Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023;4(4):669-684.
doi: 10.37349/etat.2023.00159. Epub 2023 Aug 30.

Deep learning based clinico-radiological model for paediatric brain tumor detection and subtype prediction

Abhishek Mahajan  1 , Mayur Burrewar  2 , Ujjwal Agarwal  2 , Bharadwaj Kss  3 , Apparao Mlv  3 , Amrita Guha  2 , Arpita Sahu  2 , Amit Choudhari  2 , Vivek Pawar  3 , Vivek Punia  3 , Sridhar Epari  4 , Ayushi Sahay  4 , Tejpal Gupta  2 , Girish Chinnaswamy  5 , Prakash Shetty  6 , Aliasgar Moiyadi  6
Affiliations

Deep learning based clinico-radiological model for paediatric brain tumor detection and subtype prediction

Abhishek Mahajan et al. Explor Target Antitumor Ther. 2023.

Abstract

Aim: Early diagnosis of paediatric brain tumors significantly improves the outcome. The aim is to study magnetic resonance imaging (MRI) features of paediatric brain tumors and to develop an automated segmentation (AS) tool which could segment and classify tumors using deep learning methods and compare with radiologist assessment.

Methods: This study included 94 cases, of which 75 were diagnosed cases of ependymoma, medulloblastoma, brainstem glioma, and pilocytic astrocytoma and 19 were normal MRI brain cases. The data was randomized into training data, 64 cases; test data, 21 cases and validation data, 9 cases to devise a deep learning algorithm to segment the paediatric brain tumor. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the deep learning model were compared with radiologist's findings. Performance evaluation of AS was done based on Dice score and Hausdorff95 distance.

Results: Analysis of MRI semantic features was done with necrosis and haemorrhage as predicting features for ependymoma, diffusion restriction and cystic changes were predictors for medulloblastoma. The accuracy of detecting abnormalities was 90%, with a specificity of 100%. Further segmentation of the tumor into enhancing and non-enhancing components was done. The segmentation results for whole tumor (WT), enhancing tumor (ET), and non-enhancing tumor (NET) have been analyzed by Dice score and Hausdorff95 distance. The accuracy of prediction of all MRI features was compared with experienced radiologist's findings. Substantial agreement observed between the classification by model and the radiologist's given classification [K-0.695 (K is Cohen's kappa score for interrater reliability)].

Conclusions: The deep learning model had very high accuracy and specificity for predicting the magnetic resonance (MR) characteristics and close to 80% accuracy in predicting tumor type. This model can serve as a potential tool to make a timely and accurate diagnosis for radiologists not trained in neuroradiology.

Keywords: Deep learning model; artificial intelligence; brainstem glioma; ependymoma; medulloblastoma; paediatric brain tumors; pilocytic astrocytoma.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there is no conflict of interest.

Figures

Figure 1
Figure 1
Figure shows annotation for tumor identification. A: anterior; P: posterior; R: right; L: left
Figure 2
Figure 2
Figure shows annotation for enhancing (green) and non-enhancing (yellow) components of the tumor. A: anterior; P: posterior; R: right; L: left
Figure 3
Figure 3
Figure shows annotations for training the model to identify the site of the tumor. Blue: forebrain; pink: cerebellum; aqua: brainstem; A: anterior; P: posterior; R: right; L: left
Figure 4
Figure 4
Training and validation curve for lobe segmentation network
Figure 5
Figure 5
Training and validation curve for stage 1 network for tumor segmentation
Figure 6
Figure 6
Training and validation curves of stage 2 network for tumor segmentation
Figure 7
Figure 7
Target and actual prediction labels in a case of fourth ventricle brain tumor. Figure shows prediction label of the trained model
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Madhavan R, Kannabiran BP, Nithya AM, Kani J, Balasubramaniam P, Shanmugakumar S. Pediatric brain tumors: an analysis of 5 years of data from a tertiary cancer care center, India. Indian J Cancer. 2016;53:562–5. doi: 10.4103/ijc.IJC_66_17. - DOI - PubMed
    1. AlRayahi J, Zapotocky M, Ramaswamy V, Hanagandi P, Branson H, Mubarak W, et al. Pediatric brain tumor genetics: what radiologists need to know. Radiographics. 2018;38:2102–22. doi: 10.1148/rg.2018180109. - DOI - PubMed
    1. Lacayo A, Farmer PM. Brain tumors in children: a review. Ann Clin Lab Sci. 1991;21:26–35. - PubMed
    1. Panigrahy A, Blüml S. Neuroimaging of pediatric brain tumors: from basic to advanced magnetic resonance imaging (MRI) J Child Neurol. 2009;24:1343–65. doi: 10.1177/0883073809342129. - DOI - PubMed
    1. Packer RJ. Childhood brain tumors: accomplishments and ongoing challenges. J Child Neurol. 2008;23:1122–7. doi: 10.1177/0883073808320758. - DOI - PMC - PubMed

LinkOut - more resources