SPShrinivas Pundlik

Shrinivas Pundlik

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shrinivas Pundlik has a total of 84 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Association of Reticular Pseudodrusen Burden and Dark Adaptation in Nonadvanced Age-Related Macular Degeneration

    by Ariel Yuhan Ong, Robbert R. Struvyen, David A. Merle, Kevin Mendez, Helia Ashourizadeh, Souvick Mukherjee, Afonso Lima-Cabrita, Jooyoung Chang, Dylan Wu, Shrinivas Pundlik, et al.

  • Open Access

    Naturalistic driving data extraction and processing for studying driver head scanning behavior at intersections

    by Shrinivas Pundlik, Seonggyu Choe, Patrick Baker, Chen-Yuan Lee, Naser Al-Madi, Alex R. Bowers, Gang Luo

    Naturalistic driving (ND) studies offer key insights about real-world driver behavior compared to lab and on-road studies along a fixed course. We describe an ND data processing pipeline for characterizing the scene and driver behavior at intersections. The in-car recording system recorded the vehicle's speed, location, and videos of the cabin and the front scene. Intersection locations were approximately marked from the drive log, and corresponding cabin and scene videos were clipped for ± 100 m segments around the marked intersection locations. Scene videos were processed to extract intersection scene characteristics including the type of signage, vehicle maneuver, traffic density, and to precisely estimate the vehicle's entry and exit from an intersection. Driver head pose in cabin videos was estimated using a custom-developed AI model for wide angle head turns. Evaluation involved 365 manually-annotated intersection instances from 6 vehicles driven in 3 US states. Signage and maneuvers were correctly detected in 99% and 95% of cases, respectively. Median[IQR] intersection entry error was 1.1[0.3-4.2] meters, 0.23 [0.07-0.63] seconds; overlap between estimated and ground truth intersection bounds was 0.88[0.8-0.94]. There was strong positive correlation between estimated and annotated traffic density (R = 0.73, p < 0.001). Head pose estimation over a range of ± 135° had a mean absolute error of 6.75 ± 5.0° and an RMSE of 8.4°. Our approach can potentially allow automated processing of a vast amount of ND data while enabling the study of specific driver behaviors that were previously not achieved.


  • Open Access

    Quantitative Assessment of Strabismus Using Cloud AI Computing: Validation Study

    by Junxian He, Jiawei Zhang, Zheng Wang, Shrinivas Pundlik, Rui Liu, Gang Luo

    Background: Strabismus measurement is essential in vision assessment and screening. It typically requires skilled clinicians or specialized equipment. Photographic strabismus measurement methods have value in terms of accessibility and convenience of use. Objective: This study aimed to evaluate Eyeturn Cloud, a cloud-based artificial intelligence (AI) system for measuring strabismus angles based on eye images captured with smartphone cameras under cover test conditions. Methods: The Eyeturn Cloud web app uses AI models to recognize eyes, eye lid, and iris, and then to segment iris precisely. It then computes strabismus based on ellipse fitting of the iris boundary and corneal reflection. The system was evaluated in patients (without glasses) with manifest strabismus and control participants. Clinicians measured eye deviations using the prism alternate cover test and also captured pictures of their eyes under alternate cover and unilateral cover conditions. The pictures were processed by Eyeturn Cloud. Results: In total, 79 (mean age 11.9, SD 6.3 years; esotropia: n=15, exotropia: n=55, orthotropia: n=9) participants were enrolled; of which, data were available for 71 participants (8/79, 10.1% processing failure). The range of prism alternate cover test strabismus magnitude was from 78 base in to 78 base out prism diopters (PDs). A strong correlation was found between Eyeturn Cloud and clinical measurements (R2=0.95; slope=0.91; P<.001). Bland-Altman analysis revealed that 95% limits of agreement between the 2 measurements were –20.2 to 14.6 PD. A repeatability test with 15 participants (4 photos each) found a 1.53 PD SD. Conclusions: The cloud AI web app can compute strabismus angles reliably under alternate and unilateral cover conditions in clinical settings, and its potential for use in telehealth settings needs further evaluation.


  • Open Access

    Quantitative Assessment of Strabismus Using Cloud AI Computing: Validation Study (Preprint)

    by Junxian He, Jiawei Zhang, Zheng Wang, Shrinivas Pundlik, Rui Liu, Gang Luo

    BACKGROUND Strabismus measurement is essential in vision assessment and screening. It typically requires skilled clinicians or specialized equipment. Photographic strabismus measurement methods have value in terms of accessibility and convenience of use. OBJECTIVE This study aimed to evaluate Eyeturn Cloud, a cloud-based artificial intelligence (AI) system for measuring strabismus angles based on eye images captured with smartphone cameras under cover test conditions. METHODS The Eyeturn Cloud web app uses AI models to recognize eyes, eye lid, and iris, and then to segment iris precisely. It then computes strabismus based on ellipse fitting of the iris boundary and corneal reflection. The system was evaluated in patients (without glasses) with manifest strabismus and control participants. Clinicians measured eye deviations using the prism alternate cover test and also captured pictures of their eyes under alternate cover and unilateral cover conditions. The pictures were processed by Eyeturn Cloud. RESULTS In total, 79 (mean age 11.9, SD 6.3 years; esotropia: n=15, exotropia: n=55, orthotropia: n=9) participants were enrolled; of which, data were available for 71 participants (8/79, 10.1% processing failure). The range of prism alternate cover test strabismus magnitude was from 78 base in to 78 base out prism diopters (PDs). A strong correlation was found between Eyeturn Cloud and clinical measurements (R2=0.95; slope=0.91; P<.001). Bland-Altman analysis revealed that 95% limits of agreement between the 2 measurements were –20.2 to 14.6 PD. A repeatability test with 15 participants (4 photos each) found a 1.53 PD SD. CONCLUSIONS The cloud AI web app can compute strabismus angles reliably under alternate and unilateral cover conditions in clinical settings, and its potential for use in telehealth settings needs further evaluation.

  • JoVE Video Dataset

    by Gang Luo, Chen-Yuan Lee, Zheng Wang, Preana Shivshanker, Yan Jiang, Shrinivas Pundlik

    To improve access to vision care and to enable mass vision screening, a smartphone app has been developed to measure refractive errors. Without needing any external attachment, the app running on a standalone phone can be used by lay personnel to measure subjective refraction. Its validity has been pilot-tested in clinical settings and underserved communities. The app estimates the refractive error by measuring the distances of far points for discerning visual stimuli. Spherical equivalent refraction and astigmatism can be measured using Tumbling E letters and grating patterns, respectively. The purpose of this paper is to describe the measurement protocols for performing subjective refraction using the app. Experimental results with 34 subjects (30 eyes for spherical equivalent and 38 eyes for astigmatism assessment) are presented. Measurement with the app was compared with standard clinical methods. The average absolute error of spherical equivalent refraction was 0.63D, and the average absolute error of astigmatism measurement was 0.28D. In addition, 22 subjects were enrolled to evaluate inter-pupillary distance (IPD) measurement with the app. The average absolute error in IPD measurement with the app was 1.2 mm. The protocol for measuring IPD with the app is also described.

  • Subjective Refraction Test Using a Smartphone for Vision Screening

    by Gang Luo, Chen-Yuan Lee, Zheng Wang, Preana Shivshanker, Yan Jiang, Shrinivas Pundlik

    To improve access to vision care and to enable mass vision screening, a smartphone app has been developed to measure refractive errors. Without needing any external attachment, the app running on a standalone phone can be used by lay personnel to measure subjective refraction. Its validity has been pilot-tested in clinical settings and underserved communities. The app estimates the refractive error by measuring the distances of far points for discerning visual stimuli. Spherical equivalent refraction and astigmatism can be measured using Tumbling E letters and grating patterns, respectively. The purpose of this paper is to describe the measurement protocols for performing subjective refraction using the app. Experimental results with 34 subjects (30 eyes for spherical equivalent and 38 eyes for astigmatism assessment) are presented. Measurement with the app was compared with standard clinical methods. The average absolute error of spherical equivalent refraction was 0.63D, and the average absolute error of astigmatism measurement was 0.28D. In addition, 22 subjects were enrolled to evaluate inter-pupillary distance (IPD) measurement with the app. The average absolute error in IPD measurement with the app was 1.2 mm. The protocol for measuring IPD with the app is also described.


  • Open Access

    Gaze Scanning on Mid-Block Sidewalks by Pedestrians With Homonymous Hemianopia With or Without Spatial Neglect

    by Shrinivas Pundlik, Matteo Tomasi, Kevin E. Houston, Ayush Kumar, Prerana Shivshanker, Alex R. Bowers, Eli Peli, Gang Luo

    Purpose: The purpose of this study was to investigate gaze-scanning by pedestrians with homonymous hemianopia (HH) when walking on mid-block sidewalks. Methods: Pedestrians with right homonymous hemianopia (RHH), and left homonymous hemianopia (LHH) without and with left spatial neglect (LHSN) walked on city streets wearing a gaze-tracking system. Gaze points were obtained by combining head movement and eye-in-head movement. Mixed-effects regression models were used to compare horizontal gaze scan magnitudes and rates between the side of the hemi-field loss (BlindSide) and the seeing side (SeeingSide), among the three subject groups, and between mid-block walking and street crossing segments. Results: A total of 7021 gaze scans were obtained from 341 minutes of mid-block walking videos by 19 participants (6 with LHH, 7 with RHH, and 6 with LHSN). The average gaze magnitude and scanning rate in mid-block segments were significantly higher towards the BlindSide than the SeeingSide in LHH (magnitude larger by 1.9° (degrees), P = 0.006; scan rate higher by 4.2 scans/minute, P < 0.001) and RHH subjects (magnitude larger by 3.3°, P < 0.001; scan rate higher by 3.2 scans/minute, P = 0.002), but they were not significantly different in LHSN subjects. The scanning rate, in terms of scans/minute (mean, 95% confidence interval [CI]) was significantly lower in LHSN subjects (mean = 6.9, 95% CI = 5.6–8.7) than LHH (mean = 10.2, 95% CI = 8.0–13.1; P = 0.03) and RHH (mean = 11.1, 95% CI = 9.0–13.7; P = 0.007) subjects. Compared to street-crossings, the scan rate during the mid-block segments was lower by 3.5 scans/minute (P < 0.001) and the gaze magnitude was smaller by 3.8° (P < 0.001) over the 3 groups. Conclusions: Evidence of compensatory scanning suggests a proactive, top-down mechanism driving gaze in HH. The presence of spatial neglect (SN) appeared to negatively impact the top-down process.


  • Investigation of Population-Based Fall Risk in Eye Diseases

    by Shrinivas Pundlik, Gang Luo

    It is well-known that older adults are at higher risk of falls and resulting injuries. Falls and their aftermath are one of the major public health concerns in aging societies. The aging-related risk of falls and fractures can be attributed to factors such as deteriorating muscle strength, balance, and vision.1,2 One way to further break down the vision factor can be by age-related eye diseases such as cataract, age-related macular degeneration (AMD), and glaucoma. Given their rapidly increasing prevalence, understanding the risk of falls by diagnosis of these eye diseases has clinical and societal importance. However, population-based risk assessment for falls and injuries in adults with these eye diseases has been lacking, as previous studies (cross-sectional or cohort) were either based on relatively small samples or based on self-reports. A recent large-scale population-based cohort study of fall risk by Tsang et al3 addressed the issue by investigating the medical records of more than 3 million individuals.


  • Open Access

    Field Evaluation of a Mobile App for Assisting Blind and Visually Impaired Travelers to Find Bus Stops

    by Shrinivas Pundlik, Prerana Shivshanker, Tim Traut-Savino, Gang Luo

    Purpose: GPS location-based navigation apps are insufficient to aid blind and visually impaired (BVI) travelers for micro-navigation tasks, such as finding the exact location of bus stops. The resulting large gaps could lead to BVI travelers missing their bus. We evaluated the ability of a signage detection mobile app, All_Aboard, to guide BVI travelers precisely to the bus stops compared to Google Maps alone. Methods: The All_Aboard app detected bus stop signs in real-time via smartphone camera using a deep neural network model, and provided distance coded audio feedback to help localize the detected sign. BVI individuals used the All_Aboard and Google Maps app to localize 10 bus stops each in downtown and suburban Boston, Massachusetts. For each bus stop, the subjects used both apps to navigate as close as possible to the physical bus stop sign, starting from 30 to 50 meters away. The outcome measures were success rate and gap distance between the app-indicated location and the actual physical location of the bus stop. Results: The study involved 24 legally blind participants (mean age [SD] = 51 [14] years; 11 [46%] women). The success rate of the All_Aboard app (91%) was significantly higher than the Google Maps (52%, P < 0.001). The gap distance when using the All_Aboard app was significantly lower (mean = 1.8, 95% confidence interval [CI] = 1.2–2.3 meters) compared to the Google Maps alone (mean = 7, 95% CI = 6.5–7.5 meters, P < 0.001). Conclusions: All_Aboard micro-navigation app guided BVI travelers to bus stops more accurately and reliably than a location-based macro-navigation app alone. Translational Relevance: The All_Aboard app together with a macro-navigation app can potentially help BVI individuals independently access public transportation.


  • Open Access

    Evaluation of a mobile app for dark adaptation measurement in individuals with age-related macular degeneration

    by Shrinivas Pundlik, Prerana Shivshanker, Archana Nigalye, Gang Luo, Deeba Husain

    We present clinical evaluation of a mobile app for dark adaptation (DA) measurement in age-related macular degeneration (AMD) patients and in older adults (age > 50 years) without AMD or other retinal disorders (NV). The outcome measures were the area under dark adaptation curve (AUDAC) and the time for visual sensitivity to recover by 3 log units (TR). Larger AUDAC and TR values indicated worse DA response. The association of AUDAC with AMD was analyzed using linear regression, while time-to-event analysis was used for TR. 32 AMD patients (mean ± SD; age:72 ± 6.3 years, VA:0.09 ± 0.08 logMAR) and 25 NV subjects (mean ± sd; age:65 ± 8.7 years, VA:0.049 ± 0.07 logMAR) were measured with the app. Controlling for age, VA, and cataract severity, the AMD presence was significantly associated with higher AUDAC (β = 0.41, 95% CI 0.18–0.64, p = 0.001) and with slower sensitivity recovery (β = 0.32, 95% CI 0.15–0.69, p = 0.004). DA measurements with the app were highly correlated with those obtained with AdaptDx—an established clinical device (n = 18, ρ = 0.87, p < 0.001). AMD classification accuracy using the app was 72%, which was comparable to the 71% accuracy of AdaptDx. Our findings indicate that the mobile app provided reliable and clinically meaningful DA measurements that were strongly correlated with the current standard of care in AMD.