Hardware accelerated segmentation of CT images for adaptive radiotherapy

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

Research output: Contribution to conferenceAbstract

Abstract

Radiotherapy aims to kill cancer cells by exposing them to radiation. Changes in the position, size and shape of organs between the acquisition of images used to plan the treatment and the treatment delivery can compromise accuracy. Currently, images acquired at the time of treatment are compared to the planning images by clinical staff to ensure that the accuracy of the treatment is within acceptable limits. Adaptive radiotherapy seeks to improve the accuracy of radiotherapy by using images acquired at the time of treatment to adapt the original plan. The image processing and dose calculation steps required to automatically adapt the treatment cannot currently be performed fast enough to make them clinically viable. Hardware acceleration of these algorithms has the potential to make automatic adaptive radiotherapy a clinical possibility.
This paper presents a global thresholding algorithm based on Otsu's method that was used to segment a series of CT images of a test object into three classes. The algorithm was accelerated by implementing sections of it using reconfigurable hardware in the form of a field programmable gate array (FPGA). The execution time of this implementation was compared to implementations running on an ARM Cortex-A9 and an Intel Core-i5 central processing unit (CPU). The execution times are shown in table 1. The hardware accelerated implementation was found to execute around sixty times as fast as the un-accelerated algorithm. The implementation running on the more powerful Intel CPU was also found to run around 14% slower than the hardware accelerated version. This work has served as a proof of principle, exhibiting the increases in performance possible by implementing image processing algorithms using dedicated hardware resources. It is intended to extend this work by implementing more complex algorithms and applying these to images used in the treatment of bladder cancer patients.

Conference

ConferenceSINAPSE Annual Scientific Meeting 2016
CountryUnited Kingdom
CityStirling
Period17/06/16 → …
Internet address

Fingerprint

Radiotherapy
Hardware
Program processors
Image processing
Therapeutics
Reconfigurable hardware
Organ Size
Field programmable gate arrays (FPGA)
Urinary Bladder Neoplasms
Cells
Radiation
Planning
Neoplasms

Keywords

  • adaptive radiotherapy
  • global  thresholding algorithm 
  • cancer treatment
  • CT image

Cite this

Robinson, F., Crockett, L., Nailon, B., Stewart, B., & McLaren, D. (2016). Hardware accelerated segmentation of CT images for adaptive radiotherapy. Abstract from SINAPSE Annual Scientific Meeting 2016, Stirling, United Kingdom.
Robinson, Fraser ; Crockett, Louise ; Nailon, Bill ; Stewart, Bob ; McLaren, Duncan. / Hardware accelerated segmentation of CT images for adaptive radiotherapy. Abstract from SINAPSE Annual Scientific Meeting 2016, Stirling, United Kingdom.1 p.
@conference{0a887e9be8cf4159ae9ccfb0ef1a3f27,
title = "Hardware accelerated segmentation of CT images for adaptive radiotherapy",
abstract = "Radiotherapy aims to kill cancer cells by exposing them to radiation. Changes in the position, size and shape of organs between the acquisition of images used to plan the treatment and the treatment delivery can compromise accuracy. Currently, images acquired at the time of treatment are compared to the planning images by clinical staff to ensure that the accuracy of the treatment is within acceptable limits. Adaptive radiotherapy seeks to improve the accuracy of radiotherapy by using images acquired at the time of treatment to adapt the original plan. The image processing and dose calculation steps required to automatically adapt the treatment cannot currently be performed fast enough to make them clinically viable. Hardware acceleration of these algorithms has the potential to make automatic adaptive radiotherapy a clinical possibility.This paper presents a global thresholding algorithm based on Otsu's method that was used to segment a series of CT images of a test object into three classes. The algorithm was accelerated by implementing sections of it using reconfigurable hardware in the form of a field programmable gate array (FPGA). The execution time of this implementation was compared to implementations running on an ARM Cortex-A9 and an Intel Core-i5 central processing unit (CPU). The execution times are shown in table 1. The hardware accelerated implementation was found to execute around sixty times as fast as the un-accelerated algorithm. The implementation running on the more powerful Intel CPU was also found to run around 14{\%} slower than the hardware accelerated version. This work has served as a proof of principle, exhibiting the increases in performance possible by implementing image processing algorithms using dedicated hardware resources. It is intended to extend this work by implementing more complex algorithms and applying these to images used in the treatment of bladder cancer patients.",
keywords = "adaptive radiotherapy, global  thresholding algorithm , cancer treatment, CT image",
author = "Fraser Robinson and Louise Crockett and Bill Nailon and Bob Stewart and Duncan McLaren",
year = "2016",
month = "6",
day = "17",
language = "English",
note = "SINAPSE Annual Scientific Meeting 2016 ; Conference date: 17-06-2016",
url = "http://www.sinapse.ac.uk/events/2016-sinapse-asm",

}

Robinson, F, Crockett, L, Nailon, B, Stewart, B & McLaren, D 2016, 'Hardware accelerated segmentation of CT images for adaptive radiotherapy' SINAPSE Annual Scientific Meeting 2016, Stirling, United Kingdom, 17/06/16, .

Hardware accelerated segmentation of CT images for adaptive radiotherapy. / Robinson, Fraser; Crockett, Louise; Nailon, Bill; Stewart, Bob; McLaren, Duncan.

2016. Abstract from SINAPSE Annual Scientific Meeting 2016, Stirling, United Kingdom.

Research output: Contribution to conferenceAbstract

TY - CONF

T1 - Hardware accelerated segmentation of CT images for adaptive radiotherapy

AU - Robinson, Fraser

AU - Crockett, Louise

AU - Nailon, Bill

AU - Stewart, Bob

AU - McLaren, Duncan

PY - 2016/6/17

Y1 - 2016/6/17

N2 - Radiotherapy aims to kill cancer cells by exposing them to radiation. Changes in the position, size and shape of organs between the acquisition of images used to plan the treatment and the treatment delivery can compromise accuracy. Currently, images acquired at the time of treatment are compared to the planning images by clinical staff to ensure that the accuracy of the treatment is within acceptable limits. Adaptive radiotherapy seeks to improve the accuracy of radiotherapy by using images acquired at the time of treatment to adapt the original plan. The image processing and dose calculation steps required to automatically adapt the treatment cannot currently be performed fast enough to make them clinically viable. Hardware acceleration of these algorithms has the potential to make automatic adaptive radiotherapy a clinical possibility.This paper presents a global thresholding algorithm based on Otsu's method that was used to segment a series of CT images of a test object into three classes. The algorithm was accelerated by implementing sections of it using reconfigurable hardware in the form of a field programmable gate array (FPGA). The execution time of this implementation was compared to implementations running on an ARM Cortex-A9 and an Intel Core-i5 central processing unit (CPU). The execution times are shown in table 1. The hardware accelerated implementation was found to execute around sixty times as fast as the un-accelerated algorithm. The implementation running on the more powerful Intel CPU was also found to run around 14% slower than the hardware accelerated version. This work has served as a proof of principle, exhibiting the increases in performance possible by implementing image processing algorithms using dedicated hardware resources. It is intended to extend this work by implementing more complex algorithms and applying these to images used in the treatment of bladder cancer patients.

AB - Radiotherapy aims to kill cancer cells by exposing them to radiation. Changes in the position, size and shape of organs between the acquisition of images used to plan the treatment and the treatment delivery can compromise accuracy. Currently, images acquired at the time of treatment are compared to the planning images by clinical staff to ensure that the accuracy of the treatment is within acceptable limits. Adaptive radiotherapy seeks to improve the accuracy of radiotherapy by using images acquired at the time of treatment to adapt the original plan. The image processing and dose calculation steps required to automatically adapt the treatment cannot currently be performed fast enough to make them clinically viable. Hardware acceleration of these algorithms has the potential to make automatic adaptive radiotherapy a clinical possibility.This paper presents a global thresholding algorithm based on Otsu's method that was used to segment a series of CT images of a test object into three classes. The algorithm was accelerated by implementing sections of it using reconfigurable hardware in the form of a field programmable gate array (FPGA). The execution time of this implementation was compared to implementations running on an ARM Cortex-A9 and an Intel Core-i5 central processing unit (CPU). The execution times are shown in table 1. The hardware accelerated implementation was found to execute around sixty times as fast as the un-accelerated algorithm. The implementation running on the more powerful Intel CPU was also found to run around 14% slower than the hardware accelerated version. This work has served as a proof of principle, exhibiting the increases in performance possible by implementing image processing algorithms using dedicated hardware resources. It is intended to extend this work by implementing more complex algorithms and applying these to images used in the treatment of bladder cancer patients.

KW - adaptive radiotherapy

KW - global  thresholding algorithm 

KW - cancer treatment

KW - CT image

M3 - Abstract

ER -

Robinson F, Crockett L, Nailon B, Stewart B, McLaren D. Hardware accelerated segmentation of CT images for adaptive radiotherapy. 2016. Abstract from SINAPSE Annual Scientific Meeting 2016, Stirling, United Kingdom.