State of the Art: Machine Learning Applications in Glioma Imaging

Lotan, Eyal; Jain, Rajan; Razavian, Narges; Fatterpekar, Girish M.; Lui, Yvonne W.

doi:10.2214/ajr.18.20218

Cited by 83 publications

(52 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional machine‐learning algorithms were initially proposed to be used for the classification of medical images . Such algorithms might provide time‐saving and objective evaluation, for example, in multimodal studies comprising 1 H and X‐nuclei imaging.…”

Section: Latest Developments and Future Directionsmentioning

confidence: 99%

X‐nuclei imaging: Current state, technical challenges, and future directions

Kleimaier

Malzacher

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

1H imaging is concerned with contrast generation among anatomically distinct soft tissues. X‐nuclei imaging, on the other hand, aims to reveal the underlying changes in the physiological processes on a cellular level. Advanced clinical MR hardware systems improved 1H image quality and simultaneously enabled X‐nuclei imaging. Adaptation of 1H methods and optimization of both sequence design and postprocessing protocols launched X‐nuclei imaging past feasibility studies and into clinical studies. This review outlines the current state of X‐nuclei MRI, with the focus on 23Na, 35Cl, 39K, and 17O. Currently, various aspects of technical challenges limit the possibilities of clinical X‐nuclei MRI applications. To address these challenges, quintessential physical and technical concepts behind different applications are presented, and the advantages and drawbacks are delineated. The working process for methods such as quantification and multiquantum imaging is shown step‐by‐step. Clinical examples are provided to underline the potential value of X‐nuclei imaging in multifaceted areas of application. In conclusion, the scope of the latest technical advance is outlined, and suggestions to overcome the most fundamental hurdles on the way into clinical routine by leveraging the full potential of X‐nuclei imaging are presented. Level of Evidence: 1 Technical Efficacy Stage: 3 J. Magn. Reson. Imaging 2020;51:355–376.

show abstract

Section: Latest Developments and Future Directionsmentioning

confidence: 99%

X‐nuclei imaging: Current state, technical challenges, and future directions

Kleimaier

Malzacher

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…Lotan used automatic segmentation methods to obtain the tumor contours and areas, just like in our delineation. The following classification also depends on machine learning techniques [30]. Another study used diagnostic information from multiple modalities to achieve better performance [39].…”

Section: Discussionmentioning

confidence: 99%

“…Yang et al used DCNN to classify 113 gliomas and achieved good accuracy [29]. Lotan used machine learning techniques to classify tumors based on the features extracted from image segmentation [30].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Glioma Grading Based on Deep Transfer Learning of MRI Radiomic Features

Chen

Weng

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

According to a classification of central nervous system tumors by the World Health Organization, diffuse gliomas are classified into grade 2, 3, and 4 gliomas in accordance with their aggressiveness. To quantitatively evaluate a tumor’s malignancy from brain magnetic resonance imaging, this study proposed a computer-aided diagnosis (CAD) system based on a deep convolutional neural network (DCNN). Gliomas from a multi-center database (The Cancer Imaging Archive) composed of a total of 30 grade 2, 43 grade 3, and 57 grade 4 gliomas were used for the training and evaluation of the proposed CAD. Using transfer learning to fine-tune AlexNet, a DCNN, its internal layers, and parameters trained from a million images were transferred to learn how to differentiate the acquired gliomas. Data augmentation was also implemented to increase possible spatial and geometric variations for a better training model. The transferred DCNN achieved an accuracy of 97.9% with a standard deviation of ±1% and an area under the receiver operation characteristics curve (Az) of 0.9991 ± 0, which were superior to handcrafted image features, the DCNN without pretrained features, which only achieved a mean accuracy of 61.42% with a standard deviation of ±7% and a mean Az of 0.8222 ± 0.07, and the DCNN without data augmentation, which was the worst with a mean accuracy of 59.85% with a standard deviation ±16% and a mean Az of 0.7896 ± 0.18. The DCNN with pretrained features and data augmentation can accurately and efficiently classify grade 2, 3, and 4 gliomas. The high accuracy is promising in providing diagnostic suggestions to radiologists in the clinic.

show abstract

“…Because of this, ML and DL have been widely applied to a variety of glioma imaging-related tasks including: (1) brain tumor segmentation: quantifying tumor volume or segmenting the tumor region for downstream analysis tasks, and (2) predictive tasks (classification or regression): identifying the tumor type (e.g., distinguishing oligodendrogliomas from astrocytomas), grade, molecular subtypes, or genetic mutation [16,17], and predicting patients' treatment response, length of survival, prognosis, or recurrence (e.g., differentiating glioma recurrence from radiation necrosis and pseudo-progression [17]). These advances have been summarized in previous surveys on DL in glioma imaging [18,19,20], ML in glioma imaging applications [21,22], brain tumor radiomics [23,24] and neuroimaging biomarkers [25].…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence in glioma imaging: challenges and advances

et al. 2020

View full text Add to dashboard Cite

Primary brain tumors including gliomas continue to pose significant management challenges to clinicians. While the presentation, the pathology, and the clinical course of these lesions is variable, the initial investigations are usually similar. Patients who are suspected to have a brain tumor will be assessed with computed tomography (CT) and magnetic resonance imaging (MRI). The imaging findings are used by neurosurgeons to determine the feasibility of surgical resection and plan such an undertaking. Imaging studies are also an indispensable tool in tracking tumor progression or its response to treatment. As these imaging studies are non-invasive, relatively cheap and accessible to patients, there have been many efforts over the past two decades to increase the amount of clinically-relevant information that can be extracted from brain imaging. Most recently, artificial intelligence (AI) techniques have been employed to segment and characterize brain tumors, as well as to detect progression or treatment-response. However, the clinical utility of such endeavours remains limited due to challenges in data collection and annotation, model training, and in the reliability of AI-generated information.We provide a review of recent advances in addressing the above challenges. First, to overcome the challenge of data paucity, different image imputation and synthesis techniques along with annotation collection efforts are summarized. Next, various training strategies are presented to meet multiple desiderata, such as model performance, generalization ability, data privacy protection, and learning with sparse annotations. Finally, standardized performance evaluation and model interpretability methods have been reviewed. We believe that these technical approaches will facilitate the development of a fully-functional AI tool in the clinical care of patients with gliomas.

show abstract

State of the Art: Machine Learning Applications in Glioma Imaging

Cited by 83 publications

References 63 publications

X‐nuclei imaging: Current state, technical challenges, and future directions

X‐nuclei imaging: Current state, technical challenges, and future directions

Intelligent Glioma Grading Based on Deep Transfer Learning of MRI Radiomic Features

Artificial intelligence in glioma imaging: challenges and advances

Contact Info

Product

Resources

About