Parallel Classification Pipelines for Skin Cancer Detection Exploiting Hyperspectral Imaging on Hybrid Systems

Abstract

The early detection of skin cancer is of crucial importance to plan an effective therapy to treat the lesion. In routine medical practice, the diagnosis is based on the visual inspection of the lesion and it relies on the dermatologists’ expertise. After a first examination, the dermatologist may require a biopsy to confirm if the lesion is malignant or not. This methodology suffers from false positives and negatives issues, leading to unnecessary surgical procedures. Hyperspectral imaging is gaining relevance in this medical field since it is a non-invasive and non-ionizing technique, capable of providing higher accuracy than traditional imaging methods. Therefore, the development of an automatic classification system based on hyperspectral images could improve the medical practice to distinguish pigmented skin lesions from malignant, benign, and atypical lesions. Additionally, the system can assist general practitioners in first aid care to prevent noncritical lesions from reaching dermatologists, thereby alleviating the workload of medical specialists. In this paper is presented a parallel pipeline for skin cancer detection that exploits hyperspectral imaging. The computational times of the serial processing have been reduced by adopting multicore and many-core technologies, such as OpenMP and CUDA paradigms. Different parallel approaches have been combined, leading to the development of fifteen classification pipeline versions. Experimental results using in-vivo hyperspectral images show that a hybrid parallel approach is capable of classifying an image of 50 × 50 pixels with 125 bands in less than 1 s.

An all‐inclusive computer‐aided melanoma diagnosis based on soft computing

“…The effectiveness of the proposed procedure is compared with some various approaches from the literature, 43 including Nahata's, 44 Jain's, 45 Zhang's, 46 Kumar's, 47 and Torti's. 48 Table 6 specifies the behavior evaluation of the suggested approach compared with other mentioned approaches on the before-mentioned measurement indicators. Figure 5 demonstrates the bar plot of the melanoma diagnosis by the suggested approach and other comparative approaches from the literature.…”

“…The analyses were performed using five measurement indicators including specificity, accuracy, NPV, PPV, and sensitivity. These formulations are as follows: The effectiveness of the proposed procedure is compared with some various approaches from the literature, 43 including Nahata's, 44 Jain's, 45 Zhang's, 46 Kumar's, 47 and Torti's 48 . Table 6 specifies the behavior evaluation of the suggested approach compared with other mentioned approaches on the before‐mentioned measurement indicators.…”

Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images

“…HS data pre-processing was performed to standardize the spectral signature among different patients and acquisitions due to possible variations in illumination conditions [ 12 , 14 , 22 ]. First, two reference images were captured before recording the skin lesions: a white reference image ( ) was acquired, captured from a white reference tile able to reflect 99% of the incident light, and a dark reference image ( ) was recorded when the light was turned off and the camera shutter was closed.…”

“…Hyperspectral (HS) images measure the reflected or transmitted light from the captured scene, collecting light–matter interaction values associated with several wavelengths of the electromagnetic spectrum range with low to high spatial resolution. HS images comprise multiple images aligned in adjacent narrow wavelengths, forming a reflectance spectrum of all the pixels [ 11 , 12 , 13 , 14 ]. Thus, the outcome is a HS cube, which contains both the spatial and the spectral information from the sample under analysis.…”

Hardware Architectures for Real-Time Medical Imaging

“…Torti et al presented a parallel pipeline for skin cancer detection that exploits hyperspectral imaging [72]. They showed how adopting multicore and many-core technologies, such as OpenMP and CUDA paradigms, and combining them led to a significant reduction in computational times, showing that a hybrid parallel approach can classify hyperspectral images in less than 1 s.…”