Developing and validating a deep learning and radiomic model for glioma grading using multiplanar reconstructed magnetic resonance contrast-enhanced T1-weighted imaging: a robust, multi-institutional study

Ding, Jialin; Ru-bin, Zhao; Qiu, Qingtao; Chen, Jinhu; Duan, Jinghao; Cao, Xin; Yong, Yin

doi:10.21037/qims-21-722

Cited by 25 publications

(20 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionsupporting

confidence: 89%

“…We found that the discriminatory capability of the model incorporating deep learning features with radiomics features was enhanced in comparison to the model with radiomics only, demonstrating the value of deep learning features in the diagnosis of cancer. This result has also been found in other studies in the field of medical imaging (15,24). Convolutional neural networks as a deep learning technique are widely used for image recognition, which can automatically extract features from images based on convolutional operations, enabling them to detect subtle differences between MIBC and NO-MIBC.…”

supporting

confidence: 77%

See 1 more Smart Citation

CT-based deep learning radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer

et al. 2022

View full text Add to dashboard Cite

ObjectivesAlthough the preoperative assessment of whether a bladder cancer (BCa) indicates muscular invasion is crucial for adequate treatment, there currently exist some challenges involved in preoperative diagnosis of BCa with muscular invasion. The aim of this study was to construct deep learning radiomic signature (DLRS) for preoperative predicting the muscle invasion status of BCa.MethodsA retrospective review covering 173 patients revealed 43 with pathologically proven muscle-invasive bladder cancer (MIBC) and 130 with non–muscle–invasive bladder cancer (non- MIBC). A total of 129 patients were randomly assigned to the training cohort and 44 to the test cohort. The Pearson correlation coefficient combined with the least absolute shrinkage and selection operator (LASSO) was utilized to reduce radiomic redundancy. To decrease the dimension of deep learning features, Principal Component Analysis (PCA) was adopted. Six machine learning classifiers were finally constructed based on deep learning radiomics features, which were adopted to predict the muscle invasion status of bladder cancer. The area under the curve (AUC), accuracy, sensitivity and specificity were used to evaluate the performance of the model.ResultsAccording to the comparison, DLRS-based models performed the best in predicting muscle violation status, with MLP (Train AUC: 0.973260 (95% CI 0.9488-0.9978) and Test AUC: 0.884298 (95% CI 0.7831-0.9855)) outperforming the other models. In the test cohort, the sensitivity, specificity and accuracy of the MLP model were 0.91 (95% CI 0.551-0.873), 0.78 (95% CI 0.594-0.863) and 0.58 (95% CI 0.729-0.827), respectively. DCA indicated that the MLP model showed better clinical utility than Radiomics-only model, which was demonstrated by the decision curve analysis.ConclusionsA deep radiomics model constructed with CT images can accurately predict the muscle invasion status of bladder cancer.

show abstract

Section: Discussionsupporting

confidence: 89%

supporting

confidence: 77%

CT-based deep learning radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Radiomics, which aims at extracting multiple quantitative imaging features using reproducible algorithms, has been increasingly applied and represents the basis of radiogenomics, whose purpose is to determine the association between the collected imaging data and both genomic signatures and molecular phenotypes of gliomas [38,39]. Of note, there are emerging methods based upon a deep learning and radiomic model that could be promising for glioma grading using multiplanar reconstructed MR contrast-enhanced T1-weighted imaging [40].…”

Section: Flair Mri Cannot Reflect the Ptz: How Can Dlgg Delineation B...mentioning

confidence: 99%

The Concept of «Peritumoral Zone» in Diffuse Low-Grade Gliomas: Oncological and Functional Implications for a Connectome-Guided Therapeutic Attitude

2022

View full text Add to dashboard Cite

Diffuse low-grade gliomas (DLGGs) are heterogeneous and poorly circumscribed neoplasms with isolated tumor cells that extend beyond the margins of the lesion depicted on MRI. Efforts to demarcate the glioma core from the surrounding healthy brain led us to define an intermediate region, the so-called peritumoral zone (PTZ). Although most studies about PTZ have been conducted on high-grade gliomas, the purpose here is to review the cellular, metabolic, and radiological characteristics of PTZ in the specific context of DLGG. A better delineation of PTZ, in which glioma cells and neural tissue strongly interact, may open new therapeutic avenues to optimize both functional and oncological results. First, a connectome-based “supratotal” surgical resection (i.e., with the removal of PTZ in addition to the tumor core) resulted in prolonged survival by limiting the risk of malignant transformation, while improving the quality of life, thanks to a better control of seizures. Second, the timing and order of (neo)adjuvant medical treatments can be modulated according to the pattern of peritumoral infiltration. Third, the development of new drugs specifically targeting the PTZ could be considered from an oncological (such as immunotherapy) and epileptological perspective. Further multimodal investigations of PTZ are needed to maximize long-term outcomes in DLGG patients.

show abstract

“…A few studies have attempted to combine CNN with radiomics for gliomas grading. One study with a total of 252 patients developed an approach based on the combination of radiomics features and 2D CNN features from multiplanar reconstructed (MPR) images, which achieved the highest AUC of 0.874 (58). Although this approach has shown good performance, the masks used for feature extraction were manually delineated, and the input of the CNN were the slices with the largest tumor area and the two adjacent images, which Radiomics has also been applied in the survival analysis of glioma patients (28,29,54).…”

Section: Discussionmentioning

confidence: 99%

An automated approach for predicting glioma grade and survival of LGG patients using CNN and radiomics

Peng

Zhu

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

ObjectivesTo develop and validate an efficient and automatically computational approach for stratifying glioma grades and predicting survival of lower-grade glioma (LGG) patients using an integration of state-of-the-art convolutional neural network (CNN) and radiomics.MethodThis retrospective study reviewed 470 preoperative MR images of glioma from BraTs public dataset (n=269) and Jinling hospital (n=201). A fully automated pipeline incorporating tumor segmentation and grading was developed, which can avoid variability and subjectivity of manual segmentations. First, an integrated approach by fusing CNN features and radiomics features was employed to stratify glioma grades. Then, a deep-radiomics signature based on the integrated approach for predicting survival of LGG patients was developed and subsequently validated in an independent cohort.ResultsThe performance of tumor segmentation achieved a Dice coefficient of 0.81. The intraclass correlation coefficients (ICCs) of the radiomics features between the segmentation network and physicians were all over 0.75. The performance of glioma grading based on integrated approach achieved the area under the curve (AUC) of 0.958, showing the effectiveness of the integrated approach. The multivariable Cox regression results demonstrated that the deep-radiomics signature remained an independent prognostic factor and the integrated nomogram showed significantly better performance than the clinical nomogram in predicting overall survival of LGG patients (C-index: 0.865 vs. 0.796, P=0.005).ConclusionThe proposed integrated approach can be noninvasively and efficiently applied in prediction of gliomas grade and survival. Moreover, our fully automated pipeline successfully achieved computerized segmentation instead of manual segmentation, which shows the potential to be a reproducible approach in clinical practice.

show abstract

Developing and validating a deep learning and radiomic model for glioma grading using multiplanar reconstructed magnetic resonance contrast-enhanced T1-weighted imaging: a robust, multi-institutional study

Cited by 25 publications

References 44 publications

CT-based deep learning radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer

CT-based deep learning radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer

The Concept of «Peritumoral Zone» in Diffuse Low-Grade Gliomas: Oncological and Functional Implications for a Connectome-Guided Therapeutic Attitude

An automated approach for predicting glioma grade and survival of LGG patients using CNN and radiomics

Contact Info

Product

Resources

About