Classification of brain tumor isocitrate dehydrogenase status using MRI and deep learning

Nalawade, Sahil S.; Murugesan, Gowtham Krishnan; Vejdani‐Jahromi, Maryam; Fisicaro, Ryan A.; Yogananda, Chandan Ganesh Bangalore; Wagner, Ben; Mickey, Bruce; Maher, Elizabeth A.; Pinho, Marco C.; Fei, Baowei; Madhuranthakam, Ananth J.; Maldjian, Joseph A.

doi:10.1117/1.jmi.6.4.046003

Cited by 19 publications

(24 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DenseNet-161 with five-fold cross-validation was found to be the best performing model with few preprocessing steps. It attained a mean slice-wise accuracy, sensitivity, and specificity of 90.5%, 83.1%, and 94.8%, respectively, and a subject-wise accuracy, sensitivity, and specificity of 83.8%, 83.5%, and 83.5%, respectively [20]. Bangalore et al [16]…”

Section: Models Used To Predict the Isocitrate Dehydrogenase Mutation Statusmentioning

confidence: 95%

“…In 19 studies, the researchers determined the DL model accuracy. In six studies [15][16][17][18][19][20], the authors reported the sensitivity of the DL model used, and in five studies [15,16,[18][19][20], the authors reported the specificity of the DL models. In eight studies, the researchers examined glioma grading by using different DL models compared with other models [19,[21][22][23][24][25][26][27].…”

Section: Characteristics Of the Included Studiesmentioning

confidence: 99%

“…Glioblastomas with an IDH mutation have a significantly improved survival compared with IDH wild-type gliomas [ 28 ]. Out of the 20 included studies, the authors of four [ 16 , 20 , 29 , 30 ] used different DL models in combination with MR images to predict the IDH mutation status. Nalawade et al [ 20 ] used T2-weighted (T2w) MRI of 120 patients with high-grade gliomas (HGGs) and 140 patients with low-grade gliomas (LGGs) and compared them between three CNN models (Inception-v4, ResNet-50, and DenseNet-161).…”

Section: Reviewmentioning

confidence: 99%

“…Out of the 20 included studies, the authors of four [ 16 , 20 , 29 , 30 ] used different DL models in combination with MR images to predict the IDH mutation status. Nalawade et al [ 20 ] used T2-weighted (T2w) MRI of 120 patients with high-grade gliomas (HGGs) and 140 patients with low-grade gliomas (LGGs) and compared them between three CNN models (Inception-v4, ResNet-50, and DenseNet-161). DenseNet-161 with five-fold cross-validation was found to be the best performing model with few preprocessing steps.…”

Section: Reviewmentioning

confidence: 99%

See 3 more Smart Citations

Clinical Applications of Artificial Intelligence, Machine Learning, and Deep Learning in the Imaging of Gliomas: A Systematic Review

Alhasan¹

2021

Cureus

View full text Add to dashboard Cite

In neuro-oncology, magnetic resonance imaging (MRI) is a critically important, non-invasive radiologic assessment technique for brain tumor diagnosis, especially glioma. Deep learning improves MRI image characterization and interpretation through the utilization of raw imaging data and provides unprecedented enhancement of images and representation for detection and classification through deep neural networks. This systematic review and quality appraisal method aim to summarize deep learning approaches used in neuro-oncology imaging to aid healthcare professionals. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, a total of 20 low-risk studies on the established use of deep learning models to identify glioma genetic mutations and grading were selected, based on a Quality Assessment of Diagnostic Accuracy Studies 2 score of ≥9. The included studies provided the deep learning models used alongside their outcome measures, the number of patients, and the molecular markers for brain glioma classification. In 19 studies, the researchers determined that the deep learning model improved the clinical outcome and treatment protocol in patients with a brain tumor. In five studies, the authors determined the sensitivity of the deep learning model used, and in four studies, the authors determined the specificity of the models. Convolutional neural network models were used in 16 studies. In eight studies, the researchers examined glioma grading by using different deep learning models compared with other models. In this review, we found that deep learning models significantly improve the diagnostic and classification accuracy of brain tumors, particularly gliomas without the need for invasive methods. Most studies have presented validated results and can be used in clinical practice to improve patient care and prognosis.

show abstract

Section: Models Used To Predict the Isocitrate Dehydrogenase Mutation Statusmentioning

confidence: 95%

Section: Characteristics Of the Included Studiesmentioning

confidence: 99%

Section: Reviewmentioning

confidence: 99%

Section: Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Clinical Applications of Artificial Intelligence, Machine Learning, and Deep Learning in the Imaging of Gliomas: A Systematic Review

Alhasan¹

2021

Cureus

View full text Add to dashboard Cite

show abstract

“…However, such validation based on tissue sampling can be challenging, as it is evident from report by The Cancer Genome Atlas (TCGA) that around 35% in-vivo surgeries obtained adequate tissue samples to confirm the IDH class [1]. Recently, non-invasive prediction using magnetic resonance imaging (MRI) is proved as more helpful for initial diagnosis and immediate treatment planning for cancer patients [2,3]. The various machine learning algorithms [4][5][6] or deep learning techniques [7,8] have been applied to radiogenomic studies of glioma to predict genotypes and survival outcomes.…”

Section: Introductionmentioning

confidence: 99%

MRI based genomic analysis of glioma using three pathway deep convolutional neural network for IDH classification

GORE,

JAGTAP

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

As per 2016 updates by World Health Organization (WHO) on cancer disease, gliomas are categorized and further treated based on genomic mutations. The imaging modalities support a complimentary but immediate noninvasive diagnosis of cancer based on genetic mutations. Our aim is to train a deep convolutional neural network for isocitrate dehydrogenase (IDH) genotyping of glioma by auto-extracting the most discriminative features from magnetic resonance imaging (MRI) volumes. MR imaging data of total 217 patients were obtained from The Cancer Imaging Archives (TCIA) of high and low-grade gliomas. A 3-pathway convolutional neural network was trained for IDH classification. The multipath neural network, consisting of one shallow and two deep neural network paths, is used to auto-extract the significant imaging features for successful IDH discrimination into IDH mutant and wild type. An accuracy of 93.67% and cross-entropy loss of 0.052 is achieved for IDH classification. The results of 3-pathway convolutional neural network (CNN) are better than the results achieved from individual paths of 3-pathway model. The results have demonstrated the multipath convolutional neural networks as state-of-the-art method with simple design to predict IDH genotypes in glioma with auto-extraction of radiogenomic features.

show abstract

Easy-to-use machine learning system for the prediction of IDH mutation and 1p/19q codeletion using MRI images of adult-type diffuse gliomas

Nishikawa

Ohka

Suzuki³

et al. 2023

Brain Tumor Pathol

View full text Add to dashboard Cite

Classification of brain tumor isocitrate dehydrogenase status using MRI and deep learning

Cited by 19 publications

References 28 publications

Clinical Applications of Artificial Intelligence, Machine Learning, and Deep Learning in the Imaging of Gliomas: A Systematic Review

Clinical Applications of Artificial Intelligence, Machine Learning, and Deep Learning in the Imaging of Gliomas: A Systematic Review

MRI based genomic analysis of glioma using three pathway deep convolutional neural network for IDH classification

Easy-to-use machine learning system for the prediction of IDH mutation and 1p/19q codeletion using MRI images of adult-type diffuse gliomas

Contact Info

Product

Resources

About