Dataset Information

Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging.

ABSTRACT: Hyperspectral imaging (HSI) is a non-ionizing and non-contact imaging technique capable of obtaining more information than conventional RGB (red green blue) imaging. In the medical field, HSI has commonly been investigated due to its great potential for diagnostic and surgical guidance purposes. However, the large amount of information provided by HSI normally contains redundant or non-relevant information, and it is extremely important to identify the most relevant wavelengths for a certain application in order to improve the accuracy of the predictions and reduce the execution time of the classification algorithm. Additionally, some wavelengths can contain noise and removing such bands can improve the classification stage. The work presented in this paper aims to identify such relevant spectral ranges in the visual-and-near-infrared (VNIR) region for an accurate detection of brain cancer using in vivo hyperspectral images. A methodology based on optimization algorithms has been proposed for this task, identifying the relevant wavelengths to achieve the best accuracy in the classification results obtained by a supervised classifier (support vector machines), and employing the lowest possible number of spectral bands. The results demonstrate that the proposed methodology based on the genetic algorithm optimization slightly improves the accuracy of the tumor identification in ~5%, using only 48 bands, with respect to the reference results obtained with 128 bands, offering the possibility of developing customized acquisition sensors that could provide real-time HS imaging. The most relevant spectral ranges found comprise between 440.5-465.96 nm, 498.71-509.62 nm, 556.91-575.1 nm, 593.29-615.12 nm, 636.94-666.05 nm, 698.79-731.53 nm and 884.32-902.51 nm.

SUBMITTER: Martinez B

PROVIDER: S-EPMC6961052 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging.

Martinez Beatriz B Leon Raquel R Fabelo Himar H Ortega Samuel S Piñeiro Juan F JF Szolna Adam A Hernandez Maria M Espino Carlos C J O'Shanahan Aruma A Carrera David D Bisshopp Sara S Sosa Coralia C Marquez Mariano M Camacho Rafael R Plaza Maria de la Luz ML Morera Jesus J M Callico Gustavo G

Sensors (Basel, Switzerland) 20191212 24

Hyperspectral imaging (HSI) is a non-ionizing and non-contact imaging technique capable of obtaining more information than conventional RGB (red green blue) imaging. In the medical field, HSI has commonly been investigated due to its great potential for diagnostic and surgical guidance purposes. However, the large amount of information provided by HSI normally contains redundant or non-relevant information, and it is extremely important to identify the most relevant wavelengths for a certain app ...[more]

PMID: 31842410

Similar Datasets

Project description:Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal brain by these tumors makes their accurate identification by the naked eye difficult. Since surgery is the common treatment for brain cancer, an accurate radical resection of the tumor leads to improved survival rates for patients. However, the identification of the tumor boundaries during surgery is challenging. Hyperspectral imaging is a non-contact, non-ionizing and non-invasive technique suitable for medical diagnosis. This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor. The algorithm proposed in this study to approach an efficient solution consists of a hybrid framework that combines both supervised and unsupervised machine learning methods. Firstly, a supervised pixel-wise classification using a Support Vector Machine classifier is performed. The generated classification map is spatially homogenized using a one-band representation of the HS cube, employing the Fixed Reference t-Stochastic Neighbors Embedding dimensional reduction algorithm, and performing a K-Nearest Neighbors filtering. The information generated by the supervised stage is combined with a segmentation map obtained via unsupervised clustering employing a Hierarchical K-Means algorithm. The fusion is performed using a majority voting approach that associates each cluster with a certain class. To evaluate the proposed approach, five hyperspectral images of surface of the brain affected by glioblastoma tumor in vivo from five different patients have been used. The final classification maps obtained have been analyzed and validated by specialists. These preliminary results are promising, obtaining an accurate delineation of the tumor area.

Project description:IntroductionMelanoma diagnosis traditionally relies on microscopic examination of hematoxylin and eosin (H&E) slides by dermatopathologists to search for specific architectural and cytological features. Unfortunately, no single molecular marker exists to reliably differentiate melanoma from benign lesions such as nevi. This study explored the potential of autofluorescent molecules within tissues to provide molecular fingerprints indicative of degenerated melanocytes in melanoma.MethodsUsing hyperspectral imaging (HSI) and spectral phasor analysis, we investigated autofluorescence patterns in melanoma compared to intradermal nevi. Using UV excitation and a commercial spectral confocal microscope, we acquired label-free HSI data from the whole-slice samples.ResultsOur findings revealed distinct spectral phasor distributions between melanoma and intradermal nevi, with melanoma displaying a broader phasor phase distribution, signifying a more heterogeneous autofluorescence pattern. Notably, longer wavelengths associated with larger phases correlated with regions identified as melanoma by expert dermatopathologists using H&E staining. Quantitative analysis of phase and modulation histograms within the phasor clusters of five melanomas (with Breslow thicknesses ranging from 0.5 mm to 6 mm) and five intradermal nevi consistently highlighted differences between the two groups. We further demonstrated the potential for the discrimination of several melanocytic lesions using center-of-mass comparisons of phase and modulation variables. Remarkably, modulation versus phase center of mass comparisons revealed strong statistical significance among the groups. Additionally, we identified the molecular endogenous markers responsible for tissue autofluorescence, including collagen, elastin, NADH, FAD, and melanin. In melanoma, autofluorescence is characterized by a higher phase contribution, indicating an increase in FAD and melanin in melanocyte nests. In contrast, NADH, elastin, and collagen dominate the autofluorescence of the nevus.DiscussionThis work underscores the potential of autofluorescence and HSI-phasor analysis as valuable tools for quantifying tissue molecular fingerprints, thereby supporting more effective and quantitative melanoma diagnosis.

Dataset Information

Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging.

Publications

Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets