Abstract

Deep neural networks are highly effective at a range of computational tasks. However, they tend to be computationally expensive, especially in vision-related problems, and also have large memory requirements. One of the most effective methods to achieve significant improvements in computational/spatial efficiency is to binarize the weights and activations in a network. However, naive binarization results in accuracy drops when applied to networks for most tasks. In this work, we present a highly generalized, distribution-aware approach to binarizing deep networks that allows us to retain the advantages of a binarized network, while reducing accuracy drops. We also develop efficient implementations for our proposed approach across different architectures. We present a theoretical analysis of the technique to show the effective representational power of the resulting layers, and explore the forms of data they …

Abstract

Binarization is an extreme network compression approach that provides large computational speedups along with energy and memory savings, albeit at significant accuracy costs. We investigate the question of where to binarize inputs at layer-level granularity and show that selectively binarizing the inputs to specific layers in the network could lead to significant improvements in accuracy while preserving most of the advantages of binarization. We analyze the binarization tradeoff using a metric that jointly models the input binarization-error and computational cost and introduce an efficient algorithm to select layers whose inputs are to be binarized. Practical guidelines based on insights obtained from applying the algorithm to a variety of models are discussed. Experiments on Imagenet dataset using AlexNet and ResNet-18 models show 3-4% improvements in accuracy over fully binarized networks with minimal

Abstract

We, humans, have the ability to easily imagine scenes that depict sentences such as “Today is a beautiful sunny day” or “There is a Christmas feel, in the air”. While it is hard to precisely describe what one person may imagine, the essential high-level themes associated with such sentences largely remains the same. The ability to synthesize novel images that depict the feel of a sentence is very useful in a variety of applications such as education, advertisement, and entertainment. While existing papers tackle this problem given a style image, we aim to provide a far more intuitive and easy to use solution that synthesizes novel renditions of an existing image, conditioned on a given sentence. We present a method for cross-modal style transfer between an English sentence and an image, to produce a new image that imbibes the essential theme of the sentence. We do this by modifying the style transfer mechanism

Abstract

A system for capturing horizontal disparity stereo panorama is disclosed . The system includes a multi surface selective light reflector unit , a secondary reflector and a computing unit . The multi surface selective light reflector unit ( a ) obtains light rays from a 3D scene of outside world that are relevant to create ( i ) a left eye panorama and ( ii ) a right eye panorama and ( b ) reflects the light rays without internal reflections between the light rays . The secondary reflector ( a ) obtains the reflected light rays from the multi surface selective light reflector unit and ( b ) reflects the light rays through the viewing aperture . The computing unit captures ( i ) the reflected light rays from the secondary reflector and ( ii ) the upper part of the 3D scene from a concave lens as a warped image and processes the warped image to ( a ) the left eye panorama and ( b ) the right eye panorama .

Abstract

Automated and accurate segmentation of cystoid structures in Optical Coherence Tomography (OCT) is of interest in the early detection of retinal diseases. It is however a challenging task. We propose a novel method for localizing cysts in 3D OCT volumes. The proposed work is biologically inspired and based on selective enhancement of the cysts, by inducing motion to a given OCT slice. A Convolutional Neural Network (CNN) is designed to learn a mapping function that combines the result of multiple such motions to produce a probability map for cyst locations in a given slice. The final segmentation of cysts is obtained via simple clustering of the detected cyst locations. The proposed method is evaluated on two public datasets and one private dataset. The public datasets include the one released for the OPTIMA Cyst segmentation challenge (OCSC) in MICCAI 2015 and the DME dataset. After training on the OCSC train set, the method achieves a mean Dice Coefficient (DC) of 0.71 on the OCSC test set. The robustness of the algorithm was examined by cross validation on the DME and AEI (private) datasets and a mean DC values obtained were 0.69 and 0.79, respectively. Overall, the proposed system outperforms all benchmarks. These results underscore the strengths of the proposed method in handling variations in both data acquisition protocols and scanners.

Abstract

Purpose To analyse the expansion of radial peripapillary capillary (RPC) network with optical coherence tomography angiography (OCT-A) in normal human eyes and correlate RPC density with retinal nerve fibre layer thickness (RNFLT) at various distances from the optic nerve head (ONH) edge. Methods Fifty eyes of 50 healthy subjects underwent imaging with RTVue XR-100 Avanti OCT. OCT-A scans of Angio disc (6 9 6 mm) and Angio retina (8 9 8 mm) were combined to create a wide-field montage image of the RPC network. RPC density and RNFLT was calculated at different circle diameter around the ONH, and their correlation was measured. Results In the arcuate region, RPC was detected as far as 8.5 mm from the ONH edge, but not around the perifoveal area within 0.025 ± 0.01 mm2.The mean RPC density (0.1556 ± 0.015) and RNFLT (245.96 ± 5.79) were highest at 1.5 mm from ONH margin, and there was a trend in its decline, in a distance-dependent manner, with the least density at 8.5 mm (all P\0.0001). Highest RPC density was noted in the arcuate fibre region at all the distances. Overall mean RPC density correlated significantly (P\0.0001) with the overall mean RNFLT. Conclusions Wide-field montage OCT-A angiograms can visualize expansion of the RPC network, which is useful in obtaining information about various retinal disorders. The results obtained support the hypothesis that the RPC network could be responsible for RNFL nourishment.

Abstract

Optical Coherence Tomography (OCT) plays an important role in the analysis of retinal diseases such as Age-Related Macular Degeneration (AMD). In this paper, we present a method to construct a normative atlas for macula centric OCT volumes with a mean intensity template (MT) and probabilistic maps for the seven intra-retinal tissue layers. We also propose an AMD classification scheme where the deviation of the local similarity of a test volume with respect to the MT is used to characterize AMD. The probabilistic atlas was used for layer segmentation where we achieved an average dice score of 0.82 across the eight layer boundaries. On the AMD detection task, the classification accuracy and Area under the Receiver Operating Characteristic curve were 98% and 0.996 respectively, on 170 OCT test volumes.

Abstract

Automatic disease detection and classification have been attracting much interest. High performance is critical in adoption of such systems, which generally rely on training with a wide variety of annotated data. Availability of such varied annotated data in medical imaging is very scarce. Synthetic data generation is a promising solution to address this problem. We propose a novel method, based on generative adversarial networks (GAN), to generate images with lesions such that the overall severity level can be controlled. We demonstrate the reliability of the generated synthetic images independently as well as by training a computer aided diagnosis (CAD) system with the generated data. We showcase this approach for heamorrhage detection in retinal images with 4 levels of severity. Quantitative assessment results show that the generated synthetic images are very close to the real data. Haemorrhage detection was found to improve with inclusion of synthetic data in the training set with improvements in sensitivity ranging from 20% to 27% over training with just expert marked data.

Abstract

The level set based deformable models (LDM) are commonly used for medical image segmentation. However, they rely on a handcrafted curve evolution velocity that needs to be adapted for each segmentation task. The Convolutional Neural Networks (CNN) address this issue by learning robust features in a supervised end-to-end manner. However, CNNs employ millions of network parameters, which require a large amount of data during training to prevent over-fitting and increases the memory requirement and computation time during testing. Moreover, since CNNs pose segmentation as a region-based pixel labeling, they cannot explicitly model the high-level dependencies between the points on the object boundary to preserve its overall shape, smoothness or the regional homogeneity within and outside the boundary. We present a Recurrent Neural Network based solution called the RACE-net to address the above issues. RACE-net models a generalized LDM evolving under a constant and mean curvature velocity. At each time-step, the curve evolution velocities are approximated using a feed-forward architecture inspired by the multiscale image pyramid. RACE-net allows the curve evolution velocities to be learned in an end-to-end manner while minimizing the number of network parameters, computation time, and memory requirements. The RACEnet was validated on three different segmentation tasks: optic disc and cup in color fundus images, cell nuclei in histopathological images, and the left atrium in cardiac MRI volumes. Assessment on public datasets was seen to yield high Dice values between 0.87 and 0.97, which illustrates its utility as a generic, off-the-shelf architecture for biomedical segmentation.

Abstract

Feature-based registration has been popular with a variety of features ranging from voxel intensity to Self-Similarity Context (SSC). In this paper, we examine the question of how features learnt using various Deep Learning (DL) frameworks can be used for deformable registration and whether this feature learning is necessary or not. We investigate the use of features learned by different DL methods in the current state-ofthe-art discrete registration framework and analyze its performance on 2 publicly available datasets. We draw insights about the type of DL framework useful for feature learning. We consider the impact, if any, of the complexity of different DL models and brain parcellation methods on the performance of discrete registration. Our results indicate that the registration performance with DL features and SSC are comparable and stable across datasets whereas this does not hold for low level features. This shows that when handcrafted features are designed based on good insights into the problem at hand, they perform better or are comparable to features learnt using deep learning framework.