scholarly journals A learning based approach for designing extended unit cell metagratings

Nanophotonics ◽  
2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Soumyashree S. Panda ◽  
Ravi S. Hegde
Keyword(s):  
Spectral Response ◽  
Ground Truth ◽  
Unit Cell ◽  
Inverse Design ◽  
Training Dataset ◽  
Single Element ◽  
Improve Design ◽  
Time Investment ◽  
Numerical Computing ◽  
Extended Unit

Abstract The possibility of arbitrary spatial control of incident wavefronts with the subwavelength resolution has driven research into dielectric optical metasurfaces in the last decade. The unit-cell based metasurface design approach that relies on a library of single element responses is known to result in reduced efficiency attributed to the inadequate accounting of the coupling effects between meta-atoms. Metasurfaces with extended unit-cells containing multiple resonators can improve design outcomes but their design requires extensive numerical computing and optimizations. We report a deep learning based design methodology for the inverse design of extended unit-cell metagratings. In contrast to previous reports, our approach learns the metagrating spectral response across its reflected and transmitted orders. Through systematic exploration, we discover network architectures and training dataset sampling strategies that allow such learning without requiring extensive ground-truth generation. The one-time investment of model creation can then be used to significantly accelerate numerical optimization of multiple functionalities as demonstrated by considering the inverse design of various spectral and polarization dependent splitters and filters. The proposed methodology is not limited to these proof-of-concept demonstrations and can be broadly applied to meta-atom-based nanophotonic system design and in realising the next generation of metasurface functionalities with improved performance.

scholarly journals MEMS mirrors using sub-wavelength High- Contrast-Gratings with asymmetric unit cells

2016 ◽  
Vol 19 (2) ◽  
pp. 52
Author(s):  
Milan Maksimović
Keyword(s):  
Spectral Response ◽  
Practical Interest ◽  
Optimization Procedure ◽  
Material Design ◽  
Unit Cell ◽  
High Contrast ◽  
Asymmetric Unit ◽  
Unit Cells ◽  
Thin Elements ◽  
Sub Wavelength

High-contrast gratings (HCG) are ultra-thin elements operating in sub-wavelength regime with the period of the grating smaller than the wavelength and with the high-index grating material fully surrounded by low-index material. Design of MEMS mirrors made from HCG with specific reflectivity response is of great practical interest in integrated optoelectronics. We theoretically investigate design of the spectral response for HCGs with the complex unit cells. We show that the spectral response can be tailored via the unit cell perturbations and with the asymmetric unit cell perturbations may introduce completely new spectral response. Our results can serve as guidance for the design of the complex HCGs and help with the choice of the efficient initial grating topology prior to global optimization procedure.

Abstract 20: Deep Learning-Based Automated Intracranial Hemorrhage Detection and Notification

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Benjamin Zahneisen ◽  
Matus Straka ◽  
Shalini Bammer ◽  
Greg Albers ◽  
Roland Bammer
Keyword(s):  
Deep Learning ◽  
Sensitivity And Specificity ◽  
Intracranial Hemorrhage ◽  
Health Care Professionals ◽  
Gold Standard ◽  
Ground Truth ◽  
Mobile App ◽  
Training Dataset ◽  
Convolutional Network ◽  
Ground Truth Data

Introduction: Ruling out hemorrhage (stroke or traumatic) prior to administration of thrombolytics is critical for Code Strokes. A triage software that identifies hemorrhages on head CTs and alerts radiologists would help to streamline patient care and increase diagnostic confidence and patient safety. ML approach: We trained a deep convolutional network with a hybrid 3D/2D architecture on unenhanced head CTs of 805 patients. Our training dataset comprised 348 positive hemorrhage cases (IPH=245, SAH=67, Sub/Epi-dural=70, IVH=83) (128 female) and 457 normal controls (217 female). Lesion outlines were drawn by experts and stored as binary masks that were used as ground truth data during the training phase (random 80/20 train/test split). Diagnostic sensitivity and specificity were defined on a per patient study level, i.e. a single, binary decision for presence/absence of a hemorrhage on a patient’s CT scan. Final validation was performed in 380 patients (167 positive). Tool: The hemorrhage detection module was prototyped in Python/Keras. It runs on a local LINUX server (4 CPUs, no GPUs) and is embedded in a larger image processing platform dedicated to stroke. Results: Processing time for a standard whole brain CT study (3-5mm slices) was around 2min. Upon completion, an instant notification (by email and/or mobile app) was sent to users to alert them about the suspected presence of a hemorrhage. Relative to neuroradiologist gold standard reads the algorithm’s sensitivity and specificity is 90.4% and 92.5% (95% CI: 85%-94% for both). Detection of acute intracranial hemorrhage can be automatized by deploying deep learning. It yielded very high sensitivity/specificity when compared to gold standard reads by a neuroradiologist. Volumes as small as 0.5mL could be detected reliably in the test dataset. The software can be deployed in busy practices to prioritize worklists and alert health care professionals to speed up therapeutic decision processes and interventions.

scholarly journals Voxel-Based Scene Representation for Camera Pose Estimation of a Single RGB Image

2020 ◽  
Vol 10 (24) ◽  
pp. 8866
Author(s):  
Sangyoon Lee ◽  
Hyunki Hong ◽  
Changkyoung Eem
Keyword(s):  
Pose Estimation ◽  
Estimation Method ◽  
Ground Truth ◽  
Training Dataset ◽  
Interest Points ◽  
Camera Pose Estimation ◽  
Polygonal Region ◽  
Camera Pose ◽  
End To End ◽  
Image Pairs

Deep learning has been utilized in end-to-end camera pose estimation. To improve the performance, we introduce a camera pose estimation method based on a 2D-3D matching scheme with two convolutional neural networks (CNNs). The scene is divided into voxels, whose size and number are computed according to the scene volume and the number of 3D points. We extract inlier points from the 3D point set in a voxel using random sample consensus (RANSAC)-based plane fitting to obtain a set of interest points consisting of a major plane. These points are subsequently reprojected onto the image using the ground truth camera pose, following which a polygonal region is identified in each voxel using the convex hull. We designed a training dataset for 2D–3D matching, consisting of inlier 3D points, correspondence across image pairs, and the voxel regions in the image. We trained the hierarchical learning structure with two CNNs on the dataset architecture to detect the voxel regions and obtain the location/description of the interest points. Following successful 2D–3D matching, the camera pose was estimated using n-point pose solver in RANSAC. The experiment results show that our method can estimate the camera pose more precisely than previous end-to-end estimators.

Intelligent Measurement of Spinal Curvature Using Cascade Gentle AdaBoost Classifier and Region-Based DRLSE

2019 ◽  
Vol 23 (3) ◽  
pp. 502-511
Author(s):  
Liyuan Zhang ◽  
◽  
Jiashi Zhao ◽  
Zhengang Jiang ◽  
Huamin Yang
Keyword(s):  
Negative Impact ◽  
Ground Truth ◽  
Spinal Curvature ◽  
Training Dataset ◽  
Initial Contour ◽  
Detection Accuracy ◽  
Automated Method ◽  
Spine Ct ◽  
Vertebral Bodies ◽  
Adaboost Classifier

For spinal curvature measurements, because of the anatomical complexity of the spine CT image, developing an automated method to avoid manual landmark is a challenging task. In this study, we propose an intelligent framework that integrates the cascade AdaBoost classifier and region-based distance regularized level set evolution (DRLSE) with the vertebral centroid measurement. First, the histogram-of-oriented-gradients based cascade gentle AdaBoost classifier is used to detect automatically and localize vertebral bodies from computer tomography (CT) spinal images. Considering these vertebral pathological images enables us to produce a diverse training dataset. Then, the DRLSE method introduces the local region information to converge the vertebral boundary quickly. The located bounding box is regarded as an accurate initial contour. This avoids the negative impact of manual initialization. Finally, we perform vertebral centroid extraction and spinal curve fitting. The spinal curvature angle is determined by calculating the angle between two tangents to the curve. We verified the effectiveness of the proposed method on 10 spine CT volumes. Quantitative comparison against the ground-truth centroids yielded a detection accuracy rate of 98.3% and a mean centroid location error of 1.15 mm. The comparative results with existing methods demonstrate that the proposed method can accurately detect and segment vertebral bodies. Furthermore, the spinal curvature can be automatically measured without manual landmark.

scholarly journals EVICAN—a balanced dataset for algorithm development in cell and nucleus segmentation

2020 ◽  
Vol 36 (12) ◽  
pp. 3863-3870
Author(s):  
Mischa Schwendy ◽  
Ronald E Unger ◽  
Sapun H Parekh
Keyword(s):  
Deep Learning ◽  
Cell Biology ◽  
Ground Truth ◽  
Training Data ◽  
Training Dataset ◽  
Visual Cell ◽  
Application Development ◽  
Ground Truth Data ◽  
Quantitative Image ◽  
Nucleus Segmentation

Abstract Motivation Deep learning use for quantitative image analysis is exponentially increasing. However, training accurate, widely deployable deep learning algorithms requires a plethora of annotated (ground truth) data. Image collections must contain not only thousands of images to provide sufficient example objects (i.e. cells), but also contain an adequate degree of image heterogeneity. Results We present a new dataset, EVICAN—Expert visual cell annotation, comprising partially annotated grayscale images of 30 different cell lines from multiple microscopes, contrast mechanisms and magnifications that is readily usable as training data for computer vision applications. With 4600 images and ∼26 000 segmented cells, our collection offers an unparalleled heterogeneous training dataset for cell biology deep learning application development. Availability and implementation The dataset is freely available (https://edmond.mpdl.mpg.de/imeji/collection/l45s16atmi6Aa4sI?q=). Using a Mask R-CNN implementation, we demonstrate automated segmentation of cells and nuclei from brightfield images with a mean average precision of 61.6 % at a Jaccard Index above 0.5.

scholarly journals Development of U-Net Breast Density Segmentation Method for Fat-Sat MR Images Using Transfer Learning Based on Non-Fat-Sat Model

2021 ◽  
Author(s):  
Yang Zhang ◽  
Siwa Chan ◽  
Jeon-Hor Chen ◽  
Kai-Ting Chang ◽  
Chin-Yao Lin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Breast Tissue ◽  
Ground Truth ◽  
Training Dataset ◽  
Breast Volume ◽  
Segmentation Method ◽  
Tissue Segmentation ◽  
Testing Dataset ◽  
The Mean

AbstractTo develop a U-net deep learning method for breast tissue segmentation on fat-sat T1-weighted (T1W) MRI using transfer learning (TL) from a model developed for non-fat-sat images. The training dataset (N = 126) was imaged on a 1.5 T MR scanner, and the independent testing dataset (N = 40) was imaged on a 3 T scanner, both using fat-sat T1W pulse sequence. Pre-contrast images acquired in the dynamic-contrast-enhanced (DCE) MRI sequence were used for analysis. All patients had unilateral cancer, and the segmentation was performed using the contralateral normal breast. The ground truth of breast and fibroglandular tissue (FGT) segmentation was generated using a template-based segmentation method with a clustering algorithm. The deep learning segmentation was performed using U-net models trained with and without TL, by using initial values of trainable parameters taken from the previous model for non-fat-sat images. The ground truth of each case was used to evaluate the segmentation performance of the U-net models by calculating the dice similarity coefficient (DSC) and the overall accuracy based on all pixels. Pearson’s correlation was used to evaluate the correlation of breast volume and FGT volume between the U-net prediction output and the ground truth. In the training dataset, the evaluation was performed using tenfold cross-validation, and the mean DSC with and without TL was 0.97 vs. 0.95 for breast and 0.86 vs. 0.80 for FGT. When the final model developed with and without TL from the training dataset was applied to the testing dataset, the mean DSC was 0.89 vs. 0.83 for breast and 0.81 vs. 0.81 for FGT, respectively. Application of TL not only improved the DSC, but also decreased the required training case number. Lastly, there was a high correlation (R2 > 0.90) for both the training and testing datasets between the U-net prediction output and ground truth for breast volume and FGT volume. U-net can be applied to perform breast tissue segmentation on fat-sat images, and TL is an efficient strategy to develop a specific model for each different dataset.

scholarly journals Multiplexed supercell metasurface design and optimization with tandem residual networks

Nanophotonics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 1133-1143
Author(s):  
Christopher Yeung ◽  
Ju-Ming Tsai ◽  
Brian King ◽  
Benjamin Pham ◽  
David Ho ◽  
...  
Keyword(s):  
Inverse Design ◽  
Training Dataset ◽  
Structure Property ◽  
Broadband Absorption ◽  
Design And Optimization ◽  
Optical Responses ◽  
Wide Range ◽  
Metal Insulator Metal ◽  
Material Choice ◽  
Nanophotonic Structures

Abstract Complex nanophotonic structures hold the potential to deliver exquisitely tailored optical responses for a range of applications. Metal–insulator–metal (MIM) metasurfaces arranged in supercells, for instance, can be tailored by geometry and material choice to exhibit a variety of absorption properties and resonant wavelengths. With this flexibility, however, comes a vast space of design possibilities that classical design paradigms struggle to effectively navigate. To overcome this challenge, here, we demonstrate a tandem residual network approach to efficiently generate multiplexed supercells through inverse design. By using a training dataset with several thousand full-wave electromagnetic simulations in a design space of over three trillion possible designs, the deep learning model can accurately generate a wide range of complex supercell designs given a spectral target. Beyond inverse design, the presented approach can also be used to explore the structure–property relationships of broadband absorption and emission in such supercell configurations. Thus, this study demonstrates the feasibility of high-dimensional supercell inverse design with deep neural networks, which is applicable to complex nanophotonic structures composed of multiple subunit elements that exhibit coupling.

scholarly journals Facilitating MR-Guided Adaptive Proton Therapy in Children Using Deep Learning-Based Synthetic CT

2021 ◽  
Author(s):  
Chuang Wang ◽  
Jinsoo Uh ◽  
Thomas E. Merchant ◽  
Chia-ho Hua ◽  
Sahaja Acharya
Keyword(s):  
Deep Learning ◽  
Brain Tumors ◽  
Proton Therapy ◽  
Hounsfield Unit ◽  
Ground Truth ◽  
Absolute Error ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Adaptive Planning ◽  
Patients Âgés

Abstract Purpose To determine whether self-attention cycle-generative adversarial networks (cycle-GANs), a novel deep-learning method, can generate accurate synthetic computed tomography (sCT) to facilitate adaptive proton therapy in children with brain tumors. Materials and Methods Both CT and T1-weighted magnetic resonance imaging (MRI) of 125 children (ages 1-20 years) with brain tumors were included in the training dataset. A model introducing a self-attention mechanism into the conventional cycle-GAN was created to enhance tissue interfaces and reduce noise. The test dataset consisted of 7 patients (ages 2-14 years) who underwent adaptive planning because of changes in anatomy discovered on MRI during proton therapy. The MRI during proton therapy-based sCT was compared with replanning CT (ground truth). Results The Hounsfield unit-mean absolute error was significantly reduced with self-attention cycle-GAN, as compared with conventional cycle-GAN (65.3 ± 13.9 versus 88.9 ± 19.3, P < .01). The average 3-dimensional gamma passing rates (2%/2 mm criteria) for the original plan on the anatomy of the day and for the adapted plan were high (97.6% ± 1.2% and 98.9 ± 0.9%, respectively) when using sCT generated by self-attention cycle-GAN. The mean absolute differences in clinical target volume (CTV) receiving 95% of the prescription dose and 80% distal falloff along the beam axis were 1.1% ± 0.8% and 1.1 ± 0.9 mm, respectively. Areas of greatest dose difference were distal to the CTV and corresponded to shifts in distal falloff. Plan adaptation was appropriately triggered in all test patients when using sCT. Conclusion The novel cycle-GAN model with self-attention outperforms conventional cycle-GAN for children with brain tumors. Encouraging dosimetric results suggest that sCT generation can be used to identify patients who would benefit from adaptive replanning.

scholarly journals A NEW STEREO DENSE MATCHING BENCHMARK DATASET FOR DEEP LEARNING

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 405-412
Author(s):  
T. Wu ◽  
B. Vallet ◽  
M. Pierrot-Deseilligny ◽  
E. Rupnik
Keyword(s):  
Deep Learning ◽  
Ground Truth ◽  
Fine Tuning ◽  
Training Dataset ◽  
Ground Truth Data ◽  
Aerial Photogrammetry ◽  
Dense Matching ◽  
Benchmark Datasets ◽  
3D Scene ◽  
The Impact

Abstract. Stereo dense matching is a fundamental task for 3D scene reconstruction. Recently, deep learning based methods have proven effective on some benchmark datasets, for example Middlebury and KITTI stereo. However, it is not easy to find a training dataset for aerial photogrammetry. Generating ground truth data for real scenes is a challenging task. In the photogrammetry community, many evaluation methods use digital surface models (DSM) to generate the ground truth disparity for the stereo pairs, but in this case interpolation may bring errors in the estimated disparity. In this paper, we publish a stereo dense matching dataset based on ISPRS Vaihingen dataset, and use it to evaluate some traditional and deep learning based methods. The evaluation shows that learning-based methods outperform traditional methods significantly when the fine tuning is done on a similar landscape. The benchmark also investigates the impact of the base to height ratio on the performance of the evaluated methods. The dataset can be found in https://github.com/whuwuteng/benchmark_ISPRS2021.

Sign in / Sign up

Export Citation Format

Share Document