FAST: framework for heterogeneous medical image computing and visualization

Smistad, Erik; Bozorgi, Mohammadmehdi; Lindseth, Frank

doi:10.1007/s11548-015-1158-5

Cited by 39 publications

(36 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have compared our software package to MeVisLab [32], DeVIDE [33], GRAPE [34], GraphMIC [35], and FAST [4]. While FAST is a stand-alone library for OpenCL-accelerated image manipulation and visualization, the other packages are mainly focused on graph-based image processing and all of these utilize ITK, VTK [36], MITK [37, 38], or a variation of these libraries to perform the computation and rendering tasks.…”

Section: Resultsmentioning

confidence: 99%

“…OpenGL does not come without problems however. GPU drivers are mostly proprietary, each implementing a different interpretation of the OpenGL specification, sometimes exposing implementation differences and bugs [4, 47]. This may affect the core implementation; therefore care has been taken to adhere to the OpenGL 4.5 specification, but some drivers may still cause problems.…”

Section: Discussionmentioning

confidence: 99%

“…The current hardware has much higher capabilities and processing of datasets, which were previously considered as too large, has become common. With the advent of programmable GPUs in the mid-2000s, GPUs are now used to perform general-purpose computations (GPGPU) to process data in parallel, reducing the computational time drastically [4–7]. Although originally designed for graphics applications, the massively parallel design of GPUs allows data processing much more efficiently than is typically possible with traditional CPUs, while at the same time reducing the hardware footprint to the size of a graphics card.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Instant Feedback Rapid Prototyping for GPU-Accelerated Computation, Manipulation, and Visualization of Multidimensional Data

Malek

Sensen

2018

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

Objective We have created an open-source application and framework for rapid GPU-accelerated prototyping, targeting image analysis, including volumetric images such as CT or MRI data. Methods A visual graph editor enables the design of processing pipelines without programming. Run-time compiled compute shaders enable prototyping of complex operations in a matter of minutes. Results GPU-acceleration increases processing the speed by at least an order of magnitude when compared to traditional multithreaded CPU-based implementations, while offering the flexibility of scripted implementations. Conclusion Our framework enables real-time, intuition-guided accelerated algorithm and method development, supported by built-in scriptable visualization. Significance This is, to our knowledge, the first tool for medical data analysis that provides both high performance and rapid prototyping. As such, it has the potential to act as a force multiplier for further research, enabling handling of high-resolution datasets while providing quasi-instant feedback and visualization of results.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Instant Feedback Rapid Prototyping for GPU-Accelerated Computation, Manipulation, and Visualization of Multidimensional Data

Malek

Sensen

2018

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

show abstract

“…Caffe [7] was used as the underlying framework both for training and testing of the classifier, while the vessel candidate search was implemented with the FAST medical image computing framework [11].…”

Section: Vessel Classifiermentioning

confidence: 99%

Vessel Detection in Ultrasound Images Using Deep Convolutional Neural Networks

Smistad

Løvstakken

2016

Deep Learning and Data Labeling for Medical Applications

Self Cite

View full text Add to dashboard Cite

Abstract. Deep convolutional neural networks have achieved great results on image classification problems. In this paper, a new method using a deep convolutional neural network for detecting blood vessels in Bmode ultrasound images is presented. Automatic blood vessel detection may be useful in medical applications such as deep venous thrombosis detection, anesthesia guidance and catheter placement. The proposed method is able to determine the position and size of the vessels in images in real-time. 12,804 subimages of the femoral region from 15 subjects were manually labeled. Leave-one-subject-out cross validation was used giving an average accuracy of 94.5%, a major improvement from previous methods which had an accuracy of 84% on the same dataset. The method was also validated on a dataset of the carotid artery to show that the method can generalize to blood vessels on other regions of the body. The accuracy on this dataset was 96%.

show abstract

“…ImageCL has been designed to work with the FAST framework. FAST allows the user to connect filters to form image processing pipelines, which can be executed on heterogeneous systems.…”

Section: Introductionmentioning

confidence: 99%

ImageCL: Language and source‐to‐source compiler for performance portability, load balancing, and scalability prediction on heterogeneous systems

Falch

Elster

2017

Concurrency and Computation

View full text Add to dashboard Cite

SummaryApplications written for heterogeneous CPU-GPU systems often suffer from poor performance portability. Finding good work partitions can also be challenging as different devices are suited for different applications.This article describes ImageCL, a high-level domain-specific language and source-to-source compiler, targeting single system as well as distributed heterogeneous hardware. Initially targeting image processing algorithms, our framework now also handles general stencil-based operations. It resembles OpenCL, but abstracts away performance optimization details which instead are handled by our source-to-source compiler. Machine learning-based auto-tuning is used to determine which optimizations to apply. For the distributed case, by measuring performance counters on a small input on one device, previously trained performance models are used to predict the throughput of the application on multiple different devices, making it possible to balance the load evenly.Models for the communication overhead are created in a similar fashion and used to predict the optimal number of nodes to use.ImageCL outperforms other state-of-the-art solutions on image processing benchmarks in several cases, achieving speedups of up to 4.57×. On both CPUs and GPUs we are only 3% and 2% slower than an oracle for load balancing and scalability prediction, respectively, using synthetic benchmarks.

show abstract

FAST: framework for heterogeneous medical image computing and visualization

Abstract: FAST enables efficient medical image computing and visualization on heterogeneous systems. Code examples and performance evaluations have demonstrated that the toolkit is both easy to use and performs better than existing frameworks, such as ITK and VTK.

Cited by 39 publications

References 15 publications

Instant Feedback Rapid Prototyping for GPU-Accelerated Computation, Manipulation, and Visualization of Multidimensional Data

Instant Feedback Rapid Prototyping for GPU-Accelerated Computation, Manipulation, and Visualization of Multidimensional Data

Vessel Detection in Ultrasound Images Using Deep Convolutional Neural Networks

ImageCL: Language and source‐to‐source compiler for performance portability, load balancing, and scalability prediction on heterogeneous systems

Contact Info

Product

Resources

About