Automatic recognition of anatomical structures and surgical phases in robot-assisted minimally invasive esophagectomy (RAMIE) using deep learning: a retrospective cohort study - Report - MDSpire

Automatic recognition of anatomical structures and surgical phases in robot-assisted minimally invasive esophagectomy (RAMIE) using deep learning: a retrospective cohort study

  • By

  • Romy C. van Jaarsveld

  • Yiping Li

  • Ronald L. P. D. de Jong

  • Franco Badaloni

  • Gino M. Kuiper

  • Tim J. M. Jaspers

  • Marcel Breeuwer

  • Fons van der Sommen

  • Richard van Hillegersberg

  • Yasmina Al Khalil

  • Jelle P. Ruurda

  • July 9, 2026

  • 0 min

Share

Clinical Report: Deep Learning-Based Automated Identification in RAMIE

Overview

This study presents a retrospective analysis aimed at developing real-time deep learning algorithms for the recognition of anatomical features and surgical phases during Robot-Assisted Minimally Invasive Esophagectomy (RAMIE).

Background

Esophageal cancer is a significant global health concern, ranking 11th in incidence and 7th in mortality. Robot-Assisted Minimally Invasive Esophagectomy (RAMIE) is increasingly favored due to its advantages in visualization and precision during surgery. However, the complexity of the peri-esophageal anatomy and the learning curve associated with RAMIE necessitate improved intraoperative guidance.

Data Highlights

No numerical data or trial data was provided in the source material.

Key Findings

  • Development of real-time deep learning algorithms for anatomy and surgical phase recognition in RAMIE.
  • Creation of two datasets: one for anatomy segmentation and another for surgical phase recognition.
  • Manual annotation of 1504 frames from 53 RAMIE videos to ensure high-quality data for model training.
  • Recognition of key anatomical structures such as the azygos vein, vena cava, aorta, and right lung.

Clinical Implications

The implementation of deep learning algorithms in RAMIE could enhance surgeons' ability to identify critical anatomical structures in real-time.

Conclusion

The study highlights the feasibility of utilizing deep learning for anatomical and surgical phase recognition in RAMIE.

Related Resources & Content

  1. Surgical Endoscopy, 2023 -- Utilizing Deep Learning for Identifying Critical Anatomical Features in Robot-Assisted Minimally Invasive Esophagectomy
  2. Surgical Endoscopy, 2023 -- TEsoNet: Transferring Knowledge for Surgical Phase Identification from Laparoscopic Sleeve Gastrectomy to the Laparoscopic Component of Ivor–Lewis Esophagectomy
  3. Surgical Endoscopy, 2022 -- Systematic Review of Computer-Assisted Anatomical Identification in Intrathoracic and Abdominal Surgical Procedures
  4. Oesophageal cancer - ScienceDirect, 2024 -- Epidemiology and Treatment Guidelines
  5. npj Digital Medicine — Extensive Self-Supervised Video Foundation Model for Enhanced Intelligent Surgical Procedures
  6. Oesophageal cancer - ScienceDirect
  7. ESMO Clinical Practice Guideline interim update on the treatment of locally advanced oesophageal and oesophagogastric junction adenocarcinoma and metastatic squamous-cell carcinoma - PMC
  8. SEOM–GEMCAD–TTD clinical guideline for the diagnosis and treatment of esophageal cancer (update 2025) - PMC
  9. Ten-Year Outcome of Neoadjuvant Chemoradiotherapy Plus Surgery for Esophageal Cancer: The Randomized Controlled CROSS Trial | Journal of Clinical Oncology
  10. FDA Approves Nivolumab for Resected Esophageal or GEJ Cancer - ASCO
  11. 2026 NCCN Clinical Practice Guidelines in Oncology®: Key Updates Across Tumor Types - The ASCO Post
  12. German guidelines for the diagnosis and treatment of squamous-cell carcinoma and adenocarcinoma of the esophagus—version 4.0 - PMC
  13. Open, hybrid, minimally invasive, and robotic-assisted transthoracic esophagectomy for cancer: a network meta-analysis of randomized trials - PMC
  14. Approaches for esophagectomy for esophageal cancer: a Network Meta-Analysis - ScienceDirect
  15. Robot-assisted Minimally Invasive Thoracolaparoscopic Esophagectomy Versus Open Transthoracic Esophagectomy for Resectable Esophageal Cancer: A Randomized Controlled Trial - PubMed
  16. Comparative analysis of robot-assisted minimally invasive esophagectomy versus conventional minimally invasive esophagectomy, a systematic review and meta-analysis - PubMed
  17. Mckeown Esophagectomy: Minimally Invasive Robot-Assisted vs Conventional Technique - Systematic Review and Meta-Analysis of Randomized Clinical Trial - Amorim D. Neves, José Manuel Comprido, Iago T. C. Grillo, Beatriz De Melo, Bernado F. Pompeu, 2026
  18. The Current State of Robot-Assisted Minimally Invasive Esophagectomy (RAMIE): Outcomes from the Upper GI International Robotic Association (UGIRA) Esophageal Registry | Annals of Surgical Oncology | Springer Nature Link
  19. Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge
  20. Benchmarking and Enhancing Surgical Phase Recognition Models for Robotic-Assisted Esophagectomy

Original Source(s)

Automatic recognition of anatomical structures and surgical phases in robot-assisted minimally invasive esophagectomy (RAMIE) using deep learning: a retrospective cohort study

  • by Romy C. van Jaarsveld, Yiping Li, Ronald L. P. D. de Jong, Franco Badaloni, Gino M. Kuiper, Tim J. M. Jaspers, Marcel Breeuwer, Fons van der Sommen, Richard van Hillegersberg, Yasmina Al Khalil, Jelle P. Ruurda

  • July 9, 2026

Related Content

Lateral mini-incision via cervical midline approach versus traditional incision for unilateral thyroid cancer: a retrospective cohort study

Dual-view fusion of log-mel spectrogram encodings for dysarthria detection: use in the context of awake brain surgery

Acetabular superior wall fractures: a distinct acetabular fracture entity