Search Results for author: Aadarsh Jha

Found 14 papers, 9 papers with code

Map3D: Registration Based Multi-Object Tracking on 3D Serial Whole Slide Images

1 code implementation10 Jun 2020 Ruining Deng, Haichun Yang, Aadarsh Jha, Yuzhe Lu, Peng Chu, Agnes B. Fogo, Yuankai Huo

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.

Multi-Object Tracking whole slide images

Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment

2 code implementations7 Jul 2020 Aadarsh Jha, Haichun Yang, Ruining Deng, Meghan E. Kapp, Agnes B. Fogo, Yuankai Huo

In this paper, we assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework.

Instance Segmentation Segmentation +1

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

1 code implementation28 Jul 2020 Mengyang Zhao, Aadarsh Jha, Quan Liu, Bryan A. Millis, Anita Mahadevan-Jansen, Le Lu, Bennett A. Landman, Matthew J. Tyskac, Yuankai Huo

With both embedding simulation and empirical validation via the four cohorts from the ISBI cell tracking challenge, the proposed Faster Mean-shift algorithm achieved 7-10 times speedup compared to the state-of-the-art embedding based cell instance segmentation and tracking algorithm.

Cell Segmentation Cell Tracking +4

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

1 code implementation2 Nov 2020 Ruining Deng, Quan Liu, Shunxing Bao, Aadarsh Jha, Catie Chang, Bryan A. Millis, Matthew J. Tyska, Yuankai Huo

Our contribution is three-fold: (1) we approach the weakly supervised segmentation from a novel codebook learning perspective; (2) the CaCL algorithm segments diffuse image patterns rather than focal objects; and (3) the proposed algorithm is implemented in a multi-task framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) via joint image reconstruction, classification, feature embedding, and segmentation.

Image Reconstruction Segmentation +2

ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations

no code implementations3 Jan 2021 Quan Liu, Isabella M. Gaeta, Mengyang Zhao, Ruining Deng, Aadarsh Jha, Bryan A. Millis, Anita Mahadevan-Jansen, Matthew J. Tyska, Yuankai Huo

Contribution: The contribution of this paper is three-fold: (1) the proposed method aggregates adversarial simulations and single-stage pixel-embedding based deep learning; (2) the method is assessed with both the cellular (i. e., HeLa cells) and subcellular (i. e., microvilli) objects; and (3) to the best of our knowledge, this is the first study to explore annotation-free instance segmentation and tracking study for microscope videos.

Instance Segmentation Segmentation +1

SimTriplet: Simple Triplet Representation Learning with a Single GPU

1 code implementation9 Mar 2021 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

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 using negative samples; and (3) The recent mix precision training is employed to advance the training by only using a single GPU with 16GB memory.

Contrastive Learning Representation Learning +1

VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning

no code implementations22 Jun 2021 Mengyang Zhao, Quan Liu, Aadarsh Jha, Ruining Deng, Tianyuan Yao, Anita Mahadevan-Jansen, Matthew J. Tyska, Bryan A. Millis, Yuankai Huo

Recently, pixel embedding-based cell instance segmentation and tracking provided a neat and generalizable computing paradigm for understanding cellular dynamics.

3D Instance Segmentation Cell Tracking +2

Compound Figure Separation of Biomedical Images with Side Loss

1 code implementation19 Jul 2021 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

Our technical contribution is three-fold: (1) we introduce a new side loss that is designed for compound figure separation; (2) we introduce an intra-class image augmentation method to simulate hard cases; (3) the proposed framework enables an efficient deployment to new classes of images, without requiring resource extensive bounding box annotations.

Contrastive Learning Image Augmentation +1

Glo-In-One: Holistic Glomerular Detection, Segmentation, and Lesion Characterization with Large-scale Web Image Mining

1 code implementation31 May 2022 Tianyuan Yao, Yuzhe Lu, Jun Long, Aadarsh Jha, Zheyu Zhu, Zuhayr Asad, Haichun Yang, Agnes B. Fogo, Yuankai Huo

To leverage the performance of the Glo-In-One toolkit, we introduce self-supervised deep learning to glomerular quantification via large-scale web image mining.

Segmentation

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

1 code implementation30 Aug 2022 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

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 function and a hard case simulation.

Contrastive Learning Image Augmentation +2

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

no code implementations1 Feb 2023 Ruida Zeng, Aadarsh Jha, Ashwin Kumar, Terry Luo

Herein, we present Stratus, an end-to-end full-stack deep learning application deployed on the cloud.

Handwritten Digit Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.