Challenges with segmenting intraoperative ultrasound for brain tumours - Summary - MDSpire

Challenges with segmenting intraoperative ultrasound for brain tumours

  • By

  • Alistair Weld

  • Luke Dixon

  • Giulio Anichini

  • Neekhil Patel

  • Amr Nimer

  • Michael Dyck

  • Kevin O’Neill

  • Adrian Lim

  • Stamatia Giannarou

  • Sophie Camp

  • August 1, 2024

  • 0 min

Share

Objective:

To assess the challenges in tumour boundary detection using intraoperative ultrasound (iUS), specifically focusing on interobserver variation and imaging accuracy among experienced operators.

Key Findings:
  • iUS has a 77% gross total resection rate in glioma surgery, comparable to other navigation methods, indicating its effectiveness.
  • iUS shows 72.2% pooled sensitivity and 93.5% pooled specificity in assessing diffuse glioma resection, highlighting its diagnostic potential.
  • Challenges in tumour boundary detection include interobserver variation and imaging accuracy, which may affect surgical outcomes.
Interpretation:

The study highlights significant challenges in the segmentation of brain tumours using iUS, emphasizing the need for improved training and techniques to enhance accuracy and reduce interobserver variability.

Limitations:
  • Limited number of annotators and images may affect generalizability of the findings.
  • Variability in operator experience could influence results, potentially skewing the assessment of interobserver variation.
Conclusion:

Addressing segmentation errors and improving training and tools are essential for the broader adoption of iUS in brain tumour surgeries, ultimately aiming to enhance patient outcomes.

Original Source(s)

Related Content