Dataset Information

Deep learning-based prediction of H3K27M alteration in diffuse midline gliomas based on whole-brain MRI.

ABSTRACT:

Background

H3K27M mutation status significantly affects the prognosis of patients with diffuse midline gliomas (DMGs), but this tumor presents a high risk of pathological acquisition. We aimed to construct a fully automated model for predicting the H3K27M alteration status of DMGs based on deep learning using whole-brain MRI.

Methods

DMG patients from West China Hospital of Sichuan University (WCHSU; n = 200) and Chengdu Shangjin Nanfu Hospital (CSNH; n = 35) who met the inclusion and exclusion criteria from February 2016 to April 2022 were enrolled as the training and external test sets, respectively. To adapt the model to the human head MRI scene, we use normal human head MR images to pretrain the model. The classification and tumor segmentation tasks are naturally related, so we conducted cotraining for the two tasks to enable information interaction between them and improve the accuracy of the classification task.

Results

The average classification accuracies of our model on the training and external test sets was 90.5% and 85.1%, respectively. Ablation experiments showed that pretraining and cotraining could improve the prediction accuracy and generalization performance of the model. In the training and external test sets, the average areas under the receiver operating characteristic curve (AUROCs) were 94.18% and 87.64%, and the average areas under the precision-recall curve (AUPRC) were 93.26% and 85.4%.

Conclusions

The developed model achieved excellent performance in predicting the H3K27M alteration status in DMGs, and its good reproducibility and generalization were verified in the external dataset.

SUBMITTER: Huang B

PROVIDER: S-EPMC10501256 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-based prediction of H3K27M alteration in diffuse midline gliomas based on whole-brain MRI.

Huang Bowen B Zhang Yuekang Y Mao Qing Q Ju Yan Y Liu Yanhui Y Su Zhengzheng Z Lei Yinjie Y Ren Yanming Y

Cancer medicine 20230717 16

<h4>Background</h4>H3K27M mutation status significantly affects the prognosis of patients with diffuse midline gliomas (DMGs), but this tumor presents a high risk of pathological acquisition. We aimed to construct a fully automated model for predicting the H3K27M alteration status of DMGs based on deep learning using whole-brain MRI.<h4>Methods</h4>DMG patients from West China Hospital of Sichuan University (WCHSU; n = 200) and Chengdu Shangjin Nanfu Hospital (CSNH; n = 35) who met the inclusion ...[more]

PMID: 37461358

Similar Datasets

Project description:BackgroundThe prognosis of diffuse midline glioma (DMG) patients with H3K27M (H3K27M-DMG) alterations is poor; however, a model that encourages accurate prediction of prognosis for such lesions on an individual basis remains elusive. We aimed to construct an H3K27M-DMG survival model based on DeepSurv to predict patient prognosis.MethodsPatients recruited from a single center were used for model training, and patients recruited from another center were used for external validation. Univariate and multivariate Cox regression analyses were used to select features. Four machine learning models were constructed, and the consistency index (C-index) and integrated Brier score (IBS) were calculated. We used the receiver operating characteristic curve (ROC) and area under the receiver operating characteristic (AUC) curve to assess the accuracy of predicting 6-month, 12-month, 18-month and 24-month survival rates. A heatmap of feature importance was used to explain the results of the four models.ResultsWe recruited 113 patients in the training set and 23 patients in the test set. We included tumor size, tumor location, Karnofsky Performance Scale (KPS) score, enhancement, radiotherapy, and chemotherapy for model training. The accuracy of DeepSurv prediction is highest among the four models, with C-indexes of 0.862 and 0.811 in the training and external test sets, respectively. The DeepSurv model had the highest AUC values at 6 months, 12 months, 18 months and 24 months, which were 0.970 (0.919-1), 0.950 (0.877-1), 0.939 (0.845-1), and 0.875 (0.690-1), respectively. We designed an interactive interface to more intuitively display the survival probability prediction results provided by the DeepSurv model.ConclusionThe DeepSurv model outperforms traditional machine learning models in terms of prediction accuracy and robustness, and it can also provide personalized treatment recommendations for patients. The DeepSurv model may provide decision-making assistance for patients in formulating treatment plans in the future.

Project description:Diffuse intrinsic pontine glioma (DIPG) and other H3K27M-mutated diffuse midline gliomas (DMGs) are universally lethal central nervous system (CNS) tumors that occur most commonly in children and young adults1. Average life expectancy is ten months from diagnosis, and 5-year survival is less than 1%2. Palliative radiotherapy is the only established treatment3, and neither cytotoxic nor targeted pharmacological approaches have demonstrated anti-tumor responses or improved prognosis to date3,4. We previously discovered that the disialoganglioside GD2 is highly and uniformly expressed on H3K27M+ DMG cells and demonstrated that intravenously (IV) administered GD2.4-1BB.z chimeric antigen receptor (CAR) T-cells eradicated established DMGs in patient-derived orthotopic murine models5, thereby providing the rationale for a first-in-human/first-in-child Phase 1 clinical trial (NCT04196413). Because CAR T-cell-induced inflammation and edema of the brainstem can result in obstructive hydrocephalus, increased intracranial pressure, and dangerous tissue shifts, a number of neurocritical care precautions were incorporated in the clinical trial design and management plan. Here we present the clinical experience from the first four patients with H3K27M+ DMG treated with GD2-CAR T-cells at dose level 1 (DL1; 1e6 GD2-CAR T-cells/kg administered IV). Patients who exhibited clinical benefit were eligible for subsequent administrations of GD2-CAR T-cells. Given preclinical evidence for increased CAR T-cell potency6, and the potential for diminished immunogenicity with locoregional administration, second doses were administered intracerebroventricularly (ICV) through an Ommaya catheter to three patients. As predicted from preclinical models, toxicity was largely related to the neuroanatomical location of the tumors and was reversible with intensive supportive care. Although GD2 is expressed at low levels in normal neural tissue, no evidence of on-target, off-tumor toxicity was observed. Three of four patients exhibited clinical and radiographic improvement, underscoring the promise of this approach for H3K27M+ DMG therapy. Correlative studies of serum and CSF revealed marked proinflammatory cytokine production following GD2 CAR T cell administration and single cell transcriptomic analysis of 65,598 single cells from CAR T cell products and patient CSF has begun to reveal differences that correlate with the heterogeneity between subjects and routes of administration.

Dataset Information

Deep learning-based prediction of H3K27M alteration in diffuse midline gliomas based on whole-brain MRI.

Background

Methods

Results

Conclusions

Publications

Deep learning-based prediction of H3K27M alteration in diffuse midline gliomas based on whole-brain MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets