arXiv subjects

Joel Saltz

Publications and source records attributed to Joel Saltz.

48 records · Page 3Linked to original sources

arXiv2020

Label Super Resolution with Inter-Instance Loss

For the task of semantic segmentation, high-resolution (pixel-level) ground truth is very expensive to collect, especially for high resolution images such as gigapixel pathology images. On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient. Conventional methods trained on these low-resolution labels are only capable of giving low-resolution predictions. The existing state-of-the-art label super resolution (LSR) method is capable of predicting high resolution labels, using only low-resolution supervision, given the joint distribution between low resolution and high resolution labels. However, it does not consider the inter-instance variance which is crucial in the ideal mathematical formulation. In this work, we propose a novel loss function modeling the inter-instance variance. We test our method on a real world application: infiltrating breast cancer region segmentation in histopathology slides. Experimental results show the effectiveness of our method.

cs.CV↗

arXiv2019

Run-time Parameter Sensitivity Analysis Optimizations

Efficient execution of parameter sensitivity analysis (SA) is critical to allow for its routinely use. The pathology image processing application investigated in this work processes high-resolution whole-slide cancer tissue images from large datasets to characterize and classify the disease. However, the application is parameterized and changes in parameter values may significantly affect its results. Thus, understanding the impact of parameters to the output using SA is important to draw reliable scientific conclusions. The execution of the application is rather compute intensive, and a SA requires it to process the input data multiple times as parameter values are systematically varied. Optimizing this process is then important to allow for SA to be executed with large datasets. In this work, we employ a distributed computing system with novel computation reuse optimizations to accelerate SA. The new computation reuse strategy can maximize reuse even with limited memory availability where previous approaches would not be able to fully take advantage of reuse. The proposed solution was evaluated on an environment with 256 nodes (7168 CPU-cores) attaining a parallel efficiency of over 92%, and improving the previous reuse strategies in up to 2.8x.

cs.DC↗

arXiv2019

Exascale Deep Learning to Accelerate Cancer Research

Deep learning, through the use of neural networks, has demonstrated remarkable ability to automate many routine tasks when presented with sufficient data for training. The neural network architecture (e.g. number of layers, types of layers, connections between layers, etc.) plays a critical role in determining what, if anything, the neural network is able to learn from the training data. The trend for neural network architectures, especially those trained on ImageNet, has been to grow ever deeper and more complex. The result has been ever increasing accuracy on benchmark datasets with the cost of increased computational demands. In this paper we demonstrate that neural network architectures can be automatically generated, tailored for a specific application, with dual objectives: accuracy of prediction and speed of prediction. Using MENNDL--an HPC-enabled software stack for neural architecture search--we generate a neural network with comparable accuracy to state-of-the-art networks on a cancer pathology dataset that is also $16\times$ faster at inference. The speedup in inference is necessary because of the volume and velocity of cancer pathology data; specifically, the previous state-of-the-art networks are too slow for individual researchers without access to HPC systems to keep pace with the rate of data generation. Our new model enables researchers with modest computational resources to analyze newly generated data faster than it is collected.

cs.LG↗

arXiv2019

Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types

Deep learning classifiers for characterization of whole slide tissue morphology require large volumes of annotated data to learn variations across different tissue and cancer types. As is well known, manual generation of digital pathology training data is time consuming and expensive. In this paper, we propose a semi-automated method for annotating a group of similar instances at once, instead of collecting only per-instance manual annotations. This allows for a much larger training set, that reflects visual variability across multiple cancer types and thus training of a single network which can be automatically applied to each cancer type without human adjustment. We apply our method to the important task of classifying Tumor Infiltrating Lymphocytes (TILs) in H&E images. Prior approaches were trained for individual cancer types, with smaller training sets and human-in-the-loop threshold adjustment. We utilize these thresholded results as large scale "semi-automatic" annotations. Combined with existing manual annotations, our trained deep networks are able to automatically produce better TIL prediction results in 12 cancer types, compared to the human-in-the-loop approach.

eess.IV↗

arXiv2018

Disease phenotyping using deep learning: A diabetes case study

Characterization of a patient clinical phenotype is central to biomedical informatics. ICD codes, assigned to inpatient encounters by coders, is important for population health and cohort discovery when clinical information is limited. While ICD codes are assigned to patients by professionals trained and certified in coding there is substantial variability in coding. We present a methodology that uses deep learning methods to model coder decision making and that predicts ICD codes. Our approach predicts codes based on demographics, lab results, and medications, as well as codes from previous encounters. We are able to predict existing codes with high accuracy for all three of the test cases we investigated: diabetes, acute renal failure, and chronic kidney disease. We employed a panel of clinicians, in a blinded manner, to assess ground truth and compared the predictions of coders, model and clinicians. When disparities between the model prediction and coder assigned codes were reviewed, our model outperformed coder assigned ICD codes.

cs.LG↗

arXiv2018

Methods for Segmentation and Classification of Digital Microscopy Tissue Images

High-resolution microscopy images of tissue specimens provide detailed information about the morphology of normal and diseased tissue. Image analysis of tissue morphology can help cancer researchers develop a better understanding of cancer biology. Segmentation of nuclei and classification of tissue images are two common tasks in tissue image analysis. Development of accurate and efficient algorithms for these tasks is a challenging problem because of the complexity of tissue morphology and tumor heterogeneity. In this paper we present two computer algorithms; one designed for segmentation of nuclei and the other for classification of whole slide tissue images. The segmentation algorithm implements a multiscale deep residual aggregation network to accurately segment nuclear material and then separate clumped nuclei into individual nuclei. The classification algorithm initially carries out patch-level classification via a deep learning method, then patch-level statistical and morphological features are used as input to a random forest regression model for whole slide image classification. The segmentation and classification algorithms were evaluated in the MICCAI 2017 Digital Pathology challenge. The segmentation algorithm achieved an accuracy score of 0.78. The classification algorithm achieved an accuracy score of 0.81.

cs.CV↗

arXiv2018

Large-scale Analysis of Opioid Poisoning Related Hospital Visits in New York State

Opioid related deaths are increasing dramatically in recent years, and opioid epidemic is worsening in the United States. Combating opioid epidemic becomes a high priority for both the U.S. government and local governments such as New York State. Analyzing patient level opioid related hospital visits provides a data driven approach to discover both spatial and temporal patterns and identity potential causes of opioid related deaths, which provides essential knowledge for governments on decision making. In this paper, we analyzed opioid poisoning related hospital visits using New York State SPARCS data, which provides diagnoses of patients in hospital visits. We identified all patients with primary diagnosis as opioid poisoning from 2010-2014 for our main studies, and from 2003-2014 for temporal trend studies. We performed demographical based studies, and summarized the historical trends of opioid poisoning. We used frequent item mining to find co-occurrences of diagnoses for possible causes of poisoning or effects from poisoning. We provided zip code level spatial analysis to detect local spatial clusters, and studied potential correlations between opioid poisoning and demographic and social-economic factors.

q-bio.PE↗

arXiv2016

Efficient Methods and Parallel Execution for Algorithm Sensitivity Analysis with Parameter Tuning on Microscopy Imaging Datasets

Background: We describe an informatics framework for researchers and clinical investigators to efficiently perform parameter sensitivity analysis and auto-tuning for algorithms that segment and classify image features in a large dataset of high-resolution images. The computational cost of the sensitivity analysis process can be very high, because the process requires processing the input dataset several times to systematically evaluate how output varies when input parameters are varied. Thus, high performance computing techniques are required to quickly execute the sensitivity analysis process. Results: We carried out an empirical evaluation of the proposed method on high performance computing clusters with multi-core CPUs and co-processors (GPUs and Intel Xeon Phis). Our results show that (1) the framework achieves excellent scalability and efficiency on a high performance computing cluster -- execution efficiency remained above 85% in all experiments; (2) the parameter auto-tuning methods are able to converge by visiting only a small fraction (0.0009%) of the search space with limited impact to the algorithm output (0.56% on average). Conclusions: The sensitivity analysis framework provides a range of strategies for the efficient exploration of the parameter space, as well as multiple indexes to evaluate the effect of parameter modification to outputs or even correlation between parameters. Our work demonstrates the feasibility of performing sensitivity analyses, parameter studies, and auto-tuning with large datasets with the use of high-performance systems and techniques. The proposed technologies will enable the quantification of error estimations and output variations in these pipelines, which may be used in application specific ways to assess uncertainty of conclusions extracted from data generated by these image analysis pipelines.

cs.DC↗

arXiv2015

Performance Analysis and Efficient Execution on Systems with multi-core CPUs, GPUs and MICs

We carry out a comparative performance study of multi-core CPUs, GPUs and Intel Xeon Phi (Many Integrated Core - MIC) with a microscopy image analysis application. We experimentally evaluate the performance of computing devices on core operations of the application. We correlate the observed performance with the characteristics of computing devices and data access patterns, computation complexities, and parallelization forms of the operations. The results show a significant variability in the performance of operations with respect to the device used. The performances of operations with regular data access are comparable or sometimes better on a MIC than that on a GPU. GPUs are more efficient than MICs for operations that access data irregularly, because of the lower bandwidth of the MIC for random data accesses. We propose new performance-aware scheduling strategies that consider variabilities in operation speedups. Our scheduling strategies significantly improve application performance compared to classic strategies in hybrid configurations.

cs.DC↗

arXiv2014

Region Templates: Data Representation and Management for Large-Scale Image Analysis

Distributed memory machines equipped with CPUs and GPUs (hybrid computing nodes) are hard to program because of the multiple layers of memory and heterogeneous computing configurations. In this paper, we introduce a region template abstraction for the efficient management of common data types used in analysis of large datasets of high resolution images on clusters of hybrid computing nodes. The region template provides a generic container template for common data structures, such as points, arrays, regions, and object sets, within a spatial and temporal bounding box. The region template abstraction enables different data management strategies and data I/O implementations, while providing a homogeneous, unified interface to the application for data storage and retrieval. The execution of region templates applications is coordinated by a runtime system that supports efficient execution in hybrid machines. Region templates applications are represented as hierarchical dataflow in which each computing stage may be represented as another dataflow of finer-grain tasks. A number of optimizations for hybrid machines are available in our runtime system, including performance-aware scheduling for maximizing utilization of computing devices and techniques to reduce impact of data transfers between CPUs and GPUs. An experimental evaluation on a state-of-the-art hybrid cluster using a microscopy imaging study shows that this abstraction adds negligible overhead (about 3%) and achieves good scalability.

cs.DC↗

arXiv2013

Comparative Performance Analysis of Intel Xeon Phi, GPU, and CPU

We investigate and characterize the performance of an important class of operations on GPUs and Many Integrated Core (MIC) architectures. Our work is motivated by applications that analyze low-dimensional spatial datasets captured by high resolution sensors, such as image datasets obtained from whole slide tissue specimens using microscopy image scanners. We identify the data access and computation patterns of operations in object segmentation and feature computation categories. We systematically implement and evaluate the performance of these core operations on modern CPUs, GPUs, and MIC systems for a microscopy image analysis application. Our results show that (1) the data access pattern and parallelization strategy employed by the operations strongly affect their performance. While the performance on a MIC of operations that perform regular data access is comparable or sometimes better than that on a GPU; (2) GPUs are significantly more efficient than MICs for operations and algorithms that irregularly access data. This is a result of the low performance of the latter when it comes to random data access; (3) adequate coordinated execution on MICs and CPUs using a performance aware task scheduling strategy improves about 1.29x over a first-come-first-served strategy. The example application attained an efficiency of 84% in an execution with of 192 nodes (3072 CPU cores and 192 MICs).

cs.DC↗

arXiv2012

Efficient Irregular Wavefront Propagation Algorithms on Hybrid CPU-GPU Machines

In this paper, we address the problem of efficient execution of a computation pattern, referred to here as the irregular wavefront propagation pattern (IWPP), on hybrid systems with multiple CPUs and GPUs. The IWPP is common in several image processing operations. In the IWPP, data elements in the wavefront propagate waves to their neighboring elements on a grid if a propagation condition is satisfied. Elements receiving the propagated waves become part of the wavefront. This pattern results in irregular data accesses and computations. We develop and evaluate strategies for efficient computation and propagation of wavefronts using a multi-level queue structure. This queue structure improves the utilization of fast memories in a GPU and reduces synchronization overheads. We also develop a tile-based parallelization strategy to support execution on multiple CPUs and GPUs. We evaluate our approaches on a state-of-the-art GPU accelerated machine (equipped with 3 GPUs and 2 multicore CPUs) using the IWPP implementations of two widely used image processing operations: morphological reconstruction and euclidean distance transform. Our results show significant performance improvements on GPUs. The use of multiple CPUs and GPUs cooperatively attains speedups of 50x and 85x with respect to single core CPU executions for morphological reconstruction and euclidean distance transform, respectively.

cs.DC↗