arXiv subjects

Nicholas J. Durr

Publications and source records attributed to Nicholas J. Durr.

31 records · Page 2Linked to original sources

arXiv2020

Diffuser-based computational imaging funduscope

Poor access to eye care is a major global challenge that could be ameliorated by low-cost, portable, and easy-to-use diagnostic technologies. Diffuser-based imaging has the potential to enable inexpensive, compact optical systems that can reconstruct a focused image of an object over a range of defocus errors. Here, we present a diffuser-based computational funduscope that reconstructs important clinical features of a model eye. Compared to existing diffuser-imager architectures, our system features an infinite-conjugate design by relaying the ocular lens onto the diffuser. This offers shift-invariance across a wide field-of-view (FOV) and an invariant magnification across an extended depth range. Experimentally, we demonstrate fundus image reconstruction over a 33$^{\circ}$ FOV and robustness to $\pm$4D refractive error using a constant point-spread-function. Combined with diffuser-based wavefront sensing, this technology could enable combined ocular aberrometry and funduscopic screening through a single diffuser sensor.

physics.med-ph↗

arXiv2020

Imaging human blood cells in vivo with oblique back-illumination capillaroscopy

We present a non-invasive, label-free method of imaging blood cells flowing through human capillaries in vivo using oblique back-illumination capillaroscopy (OBC). Green light illumination allows simultaneous phase and absorption contrast, enhancing the ability to distinguish red and white blood cells. Single-sided illumination through the objective lens enables 200 Hz imaging with close illumination-detection separation and a simplified setup. Phase contrast is optimized when the illumination axis is offset from the detection axis by approximately 225 um when imaging 80 um deep in phantoms and human ventral tongue. We demonstrate high-speed imaging of individual red blood cells, white blood cells with sub-cellular detail, and platelets flowing through capillaries and vessels in human tongue. A custom pneumatic cap placed over the objective lens stabilizes the field of view, enabling longitudinal imaging of a single capillary for up to seven minutes. We present high-quality images of blood cells in individuals with Fitzpatrick skin phototypes II, IV, and VI, showing that the technique is robust to high peripheral melanin concentration. The signal quality, speed, simplicity, and robustness of this approach underscores its potential for non-invasive blood cell counting.

physics.bio-ph↗

arXiv2019

SLAM Endoscopy enhanced by adversarial depth prediction

Medical endoscopy remains a challenging application for simultaneous localization and mapping (SLAM) due to the sparsity of image features and size constraints that prevent direct depth-sensing. We present a SLAM approach that incorporates depth predictions made by an adversarially-trained convolutional neural network (CNN) applied to monocular endoscopy images. The depth network is trained with synthetic images of a simple colon model, and then fine-tuned with domain-randomized, photorealistic images rendered from computed tomography measurements of human colons. Each image is paired with an error-free depth map for supervised adversarial learning. Monocular RGB images are then fused with corresponding depth predictions, enabling dense reconstruction and mosaicing as an endoscope is advanced through the gastrointestinal tract. Our preliminary results demonstrate that incorporating monocular depth estimation into a SLAM architecture can enable dense reconstruction of endoscopic scenes.

eess.IV↗

arXiv2019

GANPOP: Generative Adversarial Network Prediction of Optical Properties from Single Snapshot Wide-field Images

We present a deep learning framework for wide-field, content-aware estimation of absorption and scattering coefficients of tissues, called Generative Adversarial Network Prediction of Optical Properties (GANPOP). Spatial frequency domain imaging is used to obtain ground-truth optical properties from in vivo human hands, freshly resected human esophagectomy samples and homogeneous tissue phantoms. Images of objects with either flat-field or structured illumination are paired with registered optical property maps and are used to train conditional generative adversarial networks that estimate optical properties from a single input image. We benchmark this approach by comparing GANPOP to a single-snapshot optical property (SSOP) technique, using a normalized mean absolute error (NMAE) metric. In human gastrointestinal specimens, GANPOP estimates both reduced scattering and absorption coefficients at 660 nm from a single 0.2/mm spatial frequency illumination image with 58% higher accuracy than SSOP. When applied to both in vivo and ex vivo swine tissues, a GANPOP model trained solely on human specimens and phantoms estimates optical properties with approximately 43% improvement over SSOP, indicating adaptability to sample variety. Moreover, we demonstrate that GANPOP estimates optical properties from flat-field illumination images with similar error to SSOP, which requires structured-illumination. Given a training set that appropriately spans the target domain, GANPOP has the potential to enable rapid and accurate wide-field measurements of optical properties, even from conventional imaging systems with flat-field illumination.

eess.IV↗

arXiv2019

Rethinking Monocular Depth Estimation with Adversarial Training

Monocular depth estimation is an extensively studied computer vision problem with a vast variety of applications. Deep learning-based methods have demonstrated promise for both supervised and unsupervised depth estimation from monocular images. Most existing approaches treat depth estimation as a regression problem with a local pixel-wise loss function. In this work, we innovate beyond existing approaches by using adversarial training to learn a context-aware, non-local loss function. Such an approach penalizes the joint configuration of predicted depth values at the patch-level instead of the pixel-level, which allows networks to incorporate more global information. In this framework, the generator learns a mapping between RGB images and its corresponding depth map, while the discriminator learns to distinguish depth map and RGB pairs from ground truth. This conditional GAN depth estimation framework is stabilized using spectral normalization to prevent mode collapse when learning from diverse datasets. We test this approach using a diverse set of generators that include U-Net and joint CNN-CRF. We benchmark this approach on the NYUv2, Make3D and KITTI datasets, and observe that adversarial training reduces relative error by several fold, achieving state-of-the-art performance.

cs.CV↗

arXiv2019

Structured Prediction using cGANs with Fusion Discriminator

We propose the fusion discriminator, a single unified framework for incorporating conditional information into a generative adversarial network (GAN) for a variety of distinct structured prediction tasks, including image synthesis, semantic segmentation, and depth estimation. Much like commonly used convolutional neural network -- conditional Markov random field (CNN-CRF) models, the proposed method is able to enforce higher-order consistency in the model, but without being limited to a very specific class of potentials. The method is conceptually simple and flexible, and our experimental results demonstrate improvement on several diverse structured prediction tasks.

cs.CV↗

arXiv2019

DeepLSR: a deep learning approach for laser speckle reduction

Speckle artifacts degrade image quality in virtually all modalities that utilize coherent energy, including optical coherence tomography, reflectance confocal microscopy, ultrasound, and widefield imaging with laser illumination. We present an adversarial deep learning framework for laser speckle reduction, called DeepLSR (https://durr.jhu.edu/DeepLSR), that transforms images from a source domain of coherent illumination to a target domain of speckle-free, incoherent illumination. We apply this method to widefield images of objects and tissues illuminated with a multi-wavelength laser, using light emitting diode-illuminated images as ground truth. In images of gastrointestinal tissues, DeepLSR reduces laser speckle noise by 6.4 dB, compared to a 2.9 dB reduction from optimized non-local means processing, a 3.0 dB reduction from BM3D, and a 3.7 dB reduction from an optical speckle reducer utilizing an oscillating diffuser. Further, DeepLSR can be combined with optical speckle reduction to reduce speckle noise by 9.4 dB. This dramatic reduction in speckle noise may enable the use of coherent light sources in applications that require small illumination sources and high-quality imaging, including medical endoscopy.

cs.CV↗

arXiv2018

Large dynamic range autorefraction with a low-cost diffuser wavefront sensor

Wavefront sensing with a thin diffuser has emerged as a potential low-cost alternative to a lenslet array for aberrometry. Diffuser wavefront sensors (DWS) have previously relied on tracking speckle displacement and consequently require coherent illumination. Here we show that displacement of caustic patterns can be tracked for estimating wavefront gradient, enabling the use of incoherent light sources and large dynamic-range wavefront measurements. We compare the precision of a DWS to a Shack-Hartmann wavefront sensor (SHWS) when using coherent, partially coherent, and incoherent illumination, in the application of autorefraction. We induce spherical and cylindrical errors in a model eye and use a multi-level Demon's non-rigid registration algorithm to estimate caustic displacements relative to an emmetropic model eye. When compared to spherical error measurements with the SHWS using partially coherent illumination, the DWS demonstrates a $\sim$5-fold improvement in dynamic range (-4.0 to +4.5 D vs. -22.0 to +19.5 D) with less than half the reduction in resolution (0.072 vs. 0.116 D), enabling a $\sim$3-fold increase in the number of resolvable prescriptions (118 vs. 358). In addition to being 40x lower-cost, the unique, non-periodic nature of the caustic pattern formed by a diffuser enables a larger dynamic range of aberration measurements compared to a lenslet array.

physics.optics↗

arXiv2018

Multimodal Densenet

Humans make accurate decisions by interpreting complex data from multiple sources. Medical diagnostics, in particular, often hinge on human interpretation of multi-modal information. In order for artificial intelligence to make progress in automated, objective, and accurate diagnosis and prognosis, methods to fuse information from multiple medical imaging modalities are required. However, combining information from multiple data sources has several challenges, as current deep learning architectures lack the ability to extract useful representations from multimodal information, and often simple concatenation is used to fuse such information. In this work, we propose Multimodal DenseNet, a novel architecture for fusing multimodal data. Instead of focusing on concatenation or early and late fusion, our proposed architectures fuses information over several layers and gives the model flexibility in how it combines information from multiple sources. We apply this architecture to the challenge of polyp characterization and landmark identification in endoscopy. Features from white light images are fused with features from narrow band imaging or depth maps. This study demonstrates that Multimodal DenseNet outperforms monomodal classification as well as other multimodal fusion techniques by a significant margin on two different datasets.

cs.CV↗

arXiv2018

Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images

Nuclei segmentation is a fundamental task that is critical for various computational pathology applications including nuclei morphology analysis, cell type classification, and cancer grading. Conventional vision-based methods for nuclei segmentation struggle in challenging cases and deep learning approaches have proven to be more robust and generalizable. However, CNNs require large amounts of labeled histopathology data. Moreover, conventional CNN-based approaches lack structured prediction capabilities which are required to distinguish overlapping and clumped nuclei. Here, we present an approach to nuclei segmentation that overcomes these challenges by utilizing a conditional generative adversarial network (cGAN) trained with synthetic and real data. We generate a large dataset of H&E training images with perfect nuclei segmentation labels using an unpaired GAN framework. This synthetic data along with real histopathology data from six different organs are used to train a conditional GAN with spectral normalization and gradient penalty for nuclei segmentation. This adversarial regression framework enforces higher order consistency when compared to conventional CNN models. We demonstrate that this nuclei segmentation approach generalizes across different organs, sites, patients and disease states, and outperforms conventional approaches, especially in isolating individual and overlapping nuclei.

cs.CV↗

arXiv2018

Deep Learning with Cinematic Rendering: Fine-Tuning Deep Neural Networks Using Photorealistic Medical Images

Deep learning has emerged as a powerful artificial intelligence tool to interpret medical images for a growing variety of applications. However, the paucity of medical imaging data with high-quality annotations that is necessary for training such methods ultimately limits their performance. Medical data is challenging to acquire due to privacy issues, shortage of experts available for annotation, limited representation of rare conditions and cost. This problem has previously been addressed by using synthetically generated data. However, networks trained on synthetic data often fail to generalize to real data. Cinematic rendering simulates the propagation and interaction of light passing through tissue models reconstructed from CT data, enabling the generation of photorealistic images. In this paper, we present one of the first applications of cinematic rendering in deep learning, in which we propose to fine-tune synthetic data-driven networks using cinematically rendered CT data for the task of monocular depth estimation in endoscopy. Our experiments demonstrate that: (a) Convolutional Neural Networks (CNNs) trained on synthetic data and fine-tuned on photorealistic cinematically rendered data adapt better to real medical images and demonstrate more robust performance when compared to networks with no fine-tuning, (b) these fine-tuned networks require less training data to converge to an optimal solution, and (c) fine-tuning with data from a variety of photorealistic rendering conditions of the same scene prevents the network from learning patient-specific information and aids in generalizability of the model. Our empirical evaluation demonstrates that networks fine-tuned with cinematically rendered data predict depth with 56.87% less error for rendered endoscopy images and 27.49% less error for real porcine colon endoscopy images.

cs.CV↗

arXiv2017

Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training

To realize the full potential of deep learning for medical imaging, large annotated datasets are required for training. Such datasets are difficult to acquire because labeled medical images are not usually available due to privacy issues, lack of experts available for annotation, underrepresentation of rare conditions and poor standardization. Lack of annotated data has been addressed in conventional vision applications using synthetic images refined via unsupervised adversarial training to look like real images. However, this approach is difficult to extend to general medical imaging because of the complex and diverse set of features found in real human tissues. We propose an alternative framework that uses a reverse flow, where adversarial training is used to make real medical images more like synthetic images, and hypothesize that clinically-relevant features can be preserved via self-regularization. These domain-adapted images can then be accurately interpreted by networks trained on large datasets of synthetic medical images. We test this approach for the notoriously difficult task of depth-estimation from endoscopy. We train a depth estimator on a large dataset of synthetic images generated using an accurate forward model of an endoscope and an anatomically-realistic colon. This network predicts significantly better depths when using synthetic-like domain-adapted images compared to the real images, confirming that the clinically-relevant features of depth are preserved.

cs.CV↗

arXiv2017

Deep Learning and Conditional Random Fields-based Depth Estimation and Topographical Reconstruction from Conventional Endoscopy

Colorectal cancer is the fourth leading cause of cancer deaths worldwide and the second leading cause in the United States. The risk of colorectal cancer can be mitigated by the identification and removal of premalignant lesions through optical colonoscopy. Unfortunately, conventional colonoscopy misses more than 20% of the polyps that should be removed, due in part to poor contrast of lesion topography. Imaging tissue topography during a colonoscopy is difficult because of the size constraints of the endoscope and the deforming mucosa. Most existing methods make geometric assumptions or incorporate a priori information, which limits accuracy and sensitivity. In this paper, we present a method that avoids these restrictions, using a joint deep convolutional neural network-conditional random field (CNN-CRF) framework. Estimated depth is used to reconstruct the topography of the surface of the colon from a single image. We train the unary and pairwise potential functions of a CRF in a CNN on synthetic data, generated by developing an endoscope camera model and rendering over 100,000 images of an anatomically-realistic colon. We validate our approach with real endoscopy images from a porcine colon, transferred to a synthetic-like domain, with ground truth from registered computed tomography measurements. The CNN-CRF approach estimates depths with a relative error of 0.152 for synthetic endoscopy images and 0.242 for real endoscopy images. We show that the estimated depth maps can be used for reconstructing the topography of the mucosa from conventional colonoscopy images. This approach can easily be integrated into existing endoscopy systems and provides a foundation for improving computer-aided detection algorithms for detection, segmentation and classification of lesions.

cs.CV↗