Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Interpretable Models for Detecting and Monitoring Elevated Intracranial Pressure

Darryl Hannan, Steven C. Nesbit, Ximing Wen, Glen Smith, Qiao Zhang, Alberto Goffi, Vincent Chan, Michael J. Morris, John C. Hunninghake, Nicholas E. Villalobos, Edward Kim, Rosina O. Weber, Christopher J. MacLellan

TL;DR

The paper tackles non-invasive detection of elevated intracranial pressure by monitoring optic nerve sheath diameter in ultrasound videos. It introduces two SME-guided, interpretable pipelines: a Convolutional Sparse Coding system and an R2U-Net based measurement system, optimized for mobile devices and small labeled datasets. On a dataset of 61 videos with a $5$ mm ONSD threshold, the R2U-Net approach achieves the highest video accuracy of 82.67% and outperforms ViT-B/16 and ConvNeXT baselines. Qualitative SME evaluation and explicit visualization of measurement cues support clinical applicability and interpretability for non-expert users.

Abstract

Detecting elevated intracranial pressure (ICP) is crucial in diagnosing and managing various neurological conditions. These fluctuations in pressure are transmitted to the optic nerve sheath (ONS), resulting in changes to its diameter, which can then be detected using ultrasound imaging devices. However, interpreting sonographic images of the ONS can be challenging. In this work, we propose two systems that actively monitor the ONS diameter throughout an ultrasound video and make a final prediction as to whether ICP is elevated. To construct our systems, we leverage subject matter expert (SME) guidance, structuring our processing pipeline according to their collection procedure, while also prioritizing interpretability and computational efficiency. We conduct a number of experiments, demonstrating that our proposed systems are able to outperform various baselines. One of our SMEs then manually validates our top system's performance, lending further credibility to our approach while demonstrating its potential utility in a clinical setting.

Interpretable Models for Detecting and Monitoring Elevated Intracranial Pressure

TL;DR

The paper tackles non-invasive detection of elevated intracranial pressure by monitoring optic nerve sheath diameter in ultrasound videos. It introduces two SME-guided, interpretable pipelines: a Convolutional Sparse Coding system and an R2U-Net based measurement system, optimized for mobile devices and small labeled datasets. On a dataset of 61 videos with a mm ONSD threshold, the R2U-Net approach achieves the highest video accuracy of 82.67% and outperforms ViT-B/16 and ConvNeXT baselines. Qualitative SME evaluation and explicit visualization of measurement cues support clinical applicability and interpretability for non-expert users.

Abstract

Detecting elevated intracranial pressure (ICP) is crucial in diagnosing and managing various neurological conditions. These fluctuations in pressure are transmitted to the optic nerve sheath (ONS), resulting in changes to its diameter, which can then be detected using ultrasound imaging devices. However, interpreting sonographic images of the ONS can be challenging. In this work, we propose two systems that actively monitor the ONS diameter throughout an ultrasound video and make a final prediction as to whether ICP is elevated. To construct our systems, we leverage subject matter expert (SME) guidance, structuring our processing pipeline according to their collection procedure, while also prioritizing interpretability and computational efficiency. We conduct a number of experiments, demonstrating that our proposed systems are able to outperform various baselines. One of our SMEs then manually validates our top system's performance, lending further credibility to our approach while demonstrating its potential utility in a clinical setting.
Paper Structure (10 sections, 2 figures, 1 table)

This paper contains 10 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Convolutional Sparse Coding System
  4. R2U-Net System
  5. Experiments and Results
  6. Results
  7. Discussion
  8. Conclusion
  9. Conflicts of Interest
  10. Compliance with Ethical Standards

Figures (2)

  • Figure 1: Output from our R2U-Net-based ONSD measurement system. Each stage of our proposed pipeline surfaces clinically relevant information (colored features rendered on the image) that the model is using to make its final prediction.
  • Figure 2: Grouth truth nerve slice (top) and predicted nerve mask (bottom) for POCUS Atlas image.