Parallel Implementations Assessment of a Spatial-Spectral Classifier for Hyperspectral Clinical Applications
TL;DR: A comparison between the performances provided by five different HPC platforms while processing a spatial-spectral approach to classify HS images, assessing their main benefits and drawbacks is presented.
Abstract: Hyperspectral (HS) imaging presents itself as a non-contact, non-ionizing and non-invasive technique, proven to be suitable for medical diagnosis. However, the volume of information contained in these images makes difficult providing the surgeon with information about the boundaries in real-time. To that end, High-Performance-Computing (HPC) platforms become necessary. This paper presents a comparison between the performances provided by five different HPC platforms while processing a spatial-spectral approach to classify HS images, assessing their main benefits and drawbacks. To provide a complete study, two different medical applications, with two different requirements, have been analyzed. The first application consists of HS images taken from neurosurgical operations; the second one presents HS images taken from dermatological interventions. While the main constraint for neurosurgical applications is the processing time, in other environments, as the dermatological one, other requirements can be considered. In that sense, energy efficiency is becoming a major challenge, since this kind of applications are usually developed as hand-held devices, thus depending on the battery capacity. These requirements have been considered to choose the target platforms: on the one hand, three of the most powerful Graphic Processing Units (GPUs) available in the market; and, on the other hand, a low-power GPU and a manycore architecture, both specifically thought for being used in battery-dependent environments.
Citations
More filters
TL;DR: A parallel pipeline for skin cancer detection that exploits hyperspectral imaging is presented and experimental results show that a hybrid parallel approach is capable of classifying an image of 50 × 50 pixels with 125 bands in less than 1 s.
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.
12 citations
TL;DR: A clustering-inspired active learning method for enhancing the HSI classification result and can be effectively generalized to unlabeled samples in the testing set after being fine tuned-based on the augmented training set.
Abstract: Deep neural networks (DNNs) have promoted much of the recent progress in hyperspectral image (HSI) classification, which depends on extensive labeled samples and deep network structure and has achieved surprisingly good generalization capacity. However, due to the expensive labeling cost, the labeled samples are scarce in most practice cases, which causes these DNN-based methods to be prone to over-fitting and influences the classification result. To mitigate this problem, we present a clustering-inspired active learning method for enhancing the HSI classification result, which mainly contributes to two aspects. On one hand, the modified clustering by fast search and find of peaks clustering method is utilized to select highly informative and diverse samples from unlabeled samples in the candidate set for manual labeling, which empowers us to appropriately augment the limited training set (i.e., labeled samples) and thus improves the generalization capacity of the baseline DNN model. On the other hand, another K-means clustering-based pseudo-labeling scheme is utilized to pre-train the DNN model with all samples in the candidate set. By doing this, the pre-trained model can be effectively generalized to unlabeled samples in the testing set after being fine tuned-based on the augmented training set. The experiment accuracies on two benchmark HSI datasets show the effectiveness of the proposed method.
11 citations
TL;DR: GoRG as discussed by the authors is a GPU-accelerated multiview depth estimation tool for HS images also able to process YUV images in less than 5.5 s on average.
Abstract: HyperSpectral (HS) images have been successfully used for brain tumor boundary detection during resection operations. Nowadays, these classification maps coexist with other technologies such as MRI or IOUS that improve a neurosurgeon's action, with their incorporation being a neurosurgeon's task. The project in which this work is framed generates an unified and more accurate 3D immersive model using HS, MRI, and IOUS information. To do so, the HS images need to include 3D information and it needs to be generated in real-time operating room conditions, around a few seconds. This work presents Graph cuts Reference depth estimation in GPU (GoRG), a GPU-accelerated multiview depth estimation tool for HS images also able to process YUV images in less than 5.5 s on average. Compared to a high-quality SoA algorithm, MPEG DERS, GoRG YUV obtain quality losses of -0.93 dB, -0.6 dB, and -1.96% for WS-PSNR, IV-PSNR, and VMAF, respectively, using a video synthesis processing chain. For HS test images, GoRG obtains an average RMSE of 7.5 cm, with most of its errors in the background, needing around 850 ms to process one frame and view. These results demonstrate the feasibility of using GoRG during a tumor resection operation.
5 citations
01 Aug 2022
TL;DR: In this paper , the authors proposed a novel hyperspectral image classification architecture exploiting Vision Transformers, which outperformed the state-of-the-art both in terms of false negative rates and of processing times.
Abstract: In recent years, hyperspectral imaging has been employed in several medical applications, targeting automatic diagnosis of different diseases. These images showed good performance in identifying different types of cancers. Among the methods used for classification, machine learning and deep learning techniques emerged as the most suitable algorithms to handle these data. In this paper, we propose a novel hyperspectral image classification architecture exploiting Vision Transformers. We validated the method on a real hyperspectral dataset containing 76 skin cancer images. Obtained results clearly highlight that the Vision Transforms are a suitable architecture for this task. Measured results outperform the state-of-the-art both in terms of false negative rates and of processing times. Finally, the attention mechanism is evaluated for the first time on medical hyperspectral images.
TL;DR: In this article , the authors presented the rationale and a detailed clinical paradigm for establishing microneurosurgical HSI guidance, which aimed to facilitate the related standards, medical device regulations, and value-based medical imaging systems.
References
More filters
TL;DR: This paper addresses the problem of the classification of hyperspectral remote sensing images by support vector machines by understanding and assessing the potentialities of SVM classifiers in hyperdimensional feature spaces and concludes that SVMs are a valid and effective alternative to conventional pattern recognition approaches.
Abstract: This paper addresses the problem of the classification of hyperspectral remote sensing images by support vector machines (SVMs) First, we propose a theoretical discussion and experimental analysis aimed at understanding and assessing the potentialities of SVM classifiers in hyperdimensional feature spaces Then, we assess the effectiveness of SVMs with respect to conventional feature-reduction-based approaches and their performances in hypersubspaces of various dimensionalities To sustain such an analysis, the performances of SVMs are compared with those of two other nonparametric classifiers (ie, radial basis function neural networks and the K-nearest neighbor classifier) Finally, we study the potentially critical issue of applying binary SVMs to multiclass problems in hyperspectral data In particular, four different multiclass strategies are analyzed and compared: the one-against-all, the one-against-one, and two hierarchical tree-based strategies Different performance indicators have been used to support our experimental studies in a detailed and accurate way, ie, the classification accuracy, the computational time, the stability to parameter setting, and the complexity of the multiclass architecture The results obtained on a real Airborne Visible/Infrared Imaging Spectroradiometer hyperspectral dataset allow to conclude that, whatever the multiclass strategy adopted, SVMs are a valid and effective alternative to conventional pattern recognition approaches (feature-reduction procedures combined with a classification method) for the classification of hyperspectral remote sensing data
3,607 citations
"Parallel Implementations Assessment..." refers background in this paper
...hyperplane–, the criterion applied is to maximize the distance between the classes that it is distinguishing [29]....
[...]
TL;DR: In this paper, the authors present two approaches for obtaining class probabilities, which can be reduced to linear systems and are easy to implement, and show conceptually and experimentally that the proposed approaches are more stable than the two existing popular methods: voting and the method by Hastie and Tibshirani (1998).
Abstract: Pairwise coupling is a popular multi-class classification method that combines all comparisons for each pair of classes. This paper presents two approaches for obtaining class probabilities. Both methods can be reduced to linear systems and are easy to implement. We show conceptually and experimentally that the proposed approaches are more stable than the two existing popular methods: voting and the method by Hastie and Tibshirani (1998)
1,888 citations
TL;DR: An overview of the literature on medical hyperspectral imaging technology and its applications is presented, an introduction for those new to the field, an overview for those working in the field and a reference for those searching for literature on a specific application are presented.
Abstract: Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery. HSI acquires a three-dimensional dataset called hypercube, with two spatial dimensions and one spectral dimension. Spatially resolved spectral imaging obtained by HSI provides diagnostic information about the tissue physiology, morphology, and composition. This review paper presents an overview of the literature on medical hyperspectral imaging technology and its applications. The aim of the survey is threefold: an introduction for those new to the field, an overview for those working in the field, and a reference for those searching for literature on a specific application.
1,605 citations
TL;DR: This paper assesses performance of regularized radial basis function neural networks (Reg-RBFNN), standard support vector machines (SVMs), kernel Fisher discriminant (KFD) analysis, and regularized AdaBoost (reg-AB) in the context of hyperspectral image classification.
Abstract: This paper presents the framework of kernel-based methods in the context of hyperspectral image classification, illustrating from a general viewpoint the main characteristics of different kernel-based approaches and analyzing their properties in the hyperspectral domain. In particular, we assess performance of regularized radial basis function neural networks (Reg-RBFNN), standard support vector machines (SVMs), kernel Fisher discriminant (KFD) analysis, and regularized AdaBoost (Reg-AB). The novelty of this work consists in: 1) introducing Reg-RBFNN and Reg-AB for hyperspectral image classification; 2) comparing kernel-based methods by taking into account the peculiarities of hyperspectral images; and 3) clarifying their theoretical relationships. To these purposes, we focus on the accuracy of methods when working in noisy environments, high input dimension, and limited training sets. In addition, some other important issues are discussed, such as the sparsity of the solutions, the computational burden, and the capability of the methods to provide outputs that can be directly interpreted as probabilities.
1,428 citations
"Parallel Implementations Assessment..." refers background in this paper
...In that sense, Support Vector Machines (SVMs) provide robust classification performance when the number of training samples is limited [23], which is common in medical applications [24]....
[...]
...The latter aims to generate a classification model to identify the pixels in relation with different elements –commonly known as classes– existing within the image and to depict the boundaries among these classes in the feature space, hence assigning a class to each pixel of the image [23]....
[...]
TL;DR: In this paper, the differences between multispectral and hyperspectral data, spatial and spectral resolutions, and applications of multisensor imagery in water resource studies are discussed.
Abstract: Multispectral imagery has been used as the data source for water and land observational remote sensing from airborne and satellite systems since the early 1960s. Over the past two decades, advances in sensor technology have made it possible for the collection of several hundred spectral bands. This is commonly referred to as hyperspectral imagery. This review details the differences between multispectral and hyperspectral data; spatial and spectral resolutions and focuses on the application of hyperspectral imagery in water resource studies and, in particular the classification and mapping of land uses and vegetation.
440 citations
"Parallel Implementations Assessment..." refers background in this paper
...this technology was originally aimed at remote sensing applications [2], nowadays it has spread to several research...
[...]