Keerthi Ram

Brain-wide Maps Reveal Stereotyped Cell-Type-Based Cortical Architecture and Subcortical Sexual Dimorphism

The stereotyped features of neuronal circuits are those most likely to explain the remarkable capacity of the brain to process information and govern behaviors, yet it has not been possible to comprehensively quantify neuronal distributions across animals or genders due to the size and complexity of the mammalian brain. Here we apply our quantitative brain-wide (qBrain) mapping platform to document the stereotyped distributions of mainly inhibitory cell types. We discover an unexpected cortical organizing principle: sensory-motor areas are dominated by output-modulating parvalbumin-positive interneurons, whereas association, including frontal, areas are dominated by input-modulating somatostatin-positive interneurons. Furthermore, we identify local cell type distributions with more cells in the female brain in 10 out of 11 sexually dimorphic subcortical areas, in contrast to the overall larger brains in males. The qBrain resource can be further mined to link stereotyped aspects of neuronal distributions to known and unknown functions of diverse brain regions.

Joint Optic Disc and Cup Segmentation Using Fully Convolutional and Adversarial Networks

Glaucoma is a highly threatening and widespread ocular disease which may lead to permanent loss in vision. One of the important parameters used for Glaucoma screening in the cup-to-disc ratio (CDR), which requires accurate segmentation of optic cup and disc. We explore fully convolutional networks (FCNs) for the task of joint segmentation of optic cup and disc. We propose a novel improved architecture building upon FCNs by using the concept of residual learning. Additionally, we also explore if adversarial training helps in improving the segmentation results. The method does not require any complicated preprocessing techniques for feature enhancement. We learn a mapping between the retinal images and the corresponding segmentation map using fully convolutional and adversarial networks. We perform extensive experiments of various models on a set of 159 images from RIM-ONE database and also do extensive comparison. The proposed method outperforms the state of the art methods on various evaluation metrics for both disc and cup segmentation.

Local characterization of neovascularization and identification of proliferative diabetic retinopathy in retinal fundus images

Neovascularization (NV) is a characteristic of the onset of sight-threatening stage of DR, called proliferative DR (PDR). Identification of PDR requires modeling of these unregulated ill-formed vessels, and other associated signs of PDR. We present an approach that models the micro-pattern of local variations (using texture based analysis) and quantifies structural changes in vessel patterns in localized patches, to arrive at a score of neovascularity. The distribution of patch-level confidence scores is collated into an image-level decision of presence or absence of PDR. Evaluated on a dataset of 779 images combining public data and clinical data from local hospitals, the patch-level neovascularity prediction has a sensitivity of 92.4% at 92.6% specificity. For image-level PDR identification our method is shown to achieve sensitivity of 83.3% at a high specificity operating point of 96.1% specificity, and specificity of 83% at high sensitivity operating point of 92.2% sensitivity. Our approach could have potential application in DR grading where it can localize NVE regions and identify PDR images for immediate intervention.

Computer-assisted grading of diabetic macular edema on retinal color fundus images

Diabetic macular edema (DME) is one of the vision-impairing manifestations of Diabetic Retinopathy (DR). Early detection and treatment of DME can prevent permanent vision loss in people suffering from DR. However, the clinical detection through biomicroscopy is time-consuming. In this paper, a computer-assisted grading method has been proposed to determine the DME severity based on the spatial distribution of exudative lesions around macula. The region around macula is classified into zonal levels and severity of the DME is graded based on the presence of exudative lesions in each zone. The proposed method has been evaluated on diverse public and local databases, and produced the sensitivity of 89.54% for 9.1 false positive per image (FPPI) for exudate detection and 98.8% accuracy for DME grading.

Computer-assisted identification of proliferative diabetic retinopathy in color retinal images

Advanced (proliferative) stage of diabetic retinopathy (DR) is indicated by the growth of thin, fragile and highly unregulated vessels, neovascularization (NV). In order to identify proliferative diabetic retinopathy (PDR), our approach models the micro-pattern of local variations using texture based analysis and quantifies the structural changes in vessel patterns in localized patches, to map them to the confidence score of being neovascular using supervised learning framework. Rule-based criteria on patch-level neovascularity scores in an image is used for the decision of absence or presence of PDR. Evaluated using 3 datasets, our method achieves 96% sensitivity and 92.6% specificity for localizing NV. Image-level identification of PDR achieves high sensitivity of 96.72% at 79.6% specificity and high specificity of 96.50% at 73.22% sensitivity. Our approach could have potential application in DR grading where it can localize NVE regions and identify PDR images for immediate intervention.

A High-throughput Neurohistological Pipeline for Brain-Wide Mesoscale Connectivity Mapping of the Common Marmoset

Understanding the connectivity architecture of entire vertebrate brains is a fundamental but difficult task. MRI based methods offer whole brain coverage, but remain indirect in the approach to connectivity mapping. Recent progress has been made in directly mapping whole-brain connectivity architecture in the mouse at the mesoscopic scale. The basic approach uses tracer injections systematically placed on a grid of locations spanning the brain and computational analysis of the resulting whole brain data sets. Scaling this approach to bigger primate brains poses nontrivial technical challenges. Here we present an integrated neurohistological pipeline as well as a grid-based tracer injection strategy for systematic mesoscale connectivity mapping in the common Marmoset (Callithrix jacchus). Individual brains are sectioned into ∼1700 20µm sections using the tape transfer technique, permitting high quality 3D reconstruction of a series of histochemical stains (Nissl, myelin) interleaved with tracer labelled sections. Combining the resulting 3D volumes, containing informative cytoarchitectonic markers, with in-vivo and ex-vivo MRI, and using an integrated computational pipeline, we are able to overcome the significant individual variation exhibited by Marmosets to obtain routine and high quality maps to a common atlas framework. This will facilitate the systematic assembly of a mesoscale connectivity matrix together with unprecedented 3D reconstructions of brain-wide projection patterns in a primate brain. While component instruments or protocols may be available from previous work, we believe that this is the first detailed systems-level presentation of the methodology required for high-throughput neuroanatomy in a model primate.

High precision automated detection of labeled nuclei in terabyte-scale whole-brain volumetric image data of mouse

There is a need in modern neuroscience for accurate and automated image processing techniques for analyzing the large volume of neuroanatomical data. For e.g., the use of light microscopy to image whole mouse brains in a mesoscopic scale produces individual neuroanatomical data volumes in the TerraByte range. A fundamental task involves the detection and quantification of objects of a given type, e.g. neuronal nuclei or somata, in whole mouse brains. Traditionally this quantification is performed by human visual inspection with high accuracy, that is not scalable. When state-of-the-art CNN and SVM-based methods are used to solve this classification problem, they achieve accuracy levels between 85-92%. However, higher rates of precision and recall, close to that of humans are necessary. In this paper, we describe an unsupervised, iterative algorithm, which provides a high close to human performance for a specific problem of broad interest, i.e. detection of Green Fluorescent Protein labeled nuclei in whole mouse brains. The algorithm judiciously combines classical computer vision (CV) techniques and is focused on the complex problem of decomposing strong overlapped objects (nuclei). Our proposed iterative method uses features detected on ridge lines over distance transformation and an arc based iterative spatial-filling method to solve the problem. We demonstrate our results on two whole mouse brain data sets of Gigabyte resolution and compare it with manual annotation of the brains. Our results show that an aptly designed CV algorithm with classical feature extractors, when tailored to this problem of interest, achieves near-ideal humanlike performance. Quantitative analysis, when compared with the manually annotated ground truth, reveals that our approach performs better on whole mouse brain scans than general purpose machine learning (including deep CNN) methods.There is a need in modern neuroscience for accurate and automated image processing techniques for analyzing the large volume of neuroanatomical imaging data. Even at light microscopic levels, imaging mouse brains produces individual data volumes in the TerraByte range. A fundamental task involves the detection and quantification of objects of a given type, e.g. neuronal nuclei or somata, in brain scan dataset. Traditionally this quantification has been performed by human visual inspection with high accuracy, that is not scalable. When modern automated CNN and SVM-based methods are used to solve this classification problem, they achieve accuracy levels that range between 85 – 92%. However, higher rates of precision and recall that are close to that of human performance are necessary. In this paper, we describe an unsupervised, iterative algorithm, which provides a high performance for a specific problem of detecting Green Fluorescent Protein labeled nuclei in 2D scans of mouse brains. The algorithm judiciously combines classical computer vision techniques and is focused on the complex problem of decomposing strong overlapped objects of interest. Our proposed technique uses feature detection methods on ridge lines over distance transformation of the image and an arc based iterative spatial-filling method to solve the problem. We demonstrate our results on mouse brain dataset of Gigabyte resolution and compare it with manual annotation of the brains. Our results show that an aptly designed CV algorithm with classical feature extractors when tailored to this problem of interest achieves near-ideal human-like performance. Quantitative comparative analysis, using manually annotated ground truth, reveals that our approach performs better on mouse brain scans than general purpose machine learning (including deep CNN) methods.

A Bottom-Up Saliency Estimation Approach for Neonatal Retinal Images

Retinopathy of Prematurity (ROP) is a potentially blinding disease occurring primarily in prematurely born neonates. Staging or classification of ROP into various stages is mainly dependant on the presence of ridge or demarcation line and its distance with respect to optic disc. Thus, computer aided diagnosis of ROP requires method to automatically detect the ridge. To this end, a new bottom up saliency estimation method for neonatal retinal images is proposed. The method consists of first obtaining a depth map of neonatal retinal image via an image restoration scheme based on a physical model. The obtain depth is then converted to a saliency map. Then the image is further processed to even out illumination and contrast variations and the border artifacts. Next, two additional saliency maps are estimated from the processed image using gradient and appearance cues. The obtained saliency maps are then fused by pixel-wise multiplication and addition operators. The obtained final saliency map facilitates the detection of demarcation line and is qualitatively shown to be more suitable for neonatal retinal images compared to the state of the art saliency estimation techniques. This method could thus serve as tool for improved and faster diagnosis. Additionally, we also explore the usefulness of saliency maps for the task of classification of ROP into four stages.