Aadarsh Jha

Aadarsh Jha

Vanderbilt University

H-index: 8

North America-United States

About Aadarsh Jha

Aadarsh Jha, With an exceptional h-index of 8 and a recent h-index of 8 (since 2020), a distinguished researcher at Vanderbilt University, specializes in the field of Deep Learning, Computer Vision.

His recent articles reflect a diverse array of research interests and contributions to the field:

Cloud-Based Deep Learning: End-To-End Full-Stack Handwritten Digit Recognition

AN EVALUATION OF ANTIBIOTIC PRESCRIPTION PRACTICES: PERSPECTIVES OF VETERINARY TRAINEES AND PRACTICING VETERINARIANS.

Glo-In-One: holistic glomerular detection, segmentation, and lesion characterization with large-scale web image mining

Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised Learning

Contrastive learning meets transfer learning: a case study in medical image analysis

Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking

Simtriplet: Simple triplet representation learning with a single gpu

BEDS: bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation

Aadarsh Jha Information

University

Vanderbilt University

Position

___

Citations(all)

399

Citations(since 2020)

397

Cited By

4

hIndex(all)

8

hIndex(since 2020)

8

i10Index(all)

7

i10Index(since 2020)

7

Email

University Profile Page

Vanderbilt University

Aadarsh Jha Skills & Research Interests

Deep Learning

Computer Vision

Top articles of Aadarsh Jha

Cloud-Based Deep Learning: End-To-End Full-Stack Handwritten Digit Recognition

Authors

Ruida Zeng,Aadarsh Jha,Ashwin Kumar,Terry Luo

Journal

arXiv preprint arXiv:2304.13506

Published Date

2023/2/1

Herein, we present Stratus, an end-to-end full-stack deep learning application deployed on the cloud. The rise of productionized deep learning necessitates infrastructure in the cloud that can provide such service (IaaS). In this paper, we explore the use of modern cloud infrastructure and micro-services to deliver accurate and high-speed predictions to an end-user, using a Deep Neural Network (DNN) to predict handwritten digit input, interfaced via a full-stack application. We survey tooling from Spark ML, Apache Kafka, Chameleon Cloud, Ansible, Vagrant, Python Flask, Docker, and Kubernetes in order to realize this machine learning pipeline. Through our cloud-based approach, we are able to demonstrate benchmark performance on the MNIST dataset with a deep learning model.

AN EVALUATION OF ANTIBIOTIC PRESCRIPTION PRACTICES: PERSPECTIVES OF VETERINARY TRAINEES AND PRACTICING VETERINARIANS.

Authors

S Ballal,N Ahmad,A Jha,V Sharma,R Mishra,MG Patel

Journal

Georgian Medical News

Published Date

2023/10/1

Antibiotic resistance is a major worldwide problem that has an impact on the well-being of humans as well as animals. Antibiotic resistance is caused by the misuse and excessive use of antibiotics. The key to reducing this issue lies in educating veterinary medical learners on the proper and accountable utilization of antibiotics for the care of animals. Objective-using awareness-raising and instruction as the foundation, this research of Indian veterinary learners can help resolve the issue of antibiotic resistance throughout the care of animals. The questionnaire survey was taken between June and July 2022 and it was aimed at learners registered in veterinary medical studies at academic and research institutions in India. The study included 500 pupils overall. The purpose of the survey was to gather information about students' knowledge of antibiotics, including antibiotic resistance, as well as their feelings on the consequences of antibiotic resistance on the globe at large and their acquaintance with the one health ideology. According to this study's findings, 83.3 percent of respondents thought antibiotic resistance was a serious problem. 57.92 percent of respondents understood the issue's worldwide consequences and its one health ideology. The study emphasizes the significance of expanding the veterinary educational program to include thorough instruction on prudent antibiotic usage and the concepts of one health.

Glo-In-One: holistic glomerular detection, segmentation, and lesion characterization with large-scale web image mining

Authors

Tianyuan Yao,Yuzhe Lu,Jun Long,Aadarsh Jha,Zheyu Zhu,Zuhayr Asad,Haichun Yang,Agnes B Fogo,Yuankai Huo

Journal

Journal of Medical Imaging

Published Date

2022/9/1

Purpose: The quantitative detection, segmentation, and characterization of glomeruli from high-resolution whole slide imaging (WSI) play essential roles in the computer-assisted diagnosis and scientific research in digital renal pathology. Historically, such comprehensive quantification requires extensive programming skills to be able to handle heterogeneous and customized computational tools. To bridge the gap of performing glomerular quantification for non-technical users, we develop the Glo-In-One toolkit to achieve holistic glomerular detection, segmentation, and characterization via a single line of command. Additionally, we release a large-scale collection of 30,000 unlabeled glomerular images to further facilitate the algorithmic development of self-supervised deep learning.Approach: The inputs of the Glo-In-One toolkit are WSIs, while the outputs are (1) WSI-level multi-class circle glomerular detection …

Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised Learning

Authors

Tianyuan Yao,Chang Qu,Jun Long,Quan Liu,Ruining Deng,Yuanhan Tian,Jiachen Xu,Aadarsh Jha,Zuhayr Asad,Shunxing Bao,Mengyang Zhao,Agnes B Fogo,Bennett A Landman,Haichun Yang,Catie Chang,Yuankai Huo

Journal

The journal of machine learning for biomedical imaging

Published Date

2022/8

With the rapid development of self-supervised learning (eg, contrastive learning), the importance of having large-scale images (even without annotations) for training a more generalizable AI model has been widely recognized in medical image analysis. However, collecting large-scale task-specific unannotated data at scale can be challenging for individual labs. Existing online resources, such as digital books, publications, and search engines, provide a new resource for obtaining large-scale images. However, published images in healthcare (eg, radiology and pathology) consist of a considerable amount of compound figures with subplots. In order to extract and separate compound figures into usable individual images for downstream learning, we propose a simple compound figure separation (SimCFS) framework without using the traditionally required detection bounding box annotations, with a new loss …

Contrastive learning meets transfer learning: a case study in medical image analysis

Authors

Yuzhe Lu,Aadarsh Jha,Ruining Deng,Yuankai Huo

Published Date

2022/4/4

Annotated medical images are typically more rare than labeled natural images, since they are limited by domain knowledge and privacy constraints. Recent advances in transfer and contrastive learning have provided effective solutions to tackle such issues from different perspectives. The state-of-the-art transfer learning (e.g., Big Transfer (BiT)) and contrastive learning (e.g., Simple Siamese Contrastive Learning (SimSiam)) approaches have been investigated independently, without considering the complementary nature of such techniques. It would be appealing to accelerate contrastive learning with transfer learning, given that slow convergence speed is a critical limitation of modern contrastive learning approaches. In this paper, we investigate the feasibility of aligning BiT with SimSiam. From empirical analyses, different normalization techniques (Group Norm in BiT vs. Batch Norm in SimSiam) is a key hurdle of …

Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking

Authors

Mengyang Zhao,Aadarsh Jha,Quan Liu,Bryan A Millis,Anita Mahadevan-Jansen,Le Lu,Bennett A Landman,Matthew J Tyska,Yuankai Huo

Journal

Medical Image Analysis

Published Date

2021/7/1

Recently, single-stage embedding based deep learning algorithms gain increasing attention in cell segmentation and tracking. Compared with the traditional “segment-then-associate” two-stage approach, a single-stage algorithm not only simultaneously achieves consistent instance cell segmentation and tracking but also gains superior performance when distinguishing ambiguous pixels on boundaries and overlaps. However, the deployment of an embedding based algorithm is restricted by slow inference speed (eg,≈ 1–2 min per frame). In this study, we propose a novel Faster Mean-shift algorithm, which tackles the computational bottleneck of embedding based cell segmentation and tracking. Different from previous GPU-accelerated fast mean-shift algorithms, a new online seed optimization policy (OSOP) is introduced to adaptively determine the minimal number of seeds, accelerate computation, and save …

Simtriplet: Simple triplet representation learning with a single gpu

Authors

Quan Liu,Peter C Louis,Yuzhe Lu,Aadarsh Jha,Mengyang Zhao,Ruining Deng,Tianyuan Yao,Joseph T Roland,Haichun Yang,Shilin Zhao,Lee E Wheless,Yuankai Huo

Published Date

2021

Contrastive learning is a key technique of modern self-supervised learning. The broader accessibility of earlier approaches is hindered by the need of heavy computational resources (e.g., at least 8 GPUs or 32 TPU cores), which accommodate for large-scale negative samples or momentum. The more recent SimSiam approach addresses such key limitations via stop-gradient without momentum encoders. In medical image analysis, multiple instances can be achieved from the same patient or tissue. Inspired by these advances, we propose a simple triplet representation learning (SimTriplet) approach on pathological images. The contribution of the paper is three-fold: (1) The proposed SimTriplet method takes advantage of the multi-view nature of medical images beyond self-augmentation; (2) The method maximizes both intra-sample and inter-sample similarities via triplets from positive pairs, without …

BEDS: bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation

Authors

Xing Li,Haichun Yang,Jiaxin He,Aadarsh Jha,Agnes B Fogo,Lee E Wheless,Shilin Zhao,Yuankai Huo

Published Date

2021/4/13

Reducing outcome variance is an essential task in deep learning based medical image analysis. Bootstrap aggregating, also known as bagging, is a canonical ensemble algorithm for aggregating weak learners to become a strong learner. Random forest is one of the most powerful machine learning algorithms before deep learning era, whose superior performance is driven by fitting bagged decision trees (weak learners). Inspired by the random forest technique, we propose a simple bagging ensemble deep segmentation (BEDs) method to train multiple U-Nets with partial training data to segment dense nuclei on pathological images. The contributions of this study are three-fold: (1) developing a self-ensemble learning framework for nucleus segmentation; (2) aggregating testing stage augmentation with self-ensemble learning; and (3) elucidating the idea that self-ensemble and testing stage stain augmentation …

CaCL: Class-Aware Codebook Learning for Weakly Supervised Segmentation on Diffuse Image Patterns

Authors

Ruining Deng,Quan Liu,Shunxing Bao,Aadarsh Jha,Catie Chang,Bryan A Millis,Matthew J Tyska,Yuankai Huo

Published Date

2021

Weakly supervised learning has been rapidly advanced in biomedical image analysis to achieve pixel-wise labels (segmentation) from image-wise annotations (classification), as biomedical images naturally contain image-wise labels in many scenarios. The current weakly supervised learning algorithms from the computer vision community are largely designed for focal objects (e.g., dogs and cats). However, such algorithms are not optimized for diffuse patterns in biomedical imaging (e.g., stains and fluorescence in microscopy imaging). In this paper, we propose a novel class-aware codebook learning (CaCL) algorithm to perform weakly supervised learning for diffuse image patterns. Specifically, the CaCL algorithm is deployed to segment protein expressed brush border regions from histological images of human duodenum. Our contribution is three-fold: (1) we approach the weakly supervised …

Map3d: registration-based multi-object tracking on 3d serial whole slide images

Authors

Ruining Deng,Haichun Yang,Aadarsh Jha,Yuzhe Lu,Peng Chu,Agnes B Fogo,Yuankai Huo

Journal

IEEE transactions on medical imaging

Published Date

2021/3/29

There has been a long pursuit for precise and reproducible glomerular quantification on renal pathology to leverage both research and practice. When digitizing the biopsy tissue samples using whole slide imaging (WSI), a set of serial sections from the same tissue can be acquired as a stack of images, similar to frames in a video. In radiology, the stack of images (e.g., computed tomography) are naturally used to provide 3D context for organs, tissues, and tumors. In pathology, it is appealing to do a similar 3D assessment. However, the 3D identification and association of large-scale glomeruli on renal pathology is challenging due to large tissue deformation, missing tissues, and artifacts from WSI. In this paper, we propose a novel Multi-object Association for Pathology in 3D (Map3D) method for automatically identifying and associating large-scale cross-sections of 3D objects from routine serial sectioning and WSI …

Compound figure separation of biomedical images with side loss

Authors

Tianyuan Yao,Chang Qu,Quan Liu,Ruining Deng,Yuanhan Tian,Jiachen Xu,Aadarsh Jha,Shunxing Bao,Mengyang Zhao,Agnes B Fogo,Bennett A Landman,Catie Chang,Haichun Yang,Yuankai Huo

Published Date

2021

Unsupervised learning algorithms (e.g., self-supervised learning, auto-encoder, contrastive learning) allow deep learning models to learn effective image representations from large-scale unlabeled data. In medical image analysis, even unannotated data can be difficult to obtain for individual labs. Fortunately, national-level efforts have been made to provide efficient access to obtain biomedical image data from previous scientific publications. For instance, NIH has launched the Open-i$$^\circledR $$ search engine that provides a large-scale image database with free access. However, the images in scientific publications consist of a considerable amount of compound figures with subplots. To extract and curate individual subplots, many different compound figure separation approaches have been developed, especially with the recent advances in deep learning. However, previous approaches typically …

VoxelEmbed: 3D instance segmentation and tracking with voxel embedding based deep learning

Authors

Mengyang Zhao,Quan Liu,Aadarsh Jha,Ruining Deng,Tianyuan Yao,Anita Mahadevan-Jansen,Matthew J Tyska,Bryan A Millis,Yuankai Huo

Published Date

2021

Recent advances in bioimaging have provided scientists a superior high spatial-temporal resolution to observe dynamics of living cells as 3D volumetric videos. Unfortunately, the 3D biomedical video analysis is lagging, impeded by resource insensitive human curation using off-the-shelf 3D analytic tools. Herein, biologists often need to discard a considerable amount of rich 3D spatial information by compromising on 2D analysis via maximum intensity projection. Recently, pixel embedding based cell instance segmentation and tracking provided a neat and generalizable computing paradigm for understanding cellular dynamics. In this work, we propose a novel spatial-temporal voxel-embedding (VoxelEmbed) based learning method to perform simultaneous cell instance segmenting and tracking on 3D volumetric video sequences. Our contribution is in four-fold: (1) The proposed voxel embedding generalizes the …

ASIST: annotation-free synthetic instance segmentation and tracking by adversarial simulations

Authors

Quan Liu,Isabella M Gaeta,Mengyang Zhao,Ruining Deng,Aadarsh Jha,Bryan A Millis,Anita Mahadevan-Jansen,Matthew J Tyska,Yuankai Huo

Journal

Computers in biology and medicine

Published Date

2021/7/1

BackgroundThe quantitative analysis of microscope videos often requires instance segmentation and tracking of cellular and subcellular objects. The traditional method consists of two stages: (1) performing instance object segmentation of each frame, and (2) associating objects frame-by-frame. Recently, pixel-embedding-based deep learning approaches these two steps simultaneously as a single stage holistic solution. Pixel-embedding-based learning forces similar feature representation of pixels from the same object, while maximizing the difference of feature representations from different objects. However, such deep learning methods require consistent annotations not only spatially (for segmentation), but also temporally (for tracking). In computer vision, annotated training data with consistent segmentation and tracking is resource intensive, the severity of which is multiplied in microscopy imaging due to (1 …

Instance segmentation for whole slide imaging: end-to-end or detect-then-segment

Authors

Aadarsh Jha,Haichun Yang,Ruining Deng,Meghan E Kapp,Agnes B Fogo,Yuankai Huo

Journal

Journal of Medical Imaging

Published Date

2021/1/1

Purpose: Automatic instance segmentation of glomeruli within kidney whole slide imaging (WSI) is essential for clinical research in renal pathology. In computer vision, the end-to-end instance segmentation methods (e.g., Mask-RCNN) have shown their advantages relative to detect-then-segment approaches by performing complementary detection and segmentation tasks simultaneously. As a result, the end-to-end Mask-RCNN approach has been the de facto standard method in recent glomerular segmentation studies, where downsampling and patch-based techniques are used to properly evaluate the high-resolution images from WSI (e.g., >10,000  ×  10,000  pixels on 40  ×  ). However, in high-resolution WSI, a single glomerulus itself can be more than 1000  ×  1000  pixels in original resolution which yields significant information loss when the corresponding features maps are downsampled …

The who, what, and where of primary TKAs: an analysis of HCUP data from 2009 to 2015

Authors

Chukwuweike Gwam,Samuel Rosas,Rashad Sullivan,T David Luo,Cynthia L Emory,Johannes F Plate

Journal

The Journal of Knee Surgery

Published Date

2020/4

The aim of this study was to assess (1) temporal trends, (2) primary indication, (3) patient-level demographics (age, race, gender, health status, and median income quartile), and (4) region and hospital type for all patients receiving primary total knee arthroplasty (TKA) between 2009 and the third quarter of 2015. The National Inpatient Sample Database (NIS) was used to identify all patients who underwent a TKA between 2009 and the third quarter of 2015. Regression analysis was utilized to assess trends. Chi-square analysis was used to explore categorical variables whereas Kruskal–Wallis test was used to explore nonparametric continuous variables. TKA utilization increased between 2009 and 2015 with the highest volume occurring during the fall. Primary osteoarthritis was the primary indication in 98% of cases. There was an increase in minority representation among recipients. Black TKA recipients were …

See List of Professors in Aadarsh Jha University(Vanderbilt University)

Aadarsh Jha FAQs

What is Aadarsh Jha's h-index at Vanderbilt University?

The h-index of Aadarsh Jha has been 8 since 2020 and 8 in total.

What are Aadarsh Jha's top articles?

The articles with the titles of

Cloud-Based Deep Learning: End-To-End Full-Stack Handwritten Digit Recognition

AN EVALUATION OF ANTIBIOTIC PRESCRIPTION PRACTICES: PERSPECTIVES OF VETERINARY TRAINEES AND PRACTICING VETERINARIANS.

Glo-In-One: holistic glomerular detection, segmentation, and lesion characterization with large-scale web image mining

Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised Learning

Contrastive learning meets transfer learning: a case study in medical image analysis

Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking

Simtriplet: Simple triplet representation learning with a single gpu

BEDS: bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation

...

are the top articles of Aadarsh Jha at Vanderbilt University.

What are Aadarsh Jha's research interests?

The research interests of Aadarsh Jha are: Deep Learning, Computer Vision

What is Aadarsh Jha's total number of citations?

Aadarsh Jha has 399 citations in total.

    academic-engine

    Useful Links