A Scalable Pipeline for Gigapixel Whole Slide Imaging Analysis on Leadership Class HPC Systems

Dash, Sajal; Hernandez Arreguin, Benjamin; Tsaris, Aristeidis (aris); Alamudun, Folami; Yoon, Hong-Jun; Wang, Feiyi

doi:10.1109/IPDPSW55747.2022.00223

Title: A Scalable Pipeline for Gigapixel Whole Slide Imaging Analysis on Leadership Class HPC Systems

Full Record
Other Related Research

Abstract

Whole Slide Imaging (WSI) captures microscopic details of a patient's histopathological features at multiple res-olutions organized across different levels. Images produced by WSI are gigapixel-sized, and saving a single image in memory requires a few gigabytes which is scarce since a complicated model occupies tens of gigabytes. Performing a simple met-ric operation on these large images is also expensive. High-performance computing (HPC) can help us quickly analyze such large images using distributed training of complex deep learning models. One popular approach in analyzing these images is to divide a WSI image into smaller tiles (patches) and then train a simpler model with these reduced-sized but large numbers of patches. However, we need to solve three pre-processing challenges efficiently for pursuing this patch-based approach. 1) Creating small patches from a high-resolution image can result in a high number (hundreds of thousands per image) of patches. Storing and processing these images can be challenging due to a large number of I/O and arithmetic operations. To reduce I/Oand memory accesses, an optimal balance between the size and number of patches must exist to reduce I/O and memory accesses. 2) WSI images may have tiny annotated regions for cancer tissue and a significant portionmore »« less

Authors:

Dash, Sajal ^[1];

^[1]; Tsaris, Aristeidis (aris) ^[1];

^[1];

^[1]

ORNL

Publication Date:: 2022-05-01

Research Org.:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1885343

DOE Contract Number:: AC05-00OR22725

Resource Type:: Conference

Resource Relation:: Conference: ExSAIS 2022: Workshop on Extreme Scaling of AI for Science - Virtual, Tennessee, United States of America - 5/30/2022 4:00:00 AM-6/3/2022 4:00:00 AM

Country of Publication:: United States

Language:: English

Citation Formats


                    Dash, Sajal, Hernandez Arreguin, Benjamin, Tsaris, Aristeidis, Alamudun, Folami, Yoon, Hong-Jun, and Wang, Feiyi. A Scalable Pipeline for Gigapixel Whole Slide Imaging Analysis on Leadership Class HPC Systems.  United States: N. p., 2022. 
        Web.  doi:10.1109/IPDPSW55747.2022.00223.

Copy to clipboard


                    Dash, Sajal, Hernandez Arreguin, Benjamin, Tsaris, Aristeidis, Alamudun, Folami, Yoon, Hong-Jun, & Wang, Feiyi. A Scalable Pipeline for Gigapixel Whole Slide Imaging Analysis on Leadership Class HPC Systems.  United States.  https://doi.org/10.1109/IPDPSW55747.2022.00223

Copy to clipboard


                    Dash, Sajal, Hernandez Arreguin, Benjamin, Tsaris, Aristeidis, Alamudun, Folami, Yoon, Hong-Jun, and Wang, Feiyi. 2022.  
        "A Scalable Pipeline for Gigapixel Whole Slide Imaging Analysis on Leadership Class HPC Systems".  United States.  https://doi.org/10.1109/IPDPSW55747.2022.00223.  https://www.osti.gov/servlets/purl/1885343.

Copy to clipboard


                    
@article{osti_1885343,

  title        = {A Scalable Pipeline for Gigapixel Whole Slide Imaging Analysis on Leadership Class HPC Systems},

  author       = {Dash, Sajal and Hernandez Arreguin, Benjamin and Tsaris, Aristeidis and Alamudun, Folami and Yoon, Hong-Jun and Wang, Feiyi},

  abstractNote = {Whole Slide Imaging (WSI) captures microscopic details of a patient's histopathological features at multiple res-olutions organized across different levels. Images produced by WSI are gigapixel-sized, and saving a single image in memory requires a few gigabytes which is scarce since a complicated model occupies tens of gigabytes. Performing a simple met-ric operation on these large images is also expensive. High-performance computing (HPC) can help us quickly analyze such large images using distributed training of complex deep learning models. One popular approach in analyzing these images is to divide a WSI image into smaller tiles (patches) and then train a simpler model with these reduced-sized but large numbers of patches. However, we need to solve three pre-processing challenges efficiently for pursuing this patch-based approach. 1) Creating small patches from a high-resolution image can result in a high number (hundreds of thousands per image) of patches. Storing and processing these images can be challenging due to a large number of I/O and arithmetic operations. To reduce I/Oand memory accesses, an optimal balance between the size and number of patches must exist to reduce I/O and memory accesses. 2) WSI images may have tiny annotated regions for cancer tissue and a significant portion with normal and fatty tissues; correct patch sampling should avoid dataset imbalance. 3) storing and retrieving many patches to and from disk storage might incur I/O latency while training a deep learning model. An efficient distributed data loader should reduce I/O latency during the training and inference steps. This paper explores these three challenges and provides empirical and algorithmic solutions deployed on the Summit supercomputer hosted at the Oak Ridge Leadership Computing Facility.},

  doi          = {10.1109/IPDPSW55747.2022.00223},

  url          = {https://www.osti.gov/biblio/1885343},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2022},

  month        = {5}

}

Copy to clipboard

Conference:

View Conference (3.77 MB)

https://doi.org/10.1109/IPDPSW55747.2022.00223

Other availability

Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Scaling Resolution of Gigapixel Whole Slide Images Using Spatial Decomposition on Convolutional Neural Networks

Conference Tsaris, Aristeidis (aris); Yoon, Hong-Jun; Dash, Sajal; ...

Gigapixel images are prevalent in scientific domains ranging from remote sensing, and satellite imagery to microscopy, etc. However, training a deep learning model at the natural resolution of those images has been a challenge in terms of both, overcoming the resource limit (e.g. HBM memory constraints), as well as scaling up to a large number of GPUs. In this paper, we trained Residual neural Networks (ResNet) on 22,528 x 22,528-pixel size images using a distributed spatial decomposition method on 2,304 GPUs on the Summit Supercomputer. We applied our method on a Whole Slide Imaging (WSI) dataset from The Cancer Genomemore »« less
https://doi.org/10.1145/3592979.3593401

Full Text Available
Distilling Knowledge from Ensembles of Cluster-Constrained-Attention Multiple-Instance Learners for Whole Slide Image Classification

Conference Alamudun, Folami; Dash, Sajal; Hinkle, Jacob; ...

The peculiar nature of whole slide imaging (WSI), digitizing conventional glass slides to obtain multiple high resolution images which capture microscopic details of a patient’s histopathological features, has garnered increased interest from the computer vision research community over the last two decades. Given the unique computational space and time complexity inherent to gigapixel-size whole slide image data, researchers have proposed novel machine learning algorithms to aid in the performance of diagnostic tasks in clinical pathology. One effective algorithm represents a Whole slide image as a bag of smaller image patches, which can be represented as low-dimension image patch embeddings. Weaklymore »« less
https://doi.org/10.1109/BigData55660.2022.10020938

Full Text Available
Distributed seams for gigapixel panoramas

Journal Article Philip, Sujin; Summa, Brian; Tierny, Julien; ... - IEEE Transactions on Visualization and Computer Graphics

Gigapixel panoramas are an increasingly popular digital image application. They are often created as a mosaic of many smaller images. The mosaic acquisition can take many hours causing the individual images to differ in exposure and lighting conditions. A blending operation is often necessary to give the appearance of a seamless image. The blending quality depends on the magnitude of discontinuity along the image boundaries. Often, new boundaries, or seams, are first computed that minimize this transition. Current techniques based on multi-labeling Graph Cuts are too slow and memory intensive for gigapixel sized panoramas. In this paper, we present amore »« less
https://doi.org/10.1109/TVCG.2014.2366128
SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms

Technical Report Chen, Yiran; Li, Hai (Helen)

Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraintsmore »« less
https://doi.org/10.2172/1846568

Full Text Available
Super-resolution and segmentation deep learning for breast cancer histopathology image analysis

Journal Article Juhong, Aniwat; Li, Bo; Yao, Cheng-You; ... - Biomedical Optics Express

Traditionally, a high-performance microscope with a large numerical aperture is required to acquire high-resolution images. However, the images’ size is typically tremendous. Therefore, they are not conveniently managed and transferred across a computer network or stored in a limited computer storage system. As a result, image compression is commonly used to reduce image size resulting in poor image resolution. Here, we demonstrate custom convolution neural networks (CNNs) for both super-resolution image enhancement from low-resolution images and characterization of both cells and nuclei from hematoxylin and eosin (H&E) stained breast cancer histopathological images by using a combination of generator and discriminatormore »« less
https://doi.org/10.1364/BOE.463839

Similar Records