Artificial intelligence and endoanal ultrasound: pioneering automated differentiation of benign anal and sphincter lesions - Takeaways - MDSpire

Artificial intelligence and endoanal ultrasound: pioneering automated differentiation of benign anal and sphincter lesions

  • By

  • M. Mascarenhas

  • M. J. Almeida

  • M. Martins

  • F. Mendes

  • J. Mota

  • P. Cardoso

  • B. Mendes

  • J. Ferreira

  • G. Macedo

  • C. Poças

  • June 10, 2025

  • 0 min

Share

  • 1

    Benign anorectal disorders significantly affect quality of life, making accurate diagnosis essential for symptom relief and improved patient outcomes.

  • 2

    Endoanal ultrasonography (EAUS) is the gold standard for assessing anal sphincter integrity but faces limitations in accessibility and training.

  • 3

    Artificial intelligence (AI) has the potential to enhance EAUS diagnostic accuracy and address the shortage of trained professionals.

  • 4

    A convolutional neural network (CNN) was developed to automatically classify anal fissures and lacerations from EAUS images.

  • 5

    The CNN achieved 100% accuracy for anal fissures and high sensitivity and specificity for external and internal lacerations, demonstrating AI's promise in proctology.

Original Source(s)

Artificial intelligence and endoanal ultrasound: pioneering automated differentiation of benign anal and sphincter lesions

  • by M. Mascarenhas, M. J. Almeida, M. Martins, F. Mendes, J. Mota, P. Cardoso, B. Mendes, J. Ferreira, G. Macedo, C. Poças

  • June 10, 2025

Related Content

Diagnostic value of dual-energy CT virtual monochromatic imaging for supraspinatus tendon injuries: a comparison with standard CT and MRI

High-resolution contrast-enhanced MRI with three-dimensional fast spin echo improved the diagnostic performance for identifying pituitary microadenomas in Cushing’s syndrome

MDCT-findings in patients with non-occlusive mesenteric ischemia (NOMI): influence of vasoconstrictor agents