Mayank Golhar

Mayank Golhar

Auto-generated profile, based on publicly available information

Mayank Golhar

Johns Hopkins University

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
7 September 2023 in Medical Image Analysis
Verified
Journal Article
Closed access
TBTaylor L. Bobrow
Taylor L. Bobrow
MGMayank Golhar
Mayank Golhar
RVRohan Vijayan
Rohan Vijayan
VAVenkata Akshintala
Venkata Akshintala
JGJuan R. Garcia
Juan R. Garcia
NDNicholas Durr
Nicholas Durr

25 December 2020 in IEEE Access
Verified
Journal Article
Open access
MGMayank Golhar
Mayank Golhar
TBTaylor L. Bobrow
Taylor L. Bobrow
MKMirmilad Pourmousavi Khoshknab
Mirmilad Pourmousavi Khoshknab
SJSimran Jit
Simran Jit
SNSaowanee Ngamruengphong
Saowanee Ngamruengphong
NDNicholas Durr
Nicholas Durr
While data-driven approaches excel at many image analysis tasks, the performance of these approaches is often limited by a shortage of annotated data available for training. Recent work in semi-supervised learning has shown that meaningful representations of images can be obtained from training with large quantities of unlabeled data, and that these representations can improve the performance of supervised tasks. Here, we demonstrate that an unsupervised jigsaw learning task, in combination with supervised training, results in up to a 9.8% improvement in correctly classifying lesions in colonoscopy images when compared to a fully-supervised baseline. We additionally benchmark improvements in domain adaptation and out-of-distribution detection, and demonstrate that semi-supervised learning outperforms supervised learning in both cases. In colonoscopy applications, these metrics are important given the skill required for endoscopic assessment of lesions, the wide variety of endoscopy systems in use, and the homogeneity that is typical of labeled datasets.

7 May 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
MGMayank V. Golhar
Mayank V. Golhar
TBTaylor L. Bobrow
Taylor L. Bobrow
SNSaowanee Ngamruengphong
Saowanee Ngamruengphong
NDNicholas Durr
Nicholas Durr
A major challenge in applying deep learning to medical imaging is the paucity of annotated data. This study explores the use of synthetic images for data augmentation to address the challenge of limited annotated data in colonoscopy lesion classification. We demonstrate that synthetic colonoscopy images generated by Generative Adversarial Network (GAN) inversion can be used as training data to improve polyp classification performance by deep learning models. We invert pairs of images with the same label to a semantically rich and disentangled latent space and manipulate latent representations to produce new synthetic images. These synthetic images maintain the same label as the input pairs. We perform image modality translation (style transfer) between white light and narrow-band imaging (NBI). We also generate realistic synthetic lesion images by interpolating between original training images to increase the variety of lesion shapes in the training dataset. Our experiments show that GAN inversion can produce multiple colonoscopy data augmentations that improve the downstream polyp classification performance by 2.7% in F1-score and 4.9% in sensitivity over other methods, including state-of-the-art data augmentation. Testing on unseen out-of-domain data also showcased an improvement of 2.9% in F1-score and 2.7% in sensitivity. This approach outperforms other colonoscopy data augmentation techniques and does not require re-training multiple generative models. It also effectively uses information from diverse public datasets, even those not specifically designed for the targeted downstream task, resulting in strong domain generalizability. Project code and model: https://github.com/DurrLab/GAN-Inversion .