Diagnosis of Brain Tumors

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Pathology and Molecular Diagnostics".

Deadline for manuscript submissions: closed (30 June 2023) | Viewed by 40972

Special Issue Editor


E-Mail Website
Guest Editor
Neurochirurgia Infantile, Fondazione Policlinico Universitario A. Gemelli IRCCS, Università Cattolica del Sacro Cuore, Largo Agostino Gemelli 8, 00168 Roma, Italy
Interests: pediatric neurosurgery; brain tumors; hydrocephalus; epilepsy; craniosynostosis; Chiari malformations

Special Issue Information

Dear Colleagues, 

Brain tumors still raise great interest because of the continuously increasing number of diagnoses and their challenging management. In children, they account for the second cause of mortality for malignancy after blood cancers (or even for the first cause, in some Countries). In adults, metastasis from extracranial primary tumors, high-grade gliomas and meningiomas represent a very common problem to deal with in daily clinical practice. On these grounds, many efforts are being carried out to enhance the basic and clinical research, neurosurgical techniques and technologies and, of course, the clinical, pathological and radiological diagnoses. 

This Special Issue is focused on the advances on the diagnosis of brain tumors. Actually, the better the diagnosis, the higher the possibility to face these neoplasms. It is about a “deep breath” project encompassing all the spectrum of the diagnostic process and techniques, both in children and adults. With regard to basic research, studies on tumor biology and genetics as well as on biomarkers and proteomics are stimulated. As far as the clinical research is concerned, studies on the neuropsychological assessment of neuro-oncologic patients (especially in the COVID era) and on the neurosurgical techniques for brain biopsy are welcome. Finally, a relevant space will be devoted to the advances in “purely” diagnostic branches such as the histopathology and the neuroimaging. Both high-quality original or review articles are accepted. The goal of this issue, indeed, is to provide the readers a rich update of the diagnosis of brain tumors.

Dr. Luca Massimi
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • brain tumors
  • brain surgery
  • biopsy
  • neurosurgery
  • neuroimaging
  • pathology
  • genomics
  • radiomics
  • proteomics
  • medulloblastoma
  • ependymoma
  • gliomas
  • glioblastoma
  • meningioma

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (15 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

21 pages, 729 KiB  
Article
Enhancing Prediction of Brain Tumor Classification Using Images and Numerical Data Features
by Oumaima Saidani, Turki Aljrees, Muhammad Umer, Nazik Alturki, Amal Alshardan, Sardar Waqar Khan, Shtwai Alsubai and Imran Ashraf
Diagnostics 2023, 13(15), 2544; https://doi.org/10.3390/diagnostics13152544 - 31 Jul 2023
Cited by 7 | Viewed by 2588
Abstract
Brain tumors, along with other diseases that harm the neurological system, are a significant contributor to global mortality. Early diagnosis plays a crucial role in effectively treating brain tumors. To distinguish individuals with tumors from those without, this study employs a combination of [...] Read more.
Brain tumors, along with other diseases that harm the neurological system, are a significant contributor to global mortality. Early diagnosis plays a crucial role in effectively treating brain tumors. To distinguish individuals with tumors from those without, this study employs a combination of images and data-based features. In the initial phase, the image dataset is enhanced, followed by the application of a UNet transfer-learning-based model to accurately classify patients as either having tumors or being normal. In the second phase, this research utilizes 13 features in conjunction with a voting classifier. The voting classifier incorporates features extracted from deep convolutional layers and combines stochastic gradient descent with logistic regression to achieve better classification results. The reported accuracy score of 0.99 achieved by both proposed models shows its superior performance. Also, comparing results with other supervised learning algorithms and state-of-the-art models validates its performance. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

10 pages, 2554 KiB  
Article
Intraoperative MRI Assessment of the Tissue Damage during Laser Ablation of Hypothalamic Hamartoma
by Sophie Lombardi, Domenico Tortora, Stefania Picariello, Sniya Sudhakar, Enrico De Vita, Kshitij Mankad, Sophia Varadkar, Alessandro Consales, Lino Nobili, Jessica Cooper, Martin M. Tisdall and Felice D’Arco
Diagnostics 2023, 13(14), 2331; https://doi.org/10.3390/diagnostics13142331 - 10 Jul 2023
Viewed by 1850
Abstract
Laser ablation for treatment of hypothalamic hamartoma (HH) is a minimally invasive and effective technique used to destroy hamartomatous tissue and disconnect it from the functioning brain. Currently, the gold standard to evaluate the amount of tissue being “burned” is the use of [...] Read more.
Laser ablation for treatment of hypothalamic hamartoma (HH) is a minimally invasive and effective technique used to destroy hamartomatous tissue and disconnect it from the functioning brain. Currently, the gold standard to evaluate the amount of tissue being “burned” is the use of heat maps during the ablation procedure. However, these maps have low spatial resolution and can be misleading in terms of extension of the tissue damage. The aim of this study is to use different MRI sequences immediately after each laser ablation and correlate the extension of signal changes with the volume of malacic changes in a long-term follow-up scan. During the laser ablation procedure, we imaged the hypothalamic region with high-resolution axial diffusion-weighted images (DWI) and T2-weighted images (T2WI) after each ablation. At the end of the procedure, we also added a post-contrast T1-weighted image (T1WI) of the same region. We then correlated the product of the maximum diameters on axial showing signal changes (acute oedema on T2WI, DWI restriction rim, DWI hypointense core and post-contrast T1WI rim) with the product of the maximum diameters on axial T2WI of the malacic changes in the follow-up scan, both as a fraction of the total area of the hamartoma. The area of the hypointense core on DWI acquired immediately after the laser ablation statistically correlated better with the final area of encephalomalacia, while the T2WI, hyperintense oedema, DWI rim and T1WI rim of enhancement tended to overestimate the encephalomalacic damage. In conclusion, the use of intraoperative sequences (in particular DWI) during laser ablation can give surgeons valuable information in real time about the effective heating damage on the hamartomatous tissue, with better spatial resolution in comparison to the thermal maps. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

22 pages, 1830 KiB  
Article
ETISTP: An Enhanced Model for Brain Tumor Identification and Survival Time Prediction
by Shah Hussain, Shahab Haider, Sarmad Maqsood, Robertas Damaševičius, Rytis Maskeliūnas and Muzammil Khan
Diagnostics 2023, 13(8), 1456; https://doi.org/10.3390/diagnostics13081456 - 18 Apr 2023
Cited by 9 | Viewed by 2018
Abstract
Technology-assisted diagnosis is increasingly important in healthcare systems. Brain tumors are a leading cause of death worldwide, and treatment plans rely heavily on accurate survival predictions. Gliomas, a type of brain tumor, have particularly high mortality rates and can be further classified as [...] Read more.
Technology-assisted diagnosis is increasingly important in healthcare systems. Brain tumors are a leading cause of death worldwide, and treatment plans rely heavily on accurate survival predictions. Gliomas, a type of brain tumor, have particularly high mortality rates and can be further classified as low- or high-grade, making survival prediction challenging. Existing literature provides several survival prediction models that use different parameters, such as patient age, gross total resection status, tumor size, or tumor grade. However, accuracy is often lacking in these models. The use of tumor volume instead of size may improve the accuracy of survival prediction. In response to this need, we propose a novel model, the enhanced brain tumor identification and survival time prediction (ETISTP), which computes tumor volume, classifies it into low- or high-grade glioma, and predicts survival time with greater accuracy. The ETISTP model integrates four parameters: patient age, survival days, gross total resection (GTR) status, and tumor volume. Notably, ETISTP is the first model to employ tumor volume for prediction. Furthermore, our model minimizes the computation time by allowing for parallel execution of tumor volume computation and classification. The simulation results demonstrate that ETISTP outperforms prominent survival prediction models. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

17 pages, 2061 KiB  
Article
NAMSTCD: A Novel Augmented Model for Spinal Cord Segmentation and Tumor Classification Using Deep Nets
by Ricky Mohanty, Sarah Allabun, Sandeep Singh Solanki, Subhendu Kumar Pani, Mohammed S. Alqahtani, Mohamed Abbas and Ben Othman Soufiene
Diagnostics 2023, 13(8), 1417; https://doi.org/10.3390/diagnostics13081417 - 14 Apr 2023
Cited by 3 | Viewed by 2465
Abstract
Spinal cord segmentation is the process of identifying and delineating the boundaries of the spinal cord in medical images such as magnetic resonance imaging (MRI) or computed tomography (CT) scans. This process is important for many medical applications, including the diagnosis, treatment planning, [...] Read more.
Spinal cord segmentation is the process of identifying and delineating the boundaries of the spinal cord in medical images such as magnetic resonance imaging (MRI) or computed tomography (CT) scans. This process is important for many medical applications, including the diagnosis, treatment planning, and monitoring of spinal cord injuries and diseases. The segmentation process involves using image processing techniques to identify the spinal cord in the medical image and differentiate it from other structures, such as the vertebrae, cerebrospinal fluid, and tumors. There are several approaches to spinal cord segmentation, including manual segmentation by a trained expert, semi-automated segmentation using software tools that require some user input, and fully automated segmentation using deep learning algorithms. Researchers have proposed a wide range of system models for segmentation and tumor classification in spinal cord scans, but the majority of these models are designed for a specific segment of the spine. As a result, their performance is limited when applied to the entire lead, limiting their deployment scalability. This paper proposes a novel augmented model for spinal cord segmentation and tumor classification using deep nets to overcome this limitation. The model initially segments all five spinal cord regions and stores them as separate datasets. These datasets are manually tagged with cancer status and stage based on observations from multiple radiologist experts. Multiple Mask Regional Convolutional Neural Networks (MRCNNs) were trained on various datasets for region segmentation. The results of these segmentations were combined using a combination of VGGNet 19, YoLo V2, ResNet 101, and GoogLeNet models. These models were selected via performance validation on each segment. It was observed that VGGNet-19 was capable of classifying the thoracic and cervical regions, while YoLo V2 was able to efficiently classify the lumbar region, ResNet 101 exhibited better accuracy for sacral-region classification, and GoogLeNet was able to classify the coccygeal region with high performance accuracy. Due to use of specialized CNN models for different spinal cord segments, the proposed model was able to achieve a 14.5% better segmentation efficiency, 98.9% tumor classification accuracy, and a 15.6% higher speed performance when averaged over the entire dataset and compared with various state-of-the art models. This performance was observed to be better, due to which it can be used for various clinical deployments. Moreover, this performance was observed to be consistent across multiple tumor types and spinal cord regions, which makes the model highly scalable for a wide variety of spinal cord tumor classification scenarios. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

17 pages, 5213 KiB  
Article
Application of Drug Testing Platforms in Circulating Tumor Cells and Validation of a Patient-Derived Xenograft Mouse Model in Patient with Primary Intracranial Ependymomas with Extraneural Metastases
by Muh-Lii Liang, Ting-Chi Yeh, Man-Hsu Huang, Pao-Shu Wu, Shih-Pei Wu, Chun-Chao Huang, Tsung-Yu Yen, Wei-Hsin Ting, Jen-Yin Hou, Jia-Yun Huang, Yi-Huei Ding, Jia-Huei Zheng, Hsi-Che Liu, Che-Sheng Ho, Shiu-Jau Chen and Tsung-Han Hsieh
Diagnostics 2023, 13(7), 1232; https://doi.org/10.3390/diagnostics13071232 - 24 Mar 2023
Cited by 1 | Viewed by 2740
Abstract
Primary intracranial ependymoma is a challenging tumor to treat despite the availability of multidisciplinary therapeutic modalities, including surgical resection, radiotherapy, and adjuvant chemotherapy. After the completion of initial treatment, when resistant tumor cells recur, salvage therapy needs to be carried out with a [...] Read more.
Primary intracranial ependymoma is a challenging tumor to treat despite the availability of multidisciplinary therapeutic modalities, including surgical resection, radiotherapy, and adjuvant chemotherapy. After the completion of initial treatment, when resistant tumor cells recur, salvage therapy needs to be carried out with a more precise strategy. Circulating tumor cells (CTCs) have specifically been detected and validated for patients with primary or recurrent diffused glioma. The CTC drug screening platform can be used to perform a mini-invasive liquid biopsy for potential drug selection. The validation of potential drugs in a patient-derived xenograft (PDX) mouse model based on the same patient can serve as a preclinical testing platform. Here, we present the application of a drug testing model in a six-year-old girl with primary ependymoma on the posterior fossa, type A (EPN-PFA). She suffered from tumor recurrence with intracranial and spinal seeding at 2 years after her first operation and extraneural metastases in the pleura, lung, mediastinum, and distant femoral bone at 4 years after initial treatment. The CTC screening platform results showed that everolimus and entrectinib could be used to decrease CTC viability. The therapeutic efficacy of these two therapeutic agents has also been validated in a PDX mouse model from the same patient, and the results showed that these two therapeutic agents significantly decreased tumor growth. After precise drug screening and the combination of focal radiation on the femoral bone with everolimus chemotherapy, the whole-body bone scan showed significant shrinkage of the metastatic tumor on the right femoral bone. This novel approach can combine liquid biopsy, CTC drug testing platforms, and PDX model validation to achieve precision medicine in rare and challenging tumors with extraneural metastases. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

12 pages, 3248 KiB  
Article
Uncertainty-Aware Deep Learning Classification of Adamantinomatous Craniopharyngioma from Preoperative MRI
by Eric W. Prince, Debashis Ghosh, Carsten Görg and Todd C. Hankinson
Diagnostics 2023, 13(6), 1132; https://doi.org/10.3390/diagnostics13061132 - 16 Mar 2023
Cited by 5 | Viewed by 2205
Abstract
Diagnosis of adamantinomatous craniopharyngioma (ACP) is predominantly determined through invasive pathological examination of a neurosurgical biopsy specimen. Clinical experts can distinguish ACP from Magnetic Resonance Imaging (MRI) with an accuracy of 86%, and 9% of ACP cases are diagnosed this way. Classification using [...] Read more.
Diagnosis of adamantinomatous craniopharyngioma (ACP) is predominantly determined through invasive pathological examination of a neurosurgical biopsy specimen. Clinical experts can distinguish ACP from Magnetic Resonance Imaging (MRI) with an accuracy of 86%, and 9% of ACP cases are diagnosed this way. Classification using deep learning (DL) provides a solution to support a non-invasive diagnosis of ACP through neuroimaging, but it is still limited in implementation, a major reason being the lack of predictive uncertainty representation. We trained and tested a DL classifier on preoperative MRI from 86 suprasellar tumor patients across multiple institutions. We then applied a Bayesian DL approach to calibrate our previously published ACP classifier, extending beyond point-estimate predictions to predictive distributions. Our original classifier outperforms random forest and XGBoost models in classifying ACP. The calibrated classifier underperformed our previously published results, indicating that the original model was overfit. Mean values of the predictive distributions were not informative regarding model uncertainty. However, the variance of predictive distributions was indicative of predictive uncertainty. We developed an algorithm to incorporate predicted values and the associated uncertainty to create a classification abstention mechanism. Our model accuracy improved from 80.8% to 95.5%, with a 34.2% abstention rate. We demonstrated that calibration of DL models can be used to estimate predictive uncertainty, which may enable clinical translation of artificial intelligence to support non-invasive diagnosis of brain tumors in the future. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

12 pages, 1370 KiB  
Article
Enhancing the Reliability of Intraoperative Ultrasound in Pediatric Space-Occupying Brain Lesions
by Paolo Frassanito, Vito Stifano, Federico Bianchi, Gianpiero Tamburrini and Luca Massimi
Diagnostics 2023, 13(5), 971; https://doi.org/10.3390/diagnostics13050971 - 3 Mar 2023
Cited by 5 | Viewed by 2293
Abstract
Introduction: Intraoperative ultrasound (IOUS) may aid the resection of space-occupying brain lesions, though technical limits may hinder its reliability. Methods: IOUS (MyLabTwice®, Esaote, Italy) with a microconvex probe was utilized in 45 consecutive cases of children with supratentorial space-occupying lesions aiming [...] Read more.
Introduction: Intraoperative ultrasound (IOUS) may aid the resection of space-occupying brain lesions, though technical limits may hinder its reliability. Methods: IOUS (MyLabTwice®, Esaote, Italy) with a microconvex probe was utilized in 45 consecutive cases of children with supratentorial space-occupying lesions aiming to localize the lesion (pre-IOUS) and evaluate the extent of resection (EOR, post-IOUS). Technical limits were carefully assessed, and strategies to enhance the reliability of real-time imaging were accordingly proposed. Results: Pre-IOUS allowed us to localize the lesion accurately in all of the cases (16 low-grade gliomas, 12 high-grade gliomas, eight gangliogliomas, seven dysembryoplastic neuroepithelial tumors, five cavernomas, and five other lesions, namely two focal cortical dysplasias, one meningioma, one subependymal giant cell astrocytoma, and one histiocytosis). In 10 deeply located lesions, IOUS with hyperechoic marker, eventually coupled with neuronavigation, was useful to plan the surgical route. In seven cases, the administration of contrast ensured a better definition of the vascular pattern of the tumor. Post-IOUS allowed the evaluation of EOR reliably in small lesions (<2 cm). In large lesions (>2 cm) assessing EOR is hindered by the collapsed surgical cavity, especially when the ventricular system is opened, and by artifacts that may simulate or hide residual tumors. The main strategies to overcome the former limit are inflation of the surgical cavity through pressure irrigation while insonating, and closure of the ventricular opening with Gelfoam before insonating. The strategies to overcome the latter are avoiding the use of hemostatic agents before IOUS and insonating through normal adjacent brain instead of corticotomy. These technical nuances enhanced the reliability of post-IOUS, with a total concordance to postoperative MRI. Indeed, the surgical plan was changed in about 30% of cases, as IOUS showed a residual tumor that was left behind. Conclusion: IOUS ensures reliable real-time imaging in the surgery of space-occupying brain lesions. Limits may be overcome with technical nuances and proper training. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

18 pages, 4315 KiB  
Article
Attention Deep Feature Extraction from Brain MRIs in Explainable Mode: DGXAINet
by Burak Taşcı
Diagnostics 2023, 13(5), 859; https://doi.org/10.3390/diagnostics13050859 - 23 Feb 2023
Cited by 13 | Viewed by 4203
Abstract
Artificial intelligence models do not provide information about exactly how the predictions are reached. This lack of transparency is a major drawback. Particularly in medical applications, interest in explainable artificial intelligence (XAI), which helps to develop methods of visualizing, explaining, and analyzing deep [...] Read more.
Artificial intelligence models do not provide information about exactly how the predictions are reached. This lack of transparency is a major drawback. Particularly in medical applications, interest in explainable artificial intelligence (XAI), which helps to develop methods of visualizing, explaining, and analyzing deep learning models, has increased recently. With explainable artificial intelligence, it is possible to understand whether the solutions offered by deep learning techniques are safe. This paper aims to diagnose a fatal disease such as a brain tumor faster and more accurately using XAI methods. In this study, we preferred datasets that are widely used in the literature, such as the four-class kaggle brain tumor dataset (Dataset I) and the three-class figshare brain tumor dataset (Dataset II). To extract features, a pre-trained deep learning model is chosen. DenseNet201 is used as the feature extractor in this case. The proposed automated brain tumor detection model includes five stages. First, training of brain MR images with DenseNet201, the tumor area was segmented with GradCAM. The features were extracted from DenseNet201 trained using the exemplar method. Extracted features were selected with iterative neighborhood component (INCA) feature selector. Finally, the selected features were classified using support vector machine (SVM) with 10-fold cross-validation. An accuracy of 98.65% and 99.97%, were obtained for Datasets I and II, respectively. The proposed model obtained higher performance than the state-of-the-art methods and can be used to aid radiologists in their diagnosis. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

10 pages, 1587 KiB  
Article
A Study on the Role of Intraoperative Corticobulbar Motor Evoked Potentials for Improving Safety of Cerebellopontine Angle Surgery in Elderly Patients
by Quintino Giorgio D’Alessandris, Grazia Menna, Vito Stifano, Giuseppe Maria Della Pepa, Benedetta Burattini, Michele Di Domenico, Alessandro Izzo, Manuela D’Ercole, Liverana Lauretti, Nicola Montano and Alessandro Olivi
Diagnostics 2023, 13(4), 710; https://doi.org/10.3390/diagnostics13040710 - 13 Feb 2023
Cited by 2 | Viewed by 1776
Abstract
Preservation of facial nerve function (FNF) during neurosurgery for cerebellopontine angle (CPA) tumors is paramount in elderly patients. Corticobulbar facial motor evoked potentials (FMEPs) allow assessment intraoperatively of the functional integrity of facial motor pathways, thus improving safety. We aimed to evaluate the [...] Read more.
Preservation of facial nerve function (FNF) during neurosurgery for cerebellopontine angle (CPA) tumors is paramount in elderly patients. Corticobulbar facial motor evoked potentials (FMEPs) allow assessment intraoperatively of the functional integrity of facial motor pathways, thus improving safety. We aimed to evaluate the significance of intraoperative FMEPs in patients 65 years and older. A retrospective cohort of 35 patients undergoing CPA tumors resection was reported; outcomes of patients aged 65–69 years vs. ≥70 years were compared. FMEPs were registered both from upper and lower face muscles, and amplitude ratios (minimum-to-baseline, MBR; final-to-baseline, FBR; and recovery value, FBR minus MBR) were calculated. Overall, 78.8% of patients had a good late (at 1 year) FNF, with no differences between age groups. In patients aged ≥70 years, MBR significantly correlated with late FNF. At receiver operating characteristics (ROC) analysis, in patients aged 65–69 years, FBR (with 50% cut-off value) could reliably predict late FNF. By contrast, in patients aged ≥70 years, the most accurate predictor of late FNF was MBR, with 12.5% cut-off. Thus, FMEPs are a valuable tool for improving safety in CPA surgery in elderly patients as well. Considering literature data, we noticed higher cut-off values for FBR and a role for MBR, which suggests an increased vulnerability of facial nerves in elderly patients compared to younger ones. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

19 pages, 3695 KiB  
Article
An Ensemble Model for the Diagnosis of Brain Tumors through MRIs
by Ehsan Ghafourian, Farshad Samadifam, Heidar Fadavian, Peren Jerfi Canatalay, AmirReza Tajally and Sittiporn Channumsin
Diagnostics 2023, 13(3), 561; https://doi.org/10.3390/diagnostics13030561 - 3 Feb 2023
Cited by 27 | Viewed by 4999
Abstract
Automatic brain tumor detection in MR Images is one of the basic applications of machine vision in medical image processing, which, despite much research, still needs further development. Using multiple machine learning techniques as an ensemble system is one of the solutions that [...] Read more.
Automatic brain tumor detection in MR Images is one of the basic applications of machine vision in medical image processing, which, despite much research, still needs further development. Using multiple machine learning techniques as an ensemble system is one of the solutions that can be effective in achieving this goal. In this paper, a novel method for diagnosing brain tumors by combining data mining and machine learning techniques has been proposed. In the proposed method, each image is initially pre-processed to eliminate its background region and identify brain tissue. The Social Spider Optimization (SSO) algorithm is then utilized to segment the MRI Images. The MRI Images segmentation allows for a more precise identification of the tumor region in the image. In the next step, the distinctive features of the image are extracted using the SVD technique. In addition to removing redundant information, this strategy boosts the speed of the processing at the classification stage. Finally, a combination of the algorithms Naïve Bayes, Support vector machine and K-nearest neighbor is used to classify the extracted features and detect brain tumors. Each of the three algorithms performs feature classification individually, and the final output of the proposed model is created by integrating the three independent outputs and voting the results. The results indicate that the proposed method can diagnose brain tumors in the BRATS 2014 dataset with an average accuracy of 98.61%, sensitivity of 95.79% and specificity of 99.71%. Additionally, the proposed method could diagnose brain tumors in the BTD20 database with an average accuracy of 99.13%, sensitivity of 99% and specificity of 99.26%. These results show a significant improvement compared to previous efforts. The findings confirm that using the image segmentation technique, as well as the ensemble learning, is effective in improving the efficiency of the proposed method. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

11 pages, 1133 KiB  
Article
Pediatric Low-Grade Glioma Surgery with Sodium Fluorescein: Efficient Localization for Removal and Association with Intraoperative Pathological Sampling
by Camilla de Laurentis, Pierre Aurélien Beuriat, Fred Bteich, Carmine Mottolese, Alexandru Szathmari, Matthieu Vinchon and Federico Di Rocco
Diagnostics 2022, 12(12), 2927; https://doi.org/10.3390/diagnostics12122927 - 23 Nov 2022
Cited by 5 | Viewed by 1410
Abstract
Low-grade gliomas are among the most common CNS lesions in pediatrics and surgery is often the first-line treatment. Intraoperative tools have been developed to maximize the results of surgery, and in particular dyes such as sodium fluorescein (SF) have been investigated in high-grade [...] Read more.
Low-grade gliomas are among the most common CNS lesions in pediatrics and surgery is often the first-line treatment. Intraoperative tools have been developed to maximize the results of surgery, and in particular dyes such as sodium fluorescein (SF) have been investigated in high-grade adult lesions. The use of SF in pediatric low-grade gliomas is still unclear. We retrospectively reviewed 22 pediatric CNS low-grade gliomas operated on with SF from September 2021 to October 2022. A total of 86% of lesions showed SF uptake, which was helpful intraoperatively (confirmation of initial localization of the tumor, or identification of tumor remnants) in 74% of them. The intraoperative fluorescence seems associated with gadolinium enhancement at the preoperative MRI. Interestingly, the extemporaneous pathological sampling (EPS) was informative in every case showing SF uptake, whereas in cases without SF uptake, the EPS was non-informative, although the tissue was later confirmed as pathological. These findings highlight the interest of SF for perioperative diagnosis of tumor tissue and may suggest in which cases the differentiation of tumor–healthy tissue could be especially blurred, posing difficulties for the pathologist. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

Review

Jump to: Research

12 pages, 653 KiB  
Review
Citrullination Post-Translational Modification: State of the Art of Brain Tumor Investigations and Future Perspectives
by Diana Valeria Rossetti, Alexandra Muntiu, Luca Massimi, Gianpiero Tamburrini and Claudia Desiderio
Diagnostics 2023, 13(18), 2872; https://doi.org/10.3390/diagnostics13182872 - 7 Sep 2023
Cited by 1 | Viewed by 1468
Abstract
The present review aims to describe the state of the art of research studies investigating the citrullination post-translational modification in adult and pediatric brain tumors. After an introduction to the deimination reaction and its occurrence in proteins and polypeptide chains, the role of [...] Read more.
The present review aims to describe the state of the art of research studies investigating the citrullination post-translational modification in adult and pediatric brain tumors. After an introduction to the deimination reaction and its occurrence in proteins and polypeptide chains, the role of the citrullination post-translational modification in physiological as well as pathological states, including cancer, is summarized, and the recent literature and review papers on the topic are examined. A separate section deals with the specific focus of investigation of the citrullination post-translational modification in relation to brain tumors, examining the state of the art of the literature that mainly concerns adult and pediatric glioblastoma and posterior fossa pediatric tumors. We examined the literature on this emerging field of research, and we apologize in advance for any possible omission. Although only a few studies inspecting citrullination in brain tumors are currently available, the results interestingly highlighted different profiles of the citrullinome associated with different histotypes. The data outlined the importance of this post-translational modification in modulating cancer invasion and chemoresistance, influencing key factors involved in apoptosis, cancer cell communication through extracellular vesicle release, autophagy, and gene expression processes, which suggests the prospect of taking citrullination as a target of cancer treatment or as a source of potential diagnostic and prognostic biomarkers for potential clinical applications in the future. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

18 pages, 44845 KiB  
Review
Amide Proton Transfer–Chemical Exchange Saturation Transfer Imaging of Intracranial Brain Tumors and Tumor-like Lesions: Our Experience and a Review
by Hirofumi Koike, Minoru Morikawa, Hideki Ishimaru, Reiko Ideguchi, Masataka Uetani and Mitsuharu Miyoshi
Diagnostics 2023, 13(5), 914; https://doi.org/10.3390/diagnostics13050914 - 28 Feb 2023
Cited by 6 | Viewed by 2821
Abstract
Chemical exchange saturation transfer (CEST) is a molecular magnetic resonance imaging (MRI) method that can generate image contrast based on the proton exchange between labeled protons in solutes and free, bulk water protons. Amide proton transfer (APT) imaging is the most frequently reported [...] Read more.
Chemical exchange saturation transfer (CEST) is a molecular magnetic resonance imaging (MRI) method that can generate image contrast based on the proton exchange between labeled protons in solutes and free, bulk water protons. Amide proton transfer (APT) imaging is the most frequently reported amide-proton-based CEST technique. It generates image contrast by reflecting the associations of mobile proteins and peptides resonating at 3.5 ppm downfield from water. Although the origin of the APT signal intensity in tumors is unclear, previous studies have suggested that the APT signal intensity is increased in brain tumors due to the increased mobile protein concentrations in malignant cells in association with an increased cellularity. High-grade tumors, which demonstrate a higher proliferation than low-grade tumors, have higher densities and numbers of cells (and higher concentrations of intracellular proteins and peptides) than low-grade tumors. APT-CEST imaging studies suggest that the APT-CEST signal intensity can be used to help differentiate between benign and malignant tumors and high-grade gliomas and low-grade gliomas as well as estimate the nature of lesions. In this review, we summarize the current applications and findings of the APT-CEST imaging of various brain tumors and tumor-like lesions. We report that APT-CEST imaging can provide additional information on intracranial brain tumors and tumor-like lesions compared to the information provided by conventional MRI methods, and that it can help indicate the nature of lesions, differentiate between benign and malignant lesions, and determine therapeutic effects. Future research could initiate or improve the lesion-specific clinical applicability of APT-CEST imaging for meningioma embolization, lipoma, leukoencephalopathy, tuberous sclerosis complex, progressive multifocal leukoencephalopathy, and hippocampal sclerosis. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

12 pages, 514 KiB  
Review
Brain Tumor at Diagnosis: From Cognition and Behavior to Quality of Life
by Daniela Pia Rosaria Chieffo, Federica Lino, Daniele Ferrarese, Daniela Belella, Giuseppe Maria Della Pepa and Francesco Doglietto
Diagnostics 2023, 13(3), 541; https://doi.org/10.3390/diagnostics13030541 - 2 Feb 2023
Cited by 12 | Viewed by 3994
Abstract
Background: The present narrative review aims to discuss cognitive–emotional–behavioral symptoms in adults with brain tumors at the time of diagnosis. Methods: The PubMed database was searched considering glioma, pituitary adenoma, and meningioma in adulthood as pathologies, together with cognitive, neuropsychological, or behavioral aspects. [...] Read more.
Background: The present narrative review aims to discuss cognitive–emotional–behavioral symptoms in adults with brain tumors at the time of diagnosis. Methods: The PubMed database was searched considering glioma, pituitary adenoma, and meningioma in adulthood as pathologies, together with cognitive, neuropsychological, or behavioral aspects. Results: Although a significant number of studies describe cognitive impairment after surgery or treatment in adults with brain tumors, only few focus on cognitive–emotional–behavioral symptoms at diagnosis. Furthermore, the importance of an effective communication and its impact on patients’ quality of life and compliance with treatment are seldom discussed. Conclusions: Adults with brain tumors have needs in terms of cognitive–emotional–behavioral features that are detectable at the time of diagnosis; more research is needed to identify effective communication protocols in order to allow a higher perceived quality of life in these patients. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

19 pages, 2991 KiB  
Review
Atypical Teratoid Rhabdoid Tumor: Proposal of a Diagnostic Pathway Based on Clinical Features and Neuroimaging Findings
by Rosalinda Calandrelli, Luca Massimi, Fabio Pilato, Tommaso Verdolotti, Antonio Ruggiero, Giorgio Attinà, Marco Gessi and Cesare Colosimo
Diagnostics 2023, 13(3), 475; https://doi.org/10.3390/diagnostics13030475 - 28 Jan 2023
Cited by 7 | Viewed by 2260
Abstract
Purpose: To assess the main imaging and clinical features in adult- and pediatric-onset atypical teratoid rhabdoid tumor (ATRT) in order to build a predefined pathway useful for the diagnosis. Methods: We enrolled 11 ATRT patients (10 children, one adult) and we conducted a [...] Read more.
Purpose: To assess the main imaging and clinical features in adult- and pediatric-onset atypical teratoid rhabdoid tumor (ATRT) in order to build a predefined pathway useful for the diagnosis. Methods: We enrolled 11 ATRT patients (10 children, one adult) and we conducted a literature search on PubMed Central using the key terms “adult” or “pediatric” and “atypical teratoid/rhabdoid tumor”. We collected clinical and neuroradiological data reported in previous studies and combined them with those from our case series. A three step process was built to reach diagnosis by identifying the main distinctive clinical and imaging features. Results: Clinical evaluation: neurological symptoms were nonspecific. ATRT was more frequent in children under 3 years of age (7 out of 10 children) and infratentorial localization was reported more frequently in children under the age of 24 months. Midline/off-midline localization was influenced by the age. Imaging findings: Preferential location near the ventricles and liquor spaces and the presence of eccentric cysts were hallmark for ATRT; higher frequency of peripheral cysts was detected in children and in the supratentorial compartment (five out of eight patients with solid-cystic ATRT). Leptomeningeal dissemination at diagnosis was common (5 out of 10 children), while intratumoral hemorrhage, calcifications, and high cellularity were non-specific findings. Histopathological analysis: specific immunohistochemical markers were essential to confirm the diagnosis. Conclusion: In younger children, a bulky, heterogeneous mass with eccentric cystic components and development near ventricles or cisternal spaces may be suggestive of ATRT. ATRT diagnosis is more challenging in adults and relies exclusively on neuropathological examination. Full article
(This article belongs to the Special Issue Diagnosis of Brain Tumors)
Show Figures

Figure 1

Back to TopTop