GPU acceleration of liver enhancement for tumor segmentation

Nitin Satpute; Rabia Naseem; Egidijus Pelanis; Juan Gómez-Luna; Faouzi Alaya Cheikh; Ole Jakob Elle; Joaquín Olivares

doi:10.1016/j.cmpb.2019.105285

GPU acceleration of liver enhancement for tumor segmentation

Comput Methods Programs Biomed. 2020 Feb:184:105285. doi: 10.1016/j.cmpb.2019.105285. Epub 2019 Dec 17.

Authors

Nitin Satpute¹, Rabia Naseem², Egidijus Pelanis³, Juan Gómez-Luna⁴, Faouzi Alaya Cheikh², Ole Jakob Elle⁵, Joaquín Olivares⁶

Affiliations

¹ Department of Electronic and Computer Engineering, Universidad de Córdoba, Spain. Electronic address: el2sasan@uco.es.
² Norwegian Colour and Visual Computing Lab, Norwegian University of Science and Technology, Norway.
³ The Intervention Centre, Oslo University Hospital, Oslo, Norway; The Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Oslo, Norway.
⁴ Department of Computer Science, ETH Zurich, Switzerland.
⁵ The Intervention Centre, Oslo University Hospital, Oslo, Norway; The Department of Informatics, The Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway.
⁶ Department of Electronic and Computer Engineering, Universidad de Córdoba, Spain.

PMID: 31896055
DOI: 10.1016/j.cmpb.2019.105285

Abstract

Background and objective: Medical image segmentation plays a vital role in medical image analysis. There are many algorithms developed for medical image segmentation which are based on edge or region characteristics. These are dependent on the quality of the image. The contrast of a CT or MRI image plays an important role in identifying region of interest i.e. lesion(s). In order to enhance the contrast of image, clinicians generally use manual histogram adjustment technique which is based on 1D histogram specification. This is time consuming and results in poor distribution of pixels over the image. Cross modality based contrast enhancement is 2D histogram specification technique. This is robust and provides a more uniform distribution of pixels over CT image by exploiting the inner structure information from MRI image. This helps in increasing the sensitivity and accuracy of lesion segmentation from enhanced CT image. The sequential implementation of cross modality based contrast enhancement is slow. Hence we propose GPU acceleration of cross modality based contrast enhancement for tumor segmentation.

Methods: The aim of this study is fast parallel cross modality based contrast enhancement for CT liver images. This includes pairwise 2D histogram, histogram equalization and histogram matching. The sequential implementation of the cross modality based contrast enhancement is computationally expensive and hence time consuming. We propose persistence and grid-stride loop based fast parallel contrast enhancement for CT liver images. We use enhanced CT liver image for the lesion or tumor segmentation. We implement the fast parallel gradient based dynamic seeded region growing for lesion segmentation.

Results: The proposed parallel approach is 104.416 ( ± 5.166) times faster compared to the sequential implementation and increases the sensitivity and specificity of tumor segmentation.

Conclusion: The cross modality approach is inspired by 2D histogram specification which incorporates spatial information existing in both guidance and input images for remapping the input image intensity values. The cross modality based liver contrast enhancement improves the quality of tumor segmentation.

Keywords: 2D Histogram matching; Contrast enhancement; GPU; Image segmentation.

MeSH terms

Contrast Media
Humans
Image Enhancement / methods*
Liver / diagnostic imaging*
Magnetic Resonance Imaging / methods*
Tomography, X-Ray Computed / methods*

Substances

Contrast Media