Rishabh Sharma

Mr. Rishabh Sharma

Computer Science, University of Houston, Houston, Texas, USA
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
31 August 2020 in Nutrients
Verified
Journal Article
Open access
PDF file
AMArchana J. Mceligot
Archana J. Mceligot
VPValerie Poynor
Valerie Poynor
RSRishabh Sharma
Rishabh Sharma
APAnand Panangadan
Anand Panangadan
A multitude of dietary factors from dietary fat to macro and micronutrients intakes have been associated with breast cancer, yet data are still equivocal. Therefore, utilizing data from the large, multi-year, cross-sectional National Health and Nutrition Examination Survey (NHANES), we applied a novel, modern statistical shrinkage technique, logistic least absolute shrinkage and selection operator (LASSO) regression, to examine the association between dietary intakes in women, ≥50 years, with self-reported breast cancer (n = 286) compared with women without self-reported breast cancer (1144) from the 1999–2010 NHANES cycle. Logistic LASSO regression was used to examine the relationship between twenty-nine variables, including dietary variables from food, as well as well-established/known breast cancer risk factors, and to subsequently identify the most relevant variables associated with self-reported breast cancer. We observed that as the penalty factor (λ) increased in the logistic LASSO regression, well-established breast cancer risk factors, including age (β = 0.83) and parity (β = −0.05) remained in the model. For dietary macro and micronutrient intakes, only vitamin B12 (β = 0.07) was positively associated with self-reported breast cancer. Caffeine (β = −0.01) and alcohol (β = 0.03) use also continued to remain in the model. These data suggest that a diet high in vitamin B12, as well as alcohol use may be associated with self-reported breast cancer. Nonetheless, additional prospective studies should apply more recent statistical techniques to dietary data and cancer outcomes to replicate and confirm the present findings.

24 March 2022 in Medical Image Analysis
Verified
Journal Article
Closed access
Alain LalandeAlain Lalande
Alain Lalande
ZCZhihao Chen
Zhihao Chen
TPThibaut Pommier
Thibaut Pommier
TDthomas decourselle
thomas decourselle
AQAbdul Qayyum
Abdul Qayyum
FMFabrice Meriaudeau
Fabrice Meriaudeau

19 November 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
RSRishabh Sharma
Rishabh Sharma
PTPanagiotis Tsiamyrtzis
Panagiotis Tsiamyrtzis
AWandrew webb
andrew webb
ISIOANNIS SEIMENIS
IOANNIS SEIMENIS
CLConstantinos Loukas
Constantinos Loukas
NTNikolaos V. Tsekos
Nikolaos V. Tsekos
MR scans of low-gamma X-nuclei, low-concentration metabolites, or standard imaging at very low field entail a challenging tradeoff between resolution, signal-to-noise, and acquisition duration. Deep learning (DL) techniques, such as UNets, can potentially be used to improve such “low-quality” (LQ) images. We investigate three UNets for upscaling LQ MRI: dense (DUNet), robust (RUNet), and anisotropic (AUNet). These were evaluated for two acquisition scenarios. In the same-subject High-Quality Complementary Priors (HQCP) scenario, an LQ and a high quality (HQ) image are collected and both LQ and HQ were inputs to the UNets. In the No Complementary Priors (NoCP) scenario, only the LQ images are collected and used as the sole input to the UNets. To address the lack of same-subject LQ and HQ images, we added data from the OASIS-1 database. The UNets were tested in upscaling 1/8, 1/4, and 1/2 undersampled images for both scenarios. As manifested by non-statically significant differences of matrices, also supported by subjective observation, the three UNets upscaled images equally well. This was in contrast to mixed effects statistics that clearly illustrated significant differences. Observations suggest that the detailed architecture of these UNets may not play a critical role. As expected, HQCP substantially improves upscaling with any of the UNets. The outcomes support the notion that DL methods may have merit as an integral part of integrated holistic approaches in advancing special MRI acquisitions; however, primary attention should be paid to the foundational step of such approaches, i.e., the actual data collected.

29 January 2021
Verified
Book Chapter
Closed access
PDF file
RSRishabh Sharma
Rishabh Sharma
CEChristoph F. Eick
Christoph F. Eick
NTNikolaos V. Tsekos
Nikolaos V. Tsekos

31 July 2024 in Journal of Imaging Informatics in Medicine
Verified
Journal Article
Closed access
PDF file
MJMohammad Javadi
Mohammad Javadi
RSRishabh Sharma
Rishabh Sharma
PTPanagiotis Tsiamyrtzis
Panagiotis Tsiamyrtzis
AWandrew webb
andrew webb
ELErnst Leiss
Ernst Leiss
NTNikolaos V. Tsekos
Nikolaos V. Tsekos

16 June 2023 in Alzheimer's & Dementia
Verified
Journal Article
Open access
RSRishabh Sharma
Rishabh Sharma
LSLudovic Sibille
Ludovic Sibille
RFRachid Fahmi
Rachid Fahmi
Background: Brain PET imaging techniques provide in‐vivo information about brain metabolism and the density/distribution of amyloid and tau proteins, the two hallmarks of Alzheimer’s disease (AD). Combination of such imaging biomarkers has led to improved performances of deep‐learning models designed for disease‐classification and prediction of disease‐progression. However, training such networks is often a challenge, especially when subjects have missing imaging markers at given time‐points. Such incomplete data is often excluded from the training process. We propose a “multibranch”‐convolutional‐neural‐network architecture to cope with this issue and make use of all available data for better AD vs. normal‐controls (NC) classification performance.Method: We obtained multi‐time point ADNI FDG‐ and AV45‐PET scans corresponding to 257 NC and 222 AD subjects. N = 124 subjects had only one PET scan available at different time‐points. We designed a CNN with three training “branches”, taking as input either FGD, AV45, or a combination of the two when available (see Fig.1). In total, 1832 scans (786 singles and 523 pairs) were used as input for training. Branches are weighted differently (with 0 or 1) to control how training weights are updated. When both imaging‐biomarkers are available, each branch is fed with the appropriate input and contributes to the overall training. The overall network architecture is shown on Fig.1. For each branch, the calculated loss is multiplied by the associated weight and backpropagated through the network to update its training parameters. For comparison purposes, we independently trained a CNN with the same image pairs as above.Result: For validation, we only used cases with both scans available to assess the performance of each branch on the same number of inputs. Classification sensitivity, specificity, accuracy, and area‐under‐the‐curve averaged over 10 folds were: (i) FDG‐branch: 93.11%, 88.88%, 91.35%, and 0.954, (ii) AV45‐branch: 96.53%, 74.87%, 90.27%, and 0.941, (iii) Multimodal‐branch: 94.43%, 86.50%, 91.56%, and 0.961, iv) Independent multi‐input CNN: 93.71%, 71.80%, 88.60%, and 0.959.Conclusion: We designed a multibranch‐CNN to handle missing data when training a multimodal classification CNN. Better classification accuracy was achieved with the multi‐input branch compared to the independently trained multi‐modal CNN. We will test our network on other type and/or number of modalities.