TORS in the Multidisciplinary Care of Patients with Oropharyngeal Squamous Cell Carcinoma Guideline

2025-02-11

Dr. Chris Holsinger shares the new guideline from ASCO on transoral robotic surgery (TORS) for patients with oropharyngeal squamous cell carcinoma. He reviews the evidence-based recommendations on baseline assessment, the role of TORS in HPV-positive and HPV-negative disease and in the salvage/recurrent setting, which patients are eligible or ineligible for TORS, and the role of adjuvant therapy. He discusses the importance of multidisciplinary collaboration and shared decision-making between patients and their clinicians. Read the full guideline, “Transoral Robotic Surgery in the Multidisciplinary Care of Patients with Oropharyngeal Squamous Cell Carcinoma: ASCO Guideline.”

Deep Learning for Automatic Segmentation of Pituitary Adenomas: A Videomics Study

Operative Neurosurgery · 2025-10-01

BACKGROUND AND OBJECTIVES: Videomics, which integrates video-endoscopy and artificial intelligence, presents significant potential for real-time surgical analysis. Accurate intraoperative segmentation of pituitary adenomas (PAs) is crucial in endoscopic surgery to improve surgical precision. This study evaluates the performance of different deep learning (DL) models, namely the Swin Transformer, you only look once (YOLO), and Mask R-CNN, for automated PA segmentation, focusing on improving the accuracy of tumor boundary delineation. METHODS: This retrospective study involved patients who underwent endoscopic endonasal surgery for confirmed PAs from January 2022 to December 2023. A Data set of 700 representative frames was extracted. Two clinicians manually segmented the frames (inter-rater reliability of κ = 0.85). The Data set was split into 70% for training (from 14 videos), 15% for validation (from 3 videos), and 15% for testing (from 3 videos). YOLO, Mask R-CNN, and Swin Transformer models were trained and optimized for 100 epochs using mean Average Precision (mAP) as primary metric. Kruskal-Wallis H-test was used for overall comparisons ( P < .05), with pairwise Mann-Whitney U tests for detailed comparisons between models. RESULTS: The Swin Transformer model achieved superior segmentation performance, with a test segmentation mAP[0.50] of 0.607, significantly outperforming YOLOv8x (mAP[0.50] = 0.416; P = .02, 95% CI: [0.56-0.65]) and Mask R-CNN (mAP[0.50] = 0.480; P = .04, 95% CI: [0.57-0.64]). The Swin Transformer model's Dice Similarity Coefficient was 0.89 ( P < .01, 95% CI: [0.86-0.92]), compared with 0.83 for YOLOv8x and 0.81 for Mask R-CNN. The Swin Transformer also displayed optimal recall (0.91, P < .05, 95% CI: [0.88-0.94]) and precision (0.88, P < .05, 95% CI: [0.85-0.91]). CONCLUSION: The Swin Transformer model demonstrated the highest accuracy in PA boundary delineation among tested models, underscoring its potential as an advanced tool for intraoperative PA segmentation in endoscopic endonasal surgery.

Artificial intelligence for automatic detection and segmentation of nasal polyposis: a pilot study

European Archives of Oto-Rhino-Laryngology · 2024-07-13 · 9 citations

La laryngologie au crible de ses éponymes

Annales françaises d Oto-rhino-laryngologie et de Pathologie Cervico-faciale · 2019-12-01

Laryngology in the mirror of its eponyms

European Annals of Otorhinolaryngology Head and Neck Diseases · 2019-09-19 · 5 citations

Abstract 23: A flexible next-generation robotic system for transoral robotic nasopharyngectomy: A comparative preclinical study

Clinical Cancer Research · 2017-11-30 · 3 citations

Abstract Objective: To compare the technical efficacy and extent of instrument reach in performing transoral robotic nasopharyngectomy with the current da Vinci Si surgical robot system (Intuitive Surgical Inc., Sunnyvale CA) and the flexible next-generation robotic system (Da Vinci SP Surgical System, Model SP999, Endo Wrist SP, Intuitive Surgical, Inc.). Study Design: Preclinical study using human cadaver. Materials and Method: Transoral resection of the nasopharyngeal wall and dissection of the parapharyngeal fat space from midline was performed on one side with the da Vinci Si robotic system and the da Vinci SP robotic system on the contra-lateral side in a fresh cadaver. The soft palate was elevated with sutures. For the da Vinci Si system, a 12-mm 30o telescope facing superiorly with 5-mm Maryland forceps and 5-mm monopolar cautery was used to perform the dissection. For the da Vinci SP system, the flexible camera system with 6-mm monopolar cautery spatula, 6-mm bipolar Maryland forceps and 6-mm prograsp forceps were employed for dissection. Results: The mouth opening was 5 cm. Comparing the surgical view, the da Vinci SP system gave a much wider view with both Eustachian tube opening visible and the whole posterior edge of the vomer in view. In the da Vinci Si system, only the Eustachian tube cushion of the side of dissection was visible and only the attachment of the vomer bone to the roof of the nasopharynx was visible. For instrument reach, the da Vinci SP system can dissect up to 2 cm lateral to the medial pterygoid plate while the da Vinci Si system can only reach 1 cm beyond the medial pterygoid plate laterally. In the da Vinci SP system, all 3 instruments arms together with the flexible camera could be deployed for dissection. Occasional collisions of the robotic arms inside the oral cavity can be resolved by the console surgeon adjusting the positions of the robotic instruments. On the da Vinci Si system, only 2 robotic arms and the camera arm can be deployed as the external part of the robotic arms are bulky and prevented deployment of all 4 arms. External collision of the robotic arms occurred frequently and in several instance required the bedside surgeon to reposition the robotic arms. Conclusion: The flexible next-generation surgical robotic system provided superior visualization of the nasopharynx and allowed dissection with 3 robotic instruments. Compared with a standard robotic system, the flexible next-generation surgical robotic system can reach more laterally into the parapharyngeal space to perform dissection. Citation Format: Raymond King-Yin Tsang, Chris Holsinger. A flexible next-generation robotic system for transoral robotic nasopharyngectomy: A comparative preclinical study [abstract]. In: Proceedings of the AACR-AHNS Head and Neck Cancer Conference: Optimizing Survival and Quality of Life through Basic, Clinical, and Translational Research; April 23-25, 2017; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2017;23(23_Suppl):Abstract nr 23.

Cancers of the Larynx: Tis, T1, T2 Evaluation and Management

2016-01-01 · 6 citations

Origins of the binocular head mirror: The mystery of Dr. Clar, clarified

International Journal of Pediatric Otorhinolaryngology · 2015-11-24 · 6 citations

Technology with a Twist: Tools and Techniques to Advance Patient Care and Inspire Innovation

Otolaryngology · 2014-09-01

Program Description: There are significant technological advances occurring in different otolaryngology subspecialties. In addition, there are many opportunities for cross‐pollenization of ideas to envision novel ways to use these technologies. In this miniseminar, the participant will learn about novel technologies being applied in a selected number of technology‐heavy areas of otolaryngology. The panel and audience will engage in an interactive discussion about the different technologies and where else these could be employed or changed to solve other clinical problems. Topics include intraoperative computed tomography advances, vascular injury and control, frontiers in robotic surgery, computer‐assisted surgery, middle ear gels, 3‐dimensional printing, and biomaterials. Educational Objectives: (1) Discuss new technologies being applied in different fields within otolaryngology. (2) Review where these technologies have inherent strengths and limits in their current application. (3) Synthesize new and unique applications for these technologies in otolaryngology.

Transoral robotic surgery (TORS)

Head & Neck · 2012-09-10 · 21 citations