers a computational method for predicting NPH.Methods.We propose a novel method to predict NPH by combining regions of interest segmented from CT scans with connectome data to compute features which capture the impact of enlarged ventricles by excluding fiber tracts passing through these regions.The segmentation and network features are used to train a model for NPH prediction.Results.Our method outperforms the current state-of-the-art by 9 precision points and 29 recall points.Our segmentation model outperforms the current state-of-the-art in segmenting the ventricle,gray-white matter,and subarachnoid space in CT scans.Conclusion.Our experimental results demonstrate that fast and accurate volumetric segmentation of CT brain scans can help improve the NPH diagnosis process,and network properties can increase NPH prediction accuracy.展开更多
Gathering 3D material microstructural information is time-consuming,expensive,and energy-intensive.Acquisition of 3D data has been accelerated by developments in serial sectioning instrument capabilities;however,for c...Gathering 3D material microstructural information is time-consuming,expensive,and energy-intensive.Acquisition of 3D data has been accelerated by developments in serial sectioning instrument capabilities;however,for crystallographic information,the electron backscatter diffraction(EBSD)imaging modality remains rate limiting.We propose a physics-based efficient deep learning framework to reduce the time and cost of collecting 3D EBSD maps.Our framework uses a quaternion residual block self-attention network(QRBSA)to generate high-resolution 3D EBSD maps from sparsely sectioned EBSD maps.In QRBSA,quaternion-valued convolution effectively learns local relations in orientation space,while self-attention in the quaternion domain captures long-range correlations.We apply our framework to 3D data collected from commercially relevant titanium alloys,showing both qualitatively and quantitatively that our method can predict missing samples(EBSD information between sparsely sectioned mapping points)as compared to high-resolution ground truth 3D EBSD maps.展开更多
In computer vision,single-image super-resolution(SISR)has been extensively explored using convolutional neural networks(CNNs)on optical images,but images outside this domain,such as those from scientific experiments,a...In computer vision,single-image super-resolution(SISR)has been extensively explored using convolutional neural networks(CNNs)on optical images,but images outside this domain,such as those from scientific experiments,are not well investigated.Experimental data is often gathered using non-optical methods,which alters the metrics for image quality.One such example is electron backscatter diffraction(EBSD),a materials characterization technique that maps crystal arrangement in solid materials,which provides insight into processing,structure,and property relationships.We present a broadly adaptable approach for applying state-of-art SISR networks to generate super-resolved EBSD orientation maps.This approach includes quaternion-based orientation recognition,loss functions that consider rotational effects and crystallographic symmetry,and an inference pipeline to convert network output into established visualization formats for EBSD maps.The ability to generate physically accurate,high-resolution EBSD maps with super-resolution enables high-throughput characterization and broadens the capture capabilities for three-dimensional experimental EBSD datasets.展开更多
基金funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904)DOD ADNI (Department of Defense award number W81XWH-12-2-0012)+1 种基金supported by the following awards:National Institutes of Health (grant numbers T32-GM08620 and 5R01NS103774)National Science Foundation (grant number 1664172).
文摘Objective and Impact Statement.We propose an automated method of predicting Normal Pressure Hydrocephalus(NPH)from CT scans.A deep convolutional network segments regions of interest from the scans.These regions are then combined with MRI information to predict NPH.To our knowledge,this is the first method which automatically predicts NPH from CT scans and incorporates diffusion tractography information for prediction.Introduction.Due to their low cost and high versatility,CT scans are often used in NPH diagnosis.No well-defined and effective protocol currently exists for analysis of CT scans for NPH.Evans’index,an approximation of the ventricle to brain volume using one 2D image slice,has been proposed but is not robust.The proposed approach is an effective way to quantify regions of interest and offers a computational method for predicting NPH.Methods.We propose a novel method to predict NPH by combining regions of interest segmented from CT scans with connectome data to compute features which capture the impact of enlarged ventricles by excluding fiber tracts passing through these regions.The segmentation and network features are used to train a model for NPH prediction.Results.Our method outperforms the current state-of-the-art by 9 precision points and 29 recall points.Our segmentation model outperforms the current state-of-the-art in segmenting the ventricle,gray-white matter,and subarachnoid space in CT scans.Conclusion.Our experimental results demonstrate that fast and accurate volumetric segmentation of CT brain scans can help improve the NPH diagnosis process,and network properties can increase NPH prediction accuracy.
基金supported in part by NSF award SI2-SSI#1664172.N.R.B.and S.H.D.gratefully acknowledge financial support from NSWC Grant(N00174-22-1-0020)supported by the MRSEC Program of the NSF under Award No.DMR 2308708+1 种基金a member of the NSF-funded Materials Research Facilities Network(www.mrfn.org).Use was also made of computational facilities purchased with funds from the National Science Foundation(CNS-1725797)and administered by the Center for Scientific Computing(CSC)supported by the California NanoSystems Institute and the Materials Research Science and Engineering Center(MRSEC,NSF DMR 2308708)at UC Santa Barbara.
文摘Gathering 3D material microstructural information is time-consuming,expensive,and energy-intensive.Acquisition of 3D data has been accelerated by developments in serial sectioning instrument capabilities;however,for crystallographic information,the electron backscatter diffraction(EBSD)imaging modality remains rate limiting.We propose a physics-based efficient deep learning framework to reduce the time and cost of collecting 3D EBSD maps.Our framework uses a quaternion residual block self-attention network(QRBSA)to generate high-resolution 3D EBSD maps from sparsely sectioned EBSD maps.In QRBSA,quaternion-valued convolution effectively learns local relations in orientation space,while self-attention in the quaternion domain captures long-range correlations.We apply our framework to 3D data collected from commercially relevant titanium alloys,showing both qualitatively and quantitatively that our method can predict missing samples(EBSD information between sparsely sectioned mapping points)as compared to high-resolution ground truth 3D EBSD maps.
基金This research is supported in part by NSF awards number 1934641 and 1664172The MRL Shared Experimental Facilities are supported by the MRSEC Program of the NSF under Award No.DMR 1720256+5 种基金a member of the NSF-funded Materials Research Facilities Network(www.mrfn.org)Use was also made of computational facilities purchased with funds from the National Science Foundation(CNS-1725797)and administered by the Center for Scientific Computing(CSC)The CSC is supported by the California NanoSystems Institute and the Materials Research Science and Engineering Center(MRSECNSF DMR 1720256)at UC Santa BarbaraUse was made of the computational facilities purchased with funds from the National Science Foundation CC*Compute grant(OAC-1925717)and administered by the Center for Scientific Computing(CSC)The ONR Grant N00014-19-2129 is also acknowledged for the titanium datasets.
文摘In computer vision,single-image super-resolution(SISR)has been extensively explored using convolutional neural networks(CNNs)on optical images,but images outside this domain,such as those from scientific experiments,are not well investigated.Experimental data is often gathered using non-optical methods,which alters the metrics for image quality.One such example is electron backscatter diffraction(EBSD),a materials characterization technique that maps crystal arrangement in solid materials,which provides insight into processing,structure,and property relationships.We present a broadly adaptable approach for applying state-of-art SISR networks to generate super-resolved EBSD orientation maps.This approach includes quaternion-based orientation recognition,loss functions that consider rotational effects and crystallographic symmetry,and an inference pipeline to convert network output into established visualization formats for EBSD maps.The ability to generate physically accurate,high-resolution EBSD maps with super-resolution enables high-throughput characterization and broadens the capture capabilities for three-dimensional experimental EBSD datasets.
