scholarly journals Applications of radiomics and machine learning for radiotherapy of malignant brain tumors

2020 ◽  
Vol 196 (10) ◽  
pp. 856-867 ◽  
Author(s):  
Martin Kocher ◽  
Maximilian I. Ruge ◽  
Norbert Galldiks ◽  
Philipp Lohmann
Keyword(s):  
Machine Learning ◽  
Brain Tumors ◽  
Brain Metastases ◽  
Imaging Techniques ◽  
Machine Learning Algorithms ◽  
Radiotherapy Planning ◽  
Who Grade ◽  
Large Variability ◽  
Malignant Brain Tumors ◽  
Integrated Diagnosis

Abstract Background Magnetic resonance imaging (MRI) and amino acid positron-emission tomography (PET) of the brain contain a vast amount of structural and functional information that can be analyzed by machine learning algorithms and radiomics for the use of radiotherapy in patients with malignant brain tumors. Methods This study is based on comprehensive literature research on machine learning and radiomics analyses in neuroimaging and their potential application for radiotherapy in patients with malignant glioma or brain metastases. Results Feature-based radiomics and deep learning-based machine learning methods can be used to improve brain tumor diagnostics and automate various steps of radiotherapy planning. In glioma patients, important applications are the determination of WHO grade and molecular markers for integrated diagnosis in patients not eligible for biopsy or resection, automatic image segmentation for target volume planning, prediction of the location of tumor recurrence, and differentiation of pseudoprogression from actual tumor progression. In patients with brain metastases, radiomics is applied for additional detection of smaller brain metastases, accurate segmentation of multiple larger metastases, prediction of local response after radiosurgery, and differentiation of radiation injury from local brain metastasis relapse. Importantly, high diagnostic accuracies of 80–90% can be achieved by most approaches, despite a large variety in terms of applied imaging techniques and computational methods. Conclusion Clinical application of automated image analyses based on radiomics and artificial intelligence has a great potential for improving radiotherapy in patients with malignant brain tumors. However, a common problem associated with these techniques is the large variability and the lack of standardization of the methods applied.

Application of machine learning algorithms for the diagnosis of primary brain tumors.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 2533-2533
Author(s):  
Vasilii Khammad ◽  
Jose Javier Otero ◽  
Yolanda Cabello Izquierdo ◽  
Francisco Garagorry Guerra ◽  
Aline P. Becker ◽  
...  
Keyword(s):  
Machine Learning ◽  
Brain Tumors ◽  
Who Classification ◽  
Dimensional Space ◽  
Prognostic Significance ◽  
Tumor Location ◽  
Machine Learning Algorithms ◽  
Primary Brain Tumors ◽  
Molecular Features ◽  
Integrated Diagnosis

2533 Background: Primary lesions of the CNS refer to a heterogeneous group of benign or malignant tumors arising in different parts of the brain and spinal cord. According to the 2016 CNS WHO classification, the accurate diagnosis of primary brain tumors requires a layered approach of histologic, anatomic and molecular features to generate an integrated diagnosis with clinical and prognostic significance. However, in the US and worldwide, scarce resources are available to perform all the required tests routinely, so methods that improve pre-test probabilities and decrease false positive results have significant clinical and financial impact. Aims: 1) validate new diagnostic workflows with implementation of modern machine learning/artificial intelligence approaches; 2) design a reliable and interactive computational platform for primary CNS tumor diagnosis. Methods: To achieve these goals we have developed a population model in Rstudio, “La Tabla”, based on the articles from open resources of MEDLINE database and the latest version of WHO classification of CNS tumors. The data of “La Tabla” is comprised of more than 100,000 adult and pediatric cases, including rare brain tumor diagnoses, such as Gangliocytoma, Diffuse Midline Glioma and etc. Results: Boruta package and weights function in R have been used to distinguish the most important features for diagnosis prediction. To visualize correlation between these features (age, ki67 level, tumor location, presence of myxoid areas, calcifications, necrosis and etc.) and all diagnoses in two-dimensional space, we used a t-SNE algorithm. Models trained with decision tree algorithms (randomForest, XGBoost and C5.0) showed high overall accuracy in predicting diagnoses of “La Tabla” (95%, 94% and 92%) and 300 patients at OSUCCC-James (93%, 74% and 87%) in the absence of IHC and molecular data. Neural networks provided by keras and nnet packages predicted diagnoses using just clinical and histological findings with 94% and 88% accuracy on “La Tabla” and James patient databases respectively. Currently, we are building “Shiny” applications with R to deliver easily operated platform for pathologists and physicians. Conclusions: In conclusion, we managed to generate models that are able to diagnose primary brain lesions using basic clinical data (age, gender, tumor location), ki67 levels and distinct features of histological architecture. Most of the models distinguish brain tumors and associated molecular status with high accuracy and will serve as a reliable tool for second opinion in clinical neuro-oncology.

scholarly journals Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Elisabeth Sartoretti ◽  
Thomas Sartoretti ◽  
Michael Wyss ◽  
Carolin Reischauer ◽  
Luuk van Smoorenburg ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Brain Tumors ◽  
Proton Transfer ◽  
Multilayer Perceptron ◽  
Random Forest Classifier ◽  
Amide Proton ◽  
Low Grade ◽  
Who Grade ◽  
Amide Proton Transfer

AbstractWe sought to evaluate the utility of radiomics for Amide Proton Transfer weighted (APTw) imaging by assessing its value in differentiating brain metastases from high- and low grade glial brain tumors. We retrospectively identified 48 treatment-naïve patients (10 WHO grade 2, 1 WHO grade 3, 10 WHO grade 4 primary glial brain tumors and 27 metastases) with either primary glial brain tumors or metastases who had undergone APTw MR imaging. After image analysis with radiomics feature extraction and post-processing, machine learning algorithms (multilayer perceptron machine learning algorithm; random forest classifier) with stratified tenfold cross validation were trained on features and were used to differentiate the brain neoplasms. The multilayer perceptron achieved an AUC of 0.836 (receiver operating characteristic curve) in differentiating primary glial brain tumors from metastases. The random forest classifier achieved an AUC of 0.868 in differentiating WHO grade 4 from WHO grade 2/3 primary glial brain tumors. For the differentiation of WHO grade 4 tumors from grade 2/3 tumors and metastases an average AUC of 0.797 was achieved. Our results indicate that the use of radiomics for APTw imaging is feasible and the differentiation of primary glial brain tumors from metastases is achievable with a high degree of accuracy.

scholarly journals Epigenetic Classifiers for Precision Diagnosis of Brain Tumors

2019 ◽  
Vol 12 ◽  
pp. 251686571984028 ◽  
Author(s):  
Javier IJ Orozco ◽  
Ayla O Manughian-Peter ◽  
Matthew P Salomon ◽  
Diego M Marzese
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Brain Tumors ◽  
Brain Metastases ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Malignant Neoplasms ◽  
Cancer Breast ◽  
Wide Range ◽  
Breast Cancer Brain Metastases

DNA methylation profiling has proven to be a powerful analytical tool, which can accurately identify the tissue of origin of a wide range of benign and malignant neoplasms. Using microarray-based profiling and supervised machine learning algorithms, we and other groups have recently unraveled DNA methylation signatures capable of aiding the histomolecular diagnosis of different tumor types. We have explored the methylomes of metastatic brain tumors from patients with lung cancer, breast cancer, and cutaneous melanoma and primary brain neoplasms to build epigenetic classifiers. Our brain metastasis methylation (BrainMETH) classifier has the ability to determine the type of brain tumor, the origin of the metastases, and the clinical-therapeutic subtype for patients with breast cancer brain metastases. To facilitate the translation of these epigenetic classifiers into clinical practice, we selected and validated the most informative genomic regions utilizing quantitative methylation-specific polymerase chain reaction (qMSP). We believe that the refinement, expansion, integration, and clinical validation of BrainMETH and other recently developed epigenetic classifiers will significantly contribute to the development of more comprehensive and accurate systems for the personalized management of patients with brain metastases.

scholarly journals m1A RNA Methylation Regulators Contribute To Malignant Progression And Have Clinical Prognostic Impact In Gliomas

2021 ◽  
Author(s):  
Hengchang Sun ◽  
Jiao Gong ◽  
Mei Shang ◽  
Yaqiong Chen ◽  
Jiahao Chen ◽  
...  
Keyword(s):  
Gene Expression ◽  
Brain Tumors ◽  
Rna Splicing ◽  
Rna Modification ◽  
Prognostic Impact ◽  
Idh Mutation ◽  
Overall Survival Rate ◽  
Who Grade ◽  
Rna Methylation ◽  
Malignant Brain Tumors

Abstract Background Glioma is the majority of primary malignant brain tumors in adults, accounting for over 70% of malignant brain tumors. RNA modification has been proved to be closely related to the development of various carcinomas including glioma. N1-methyladenosine (m1A) is a crucial and newly validated posttranscriptional modification in RNA. Its influence on glioma is still under elucidation. Results Gene expression and clinicopathological data of glioma were downloaded from TCGA and CGGA databases. The m1A regulators’ gene expression and its relationship with tumor malignancy grade or IDH mutation or 1p19q co-deletion status in glioma, as well as its related signaling pathway were investigated. We found that m1A regulators were dysregulated and positively associated with the WHO grade of glioma. The YTHDF2 expression was associated with the overall survival rate of glioma patients and was significantly lower in IDH mutation and the 1p/19q codeletion group. YTHDF2 mainly involved in RNA splicing, mRNA processing functions, or cell cycle relate pathways in glioma. Conclusion This study elucidated the dysregulation of m1A regulators and its potential signaling pathways in glioma, which will contribute to the further understanding of m1A RNA modification in glioma.

scholarly journals OTHR-12. The development of machine learning algorithms for the differentiation of glioma and brain metastases – a systematic review

2021 ◽  
Vol 3 (Supplement_3) ◽  
pp. iii17-iii17
Author(s):  
Waverly Rose Brim ◽  
Leon Jekel ◽  
Gabriel Cassinelli Petersen ◽  
Harry Subramanian ◽  
Tal Zeevi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Deep Learning ◽  
Brain Metastases ◽  
Search Strategy ◽  
Controlled Vocabulary ◽  
Machine Learning Algorithms ◽  
Average Score ◽  
Support Vector ◽  
Therapeutic Decisions

Abstract Purpose Medical staging, surgical planning, and therapeutic decisions are significantly different for brain metastases versus gliomas. Machine learning (ML) algorithms have been developed to differentiate these pathologies. We performed a systematic review to characterize ML methods and to evaluate their accuracy. Methods Studies on the application of machine learning in neuro-oncology were searched in Ovid Embase, Ovid MEDLINE, Cochrane trials (CENTRAL) and Web of science core-collection. A search strategy was designed in compliance with a clinical librarian and confirmed by a second librarian. The search strategy comprised of controlled vocabulary including artificial intelligence, machine learning, deep learning, magnetic resonance imaging, and glioma. The initial search was performed in October 2020 and then updated in February 2021. Candidate articles were screened in Covidence by at least two reviewers each. A bias analysis was conducted in agreement with TRIPOD, a bias assessment tool similar to CLAIM. Results Twenty-nine articles were used for data extraction. Four articles specified model development for solitary brain metastases. Classical ML (cML) algorithms represented 85% of models used, while deep learning (DL) accounted for 15%. cML algorithms performed with an average accuracy, sensitivity, and specificity of 82%, 78%, 88%, respectively; DL performed 84%, 79%, 81%. The support vector machine (SVM) algorithm was the most common used cML model in the literature and convolutional neural networks (CNN) were standard for DL models. We also found T1, T1 post-gadolinium and T2 sequences were most commonly used for feature extraction. Preliminary TRIPOD analysis yielded an average score of 14.25 (range 8–18). Conclusion ML algorithms that can accurately classify glioma from brain metastases have been developed. SVM and CNN are leading approaches with high accuracy. Standardized algorithm performance reporting is a clear limitation to be addressed in future studies.

scholarly journals The Development of a Skin Image Analysis Tool by Using Machine Learning Algorithms

Cosmetics ◽  
2020 ◽  
Vol 7 (3) ◽  
pp. 67
Author(s):  
Perry Xiao ◽  
Xu Zhang ◽  
Wei Pan ◽  
Xiang Ou ◽  
Christos Bontozoglou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
Imaging Techniques ◽  
Learning Algorithms ◽  
Research Work ◽  
Software Tool ◽  
Machine Learning Algorithms ◽  
Analysis Tool ◽  
Skin Imaging ◽  
User Friendly

We present our latest research work on the development of a skin image analysis tool by using machine-learning algorithms. Skin imaging is very import in skin research. Over the years, we have used and developed different types of skin imaging techniques. As the number of skin images and the type of skin images increase, there is a need of a dedicated skin image analysis tool. In this paper, we report the development of such software tool by using the latest MATLAB App Designer. It is simple, user friendly and yet powerful. We intend to make it available on GitHub, so that others can benefit from the software. This is an ongoing project; we are reporting here what we have achieved so far, and more functions will be added to the software in the future.

scholarly journals Use of fluorescence to guide resection or biopsy of primary brain tumors and brain metastases

2014 ◽  
Vol 36 (2) ◽  
pp. E10 ◽  
Author(s):  
Serge Marbacher ◽  
Elisabeth Klinger ◽  
Lucia Schwyzer ◽  
Ingeborg Fischer ◽  
Edin Nevzati ◽  
...  
Keyword(s):  
Adverse Effects ◽  
Brain Tumors ◽  
Brain Metastases ◽  
Low Grade ◽  
High Grade ◽  
Open Resection ◽  
Who Grade ◽  
Primary Brain Tumors ◽  
High Grade Gliomas ◽  
Surgical Adjunct

Object The accurate discrimination between tumor and normal tissue is crucial for determining how much to resect and therefore for the clinical outcome of patients with brain tumors. In recent years, guidance with 5-aminolevulinic acid (5-ALA)–induced intraoperative fluorescence has proven to be a useful surgical adjunct for gross-total resection of high-grade gliomas. The clinical utility of 5-ALA in resection of brain tumors other than glioblastomas has not yet been established. The authors assessed the frequency of positive 5-ALA fluorescence in a cohort of patients with primary brain tumors and metastases. Methods The authors conducted a single-center retrospective analysis of 531 patients with intracranial tumors treated by 5-ALA–guided resection or biopsy. They analyzed patient characteristics, preoperative and postoperative liver function test results, intraoperative tumor fluorescence, and histological data. They also screened discharge summaries for clinical adverse effects resulting from the administration of 5-ALA. Intraoperative qualitative 5-ALA fluorescence (none, mild, moderate, and strong) was documented by the surgeon and dichotomized into negative and positive fluorescence. Results A total of 458 cases qualified for final analysis. The highest percentage of 5-ALA–positive fluorescence in open resection was found in glioblastomas (96%, n = 99/103). Among other tumors, 5-ALA–positive fluorescence was detected in 88% (n = 21/32) of anaplastic gliomas (WHO Grade III), 40% (n = 8/19) of low-grade gliomas (WHO Grade II), no (n = 0/3) WHO Grade I gliomas, and 77% (n = 85/110) of meningiomas. Among metastases, the highest percentage of 5-ALA–positive fluorescence was detected in adenocarcinomas (48%, n = 13/27). Low rates or absence of positive fluorescence was found among pituitary adenomas (8%, n = 1/12) and schwannomas (0%, n = 0/7). Biopsies of high-grade primary brain tumors showed positive rates of fluorescence similar to those recorded for open resection. No clinical adverse effects associated with use of 5-ALA were observed. Only 1 patient had clinically silent transient elevation of liver enzymes. Conclusions Study findings suggest that the administration of 5-ALA as a surgical adjunct for resection and biopsy of primary brain tumors and brain metastases is safe. In light of the high rate of positive fluorescence in high-grade gliomas other than glioblastomas, meningiomas, and a variety of metastatic cancers, 5-ALA seems to be a promising tool for enhancing intraoperative identification of neoplastic tissue and optimizing the extent of resection.

scholarly journals Machine Learning-Based Definition of Symptom Clusters and Selection of Antidepressants for Depressive Syndrome

Diagnostics ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1631
Author(s):  
Il Bin Kim ◽  
Seon-Cheol Park
Keyword(s):  
Machine Learning ◽  
Personalized Medicine ◽  
Imaging Techniques ◽  
Language Game ◽  
Symptom Clusters ◽  
Machine Learning Algorithms ◽  
Depressive Syndrome ◽  
Research Network ◽  
Imaging Data ◽  
Clinical Cohort

The current polythetic and operational criteria for major depression inevitably contribute to the heterogeneity of depressive syndromes. The heterogeneity of depressive syndrome has been criticized using the concept of language game in Wittgensteinian philosophy. Moreover, “a symptom- or endophenotype-based approach, rather than a diagnosis-based approach, has been proposed” as the “next-generation treatment for mental disorders” by Thomas Insel. Understanding the heterogeneity renders promise for personalized medicine to treat cases of depressive syndrome, in terms of both defining symptom clusters and selecting antidepressants. Machine learning algorithms have emerged as a tool for personalized medicine by handling clinical big data that can be used as predictors for subtype classification and treatment outcome prediction. The large clinical cohort data from the Sequenced Treatment Alternatives to Relieve Depression (STAR*D), Combining Medications to Enhance Depression Outcome (CO-MED), and the German Research Network on Depression (GRND) have recently began to be acknowledged as useful sources for machine learning-based depression research with regard to cost effectiveness and generalizability. In addition, noninvasive biological tools such as functional and resting state magnetic resonance imaging techniques are widely combined with machine learning methods to detect intrinsic endophenotypes of depression. This review highlights recent studies that have used clinical cohort or brain imaging data and have addressed machine learning-based approaches to defining symptom clusters and selecting antidepressants. Potentially applicable suggestions to realize machine learning-based personalized medicine for depressive syndrome are also provided herein.

Sign in / Sign up

Export Citation Format

Share Document