Hardware acceleration of automated 4DCT analysis

Fraser Robinson, Louise Crockett, Bill Nailon, Bob Stewart, Duncan McLaren

Research output: Contribution to conferenceAbstract

Abstract

Background -- Stereotactic ablative radiotherapy (SABR) requires cancerous lesions to be more accurately targeted than conventional techniques. The time interval in which a treatment fraction is delivered precludes manual delineation of the gross tumour volume (GTV) and organs at risk (OAR) to correct for intrafraction motion. However, automatic segmentation techniques may be able to achieve this.

The runtime performance of image analysis algorithms can benefit from implementation on appropriate hardware architectures. Field Programmable Gate Arrays (FPGA), which contain customisable hardware, have the potential to enable real-time image processing.

Aims/Objectives -- The aim of this study was to develop an FPGA-based approach for automatic image segmentation of 4DCT scans. The performance of the algorithm was assessed in terms of the accuracy of the segmentation and the runtime performance.

Methods/Results -- The segmentation algorithm was based on Otsu’s method and measured the range of motion of a phantom in eight 4DCT scans. The algorithm was implemented on an FPGA-based platform and a CPU to compare the runtime performance.

The detected range of motion was accurate in seven cases and in the eighth case, was inaccurate by the CT slice thickness.

The FPGA-based implementation executed in 14.8ms, around 14% faster than on the CPU.

Conclusions -- This study demonstrates the ability of hardware-accelerated image processing algorithms to aid radiotherapy. This work detected ranges of motion of a phantom, but could be extended to consider clinical imaging data.
It is intended to extend this work by using the FPGA device to accelerate algorithms to perform real-time adaptive radiotherapy.

Seminar

Seminar6th Annual Scientific Meeting of the Scottish Radiotherapy Research Forum
Abbreviated titleScoRRF 2017
CountryUnited Kingdom
CityStirling
Period2/11/172/11/17
Internet address

Fingerprint

Field programmable gate arrays (FPGA)
Hardware
Radiotherapy
Program processors
Image processing
Medical imaging
Image segmentation
Image analysis
Tumors

Keywords

  • radiotherapy
  • medical image processing
  • Stereotactic ablative radiotherapy
  • SABR

Cite this

Robinson, F., Crockett, L., Nailon, B., Stewart, B., & McLaren, D. (2017). Hardware acceleration of automated 4DCT analysis. Abstract from 6th Annual Scientific Meeting of the Scottish Radiotherapy Research Forum, Stirling, United Kingdom.
Robinson, Fraser ; Crockett, Louise ; Nailon, Bill ; Stewart, Bob ; McLaren, Duncan. / Hardware acceleration of automated 4DCT analysis. Abstract from 6th Annual Scientific Meeting of the Scottish Radiotherapy Research Forum, Stirling, United Kingdom.
@conference{b3b52c07576240919129e63f37dccc2d,
title = "Hardware acceleration of automated 4DCT analysis",
abstract = "Background -- Stereotactic ablative radiotherapy (SABR) requires cancerous lesions to be more accurately targeted than conventional techniques. The time interval in which a treatment fraction is delivered precludes manual delineation of the gross tumour volume (GTV) and organs at risk (OAR) to correct for intrafraction motion. However, automatic segmentation techniques may be able to achieve this.The runtime performance of image analysis algorithms can benefit from implementation on appropriate hardware architectures. Field Programmable Gate Arrays (FPGA), which contain customisable hardware, have the potential to enable real-time image processing.Aims/Objectives -- The aim of this study was to develop an FPGA-based approach for automatic image segmentation of 4DCT scans. The performance of the algorithm was assessed in terms of the accuracy of the segmentation and the runtime performance.Methods/Results -- The segmentation algorithm was based on Otsu’s method and measured the range of motion of a phantom in eight 4DCT scans. The algorithm was implemented on an FPGA-based platform and a CPU to compare the runtime performance.The detected range of motion was accurate in seven cases and in the eighth case, was inaccurate by the CT slice thickness.The FPGA-based implementation executed in 14.8ms, around 14{\%} faster than on the CPU.Conclusions -- This study demonstrates the ability of hardware-accelerated image processing algorithms to aid radiotherapy. This work detected ranges of motion of a phantom, but could be extended to consider clinical imaging data.It is intended to extend this work by using the FPGA device to accelerate algorithms to perform real-time adaptive radiotherapy.",
keywords = "radiotherapy, medical image processing, Stereotactic ablative radiotherapy, SABR",
author = "Fraser Robinson and Louise Crockett and Bill Nailon and Bob Stewart and Duncan McLaren",
year = "2017",
month = "11",
day = "2",
language = "English",
note = "6th Annual Scientific Meeting of the Scottish Radiotherapy Research Forum, ScoRRF 2017 ; Conference date: 02-11-2017 Through 02-11-2017",
url = "https://www.gla.ac.uk/events/conferences/scorrf/",

}

Robinson, F, Crockett, L, Nailon, B, Stewart, B & McLaren, D 2017, 'Hardware acceleration of automated 4DCT analysis' 6th Annual Scientific Meeting of the Scottish Radiotherapy Research Forum, Stirling, United Kingdom, 2/11/17 - 2/11/17, .

Hardware acceleration of automated 4DCT analysis. / Robinson, Fraser; Crockett, Louise; Nailon, Bill; Stewart, Bob; McLaren, Duncan.

2017. Abstract from 6th Annual Scientific Meeting of the Scottish Radiotherapy Research Forum, Stirling, United Kingdom.

Research output: Contribution to conferenceAbstract

TY - CONF

T1 - Hardware acceleration of automated 4DCT analysis

AU - Robinson, Fraser

AU - Crockett, Louise

AU - Nailon, Bill

AU - Stewart, Bob

AU - McLaren, Duncan

PY - 2017/11/2

Y1 - 2017/11/2

N2 - Background -- Stereotactic ablative radiotherapy (SABR) requires cancerous lesions to be more accurately targeted than conventional techniques. The time interval in which a treatment fraction is delivered precludes manual delineation of the gross tumour volume (GTV) and organs at risk (OAR) to correct for intrafraction motion. However, automatic segmentation techniques may be able to achieve this.The runtime performance of image analysis algorithms can benefit from implementation on appropriate hardware architectures. Field Programmable Gate Arrays (FPGA), which contain customisable hardware, have the potential to enable real-time image processing.Aims/Objectives -- The aim of this study was to develop an FPGA-based approach for automatic image segmentation of 4DCT scans. The performance of the algorithm was assessed in terms of the accuracy of the segmentation and the runtime performance.Methods/Results -- The segmentation algorithm was based on Otsu’s method and measured the range of motion of a phantom in eight 4DCT scans. The algorithm was implemented on an FPGA-based platform and a CPU to compare the runtime performance.The detected range of motion was accurate in seven cases and in the eighth case, was inaccurate by the CT slice thickness.The FPGA-based implementation executed in 14.8ms, around 14% faster than on the CPU.Conclusions -- This study demonstrates the ability of hardware-accelerated image processing algorithms to aid radiotherapy. This work detected ranges of motion of a phantom, but could be extended to consider clinical imaging data.It is intended to extend this work by using the FPGA device to accelerate algorithms to perform real-time adaptive radiotherapy.

AB - Background -- Stereotactic ablative radiotherapy (SABR) requires cancerous lesions to be more accurately targeted than conventional techniques. The time interval in which a treatment fraction is delivered precludes manual delineation of the gross tumour volume (GTV) and organs at risk (OAR) to correct for intrafraction motion. However, automatic segmentation techniques may be able to achieve this.The runtime performance of image analysis algorithms can benefit from implementation on appropriate hardware architectures. Field Programmable Gate Arrays (FPGA), which contain customisable hardware, have the potential to enable real-time image processing.Aims/Objectives -- The aim of this study was to develop an FPGA-based approach for automatic image segmentation of 4DCT scans. The performance of the algorithm was assessed in terms of the accuracy of the segmentation and the runtime performance.Methods/Results -- The segmentation algorithm was based on Otsu’s method and measured the range of motion of a phantom in eight 4DCT scans. The algorithm was implemented on an FPGA-based platform and a CPU to compare the runtime performance.The detected range of motion was accurate in seven cases and in the eighth case, was inaccurate by the CT slice thickness.The FPGA-based implementation executed in 14.8ms, around 14% faster than on the CPU.Conclusions -- This study demonstrates the ability of hardware-accelerated image processing algorithms to aid radiotherapy. This work detected ranges of motion of a phantom, but could be extended to consider clinical imaging data.It is intended to extend this work by using the FPGA device to accelerate algorithms to perform real-time adaptive radiotherapy.

KW - radiotherapy

KW - medical image processing

KW - Stereotactic ablative radiotherapy

KW - SABR

M3 - Abstract

ER -

Robinson F, Crockett L, Nailon B, Stewart B, McLaren D. Hardware acceleration of automated 4DCT analysis. 2017. Abstract from 6th Annual Scientific Meeting of the Scottish Radiotherapy Research Forum, Stirling, United Kingdom.