Hyperspectral imaging benchmark based on machine learning for intraoperative brain tumour detection.

Brain surgery is one of the most common and effective treatments for brain tumour. However, neurosurgeons face the challenge of determining the boundaries of the tumour to achieve maximum resection, while avoiding damage to normal tissue that may cause neurological sequelae to patients. Hyperspectral (HS) imaging (HSI) has shown remarkable results as a diagnostic tool for tumour detection in different medical applications. In this work, we demonstrate, with a robust k-fold cross-validation approach, that HSI combined with the proposed processing framework is a promising intraoperative tool for in-vivo identification and delineation of brain tumours, including both primary (high-grade and low-grade) and secondary tumours. Analysis of the in-vivo brain database, consisting of 61 HS images from 34 different patients, achieve a highest median macro F1-Score result of 70.2 ± 7.9% on the test set using both spectral and spatial information. Here, we provide a benchmark based on machine learning for further developments in the field of in-vivo brain tumour detection and delineation using hyperspectral imaging to be used as a real-time decision support tool during neurosurgical workflows.

VNIR-NIR hyperspectral imaging fusion targeting intraoperative brain cancer detection.

Currently, intraoperative guidance tools used for brain tumor resection assistance during surgery have several limitations. Hyperspectral (HS) imaging is arising as a novel imaging technique that could offer new capabilities to delineate brain tumor tissue in surgical-time. However, the HS acquisition systems have some limitations regarding spatial and spectral resolution depending on the spectral range to be captured. Image fusion techniques combine information from different sensors to obtain an HS cube with improved spatial and spectral resolution. This paper describes the contributions to HS image fusion using two push-broom HS cameras, covering the visual and near-infrared (VNIR) [400-1000 nm] and near-infrared (NIR) [900-1700 nm] spectral ranges, which are integrated into an intraoperative HS acquisition system developed to delineate brain tumor tissue during neurosurgical procedures. Both HS images were registered using intensity-based and feature-based techniques with different geometric transformations to perform the HS image fusion, obtaining an HS cube with wide spectral range [435-1638 nm]. Four HS datasets were captured to verify the image registration and the fusion process. Moreover, segmentation and classification methods were evaluated to compare the performance results between the use of the VNIR and NIR data, independently, with respect to the fused data. The results reveal that the proposed methodology for fusing VNIR-NIR data improves the classification results up to 21% of accuracy with respect to the use of each data modality independently, depending on the targeted classification problem.

Ozone therapy versus surgery for lumbar disc herniation: A randomized double-blind controlled trial.

OBJECTIVES: Surgery is the treatment of choice for symptomatic disc herniation after conservative management. Several studies have suggested the potential utility of intradiscal ozone infiltration in this pathology. The aim of this trial was to compare intradiscal ozone infiltration vs. oxygen infiltration vs. surgery. DESIGN AND INTERVENTIONS: This was a randomized, double-blinded, and controlled trial in patients on a waiting list for herniated disc surgery. There were three treatment groups: surgery; intradiscal ozone infiltration (plus foraminal infiltration of ozone, steroids, and anesthetic); intradiscal oxygen infiltration (plus foraminal infiltration of oxygen, steroids, and anesthetic). MAIN OUTCOME MEASURES: The requirements for surgery. RESULTS: Five years after the treatment of the last recruited patient (median follow-up: 78 months), the requirement for further surgery was 20 % for patients in the ozone group and 60 % for patients in the oxygen group. 11 % of patients initially treated with surgery also required a second surgery. Compared to the surgery group, the ozone group showed: 1) significantly lower number of inpatient days: median 3 days (interquartile range: 3-3.5 days) vs. 0 days (interquartile range: 0-1.5 days), p = 0.012; 2) significantly lower costs: median EUR 3702 (interquartile range: EUR 3283-7630) vs. EUR 364 (interquartile range: EUR 364-2536), p = 0.029. CONCLUSIONS: Our truncated trial showed that intradiscal ozone infiltrations decreased the requirements for conventional surgery, resulting in decreased hospitalization durations and associated costs. These findings and their magnitude are of interest to patients and health services providers. Further validation is ongoing.

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

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.

Surgical Aid Visualization System for Glioblastoma Tumor Identification based on Deep Learning and In-Vivo Hyperspectral Images of Human Patients.

Brain cancer surgery has the goal of performing an accurate resection of the tumor and preserving as much as possible the quality of life of the patient. There is a clinical need to develop non-invasive techniques that can provide reliable assistance for tumor resection in real-time during surgical procedures. Hyperspectral imaging (HSI) arises as a new, noninvasive and non-ionizing technique that can assist neurosurgeons during this difficult task. In this paper, we explore the use of deep learning (DL) techniques for processing hyperspectral (HS) images of in-vivo human brain tissue. We developed a surgical aid visualization system capable of offering guidance to the operating surgeon to achieve a successful and accurate tumor resection. The employed HS database is composed of 26 in-vivo hypercubes from 16 different human patients, among which 258,810 labelled pixels were used for evaluation. The proposed DL methods achieve an overall accuracy of 95% and 85% for binary and multiclass classifications, respectively. The proposed visualization system is able to generate a classification map that is formed by the combination of the DL map and an unsupervised clustering via a majority voting algorithm. This map can be adjusted by the operating surgeon to find the suitable configuration for the current situation during the surgical procedure.

Deep Learning-Based Framework for In Vivo Identification of Glioblastoma Tumor using Hyperspectral Images of Human Brain.

The main goal of brain cancer surgery is to perform an accurate resection of the tumor, preserving as much normal brain tissue as possible for the patient. The development of a non-contact and label-free method to provide reliable support for tumor resection in real-time during neurosurgical procedures is a current clinical need. Hyperspectral imaging is a non-contact, non-ionizing, and label-free imaging modality that can assist surgeons during this challenging task without using any contrast agent. In this work, we present a deep learning-based framework for processing hyperspectral images of in vivo human brain tissue. The proposed framework was evaluated by our human image database, which includes 26 in vivo hyperspectral cubes from 16 different patients, among which 258,810 pixels were labeled. The proposed framework is able to generate a thematic map where the parenchymal area of the brain is delineated and the location of the tumor is identified, providing guidance to the operating surgeon for a successful and precise tumor resection. The deep learning pipeline achieves an overall accuracy of 80% for multiclass classification, improving the results obtained with traditional support vector machine (SVM)-based approaches. In addition, an aid visualization system is presented, where the final thematic map can be adjusted by the operating surgeon to find the optimal classification threshold for the current situation during the surgical procedure.

Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations.

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.

An Intraoperative Visualization System Using Hyperspectral Imaging to Aid in Brain Tumor Delineation.

Hyperspectral imaging (HSI) allows for the acquisition of large numbers of spectral bands throughout the electromagnetic spectrum (within and beyond the visual range) with respect to the surface of scenes captured by sensors. Using this information and a set of complex classification algorithms, it is possible to determine which material or substance is located in each pixel. The work presented in this paper aims to exploit the characteristics of HSI to develop a demonstrator capable of delineating tumor tissue from brain tissue during neurosurgical operations. Improved delineation of tumor boundaries is expected to improve the results of surgery. The developed demonstrator is composed of two hyperspectral cameras covering a spectral range of 400-1700 nm. Furthermore, a hardware accelerator connected to a control unit is used to speed up the hyperspectral brain cancer detection algorithm to achieve processing during the time of surgery. A labeled dataset comprised of more than 300,000 spectral signatures is used as the training dataset for the supervised stage of the classification algorithm. In this preliminary study, thematic maps obtained from a validation database of seven hyperspectral images of in vivo brain tissue captured and processed during neurosurgical operations demonstrate that the system is able to discriminate between normal and tumor tissue in the brain. The results can be provided during the surgical procedure (~1 min), making it a practical system for neurosurgeons to use in the near future to improve excision and potentially improve patient outcomes.

Spinal cord stimulation as adjuvant during chemotherapy and reirradiation treatment of recurrent high-grade gliomas.

AIMS: Relapsed high-grade gliomas (HGGs) have poor prognoses and there is no standard treatment. HGGs have ischemia/hypoxia associated and, as such, drugs and oxygen have low access, with increased resistance to chemotherapy and radiotherapy. Tumor hypoxia modification can improve outcomes and overall survival in some patients with these tumors. In previous works, we have described that cervical spinal cord stimulation can modify tumor microenvironment in HGG by increasing tumor blood flow, oxygenation, and metabolism. The aim of this current, preliminary, nonrandomized, study was to assess the clinical effect of spinal cord stimulation during brain reirradiation and chemotherapy deployed for the treatment of recurrent HGG; the hypothesis being that an improvement in oxygenated blood supply would facilitate enhanced delivery of the scheduled therapy. MATERIALS AND METHODS: Seven patients had spinal cord stimulation applied during the scheduled reirradiation and chemotherapy for the treatment of recurrent HGG (6 anaplastic gliomas and 1 glioblastoma). Median dose of previous irradiation was 60 Gy (range = 56-72 Gy) and median dose of reirradiation was 46 Gy (range = 40-46 Gy). Primary end point of the study was overall survival (OS) following confirmation of HGG relapse. RESULTS: From the time of diagnosis of last tumor relapse before reirradiation, median OS was 39 months (95% CI = 0-93) for the overall study group: 39 months (95% CI = 9-69) for those with anaplastic gliomas and 16 months for the patient with glioblastoma. Posttreatment, doses of corticosteroids was significantly decreased (P = .026) and performance status significantly improved (P = .046). CONCLUSIONS: Spinal cord stimulation during reirradiation and chemotherapy is feasible and well tolerated. In our study, spinal cord stimulation was associated with clinical improvement and longer survival than previously reported in recurrent anaplastic gliomas. Spinal cord stimulation as adjuvant during chemotherapy and reirradiation in relapsed HGGs merits further research.

Psychomotor and executive functioning after unilateral posteroventral pallidotomy in patients with Parkinson's disease.

The goal of the study was to explore the immediate effects of unilateral posteroventral stereotactic pallidotomy (PVP) on psychomotor and executive functioning in patients with Parkinson's disease (PD). The original drawing task, conducted on a digitizing tablet, and neuropsychological tests were administered to 25 patients with PD, 2 or 3 days before and after the surgery. To assess executive functions, the following tests were used: Trail Making Test (TMT), Stroop Colour Interference Test and Wisconsin Card Sorting Test (WCST). To evaluate global mental functioning, Mini Mental State Examination (MMSE) was applied. Benton Visual Retention Test (BVRT) was introduced as a control non-executive task. The patients undergoing a surgery were compared with age and education matched healthy and PD controls. PVP resulted in an increased movability of the upper contralateral limbs reflected in larger average pressure put during the drawing task after the surgery. Assessment of the emotional state showed a significant postoperative improvement. An isolated significant decline of WCST performance, not related to the side of the lesion, was observed immediately after the surgery. The performance of the other executive and non-executive tasks remained unchanged. The results showed that unilateral PVP may lead to immediate selective executive impairment and is needed to be explored in further studies.

[Stereotactic pallidotomy and thalamotomy in the treatment of primary dystonia]. / Leczenie dystonii pierwotnej stereotaktyczna palidotomia i talamotomia.

BACKGROUND AND PURPOSE: The goal of the study was to assess the results of the stereotactic pallidotomy and thalamotomy in the treatment of primary dystonia. MATERIAL AND METHODS: Thirty patients with primary dystonia underwent twenty-eight stereotactic pallidotomies and twenty two thalamotomies. The operations were based on the fused images of computed tomography and magnetic resonance imaging, and were verified by an intraoperative neurophysiological investigation. Neurological and neuropsychological assessments were performed before surgery and at 3 days, 3 and 6 months after the operation. The Mann-Whitney U test was used to find out statistic differences between subgroups and the Wilcoxon test to compare results between particular assessments. RESULTS: The statistic analysis showed postsurgical amelioration of the neurological state lasting at least 6 months. A better long-term outcome was revealed in the subgroup of pallidotomies vs. thalamotomies, in the subgroup with the onset of dystonia after the age of 35 vs. earlier onset, and in the subgroup of the focal and local dystonia vs. generalized dystonia. The statistically significant improvement was achieved at a depression level and the statistically significant deterioration was not stated in the mental status after the operations. A very low percentage of neurological complications after the operations was found in the study. CONCLUSIONS: The stereotactic pallidotomies and thalamotomies are effective and safe options in the treatment of the intractable cases of primary dystonia. Both resulted predominantly in contralateral improvement of motor functions. However, the results of pallidotomies are better than thalamotomies six months after the surgery. The improvement of the mood without cognitive deterioration was revealed in the neuropsychological tests after the operations. Only few, persistent and mild complications were ascertained in the study.

[Early postoperative assessment of cognitive functions after stereotactic pallidotomy in patients with primary dystonia - preliminary results]. / Ocena funkcji poznawczych pacjentów z dystonia pierwotna we wczesnym okresie po operacji palidotomii stereotaktycznej - doniesienie wstepne.

BACKGROUND AND PURPOSE: The newest studies notify that globus pallidus, besides the motor control, plays an important role in cognitive functioning of: memory, attention, linguistic skills, visuospatial ability, and executive functions. Stereotactic pallidotomy (the lesion of the motor region of the globus pallidus) is one of the surgery options that is used in the treatment of the primary dystonia. Motor region is located in the postero-ventral part of the internal globus pallidus. The goal of the study was to assess of the influence of pallidotomy on cognitive functioning in the group of patients suffering from the primary dystonia. MATERIAL AND METHODS: Eighteen patients diagnosed with primary dystonia were treated by stereotactic pallidotomy and they were investigated neuropsychologically. The study was performed between March 2004 and February 2005. Neuropsychological assessment was conducted 1-2 days prior to operation and 2 days following the surgery. The clinical course of the cognitive functions and emotional status were assessed by the following neuropsychological tests: Mini Mental State Examination (MMSE), Trail Making Test A and B (TMT A and B), Stroop Color-Word Interference Test, N-back Test, Auditory Verbal Learning Test (AVLT), Benton Visual Retention Test (BVRT), Wisconsin Card Sorting Test (WCST), Beck Depression Inventory (BDI), Montgomery-Asberg Depression Rating Scale (MADRS). RESULTS: The statistically significant differences have been obtained between the results before and after the surgery in the depression scales: BDI (p<0.02) and in MADRS (p<0.01). None of the neuropsychological tests revealed significant differences between the results before and after the surgery. The only trend (p=0.06-0.07) was noted between results of AVLT before and after the surgery. The average results were worse after the surgery in the first, fifth and sixth attempt of the reply. CONCLUSIONS: Stereotactic pallidotomy has not significantly changed cognitive functions in the patients suffering from primary dystonia. Whereas, the emotional state has significantly improved in consequence of the applying surgery. Stereotactic pallidotomy in primary dystonia seems to be a treatment option safe for the patients' cognitive functions.