Deep learning-based anatomical site classification for upper gastrointestinal endoscopy - Takeaways - MDSpire

Deep learning-based anatomical site classification for upper gastrointestinal endoscopy

  • By

  • Qi He

  • Sophia Bano

  • Omer F. Ahmad

  • Bo Yang

  • Xin Chen

  • Pietro Valdastri

  • Laurence B. Lovat

  • Danail Stoyanov

  • Siyang Zuo

  • May 6, 2020

  • 0 min

Share

  • 1

    Oesophagogastroduodenoscopy (EGD) is essential for diagnosing upper gastrointestinal diseases, including early gastric cancer.

  • 2

    AI can enhance EGD by improving photo-documentation and supporting the detection of lesions through deep learning methods.

  • 3

    A modified guideline for upper GI endoscopic photo-documentation was proposed, balancing British and Japanese standards.

  • 4

    A new annotated dataset of 3704 EGD images was created to aid in the development and validation of AI systems for endoscopy.

  • 5

    The study introduced a complete workflow for EGD image classification, including data collection and automatic ROI extraction.

Original Source(s)

Deep learning-based anatomical site classification for upper gastrointestinal endoscopy

  • by Qi He, Sophia Bano, Omer F. Ahmad, Bo Yang, Xin Chen, Pietro Valdastri, Laurence B. Lovat, Danail Stoyanov, Siyang Zuo

  • May 6, 2020

Related Content

A novel technique for flat umbilicus repair in abdominoplasty: bipolar fan-shaped incision and folded suture using paraumbilical flaps

Airway pressure reliably predicts intra-abdominal pressure during laparoscopic surgery

Impact of a digital pre- and rehabilitation program on postoperative outcomes after pelvic gynecological surgery