GLAPAL-H: Global, Local, And Parts Aware Learner for Hydrocephalus Infection Diagnosis in Low-Field MRI

Abstract

Objective: The study aims to develop a method for differentiating between healthy, post-infectious hydrocephalus (PIH), and non-post-infectious hydrocephalus (NPIH) in infants using low-field MRI, which is a safer, low-cost alternative to CT scans. The study develops a custom approach that captures hydrocephalic etiology while simultaneously addressing quality issues encountered in low-field MRI.

Methods: Specifically, we propose GLAPAL-H, a Global, Local, And Parts Aware Learner, which develops a multi-task architecture with global, local, and parts segmentation branches. The architecture segments images into brain tissue and CSF while using a shallow CNN for local feature extraction and develops a parallel deep CNN branch for global feature extraction. Three regularized training loss functions are developed - one for each of global, local, and parts components. The global regularizer captures holistic features, the local focuses on fine details, and the parts regularizer learns soft segmentation masks that enable local features to capture hydrocephalic etiology.

Results: The study's results show that GLAPAL-H outperforms state-of-the-art alternatives, including CT-based approaches, for both Two-Class (PIH vs. NPIH) and Three-Class (PIH vs. NPIH vs. Healthy) classification tasks in accuracy, interpretability, and generalizability.

Conclusion/significance: GLAPAL-H highlights the potential of low-field MRI as a safer, low-cost alternative to CT imaging for pediatric hydrocephalus infection diagnosis and management. Practically, GLAPAL-H demonstrates robustness against quantity and quality of training imagery, enhancing its deployability. The code for this work is available here: https://github.com/mukherjeesrijit/glapalh.

Fig. 1:

(A) Comparison of CT and low-field MRI for PIH, NPIH, and healthy infants, with slice counts and label distribution. Note the quality difference between high-quality CT and low-field FLAIR (Fluid Attenuated Inversion Recovery) MRI. CT scans are omitted for healthy infants due to radiation risk. (B, C) BAR-Net [39] activation maps for low-field MRI: (B) global activation across the brain, (C) localized activation (red circles) in brain tissue or CSF, inspiring segmentation-based feature extraction and classification. (D) From [5], reprinted with permission from AAAS, the figure shows preoperative CT scan scoring by two experienced neurosurgeons, assigning points for loculations, debris, calcification, and abscess formation.

Fig. 2:

An overview of the GLAPAL-H model with three parallel branches: (1) the global branch for global feature extraction, (2) the segmentation branch, which employs brain tissue, and CSF mask prediction, and (3) the local branch for extracting the local features with parts-based brain tissue and CSF guidance. Features from the global and local branches are combined through a fusion head using concatenation and linear layers to get the classification outputs. The network optimizes a composite loss function, which includes contributions from the global, local, parts-based, segmentation, and cross-entropy losses.

Fig. 3:

ROC Curves of GLAPAL-H and SOTA methods for both the Two Class and the Three Class Problems.

Fig. 4:

Normalized confusion matrices across labels for the Two Class and Three Class Problems of the top three methods: GLAPAL-H, BAR-Net, and MedNeXt on FLAIR: showing the superiority of GLAPAL-H in robust infection detection.

Fig. 5:

GLAPAL-H shows better robustness considering the perturbation of performance from the Two Class to the Three Class Problem when compared to MedNeXt and BAR-Net.

Fig. 6:

Low Training vs High Training Performance of GLAPAL-H and MedNeXt (Three Class Problem) with 40% and 100% of the training dataset, respectively.

Fig. 7:

Class Activation Maps (CAM) of two PIH infants corresponding to the local and global branches of GLAPAL-H, CAM of GLAPAL-H, along with CAM of MedNeXt and BAR-Net for the Three Class Problem.

Fig. 8:

Examples of Misclassified Edge Cases.