Akshay Pai

Dr. Akshay Pai


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 December 2015 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
APAkshay Pai
Akshay Pai
SSStefan Sommer
Stefan Sommer
LSLauge Sorensen
Lauge Sorensen
SDSune Darkner
Sune Darkner
JSJon Sporring
Jon Sporring
MNMads Nielsen
Mads Nielsen
In this paper, we propose a multi-scale, multi-kernel shape, compactly supported kernel bundle framework for stationary velocity field-based image registration (Wendland kernel bundle stationary velocity field, wKB-SVF). We exploit the possibility of directly choosing kernels to construct a reproducing kernel Hilbert space (RKHS) instead of imposing it from a differential operator. The proposed framework allows us to minimize computational cost without sacrificing the theoretical foundations of SVF-based diffeomorphic registration. In order to recover deformations occurring at different scales, we use compactly supported Wendland kernels at multiple scales and orders to parameterize the velocity fields, and the framework allows simultaneous optimization over all scales. The performance of wKB-SVF is extensively compared to the 14 non-rigid registration algorithms presented in a recent comparison paper. On both MGH10 and CUMC12 datasets, the accuracy of wKB-SVF is improved when compared to other registration algorithms. In a disease-specific application for intra-subject registration, atrophy scores estimated using the proposed registration scheme separates the diagnostic groups of Alzheimer's and normal controls better than the state-of-the-art segmentation technique. Experimental results show that wKB-SVF is a robust, flexible registration framework that allows theoretically well-founded and computationally efficient multi-scale representation of deformations and is equally well-suited for both inter- and intra-subject image registration.

19 September 2017 in arXiv
Verified
Preprint
Open access
PDF file
AMAshish Mahabal
Ashish Mahabal
KSKshiteej Sheth
Kshiteej Sheth
FGFabian Gieseke
Fabian Gieseke
APAkshay Pai
Akshay Pai
SDS. George Djorgovski
S. George Djorgovski
TCthe CSS/CRTS/PTF Collaboration
the CSS/CRTS/PTF Collaboration
Astronomy light curves are sparse, gappy, and heteroscedastic. As a result standard time series methods regularly used for financial and similar datasets are of little help and astronomers are usually left to their own instruments and techniques to classify light curves. A common approach is to derive statistical features from the time series and to use machine learning methods, generally supervised, to separate objects into a few of the standard classes. In this work, we transform the time series to two-dimensional light curve representations in order to classify them using modern deep learning techniques. In particular, we show that convolutional neural networks based classifiers work well for broad characterization and classification. We use labeled datasets of periodic variables from CRTS survey and show how this opens doors for a quick classification of diverse classes with several possible exciting extensions.

29 May 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SBSimone Bonechi
Simone Bonechi
PAPaolo Andreini
Paolo Andreini
MBMonica Bianchini
Monica Bianchini
APAkshay Pai
Akshay Pai
FSFranco Scarselli
Franco Scarselli
In recent years, Deep Neural Networks (DNNs) have led to impressive results in a wide variety of machine learning tasks, typically relying on the existence of a huge amount of supervised data. However, in many applications (e.g., bio–medical image analysis), gathering large sets of labeled data can be very difficult and costly. Unsupervised domain adaptation exploits data from a source domain, where annotations are available, to train a model able to generalize also to a target domain, where labels are unavailable. Recent research has shown that Generative Adversarial Networks (GANs) can be successfully employed for domain adaptation, although deciding when to stop learning is a major concern for GANs. In this work, we propose some confidence measures that can be used to early stop the GAN training, also showing how such measures can be employed to predict the reliability of the network output. The effectiveness of the proposed approach has been tested in two domain adaptation tasks, with very promising results.

30 August 2024 in Current Research in Nutrition and Food Science Journal
Verified
Journal Article
Open access
PDF file
MMMeghna Suresh Motwani
Meghna Suresh Motwani
KDKasturi V. Deorukhkar
Kasturi V. Deorukhkar
NSNeha Sanwalka
Neha Sanwalka
NKNikita S. Kochrekar
Nikita S. Kochrekar
APAkshay Pai
Akshay Pai
SMSubhadra Mandalika
Subhadra Mandalika
The rising burden of non-communicable diseases (NCDs) in India necessitates more studies on nutritional intake and dietary behaviour. While data exists on low-income groups, rural populations and the population at large, limited information exists on that of urban, working professionals – a demographic that has the means and access to make informed choices, and yet, have a disproportionately high risk of NCDs. The aim of this study was to investigate nutrient intake in Indian professionals. A cross-sectional study was conducted on 214 working professionals (aged 30-40 years; 69 females and 145 males) in Mumbai. Habitual food intake was investigated by two 24-hour recalls and a semi-quantitative food frequency questionnaire. Nutrient adequacy ratios were calculated in comparison to Indian estimated average requirements. Compared to recommendations, a lower total energy and carbohydrate intake, while a higher protein and fat intake was observed among the participants. However, the intake of omega-3 fats, and overall fruit and vegetable intake was poor. A significantly higher energy from proteins and fats was observed among non-vegetarians, while vegetarians consumed more energy from carbohydrates. Insufficient intake of vitamins and minerals was prevalent with over 50% of study participants consuming <50% of their required intake of Vitamin A, B12, folate, riboflavin, zinc and potassium. Intake of copper, pyridoxine and iron were also suboptimal. To conclude, the insufficient intake of micronutrient and macronutrient imbalances in the studied population, highlights the urgency of targeted nutritional interventions and education in urban, corporate populations in India, to mitigate the risk of NCDs.

11 October 2020 in medRxiv
Verified
Preprint
Open access
PDF file
EJEspen Jimenez-Solem
Espen Jimenez-Solem
TPTonny Studsgaard Petersen
Tonny Studsgaard Petersen
CHCasper Hansen
Casper Hansen
CHChristian Hansen
Christian Hansen
CLChristina Lioma
Christina Lioma
MSMartin Sillesen
Martin Sillesen
Background: Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that Machine Learning (ML) models could be used to predict risks at different stages of management (at diagnosis, hospital admission and ICU admission) and thereby provide insights into drivers and prognostic markers of disease progression and death. Methods: From a cohort of approx. 2.6 million citizens in the two regions of Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. A cohort of SARS- CoV-2 positive cases from the United Kingdom Biobank was used for external validation. Findings: The ML models predicted the risk of death (Receiver Operation Characteristics – Area Under the Curve, ROC-AUC) of 0.904 at diagnosis, 0.818, at hospital admission and 0.723 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. We identified some common risk factors, including age, body mass index (BMI) and hypertension as driving factors, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. Interpretation: ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. Prognostic features included age, BMI and hypertension, although markers of shock and organ dysfunction became more important in more severe cases. We provide access to an online risk calculator based on these findings. Funding: The study was funded by grants from the Novo Nordisk Foundation to MS (#NNF20SA0062879 and #NNF19OC0055183) and MN (#NNF20SA0062879). The foundation took no part in project design, data handling and manuscript preparation.

15 March 2017 in arXiv
Verified
Preprint
Open access
PDF file
LKLine Kühnel
Line Kühnel
SSStefan Sommer
Stefan Sommer
APAkshay Pai
Akshay Pai
LRLars Lau Raket
Lars Lau Raket
This paper introduces a class of mixed-effects models for joint modeling of spatially correlated intensity variation and warping variation in 2D images. Spatially correlated intensity variation and warp variation are modeled as random effects, resulting in a nonlinear mixed-effects model that enables simultaneous estimation of template and model parameters by optimization of the likelihood function. We propose an algorithm for fitting the model which alternates estimation of variance parameters and image registration. This approach avoids the potential estimation bias in the template estimate that arises when treating registration as a preprocessing step. We apply the model to datasets of facial images and 2D brain magnetic resonance images to illustrate the simultaneous estimation and prediction of intensity and warp effects.