Computer Vision Foundation Models in Endoscopy: Proof of Concept in Oropharyngeal Cancer.

OBJECTIVES: To evaluate the performance of vision transformer-derived image embeddings for distinguishing between normal and neoplastic tissues in the oropharynx and to investigate the potential of computer vision (CV) foundation models in medical imaging. METHODS: Computational study using endoscopic frames with a focus on the application of a self-supervised vision transformer model (DINOv2) for tissue classification. High-definition endoscopic images were used to extract image patches that were then normalized and processed using the DINOv2 model to obtain embeddings. These embeddings served as input for a standard support vector machine (SVM) to classify the tissues as neoplastic or normal. The model's discriminative performance was validated using an 80-20 train-validation split. RESULTS: From 38 endoscopic NBI videos, 327 image patches were analyzed. The classification results in the validation cohort demonstrated high accuracy (92%) and precision (89%), with a perfect recall (100%) and an F1-score of 94%. The receiver operating characteristic (ROC) curve yielded an area under the curve (AUC) of 0.96. CONCLUSION: The use of large vision model-derived embeddings effectively differentiated between neoplastic and normal oropharyngeal tissues. This study supports the feasibility of employing CV foundation models like DINOv2 in the endoscopic evaluation of mucosal lesions, potentially augmenting diagnostic precision in Otorhinolaryngology. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:4535-4541, 2024.

Treatment of oropharyngeal squamous cell carcinoma: Is swallowing quality better after TORS or RT?

BACKGROUND AND PURPOSE: To answer an important question regarding the long-term morbidity of two oncological equivalent treatment for oropharyngeal squamous cell carcinoma (OPSCC), namely a comparison of swallowing function results between patients treated with trans-oral robotic surgery (TORS) versus patients treated with radiotherapy (RT). MATERIALS AND METHODS: Studies included patients with OPSCC treated with TORS or RT. Articles reporting complete data on MD Anderson Dysphagia Inventory (MDADI) and comparing the two treatments (TORS vs RT) were included in the meta-analysis. Swallowing assessed with MDADI was the primary outcome, the evaluation with instrumental methods was the secondary aim. RESULTS: Included studies provided a total of 196 OPSCC primarily treated with TORS vs 283 OPSCC primarily treated with RT. The mean difference in MDADI score at the longest follow-up was not significantly different between TORS and RT group (mean difference [MD] -0.52; 95% CI -4.53-3.48; p = 0.80). After treatment, mean composite MDADI scores demonstrated a slight impairment in both groups without reaching a statistical difference compared to the baseline status. DIGEST score and Yale score showed a significantly worse function in both treatment groups at 12-month follow-up compared to baseline status. CONCLUSION: The meta-analysis demonstrates that up-front TORS (+- adjuvant therapy) and up-front RT (+- CT) appear to be equivalent treatments in functional outcomes in T1-T2, N0-2 OPSCC, however, both treatments cause impaired swallowing ability. Clinicians should have a holistic approach and work with patients to develop an individualized nutrition plan and swallowing rehabilitation protocol from diagnosis to post-treatment surveillance.

Influence of Otolaryngological Subspecialties on Perception of Transoral Robotic Surgery: An International YO-IFOS Survey.

BACKGROUND: To investigate perception, adoption, and awareness on the part of otolaryngology and head and neck surgeons (OTO-HNS) of transoral robotic surgery (TORS). METHODS: Several items assessed: awareness/perception; access to TORS; training; indications and advantages/hurdles to TORS practice. A subanalysis was performed to assess differences according to the identified otolaryngological subspecialties. RESULTS: A total of 359 people completed the survey. Among subspecialties, while for otolaryngologists 30/359 (8.4%) and H&N surgeons 100/359 (27.9%) TORS plays an effective role in hospital stay, laryngologists frequently disagreed (54.3%). There was a lower incidence among rhinologists and otologists (1.9%). Pediatric surgeons (0.8%) reported a positive response regarding the adoption of robotic surgery, and head and neck specialists expressed an even greater response (14.2%). Low adherence was related to perceived cost-prohibitive TORS, by 50% of H&N surgeons. CONCLUSIONS: Perception, adoption, and knowledge about TORS play a key role in the application of the robotic system, significantly varying across subspecialties.

Open and endoscopic surgery improve survival for squamous and nonsquamous cell nasopharyngeal carcinomas: An NCDB cohort study.

BACKGROUND: Nasopharyngeal tumors (NPTs) are primarily treated with nonsurgical therapy. Recent studies have demonstrated endoscopic salvage surgery for NPT recurrences may improve survival relative to reirradiation. However, there are very limited data on open compared with endoscopic approaches for NPTs. We investigated whether endoscopic and open surgical approaches to the nasopharynx improve overall survival for all histologic subtypes of NPTs. METHODS: We performed a retrospective cohort study using the National Cancer Database (NCDB). All adult patients with NPTs from 2004 to 2016 without distant metastasis who underwent treatment with curative intent were included. We extracted clinical and treatment variables to assess our primary outcome of overall survival. RESULTS: On univariate analysis, patients undergoing endoscopic surgery, but not open surgery, had significantly improved overall survival relative to those undergoing nonsurgical treatment. Post hoc analysis demonstrated significantly improved overall survival for surgery in patients with minor salivary gland histology, but not squamous cell carcinoma (SCC) histology or by T or N classification. A Cox proportional hazards model was used for multivariate regression. After adjusting for covariates, both endoscopic and open approaches were associated with improved overall survival relative to nonsurgical treatment for all tumor types. A multivariate regression of SCC found that open surgery, but not endoscopic surgery, was significantly associated with improved overall survival. CONCLUSION: Both endoscopic and open surgical approaches are associated with improved overall survival of patients with NPT. These findings highlight important oncologic validity as endoscopic and robotic platforms to the nasopharynx become more widely adopted.

Long-term results of robotic-assisted nasopharyngectomy for recurrent nasopharyngeal carcinoma.

BACKGROUND: We have previously reported our early experience in robotic-assisted nasopharyngectomy. The current case series is a report of our experience in 33 robotic-assisted nasopharyngectomy. METHODS: Prospective series of patients who underwent robotic-assisted nasopharyngectomy for local recurrent nasopharyngeal carcinoma from January 2010 to March 2019. RESULTS: Thirty-one patients underwent robotic-assisted nasopharyngectomy with two additional second procedure for positive margin. Median age is 55 years (29-85). Twenty-five patients had rT1 disease and six patients had tumor invaded sphenoid floor (rT3). Median operative time was 227 min and median blood loss was 200 ml. The median follow-up period for all patients were 38 months. Four patients had local recurrence. Five-year local control rate, overall survival, and disease-free survival are 85.1%, 55.7%, and 69.1%, respectively. CONCLUSION: Robotic-assisted nasopharyngectomy for recurrent nasopharyngectomy was showed to have a high local control rate. The operating time was comparable to open surgery.

Posttreatment FDG-PET/CT Hopkins criteria predict locoregional recurrence after definitive radiotherapy for oropharyngeal squamous cell carcinoma.

BACKGROUND: Metabolic response assessment for oropharyngeal squamous cell carcinoma (OPSCC) aids in identifying locoregional persistence/recurrence (LRR). The Hopkins Criteria are a standardized qualitative response assessment system using posttreatment FDG-PET/CT. METHODS: We conducted a retrospective cohort study of patients with node-positive OPSCC treated with definitive (chemo)radiotherapy. We assessed Hopkins Criteria performance for LRR, then developed and validated a competing-risks model. RESULTS: Between 2004 and 2018, 259 patients were included with median follow-up of 43 months. The Hopkins Criteria sensitivity, specificity, negative predictive value, and accuracy were 68%, 88%, 95%, and 85%. The 36-month cumulative incidence of LRR was greater with positive scores (45% vs. 5%, HR 12.60, p < 0.001). PET/CTs performed ≤10 weeks after radiotherapy were associated with a four-fold increase in pathologically negative biopsies/surgeries (36% vs. 9%, p = 0.03). The AUC for LRR was 0.89 using a model integrating the Hopkins score. CONCLUSIONS: The Hopkins Criteria predict LRR with high accuracy for OPSCC response assessment.

Precision head and neck surgery: robotics and surgical vision technology.

PURPOSE OF REVIEW: As the molecular basis of head and neck cancer becomes more clearly defined, precision medicine has gradually refined the multidisciplinary treatment paradigm for patients with oropharyngeal cancer. Although precision medicine is often thought to refer to new molecular diagnostics or unique medical therapy, the recent adoption of robotic surgery has ushered in the era of 'precision' head and neck surgery. RECENT FINDINGS: Surgeons now routinely utilize a virtual reality environment to reduce the morbidity of head and neck surgical care and improve oncologic and functional outcomes. The development and subsequent FDA approval of the da Vinci SP system, a single-arm system with a flexible camera, has allowed for improved visualization and access to the deep oropharynx and larynx. Groups investigating anti-EGFR antibodies tagged with fluorescent dye as well as inherent autofluorescence differences between normal and cancerous mucosal tissues show promise for improving positive surgical margin rates. SUMMARY: The evolution of robotics and visualization for oropharyngeal cancer represents a novel and innovative utilization of new technology to improve care. Further advancements in techniques, from refinement of the robotic platform itself, to novel real-time tumour imaging options will be critical to further advance precision care for these patients.

Prolongation of definitive head and neck cancer radiotherapy: Survival impact and predisposing factors.

BACKGROUND AND PURPOSE: To quantify the survival impact of prolongation of definitive radiotherapy (RT) for head and neck cancer in a national, modern cohort, and to identify predictive factors for prolongation. MATERIALS AND METHODS: The National Cancer Database was queried for adults with non-metastatic cancer of the nasopharynx, oropharynx, larynx, or hypopharynx diagnosed 2004-2015, treated with definitive RT to 66-70 Gy in 30-35 fractions at 2-2.2 Gy per fraction. Multivariable Cox regression and propensity score matching were used to model the survival impact of RT prolongation, adjusting for potential confounders such as age and comorbidity. Predictors of RT prolongation were identified using multivariable multinomial logistic regression. RESULTS: In total, 36,367 patients were identified. As a continuous variable, RT prolongation increased the relative hazard of death by 2% per day (P < .0001). In the matched cohorts, patients with short (4-8 days) or long prolongation (>8 days) had lower absolute 4-year overall survival by 4% and 12%, respectively (P < .0001), while prolongation of 1-3 days was not significantly adverse. Major predictors of increased risk of prolongation were administration of systemic therapy, baseline comorbidity, lack of private insurance, and tumor/nodal stage. Conversely, higher facility volume was significantly protective, with a 55% lower risk of long prolongation within the topmost quartile (>11.5 patients/year). CONCLUSION: RT prolongation, especially >8 days, is significantly deleterious. Systemic therapy and facility volume were major predictors. Early identification of patients at increased risk of treatment interruptions may facilitate implementation of preventive measures.

Robotic surgery may improve overall survival for T1 and T2 tumors of the hypopharynx: An NCDB cohort study.

BACKGROUND: Hypopharyngeal cancer is associated with poor survival. Robotic surgery is emerging as a treatment for hypopharyngeal tumors, but no rigorous data are available to assess its effect on survival. METHODS: The National Cancer Database (NCDB) was used to identify patients with T1 and T2 hypopharyngeal tumors undergoing robotic surgery, laser surgery, and primary radiation with or without chemotherapy from 2010 to 2016. All adult patients with available staging and no distant metastasis were included. RESULTS: We compared 57 patients undergoing robotic surgery, 236 undergoing laser surgery, and 5,742 undergoing primary radiation. Compared to laser surgery, patients undergoing robotic surgery were significantly more likely to have negative margins, neck dissection, lower incomes, and care at an academic center. Rates of robotic surgery also significantly increased from 2010 to 2015. After multivariate regression, robotic surgery was associated with significantly improved overall survival compared to laser surgery and primary radiation. CONCLUSION: Robotic surgery improves overall survival for T1 and T2 hypopharyngeal tumors compared to laser surgery and primary radiation in this NCDB cohort. This effect may be mediated by decreased positive margin rates relative to laser surgery. Rates of hypopharyngeal robotic surgery are expected to increase with wider adoption of robotic platforms and may improve overall survival rates for hypopharyngeal cancer.

Postoperative Observation Versus Radiotherapy for Pathologic N1 Oral Cavity Squamous Cell Carcinoma.

OBJECTIVES: To investigate the benefit of postoperative radiotherapy (PORT) for low-volume (pN1) nodal disease after resection of oral cavity squamous cell carcinoma. MATERIALS AND METHODS: The National Cancer Database was queried for adults with nonmetastatic squamous cell carcinoma of the oral cavity treated by surgical resection with pathologic stage T1-2 N0-2 (American Joint Committee on Cancer 7th edition) and with the maximal exclusion of standard indications for PORT. Overall survival was compared within pN1 for observation versus PORT and then compared for pN1 versus pN0 and versus pN2 stratified by receipt of observation or PORT. Multivariable Cox regression was used to adjust for potential confounders between PORT and survival, including comorbidity and age. RESULTS: Overall 5017 pN0, 530 pN1, and 253 pN2 patients were identified, of whom 9%, 35%, and 64% received PORT, respectively. Within the pN1 cohort, PORT was associated with improved survival versus observation (adjusted hazard ratio, 0.66; 95% confidence interval, 0.46-0.97; P=0.03). Among observed patients, the prognosis of pN1 was equivalent to pN2 and inferior to pN0; in contrast, among patients treated with PORT, the prognosis of pN1 was equivalent to pN0 and superior to pN2. Without PORT, pN1 remained an adverse risk factor relative to pN0 regardless of the depth of invasion, lymph node size, lymph node location, and extent of lymph node dissection. CONCLUSIONS: PORT was associated with a survival benefit compared with observation. Notably, pN1 was an adverse risk factor relative to pN0 if, and only if, patients did not receive PORT, suggesting pN1 by itself may be an indication for PORT.

Bleeding Complications After Transoral Robotic Surgery: A Meta-Analysis and Systematic Review.

OBJECTIVE: Postoperative hemorrhage is the most common complication of transoral robotic surgery (TORS), the severity of which can range from minor bleeding treated with observation to catastrophic hemorrhage leading to death. To date, little is known about the incidence, risk factors, and management of post-TORS hemorrhage. STUDY DESIGN: Systematic Review and Metanlysis. METHODS: A systematic review of the published literature using the Cochrane Handbook for Systematic Reviews of Interventions was performed and examined TORS, postoperative hemorrhage, and the use of prophylactic transcervical arterial ligation (TAL). RESULTS: A total of 13 articles were included in the analysis. To date, there have been 332 cases of hemorrhage following a total of 5748 TORS. The pooled median post-TORS hemorrhage rate was 6.47%. The overall incidence of minor and major hemorrhage was 5.29% and 2.90%. Patients with prior radiation (relative risk [RR] = 1.46, 95% confidence interval [CI] = 1.00-2.12), large tumors (RR = 2.11, 95% CI = 1.48-2.99), and those requiring perioperative coagulation (RR = 2.25, 95% CI = 1.54-3.28) had significantly higher relative risks of hemorrhage. There was no significant difference in the relative risk of overall hemorrhage with TAL. Looking at major hemorrhage, patients undergoing TAL had a large but insignificant relative risk reduction in post-TORS hemorrhage (RR = 0.40, 95% CI = 0.15-1.07). CONCLUSION: The incidence of post-TORS hemorrhage is low (5.78%), and for major hemorrhage requiring emergent embolization, TAL, or tracheotomy to control hemorrhage it is even lower (2.90%). Large tumors, perioperative anticoagulation, and prior radiation were associated with significantly increased risk of post-TORS hemorrhage. TAL does not reduce the overall incidence of post-TORS hemorrhage but may lead to fewer severe hemorrhages. LEVEL OF EVIDENCE: III Laryngoscope, 131:95-105, 2021.

Anatomical-based classification for transoral base of tongue resection.

BACKGROUND: To propose a classification of transoral base of tongue (BOT) procedures able to provide uniform terminology in order to better define postoperative results. METHODS: The classification resulted from the consensus of the different authors and is based on anatomical and surgical principles. RESULTS: The classification comprises three types of BOT resections: type 1 is the resection of the entire lingual tonsil to the muscular plane; type 2 is performed by removing the entire lingual tonsil and part of BOT muscles; type 3 is performed by removing the entire lingual tonsil and the entire BOT muscles. Based on the extension of the dissection, we can use the suffix A (contralateral BOT), B (supraglottic larynx), C (lateral oropharynx), and/or D (oral tongue). CONCLUSION: The proposed classification could allow us to easily compare data from different centers.

The emergence of endoscopic head and neck surgery.

Endoscopic and minimally invasive techniques represent a natural evolution for the discipline of head and neck surgery. Endoscopic head and neck surgery (eHNS) encompasses transoral laser microsurgery, transoral robotic surgery, as well as video-assisted and robotic surgery of the neck and thyroid. In the next 5 years, with robotic surgery and laser technology as a common platform, we foresee the development and widespread use of eHNS procedures, via transoral and transaxillary approaches.

A new endoscopic surgical approach to the larynx, hypopharynx, and neck lymphatics: The robotic-assisted extended "Sistrunk" approach (RESA).

BACKGROUND: We report on the feasibility of a novel robotic-assisted extended "Sistrunk" approach (RESA) to the larynx, hypopharynx, and lateral neck lymphatics. METHODS: Studies were performed using the da Vinci Xi and SP system on three cadavers comprising of three supraglottic laryngectomies, one partial hypopharyngectomy, and four lateral level II to IV neck dissections. RESULTS: In all resections at first a central common working space overlying the hyoid bone was created. The da Vinci Xi system was used with two vestibular and two submental ports for laryngeal/hypopharyngeal resections, and an additional port through a facelift incision for level II to IV neck dissections. The da Vinci SP system was used with only one submental port. CONCLUSIONS: We describe herein a novel endoscopic robotic approach to the larynx, hypopharynx, and neck based on the traditional "Sistrunk" procedure. The technique should help improving exposure of the primary lesion and reduce access-related morbidity to the neck.

Management of dysphagia in the patient with head and neck cancer during COVID-19 pandemic: Practical strategy.

The global pandemic of 2019 novel coronavirus disease (COVID-19) has tremendously altered routine medical service provision and imposed unprecedented challenges to the health care system. This impacts patients with dysphagia complications caused by head and neck cancers. As this pandemic of COVID-19 may last longer than severe acute respiratory syndrome (SARS) in 2003, a practical workflow for managing dysphagia is crucial to ensure a safe and efficient practice to patients and health care personnel. This document provides clinical practice guidelines based on available evidence to date to balance the risks of SARS-CoV-2 exposure with the risks associated with dysphagia. Critical considerations include reserving instrumental assessments for urgent cases only, optimizing the noninstrumental swallowing evaluation, appropriate use of personal protective equipment (PPE), and use of telehealth when appropriate. Despite significant limitations in clinical service provision during the pandemic of COVID-19, a safe and reasonable dysphagia care pathway can still be implemented with modifications of setup and application of newer technologies.

Robotic Head and Neck Surgery.

Robotic head and neck surgery applies minimally invasive principles to unique anatomy and natural orifices for surgical access. Expanding from a tradition of minimally invasive endoscopic otolaryngology procedures, surgical robotics has transformed head and neck surgery. However, surgeons are faced with significant challenges, and anatomic constraints impede visualization and constrain surgical maneuvers. Transoral robotic surgery (TORS) has been developed over the past decade with favorable oncologic and functional outcomes, changing the way head and neck surgeons approach both malignant and benign diseases. As new robotic platforms emerge, access will continue to improve and push the boundaries of minimally invasive approaches.

Submandibular gland resection via the trans-hairline approach: A preclinical study of a novel flexible single-port surgical system and the surgical experiences of standard multiarm robotic surgical systems.

BACKGROUND: Cosmetic outcome after submandibular gland (SMG) surgery has greatly improved since the development of robotic surgery through a trans-hairline approach. However, the bulky sizes of robotic arms and the rigid design of camera and instruments in the current multiarm robotic systems increased the surgical difficulty. METHODS: Clinical and preclinical studies demonstrated the surgical configuration and procedures of robotic trans-hairline SMG resection using a flexible, single-port, and multiarm systems. RESULTS: The surgical procedures of trans-hairline approach for SMG resection could be successfully performed using the flexible single-port (SP) robotic system in the preclinical study. The unique features include an easier docking procedure, different viewing angles, the use of the third arm, and coordination of instrument positions without a bedside assistant, which are unavailable in current multiarm robotic systems. CONCLUSIONS: This study demonstrates the feasibility and the advantages of applying the flexible, SP robotic system in SMG resection through the trans-hairline approach.