Search

Your search keyword '"Guleria, Shan"' showing total 19 results
Start Over Author "Guleria, Shan"
19 results on '"Guleria, Shan"'

2. The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning

Author

Guleria, Shan, Schwartz, Benjamin, Sharma, Yash, Fernandes, Philip, Jablonski, James, Adewole, Sodiq, Srivastava, Sanjana, Rhoads, Fisher, Porter, Michael, Yeghyayan, Michelle, Hyatt, Dylan, Copland, Andrew, Ehsan, Lubaina, Brown, Donald, and Syed, Sana

Subjects
Quantitative Biology - Quantitative Methods, Computer Science - Machine Learning
Abstract

Introduction: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process. Methods: An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning. Results: When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well. Discussion: Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved.

Published
2023

11. Artificial Intelligence-Based Analytics for Diagnosis of Small Bowel Enteropathies and Black Box Feature Detection

Author

Syed, Sana, primary, Ehsan, Lubaina, additional, Shrivastava, Aman, additional, Sengupta, Saurav, additional, Khan, Marium, additional, Kowsari, Kamran, additional, Guleria, Shan, additional, Sali, Rasoul, additional, Kant, Karan, additional, Kang, Sung-Jun, additional, Sadiq, Kamran, additional, Iqbal, Najeeha T., additional, Cheng, Lin, additional, Moskaluk, Christopher A., additional, Kelly, Paul, additional, Amadi, Beatrice C., additional, Ali, S. Asad, additional, Moore, Sean R., additional, and Brown, Donald E., additional

Published
2020
Full Text
View/download PDF

12. Pathobiome driven gut inflammation in Pakistani children with Environmental Enteric Dysfunction

Author

Iqbal, Najeeha T., primary, Syed, Sana, additional, Kabir, Furqan, additional, Jamil, Zehra, additional, Akhund, Tauseef, additional, Qureshi, Shahida, additional, Liu, Jie, additional, Ma, Jennie Z., additional, Guleria, Shan, additional, Gewirtz, Andrew, additional, Duggan, Christopher P., additional, Hughes, Molly A., additional, Sadiq, Kamran, additional, and Ali, Asad, additional

Published
2019
Full Text
View/download PDF

14. Prostate-Specific Antigen 5 Years following Stereotactic Body Radiation Therapy for Low- and Intermediate-Risk Prostate Cancer: An Ablative Procedure?

Author

Kataria, Shaan, primary, Koneru, Harsha, additional, Guleria, Shan, additional, Danner, Malika, additional, Ayoob, Marilyn, additional, Yung, Thomas, additional, Lei, Siyuan, additional, Collins, Brian T., additional, Suy, Simeng, additional, Lynch, John H., additional, Kole, Thomas, additional, and Collins, Sean P., additional

Published
2017
Full Text
View/download PDF

15. Prostate specific antigen five years following stereotactic body radiation therapy (SBRT) for low and intermediate risk prostate cancer: An ablative procedure?

Author

Kataria, Shaan, primary, Koneru, Harsha, additional, Guleria, Shan, additional, Danner, Malika, additional, Ayoob, Marilyn, additional, Yung, Thomas M., additional, Lei, Siyuan, additional, Collins, Brian Timothy, additional, Suy, Simeng, additional, Dritschilo, Anatoly, additional, Lynch, John, additional, Kole, Thomas Pedicino, additional, and Collins, Sean P., additional

Published
2017
Full Text
View/download PDF

16. Acute Urinary Morbidity Following Stereotactic Body Radiation Therapy for Prostate Cancer with Prophylactic Alpha-Adrenergic Antagonist and Urethral Dose Reduction

Author

Repka, Michael C., primary, Guleria, Shan, additional, Cyr, Robyn A., additional, Yung, Thomas M., additional, Koneru, Harsha, additional, Chen, Leonard N., additional, Lei, Siyuan, additional, Collins, Brian T., additional, Krishnan, Pranay, additional, Suy, Simeng, additional, Dritschilo, Anatoly, additional, Lynch, John, additional, and Collins, Sean P., additional

Published
2016
Full Text
View/download PDF

17. The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning.

Author

Guleria S, Schwartz B, Sharma Y, Fernandes P, Jablonski J, Adewole S, Srivastava S, Rhoads F, Porter M, Yeghyayan M, Hyatt D, Copland A, Ehsan L, Brown D, and Syed S

Abstract

Introduction: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process., Methods: An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning., Results: When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well., Discussion: Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved., Competing Interests: Potential competing interests: None declared.

Published
2023

18. Semi-Supervised Classification of Noisy, Gigapixel Histology Images.

Author

Pulido JV, Guleria S, Ehsan L, Fasullo M, Lippman R, Mutha P, Shah T, Syed S, and Brown DE

Abstract

One of the greatest obstacles in the adoption of deep neural networks for new medical applications is that training these models typically require a large amount of manually labeled training samples. In this body of work, we investigate the semi-supervised scenario where one has access to large amounts of unlabeled data and only a few labeled samples. We study the performance of MixMatch and FixMatch-two popular semi-supervised learning methods-on a histology dataset. More specifically, we study these models' impact under a highly noisy and imbalanced setting. The findings here motivate the development of semi-supervised methods to ameliorate problems commonly encountered in medical data applications.

Published
2020
Full Text
View/download PDF

19. SCREENING FOR BARRETT'S ESOPHAGUS WITH PROBE-BASED CONFOCAL LASER ENDOMICROSCOPY VIDEOS.

Author

Pulido JV, Guleria S, Ehsan L, Shah T, Syed S, and Brown DE

Abstract

Histologic diagnosis of Barrett's esophagus and esophageal malignancy via probe-based confocal laser endomicroscopy (pCLE) allows for real-time examination of epithelial architecture and targeted biopsy sampling. Although pCLE demonstrates high specificity, sensitivity remains low. This study employs deep learning architectures in order to improve the accuracy of pCLE in diagnosing esophageal cancer and its precursors. pCLE videos are curated and annotated as belonging to one of the three classes: squamous, Barrett's (intestinal metaplasia without dysplasia), or dysplasia. We introduce two novel video architectures, AttentionPooling and Multi-Module AttentionPooling deep networks, that outperform other models and demonstrate a high degree of explainability.

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results