Automated tumor segmentation and brain tissue extraction from multiparametric MRI of pediatric brain tumors: A multi-institutional study

Anahita Fathi Kazerooni; Sherjeel Arif; Rachel Madhogarhia; Nastaran Khalili; Debanjan Haldar; Sina Bagheri; Ariana M Familiar; Hannah Anderson; Shuvanjan Haldar; Wenxin Tu; Meen Chul Kim; Karthik Viswanathan; Sabine Muller; Michael Prados; Cassie Kline; Lorenna Vidal; Mariam Aboian; Phillip B Storm; Adam C Resnick; Jeffrey B Ware; Arastoo Vossough; Christos Davatzikos; Ali Nabavizadeh

doi:10.1093/noajnl/vdad027

Automated tumor segmentation and brain tissue extraction from multiparametric MRI of pediatric brain tumors: A multi-institutional study

Neurooncol Adv. 2023 Mar 16;5(1):vdad027. doi: 10.1093/noajnl/vdad027. eCollection 2023 Jan-Dec.

Authors

Anahita Fathi Kazerooni^{1

2

3

4}, Sherjeel Arif¹, Rachel Madhogarhia¹, Nastaran Khalili¹, Debanjan Haldar^{1

5}, Sina Bagheri^{1

6}, Ariana M Familiar¹, Hannah Anderson^{1

6}, Shuvanjan Haldar⁷, Wenxin Tu⁸, Meen Chul Kim¹, Karthik Viswanathan¹, Sabine Muller⁹, Michael Prados¹⁰, Cassie Kline¹¹, Lorenna Vidal¹², Mariam Aboian¹³, Phillip B Storm^{1

3

4}, Adam C Resnick^{1

4}, Jeffrey B Ware⁶, Arastoo Vossough^{1

6

12}, Christos Davatzikos^{2

6}, Ali Nabavizadeh^{1

6}

Affiliations

¹ Center for Data-Driven Discovery in Biomedicine (D3b), Children's Hospital of Philadelphia, Philadelphia, PA, USA.
² AI2D Center for AI and Data Science for Integrated Diagnostics, University of Pennsylvania, Philadelphia, PA, USA.
³ Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
⁴ Department of Neurosurgery, Children's Hospital of Philadelphia, Philadelphia, PA, USA.
⁵ Institute of Translational Medicine and Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
⁶ Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
⁷ Department of Biomedical Engineering, Rutgers University, New Brunswick, NJ, USA.
⁸ College of Arts and Sciences, University of Pennsylvania, Philadelphia, PA, USA.
⁹ Department of Neurology and Pediatrics, University of California San Francisco, San Francisco, CA, USA.
¹⁰ Department of Neurological Surgery and Pediatrics, University of California San Francisco, San Francisco, CA, USA.
¹¹ Division of Oncology, Children's Hospital of Philadelphia, Philadelphia, PA, USA.
¹² Division of Radiology, Children's Hospital of Philadelphia, Philadelphia, PA, USA.
¹³ Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.

Abstract

Background: Brain tumors are the most common solid tumors and the leading cause of cancer-related death among all childhood cancers. Tumor segmentation is essential in surgical and treatment planning, and response assessment and monitoring. However, manual segmentation is time-consuming and has high interoperator variability. We present a multi-institutional deep learning-based method for automated brain extraction and segmentation of pediatric brain tumors based on multi-parametric MRI scans.

Methods: Multi-parametric scans (T1w, T1w-CE, T2, and T2-FLAIR) of 244 pediatric patients ( n = 215 internal and n = 29 external cohorts) with de novo brain tumors, including a variety of tumor subtypes, were preprocessed and manually segmented to identify the brain tissue and tumor subregions into four tumor subregions, i.e., enhancing tumor (ET), non-enhancing tumor (NET), cystic components (CC), and peritumoral edema (ED). The internal cohort was split into training ( n = 151), validation ( n = 43), and withheld internal test ( n = 21) subsets. DeepMedic, a three-dimensional convolutional neural network, was trained and the model parameters were tuned. Finally, the network was evaluated on the withheld internal and external test cohorts.

Results: Dice similarity score (median ± SD) was 0.91 ± 0.10/0.88 ± 0.16 for the whole tumor, 0.73 ± 0.27/0.84 ± 0.29 for ET, 0.79 ± 19/0.74 ± 0.27 for union of all non-enhancing components (i.e., NET, CC, ED), and 0.98 ± 0.02 for brain tissue in both internal/external test sets.

Conclusions: Our proposed automated brain extraction and tumor subregion segmentation models demonstrated accurate performance on segmentation of the brain tissue and whole tumor regions in pediatric brain tumors and can facilitate detection of abnormal regions for further clinical measurements.

Keywords: deep learning; magnetic resonance imaging; pediatric brain tumor; skull-stripping; tumor segmentation.

Abstract

Grants and funding