Search

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain behaviors. We propose an architecture called Attentional Bottleneck with the goal of improving transparency. Our key idea is to combine visual attention, which identifies what aspects of the input the model is using, with an information bottleneck that enables the model to only use aspects of the input which are important. This not only provides sparse and interpretable attention maps (e.g. focusing only on specific vehicles in the scene), but it adds this transparency at no cost to model accuracy. In fact, we find improvements in accuracy when applying Attentional Bottleneck to the ChauffeurNet model, whereas we find that the accuracy deteriorates with a traditional visual attention model.

Precision genome engineering, with targeted therapy towards patient-specific mutations is predicted to be the future of personalized medicine. Ophthalmology is in the frontiers of development of targeted therapy since the eye is an accessible organ and has the ease of both delivery as well as monitoring effects of therapy.We reviewed literature using keywords CRISPR, precision medicine, genomic editing, retinal dystrophies, retinitis pigmentosa, Usher syndrome, Stargardt's Disease. Further, we collated data on current clinical trials.There is growing evidence on the role of genomic editing in retinal dystrophies, the various methods used, and stage of development of different therapies have been summarized in this paper.The CRISPR-Cas9 system has revolutionized genome editing, and opened avenues in drug discovery. It is important to understand the role of this system along with its applicability in the field of ophthalmology. In this review article, we briefly describe its methodology, the strategies of employing it for making genetic perturbations, and explore its applications in inherited retinal dystrophies.

Lesions occurring in them are infrequently reported. In this retrospective study, we analyze all types of lesions affecting bones of the hands or feet, including infections and inflammatory conditions, benign and malignant tumors, and tumor like lesions, correlating clinical, pathologic and biopsy findings. Out of 50 lesions included in the study, infections/ inflammatory lesions constituted 46.0%, benign tumors 32.0%, malignant tumors 12.0%, and tumor like lesions 10.0%. Osteomyelitis was the most common lesion in this series, accounting for 44% of the cases. In other study also it is the commonest lesion. Walking barefoot and Diabetes mellitus constitutes a significant predisposing risk factor for osteomyelitis of the foot. Tuberculosis constitutes the major cause of osteomyelitis in India hence higher incidence of tuberculous osteomyelitis in the small bones of the hands or feet as compared to that in the West. Benign tumors were more common than malignant tumors in our series, GCT constituting 43.8% of benign tumors. Chondrosarcoma was the most common malignant tumor. Metastatic bone lesions and hematologic neoplasms were not seen in our study. Bones of the hands and feet are the most common extragnathic sites for GCR. Three such cases with typical histologic features were diagnosed in bones of the hand. It was difficult to differentiate them clinically and radiologically from GCT. This is important in view of the lower recurrence rate in the former compared to the latter. The only other 3 cases of GCR reported during the study period were located in the mandible. In view of overlapping ultrastructural and light microscopic features, as well as similar biologic behavior, aneurysmal bone cyst and giant-cell reparative lesions are thought to represent related responses to intraosseous hemorrhage. Florid reactive periostitis is a reactive process that predominantly involves the bones of the hands or feet, mostly in young women, and a history of minor trauma is seen in less than half of the cases. Similar clinical findings were noted in our patient as well. The importance of this entity lies in the possibility of it being misdiagnosed as a malignant lesion, especially osteosarcoma. Such a lesion was not seen in any other bone in our institution during the study period. Conclusion: Lesions of the bones of the hands or feet are uncommon. Infections/inflammatory lesions are more common in India. Benign tumors were more common than malignant tumors in our series. Giant cell tumor is the commonest neoplastic lesion. . Awareness and correlation of clinical, radiologic, and pathologic features help in making correct diagnoses Keywords: Hand Swelling, Foot swelling, Neoplasia in Hand, Neoplasia in foot

Diabetes mellitus is a metabolic disorder. This review article is planned to The anti-diabetic effect of Withania Coagulans have been successfully used in Ayurvedic and other traditional formulations and found to be efficient and inexpensive as compared to synthetic drugs. It also aims to test and verify the W. coagulans fruits, showed significant inhibition on postprandial rise in hyperglycemia post-sucrose load in normoglycemic rats as well as streptozotocin-induced diabetic rats. which is comparable to the standard antidiabetic drug Glibenclamide for medical care, The present study defines the systematic evaluation and the role of minerals in glycemic potential of aqueous extract of Withania coagulans fruits in order to develop an effective and safe alternative treatment for diabetes mellitus. These studies conducted to determine the antidiabetic effect of Withania coagulans and pancreatic histological features in streptozotocin induced diabetic rat. Results: The study is based on results of lowering in blood glucose levels of normal, sub, mild diabetic rats assessed during fasting blood glucose, glucose tolerance test studies. The dose of 1000mg/kg was identified as the most effective dose, which reduce the blood glucose level maximum by 35.2% at 5 hours in normal rats during blood glucose studies. Glucose tolerance test studies is normal, sub and mild diabetic rats showed the maximum reduction of 16.7, 29.8 and 38.5% at 4hour respectively. Long term study incase of severely diabetic rats showed reduction fasting glucose level respectively after 30 days of treatment. The present study confirming antidiabetic effect of aqueous extract of Withania Coagulans, helps in identifying the role of trace minerals like Mg and Ca responsible for antidiabetic potential of this potent indigenous shrub. Conclusion: The present research has presented comprehensive details of antidiabetic plants used in the treatment of diabetes mellitus. Most of these plant derived medicines. Keywords: Anti-Diabetic effect, Screening & Evaluation, Streptozocin, Glibenclamide, Diabetic rats.

The aim of this study is to design and develop a blockchain-based web app called Health Stack to maintain accurate and complete medical records of patients, to help doctors to fetch previous medical history of the patients, to assist user to find out the disease he or she is suffering from and much more. For medical services, secure data storage is one of major concern for people. This problem can be resolved by developing an app using a blockchain technology having the features of decentralization and verifiability. Development of this app doesn’t involve any kind of dependency on third-party.

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain behaviors. We propose an architecture called Attentional Bottleneck with the goal of improving transparency. Our key idea is to combine visual attention, which identifies what aspects of the input the model is using, with an information bottleneck that enables the model to only use aspects of the input which are important. This not only provides sparse and interpretable attention maps (e.g. focusing only on specific vehicles in the scene), but it adds this transparency at no cost to model accuracy. In fact, we find slight improvements in accuracy when applying Attentional Bottleneck to the ChauffeurNet model, whereas we find that the accuracy deteriorates with a traditional visual attention model.

Objectives: Diffuse axonal injury is one of the major causes of unconsciousness, profound neurologic deficits and persistent vegetative state after head trauma. In recent years, MR imaging has been gaining popularity as an adjunctive imaging method in patients with DAI. Our study aims to assess the relative diagnostic and prognostic capability of various MRI sequences. Patients and Methods: Retrospective observational study done in 1 year duration on 30 DAI patients. Clinical assessment done with GCS at admission and GOS at 6 month.MRI Brain FLAIR, DWI, T2*GRE AND SWI sequences taken. DAI grade were evaluated for different MRI sequences .Prognosis was correlated to total number of lesion/locations and DAI grade of patients. Statistical analysis was done using SPSS Statistical software (ver.20.0.0) and XL-Stat and ANOVA one way test, post hoc test (Turkey test) and Chi square test. Result: We studied 30 male patients,mean age 32.57±8.72 ranges. The commonest mode of injury is RTA-80%, fall-16% followed by assault-3.33%.Out of 30 patients, 17 patients (56.67%) had GCS < =8, 13 patients (43.33%) had GCS between 9 and 12 and no patient had a GCS score between 13 and 15. The mean GCS score was 8.47±1.50.At a 6 month follow up, out of a total of 30 patients, 2 patients (6.66%) expired (GOS-1) , 3 patients (10%) remained in persistent vegetative state (GOS-2), 11 patients (36.67%) and 10 patients (33.33%) were found to be severely (GOS-3) and moderately (GOS-4) disabled respectively and 4 patients (13.33%) showed good recovery (GOS-5). Mean GOS is 3.37+/-1.06. Newer imaging -SWI able to detects lesion better (diagnosis of DAI) as compared to other older sequences like FLAIR,DWI,T2*GRE. But no statistically significant found between total number of lesion/locations to the outcome and also newer imaging do not change the grade of DAI patients. Conclusion: Although advanced imaging in head injury, SWI helps in diagnosing the diffuse axonal injury more efficiently than other imaging sequences, but it is the grade of patients at admission that predicts the outcome best.

To compare the clinical outcomes between sutured transscleral-fixated and intrascleral haptic-fixated posterior chamber intraocular lens (IOL). Dr Rajendra Prasad Centre for Ophthalmic Sciences, All India Institute of Medical Sciences, New Delhi. A comparative case series. Forty eyes of 40 patients were included; 20 in each group. Patients in group 1 underwent sutured transscleral-fixated IOL and those in group 2 underwent intrascleral haptic-fixated IOL augmented by fibrin glue. Parameters evaluated were uncorrected visual acuity (UCVA), best corrected visual acuity (BCVA), intraocular pressure (IOP), central macular thickness (CMT), IOL tilt on ultrasound biomicroscopy (UBM), and pseudophakodonesis on slitlamp and UBM. The most common cause of aphakia was complicated cataract surgery (50%). The mean preoperative UCVA in logarithm of minimum angle of resolution (logMAR) was 1.59±0.24 and 1.63±0.26 in group 1 and 2, respectively (P=0.45). There was significant improvement in UCVA in both groups (P=0.001) at 6 months (group 1: 0.33±0.17; group 2: 0.22±0.10); the improvement being greater in group 2 (P

The original version of this Article contained errors in Fig. 8. In panel a, the labels ‘VEGF’, ‘Notch’, ‘p21’, and ‘P-ERK’ were inadvertently omitted. This has been corrected in the PDF and HTML versions of the Article.

Objective The objective of this study was to review the treatment outcomes of patients with secondary glaucoma in cases of autosomal dominant neovascular inflammatory vitreoretinopathy (ADNIV), a hereditary autoimmune uveitis due to mutations in CAPN5. Patients and methods A retrospective, observational case series was assembled from ADNIV patients with secondary glaucoma. The main outcome measures were intraocular pressure (IOP), visual acuity, use of antiglaucoma medications, ocular surgeries, and adverse outcomes. Perimetry and optic disk optical coherence tomography (OCT) were also analyzed. Results Nine eyes of five ADNIV patients with secondary glaucoma were reviewed. Each received a fluocinolone acetonide (FA) implant for the management of posterior uveitis. Following implantation, no eyes developed neovascular glaucoma. Five eyes (in patients 1, 2, and 5) required Ahmed glaucoma valve surgery for the management of steroid-responsive glaucoma. Patient 2 also developed angle closure with iris bombe and underwent laser peripheral iridotomy. Patient 4 had both hypotony and elevated IOP that required periodic antiglaucoma medication in the FA-implanted eye. Patient 3 did not develop steroid-response glaucoma in either eye. Optic disk examinations were obscured by fibrosis and better assessed with OCT. Conclusion ADNIV patients show combined mechanism secondary glaucoma best assessed by OCT of the optic disk. The FA implants have reduced uveitic and neovascular glaucoma. Nevertheless, IOP management remains complex due to steroid-response glaucoma, angle closure glaucoma, and hypotony.

Purpose: To compare the efficacy of subthreshold micropulse yellow laser (SMYL) and intravitreal aflibercept injection (IAI) combination therapy with IAI monotherapy in the treatment of diabetic macular edema (DME) and to evaluate the number of injections and SMYL sessions required. Methods: This prospective study compared a group of 28 patients treated with a combination of SMYL and IAI with a group of 28 patients treated only with IAI. All patients initially received 3 monthly IAIs, and the monotherapy group was given additional injections as needed. The combination therapy patients additionally received SMYL after the loading phase. The primary outcome measures were the change in the best-corrected visual acuity (BCVA) and central macular thickness (CMT) from baseline to month 12; the secondary outcomes were the mean number of required injections and SMYL sessions. Results: In the monotherapy group, the BCVA improved from 0.38 ± 0.10 to 0.20 ± 0.10 logMAR; in the combination group, BCVA improved from 0.40 ± 0.09 to 0.17 ± 0.06 logMAR at the end of the 12th month. The CMT was reduced from 451.28 ± 44.85 to 328.8 ± 49.69 μm in the monotherapy group and from 466.07 ± 71.79 to 312.0 ± 39.29 μm in the combination group. Improvement of the mean BCVA and reduction of the mean CMT were similar in each group. The combination group required significantly fewer injections (3.21 ± 0.41 vs 5.39 ± 1.54; P < 0.001). By month 12, 75% of patients in the monotherapy group had required additional IAIs when compared with 16% in the combination group (P < 0.001). Conclusion: SMYL combination therapy demonstrated significant visual improvements in patients with DME. In the combination group, the retreatment rate and number of required injections were significantly lower compared with the IAI monotherapy group.

We report an unusual complication of phacoemulsification wherein an entire cataractous lens migrated through a giant retinal tear into the subretinal space. This case was managed successfully with pars plana vitrectomy and perfluorocarbon liquid–assisted phacofragmentation. To our knowledge, only a single case of a subretinal lens after phacoemulsification has been previously reported.

Introduction Even in this modern era of neurosurgery, we could not achieve 0% mortality in operated aneurysmal subarachnoid hemorrhage (SAH) patients. An analysis of factors affecting outcome was never published in detail, and a recent update of guidelines for management of aneurysm SAH noted deficiency in knowledge about this issue. Objective The study aims to assess the effect of various factors on the outcome of operated aneurysmal SAH patients. Methods: The various factors regarding age, sex, associated chronic diseases, clinical condition of patients, surgery interval, and nature of aneurysm were correlated with outcomes of 345 operated aneurismal SAH patients. Statistical analysis was done by chi-square test and logistic regression. Results As per grade, patients' survival is 80.16% for fair grade and 21.65 % for poor grade, which was statistically significant (p 0.05). On comparing with Hunt and Hess (H-H) grade, all the above-mentioned variables showed significantly better survival in fair grade than in poor grade (p

PURPOSE The aim of this study was to evaluate the surgical outcomes of a modified approach in the management of thick submacular hemorrhage in patients with wet age-related macular degeneration. DESIGN This was a retrospective study. METHODS A retrospective chart review was performed on 10 eyes of 10 patients with submacular hemorrhage secondary to wet age-related macular degeneration treated with 23-gauge pars plana vitrectomy, followed by submacular injection of recombinant tissue plasminogen activator (12.5 μg/0.1 mL), bevacizumab (2.5 mg/0.1 mL), and air (0.3 mL). Gas tamponade was given with 20% SF6 and postoperative propped-up positioning. Patients were evaluated for displacement of hemorrhage, preoperative and postoperative best-corrected visual acuity, occurrence of intraoperative and postoperative complications, and recurrence of hemorrhage. All patients were followed up for 6 months. RESULTS Displacement of the submacular bleed was achieved in all cases. Improvement of best-corrected visual acuity was seen in 8 of 10 patients. Rebleed was seen in 2 eyes that were retreated with intravitreal injection of recombinant tissue plasminogen activator, bevacizumab, and 20% SF6 gas. CONCLUSIONS This modified technique aids in the effective displacement of thick submacular hemorrhage with simultaneous treatment of the underlying choroidal neovascular membrane, which halts the disease progression resulting in significant improvement of visual acuity.

Purpose To analyze type 1 neovascular membranes in age-related macular degeneration (AMD) using optical coherence tomography (OCT) angiography, to correlate morphologic characteristics with imaging and clinical criteria, and to analyze structural features of type 1 neovascularization sequentially after anti–vascular endothelial growth factor (VEGF) therapy. Design Prospective interventional case series. Methods Macular OCT angiography images were acquired using the RTVue XR Avanti with AngioVue. Distinct morphologic patterns and quantifiable features of the neovascular membranes were studied on en face projection images at baseline and follow-up. Results Thirty-three eyes of 25 patients were included. In 75% of the eyes, a highly organized vascular complex could be identified. A large main central vessel trunk/feeder vessel could be seen in 72% of these eyes, with vessels radiating in a branching pattern either in all directions from the center of the lesion (“medusa” pattern), or from one side of the lesion (“seafan” pattern). Of the 18 eyes with follow-up OCT angiography, the lesion area and vessel density remained unchanged, even after anti–vascular endothelial growth factor (VEGF) therapy, indicating a more mature longstanding neovascular complex resistant to anti-VEGF therapy. Conclusions OCT angiography provides a unique opportunity to study the morphology of occult type 1 neovascular membranes in AMD and allows precise structural and vascular assessment noninvasively. We identified a large mature neovascular complex in approximately 75% of eyes, typically consisting of a feeder vessel and large branching vessels resistant to anti-VEGF therapy. OCT angiography may better guide evaluation and treatment of neovascular AMD, and may contribute to the development of improved therapies.

The problem of training a classifier from a handful of positive examples, without having to supply class specific negatives is of great practical importance. The proposed approach to solving this problem builds on the idea of training LDA classifiers using only class specific foreground images and a large collection of unlabelled images, as described in [11]. While we adopt the LDA training methodology of [11], we depart from HOG features and work with those extracted from a Convolutional Neural Network (CNN) pre-trained on Image Net (Over feat). We combine Over feat features with the LDA training methodology to derive generative classifiers. When evaluated on a K-way classification problem, these classifiers are almost as good as those trained discriminatively using the same features. Unlike the HOG based approach of [11], our classifiers do not need any post-processing step of calibration, a step that requires positives and negatives. Finally, we show that in an instance retrieval setup, we can employ these generative classifiers to derive a novel query-expansion framework that achieves a significant performance boost by utilizing only the top ranked positive examples from an initial nearest-neighbor list.

We propose a simple yet effective multi-feature fusion approach based on regression models for logo retrieval. Rather than fusing original features, we focus on similarities between pairs of images from multiple features, where only an annotation of similar/dissimilar pairs of images is needed. For each pair of images, a new vector is constructed by concatenating the similarities between the image pair from multiple features. A regression model is fitted on the new set of vectors with similar/dissimilar annotations as labels. Similarities from multiple features between the query and database images can then be converted to a new similarity score using the learned regression model. Initially retrieved database images are then re-ranked using the similarities predicted by the regression model. Logo class information from the training samples can also be included in the training process by learning an ensemble of regression models for individual logo classes. Extensive experiments on public logo datasets Flickrl.ogol Z and Belga Logo demonstrate the effectiveness and superior generalization ability of our approach for fusing various features.

Jalili syndrome (JS) (MIM#217080) is a rare genetic disorder characterized by the comorbid appearance of cone-rod dystrophy (CORD) and amelogenesis imperfecta (AI). JS is an autosomal recessive inherited disorder caused by different mutations, all with a linkage at achromatopsia locus 2 q11 on the metal transporter gene CNNM4. The case report presented here describes JS with distinct phenotypic variations such as situs inversus totalis (SIT) along with additional ophthalmic findings such as keratoconus and ectopia lentis. It is the first case of JS reported from the Indian subcontinent, affecting a male patient of Muslim faith from an area having high fluoride levels in the ground water. A positive history of consanguineous marriage among his family members of past generations was also evident.

We propose a purely geometric correspondence-free approach to urban geo-localization using 3D point-ray features extracted from the Digital Elevation Map of an urban environment. We derive a novel formulation for estimating the camera pose locus using 3D-to-2D correspondence of a single point and a single direction alone. We show how this allows us to compute putative correspondences between building corners in the DEM and the query image by exhaustively combining pairs of point-ray features. Then, we employ the two-point method to estimate both the camera pose and compute correspondences between buildings in the DEM and the query image. Finally, we show that the computed camera poses can be efficiently ranked by a simple skyline projection step using building edges from the DEM. Our experimental evaluation illustrates the promise of a purely geometric approach to the urban geo-localization problem.

Important diagnostic criteria for glaucoma are changes in the 3D structure of the optic disc due to optic nerve damage. We propose an automatic approach for detecting these changes in 3D models reconstructed from fundus images of the same patient taken at different times. For each time session, only two uncalibated fundus images are required. The approach applies a 6-point algorithm to estimate relative camera pose assuming a constant camera focal length. To deal with the instability of 3D reconstruction associated with fundus images, our approach keeps multiple candidate reconstruction solutions for each image pair. The best 3D reconstruction is found by optimizing the 3D registration of all images after an iterative bundle adjustment that tolerates possible structure changes. The 3D structure changes are detected by evaluating the reprojection errors of feature points in image space. We validate the approach by comparing the diagnosis results with manual grading by human experts on a fundus image dataset.

This paper presents a novel method to recover 3D structure of the optic disc in the retina from two uncalibrated fundus images. Retinal images are commonly uncalibrated when acquired clinically, creating rectification challenges as well as significant radiometric and blur differences within the stereo pair. By exploiting structural peculiarities of the retina, we modified the Graph Cuts computational stereo method (one of current state-of-the-art methods) to yield a high quality algorithm for fundus stereo reconstruction. Extensive qualitative and quantitative experimental evaluation (where OCT scans are used as 3D ground truth) on our and publicly available datasets shows the superiority of the proposed method in comparison to other alternatives.

We address the problem of matching images with disparate appearance arising from factors like dramatic illumination (day vs. night), age (historic vs. new) and rendering style differences. The lack of local intensity or gradient patterns in these images makes the application of pixel-level descriptors like SIFT infeasible. We propose a novel formulation for detecting and matching persistent features between such images by analyzing the eigen-spectrum of the joint image graph constructed from all the pixels in the two images. We show experimental results of our approach on a public dataset of challenging image pairs and demonstrate significant performance improvements over state-of-the-art.

Despite recent advances, automatic blood vessel extraction from low quality retina images remains difficult. We propose an interactive approach that enables a user to efficiently obtain near perfect vessel segmentation with a few mouse clicks. Given two seed points, the approach seeks an optimal path between them by minimizing a cost function. In contrast to the Live-Vessel approach, the graph in our approach is based on the curve fragments generated with vessel tracing instead of individual pixels. This enables our approach to overcome the shortcut problem in extracting tortuous vessels and the problem of vessel interference in extracting neighboring vessels in minimal-cost path techniques, resulting in less user interaction for extracting thin and tortuous vessels from low contrast images. It also makes the approach much faster.

Matching street-level images to a database of airborne images is hard because of extreme viewpoint and illumination differences. Color/gradient distributions or local descriptors fail to match forcing us to rely on the structure of self-similarity of patterns on facades. We propose to capture this structure with a novel "scale-selective self-similarity" (S4) descriptor which is computed at each point on the facade at its inherent scale. To achieve this, we introduce a new method for scale selection which enables the extraction and segmentation of facades as well. Matching is done with a Bayesian classification of the street-view query S4 descriptors given all labeled descriptors in the bird's-eye-view database. We show experimental results on retrieval accuracy on a challenging set of publicly available imagery and compare with standard SIFT-based techniques.

We propose an adaptive rendering approach for large-scale skyline characterization and matching with applications to automated geo-tagging of photos and images. Given an image, our system automatically extracts the skyline and then matches it to a database of reference skylines extracted from rendered images using digital elevation data (DEM). The sampling density of these rendering locations determines both the accuracy and the speed of skyline matching. The proposed approach successfully combines global planning and local greedy search strategies to select new rendering locations incrementally. We report quantitative and qualitative results from synthesized and real experiments, where we achieve a computational speedup of around 4X.

We study the feasibility of solving the challenging problem of geolocalizing ground level images in urban areas with respect to a database of images captured from the air such as satellite and oblique aerial images. We observe that comprehensive aerial image databases are widely available while complete coverage of urban areas from the ground is at best spotty. As a result, localization of ground level imagery with respect to aerial collections is a technically important and practically significant problem. We exploit two key insights: (1) satellite image to oblique aerial image correspondences are used to extract building facades, and (2) building facades are matched between oblique aerial and ground images for geo-localization. Key contributions include: (1) A novel method for extracting building facades using building outlines; (2) Correspondence of building facades between oblique aerial and ground images without direct matching; and (3) Position and orientation estimation of ground images. We show results of ground image localization in a dense urban area.

Analyzing change in the 3D structure of the optic disc over time has long been recognized as central to the diagnosis of glaucoma but has been inadequately addressed by computer vision methods. Currently, clinicians examine stereo pairs from different time instants for interval changes indicative of glaucoma. Due to the clinical procedures in capturing optic disc images, these stereo pairs are usually completely uncalibrated - the camera intrinsics and extrinsics are unknown. Clinicians have to account for these unknown factors and hence their diagnoses of optic disc stability or change are subjective. Changes in the 3D structure of the optic disc are typically accompanied by changes in the 3D structure of blood vessels in that region. Therefore, change in the 3D structure of blood vessels can be used for glaucoma diagnosis. In this paper, we introduce a projective geometry based approach that reconstructs and aligns 3D blood vessel networks given two stereo pairs of optic disc images. We demonstrate that this alignment can identify regions where the vessel structure has changed. Since calibration is unavailable, the 3D structures and the alignment have a projective ambiguity, and hence, we cannot use an absolute threshold on the alignment error to automatically identify change. We have therefore developed an interactive tool that highlights regions with the largest alignment errors. This tool demonstrates the utility of our approach and also can guide clinical observers to optic disc regions where they should look for changes. We believe that our approach can serve as a platform to develop much needed novel tools for glaucoma diagnosis.

We present a novel LIDAR streaming architecture for real-time, on-board processing using unmanned robots. We propose a two-level 3D data structure that allows pipelined and streaming processing of the 3D data as it arrives from a moving robot: (i) at the coarse level, the incoming 3D scans are stored in memory in a dense 3D voxel grid with a relatively large voxel size - this ensures buffering of the most recent data and the availability of sufficient 3D measurements within a specific processing volume at the next level; (ii) at the fine level, we employ a data chunking mechanism guided by the movement of the robot and a rolling dense 3D voxel grid for processing the data in the immediate vicinity of the robot, which enables reuse of previously computed features. The architecture proposed requires a very small memory footprint, minimal data copying, and allows a fast spatial access for 3D data, even at the finest resolutions. We illustrate the proposed streaming architecture on a real-time 3D structure characterization task for detecting doors and stairs in indoor environments and show qualitative results demonstrating the effectiveness of our approach.

Fast-dissolving drug delivery systems have been developed as an alternative to conventional dosage form as an oral means of drug delivery in case of chronic conditions. Now a day's fast dissolving films are preferred over conventional tablets and capsules for masking the taste of bitter drugs to increase the patient compliance. Fast dissolving films consist of a very thin oral strip which dissolves in less than one minute when placed on the tongue. Dissolvable oral thin films are in the market since past few years in the form of breath strips and are widely accepted by consumers for delivering vitamins, vaccines and other drug products. The various manufacturing techniques for the preparation of films have also been detailed in the review. The present review details most of the patents on such fast dissolving films in recent years. A brief study has been made on various parameters which are used to evaluate such films. In case of chronic disorders these fast dissolving films are better for delivering drugs and obtaining faster therapeutic blood levels and superior in comparison to other oral conventional dosage forms.

Localizing blood vessels in eye images is a crucial step in the automated and objective diagnosis of eye diseases. Most previous research has focused on extracting the centerlines of vessels in large field of view images. However, for diagnosing diseases of the optic disk region, like glaucoma, small field of view images have to be analyzed. One needs to identify not only the centerlines, but also vessel widths, which vary widely in these images. We present an automatic technique for localizing vessels in small field of view images using multi-scale matched filters. We also estimate local vessel properties - width and orientation - along the length of each vessel. Furthermore, we explicitly account for highlights on thick vessels - central reflexes - which are ignored in many previous works. Qualitative and quantitative results demonstrate the efficacy of our method - e.g. vessel centers are localized with RMS and median errors of 2.11 and 1 pixels, respectively in 700×700 images.

We present a real-time pedestrian detection system based on structure and appearance classification. We discuss several novel ideas that contribute to having low-false alarms and high detection rates, while at the same time achieving computational efficiency: (i) At the front end of our system we employ stereo to detect pedestrians in 3D range maps using template matching with a representative 3D shape model, and to classify other background objects in the scene such as buildings, trees and poles. The structure classification efficiently labels substantial amount of non-relevant image regions and guides the further computationally expensive process to focus on relatively small image parts; (ii)We improve the appearance-based classifiers based on HoG descriptors by performing template matching with 2D human shape contour fragments that results in improved localization and accuracy; (iii) We build a suite of classifiers tuned to specific distance ranges for optimized system performance. Our method is evaluated on publicly available datasets and is shown to match or exceed the performance of leading pedestrian detectors in terms of accuracy as well as achieving real-time computation (10 Hz), which makes it adequate for in-vehicle navigation platform.

We present an on-the-move LIDAR-based object detection system for autonomous and semi-autonomous unmanned vehicle systems. In this paper we make several contributions: (i) we describe an algorithm for real-time detection of objects such as doors and stairs in indoor environments; (ii) we describe efficient data structures and algorithms for processing 3D point clouds acquired by laser scanners in a streaming manner, which minimize the memory copying and access. We show qualitative results demonstrating the effectiveness of our approach on runs in an indoor office environment.

We present a real-time pedestrian detection system which uses cues derived from structure and appearance classification We discuss several novel ideas to achieve computational efficien y while improving on both detection and false-alarm rates: (i) At the front end of our system we employ stereo to detect pedestrians in 3D range maps, and to classify surrounding structure such as buildings, trees, poles etc. in the scene. The structure classificatio efficientl labels substantial amount of non-relevant image regions and guides the further computationally expensive process to focus on relatively small image parts; (ii) We improve the appearance-based classifier based on HoG descriptors by performing template matching with 2D human shape contour fragments that results in improved localization and accuracy; (iii) We train individual classifier at several depth ranges that allow us to account for appearance and 2D shape changes at variable distances in front of the camera. Our method is evaluated on publicly available datasets and is shown to match or exceed the performance of leading pedestrian detectors in terms of accuracy as well as achieving real-time computation (10 Hz), which makes it adequate for deployment in fiel robots and other navigation platforms.

We propose a principled statistical approach for using 3D information and scene context to reduce the number of false positives in stereo based pedestrian detection. Current pedestrian detection algorithms have focused on improving the discriminability of 2D features that capture the pedestrian appearance, and on using various classifier architectures. However, there has been less focus on exploiting the geometry and spatial context in the scene to improve pedestrian detection performance. We make several contributions: (i) we define a new 3D feature, called a Vertical Support Histogram, from dense stereo range maps to locally characterize 3D structure; (ii) we estimate the likelihoods of these 3D features using kernel density estimation, and use them within a Markov Random Field (MRF) to enforce spatial constraints between the features, and to obtain the Maximum A-Posteriori (MAP) scene labeling; (iii) we employ the MAP scene labelings to reduce the number of candidate windows that are tested by a standard, state-of-the-art pedestrian appearance classifier. We evaluate our algorithm on a very challenging, publicly available stereo dataset and compare the performance with state-of-the-art methods.

We present a new multi-stage algorithm for car and truck detection from a moving vehicle. The algorithm performs a search for pertinent features in three dimensions, guided by a ground plane and lane boundary estimation sub-system, and assembles these features into vehicle hypotheses. A number of classifiers are applied to the hypotheses in order to remove false detections. Quantitative analysis on real-world test data show a detection rate of 99.4% and a false positive rate of 1.77%; a result that compares favourably with other systems in the literature.

This paper addresses the frame-to-frame data association and state estimation problems in localization of a pedestrian relative to a moving vehicle from a far infra-red video sequence. In a novel application of the hierarchical model-based motion estimation framework, we are able to solve the frame-to-frame data association problem as well as estimate a sub-pixel accurate height ratio for a pedestrian in two frames. To estimate the position and velocity of a pedestrian, instead of using a constant pedestrian height model, we propose a novel approach of using the interacting multiple-hypothesis-mode/height filtering algorithm. We present a method to calculate the probability of each mode from the estimated and measured pedestrian height ratios in images. These mode probabilities are then used to accurately estimate the pedestrian location by combining the mode based estimations. We demonstrate the effectiveness of our approach comparing it to a constant height model based approach on several IR sequences.

This paper addresses the frame-to-frame data association and state estimation problems in localization of a pedestrian relative to a moving vehicle from a monocular far infra-red video sequence. Using a novel application of the hierarchical model-based motion estimation framework, we are able to use the image appearance information to solve the frame-to-frame data association problem and estimate a sub-pixel accurate height ratio for a pedestrian in two frames. Then, to localize the pedestrian, we propose a novel approach of using the pedestrian height ratio estimates to guide an interacting multiple-hypothesis-mode/height filtering algorithm instead of using a constant pedestrian height model. Experiments on several IR sequences demonstrate that this approach achieves results comparable to those from a known pedestrian height thus avoiding errors from a constant height model based approach.

We describe a low-cost vision-based sensing and positioning system that enables intelligent vehicles of the future to autonomously drive in an urban environment with traffic. The system was built by integrating Sarnoff's algorithms for driver awareness and vehicle safety with commercial off-the-shelf hardware on a robot vehicle. We implemented a modular and parallelized software architecture that allowed us to achieve an overall sensor update rate of 12 Hz with multiple high resolution HD cameras without sacrificing robustness and infield field performance. The system was field tested on the team autonomous solutions vehicle, one of the top twenty teams in the 2007 DARPA Urban Challenge competition. In addition to enabling autonomy, our low-cost perception system has an intermediate advantage of providing driver awareness for convenience functions such as adaptive cruise control, lane departure sensing and forward and side-collision warning.

Development of a practical stereo vision sensor for real-world applications must account for the variability of high-volume production processes and the impact of unknown environmental conditions during its operation. One critical factor of stereo depth estimation performance is the relative alignment of the stereo camera pair. While imperfectly aligned stereo cameras may be rectified in the image domain, there are some errors introduced by both the calibration recovery and image rectification processes. Finally, additional uncalibrated misalignments, for example due to thermal or mechanical deformation in a harsh automotive environment, may occur which will further deteriorate stereo depth estimation. This paper describes an experimental framework for determining these limits using image processing algorithms, operating on graphically synthesized imagery, with performance envelope validation on real stereo image data.

Genetic regulatory networks (GRNs) control gene expression and are responsible for establishing the regular cellular patterns that constitute an organism. This paper introduces a model of biological development that generates cellular patterns via chemical interactions. GRNs for protein expression are generated and evaluated for their effectiveness in constructing 2D patterns of cells such as borders, patches, and mosaics. Three types of searches were performed: (a) a Monte Carlo search of the GRN space using a utility function based on spatial interestingness; (b) a hill climbing search to identify GRNs that solve specific pattern problems; (c) a search for combinatorial codes that solve difficult target patterns by running multiple disjoint GRNs in parallel. We show that simple biologically realistic GRNs can construct many complex cellular patterns. Our model provides an avenue to explore the evolution of complex GRNs that drive development.

Glaucoma diagnosis, management, and research require complex assessments of the optic disc. Over many decades, the gold standard of optic disc evaluation in glaucoma has been the qualitative evaluation of stereo photographic images of the optic disc, most typically as 35-mm slides or other film-based media. More recently, automated optic disc analyzers have been introduced that use either laser technologies or polarized light to image the optic disc and/or the retinal nerve fiber layer. Studies with these instruments infrequently compare them directly to stereo photographs, and available reports generally find their diagnostic precision comparable to stereo photographs.1–5 So far, the qualitative evaluation of stereo optic disc images by experienced observers remains the reference standard for optic disc evaluation in glaucoma6–8 despite the subjectivity and variability inherent in this conventional approach.9,10 As examples, contemporary clinical glaucoma trials, such as the Ocular Hypertension Treatment Study (OHTS),11,12 the Low-Pressure Glaucoma Treatment Study (LoGTS)13 and the European Glaucoma Prevention Study (EGPS),14,15 used human observers to grade conventional stereo photos to evaluate the optic disc. We are adapting modern computer vision methods to optic disc diagnosis in glaucoma but were concerned with the limited number of published comparisons of digital and film imaging formats for optic disc photographs, as ophthalmic photography has migrated from film-based to digital images. The few published reports mostly have assessed the utility of digital optic nerve images for quantitative parameters long used in glaucoma evaluation, such as the cup-to-disc ratio.16–21 In contrast, in a considerably more extensive body of literature, the utility of digital images has been compared to that of film images in retinal diseases such as diabetic retinopathy22–26 or macular degeneration.27–29 To address the suitability of digital stereo optic disc images as a platform for developing novel computerized approaches for glaucoma diagnosis, we assessed the quality and definition of optic disc features by directly comparing optic disc images obtained from individual subjects and displayed in different formats. We sought to avoid the well-known inaccuracies in trying to assign quantitative estimates such as the cup-to-disc ratio.9,10 Specifically, we obtained stereo color optic disc images contemporaneously in both digital and 35-mm slide film formats in subjects with a range of optic disc cup sizes and included both scanned and grayscale images in the analysis.