Our Research

Electrical Stimulation for Haptic Feedback in VR

EEG-Guided Electrical Stimulation for Immersive Virtual Reality is a project funded by NSF. In collaboration with researchers at UPitt, we are working towards developing sensory models for fingertips when stimulated with electrical current waves spatially and temporally, in order to eventually enable realistic haptic feedback for virtual and mixed reality applications where feeling of texture are essential for enhanced immersive experiences.

Securing GNSS-based Infrastructures

This project develops novel anti-jamming techniques for Global Navigation Satellite Systems (GNSS) that are effective, yet computationally affordable. GNSS is ubiquitous in civilian, security and defense applications, causing a growing dependence on such technology for position and timing purposes, particularly in critical infrastructures. The threat of a potential disruption of GNSS is real and can lead to catastrophic consequences. This project studies methods to secure GNSS receivers from jamming interference, and doing so within size, weight, and power (SWAP) requirements. Existing solutions are either bulky and not cost-effective, such as those based on antenna array technology, or specifically adapted to an interference type. In addition, most of these solutions require the detection and classification of the interference before mitigating its effects, which constitutes a single point of error in the process. This project will investigate GNSS receivers that are resilient to interference without requiring detection and classification, by leveraging robust statistics to design methods that require few modifications with respect to state-of-the-art receiver architectures, keeping SWAP requirements comparable to those from standard GNSS receivers. The findings will be implemented and validated on an end-to-end GNSS software-defined radio receiver, successfully transitioning research into practice. Educational activities are closely integrated with this research agenda, including a course developed by the principal investigator and outreach activities.

This research advances knowledge of how robust statistics can be leveraged to design cost-effective and efficient mitigation techniques for anti-jamming GNSS. The main premise of the project is that most interference sources have a sparse representation, on which they can be seen as outliers to the nominal signal model. Tools from robust statistics are then used to discard those outliers in a sound manner, identifying and substituting specific critical operations in GNSS processing. This approach avoids the need for detecting and estimating interference, processes which can cause errors. The project envisions a lightweight, yet robust, GNSS receiver that can be easily adopted in substitution of current GNSS receivers that are supporting operation of critical infrastructures. It will enable reliable and precise anti-jamming technology with drastic SWAP and cost improvements. Particularly, the project will provide a GNSS receiver solution that can cope with common jamming interference. The development of such receiver enhancements, along with their validation in a software receiver, will allow for large-scale deployments of GNSS receivers that are more resilient and reliable.

Principal Investigator: Pau Closas (Northeastern University)

Research Group: Information Processing Lab

Funding: National Science Foundation (CNS-1815349)

Abstract Source: NSF

Skin Cancer Diagnosis

Melanoma is diagnosed in approximately 124,000 people and is responsible for about 10,000 deaths every year, in the USA. Dermatologists rely on visual and dermatoscopic examination to discriminate benign melanocytic lesions from malignant, resulting in high and highly variable benign-to-malignant biopsy ratios from 8:1 to 47:1, and millions of unnecessary biopsies of benign lesions. Reflectance confocal microscopy (RCM) imaging has been proven for noninvasively guiding diagnosis of melanoma in several large clinical studies. RCM imaging at the dermal-epidermal junction (DEJ) provides sensitivity of 92-88% and specificity of 71-84%. The specificity is 2 times superior to that of dermatoscopy. RCM imaging at the DEJ is now being implemented to rule out malignancy, reduce biopsy and guide treatment. However, this is currently at only a few sites, where there are highly trained experts who can ensure that imaging is appropriately performed and images are read correctly. These experts are a small international cohort of “early adopter” clinicians, who have worked with RCM technology during the past decade and have become highly skilled readers. For novice (non-expert) clinicians in the wider cohort who are keen to adopt RCM, learning to read images is challenging and requires substantial effort and time. Two major technical barriers underlie the dramatic variability in diagnostic accuracy among novice clinicians. Together they limit utility, reproducibility and wider adoption of RCM. The first is user dependent subjective variability in depths near the DEJ at which images are acquired, and the second is variability in interpretation of images. We propose to address these barriers with computational “multi-faceted” classification modeling (innovation), image analysis and machine learning algorithms. Our specific aims are: (1) to develop and evaluate algorithms for both dermatoscopic images and RCM depth-stacks, to enable automated standardized and consistent acquisition of RCM mosaics at the DEJ in melanocytic lesions; (2) to develop and evaluate algorithms to discriminate patterns of cellular morphology at the DEJ into two classes, benign lesions versus malignant (dysplastic lesions and melanoma); and (3) to test our algorithms on patients for acquisition of RCM mosaics and classification into those two groups, with statistical validation against pathology, with statistical validation against pathology. Preliminary studies show that our algorithms can delineate the DEJ with accuracy in the range ~3-13 μm in strongly pigmented dark skin and ~5-20 μm in lightly pigmented fair skin, and can detect cellular morphologic patterns with sensitivity in the range 67-80% and specificity 78-99%. Melanocytic lesions can be distinguished from the surrounding normal skin at the DEJ with 80% classification accuracy. Our success will produce standardized imaging and analysis approaches, to advance RCM for noninvasive detection of melanoma. Furthermore, these approaches can be useful for non-melanoma skin cancers, cutaneous lymphoma and other skin disorders (wider impact).

ASSIST/iROP

Retinopathy of prematurity (ROP) is a leading cause of childhood visual loss worldwide, and the social burdens of infancy-acquired blindness are enormous. Early diagnosis is critically important for successful treatment, and can prevent most cases of blindness. However, lack of access to expert medical diagnosis and care, especially in rural areas, remains a growing healthcare challenge. In addition, clinical expertise in ROP is lacking, and medical professionals are struggling to meet the increasing need for ROP care. As point-of-care technologies for diagnosis and intervention are rapidly expanding, the potential ability to assess ROP severity from any location with an internet connection and a camera, even without immediate ophthalmologic consultation available, could significantly improve delivery of ROP care by identifying infants who are in most urgent need for referral and treatment. This would dramatically reduce the incidence of blindness without a proportionate increase in the need for human resources, which take many years to develop.

Project Website: i-rop.github.io
Principal Investigators: Jayashree-Kalpathy Cramer (HMS-MGH), Stratis Ioannidis (DNAL), Jennifer Dy (ML), Deniz Erdogmus (CSL), Michael Chiang (OHSU), Kemal Sonmez (OHSU), J. Peter Campbell (OHSU), R.V. Paul Chan (UIC).
Funding: National Institutes of Health (R01EY019474, P30EY10572), National Science Foundation (SCH-1622542; SCH-1622536; SCH-1622679).