Techniques of medical image processing and analysis accelerated by high-performance computing: a systematic literature review

Abstract

Techniques of medical image processing and analysis play a crucial role in many clinical scenarios, including in diagnosis and treatment planning. However, immense quantities of data and high complexity of the algorithms often used are computationally demanding. As a result, there now exists a wide range of techniques of medical image processing and analysis that require the application of high-performance computing solutions in order to reduce the required runtime. The main purpose of this review is to provide a comprehensive reference source of techniques of medical image processing and analysis that have been accelerated by high-performance computing solutions. With this in mind, the articles available in the Scopus and Web of Science electronic repositories were searched. Subsequently, the most relevant articles found were individually analyzed in order to identify: (a) the metrics used to evaluate computing performance, (b) the high-performance computing solution used, (c) the parallel design adopted, and (d) the task of medical image processing and analysis involved. Hence, the techniques of medical image processing and analysis found were identified, reviewed, and discussed, particularly in terms of computational performance. Consequently, the techniques reviewed herein present the progress made so far in reducing the computational runtime involved, and the difficulties and challenges that remain to be overcome.

A CUDA-powered method for the feature extraction and unsupervised analysis of medical images

“…In order to collect statistically sound results and take into consideration the variability and heterogeneity typically characterizing medical images, we randomly selected 30 images from 3 different patients (10 per patient) affected by brain metastases and 30 images from 3 different patients affected by ovarian cancer. We tested both the CPU and GPU versions by considering various window sizes, that is, ∈ {3, 7, 11, 15, 19, 23, 27, 31} , as well as two different intensity levels (i.e., 2 8 and 2 16 ). For each combination of and intensity levels, we also enabled and disabled the GLCM symmetry to evaluate how the symmetry affects the running time.…”

“…HaraliCU exploits an effective and efficient encoding, to mitigate the memory requirements related to the allocation of a GLCM having 2 16 rows and columns for each sliding window, and to the size of each GLCM, which is strictly related to the number of different gray levels inside the considered sliding window. Such an encoding removes all zero elements inside the GLCM and consists in storing each GLCM in a list-based data structure where each element is a pair ⟨ , ⟩ , with being a couple ⟨i, j⟩ of gray levels and the corresponding frequency of the considered sliding window.…”

“…In this work, we extract the following 16 Haralick features [18,19], which are then considered for the unsupervised learning [42]: angular second moment, autocorrelation, cluster prominence, cluster shade, contrast, difference entropy, difference variance, dissimilarity, entropy, homogeneity, inverse difference moment, maximum probability, sum of average, sum of entropy, sum of squares, sum of variance.…”

“…The use of high-performance computing (HPC) is gaining ground in high-dimensional imaging data processing [16], as in the context of hyperspectral image processing [5,35] and medical image analysis [12]. In particular, for the specific case of medical imaging, along with the acceleration of the training of deep neural networks [47], graphics processing unit (GPU)-powered implementations allowed for real-time performance in image reconstruction [46,59], segmentation [2], as well as feature extraction [42] and classification [22].…”

GPU Accelerated Image Processing in CCD-Based Neutron Imaging

“…Furthermore, a fast image-processing work-flow allows scientist to perform dynamic measuring rows and to directly assure the quality of the acquired images on-site. Especially in medical imaging in the X-ray domain, GPU based image processing is well established and has shown potential for speed increase in several orders of magnitudes [5]. Noise reduction is an important first step of all image pipelines and therefore chosen as an example in this work.…”