Narrow-Band Imaging in Transoral Laser Surgery for Early Glottic Cancer: A Randomized Controlled Trial

Diagnosis of laryngopharyngeal carcinoma through office-based flexible laryngoscopy as a reliable alternative for biopsies under general anesthesia: Faster diagnostics with equal oncological outcome

PURPOSE

Diagnostic endoscopy with biopsy under general anesthesia (DE-GA) is still considered as the established standard to assess laryngopharyngeal cancer patients. Office-based flexible laryngoscopic biopsy (FLB) offers an alternative, but the effect on oncological outcome remains uncertain. Therefore, the diagnostic process and survival of patients undergoing FLB, compared to those undergoing DE-GA were evaluated.

METHODS

Patients suspected of laryngopharyngeal cancer who underwent FLB were evaluated. Patients with FLB-confirmed squamous cell carcinoma (SCC) were matched with DE-GA patients based on tumor site, T-classification, N-classification, age, and p16 overexpression. Time from first visit to diagnosis (FVD), time to treatment interval (TTI), disease-specific survival (DSS) and overall survival (OS) were analyzed.

RESULTS

FLB yielded a definitive diagnosis in 155/164 (95 %) patients. No complications were observed. Ninety-eight of the 124 patients in which FLB revealed a SCC received curative treatment and were compared with 98 matched patients who underwent DE-GA. Median FVD interval was 6 days after FLB and 15 days after DE-GA (p < 0.001). Median TTI interval (FLB: 28 days, DE-GA: 28 days) was equal (p = 0.91). Oncological outcomes were comparable (p > 0.05) between FLB (OS: 2-yr: 76 %, 5-yr: 42 %; DSS: 2-yr: 86 %, 5-yr: 85 %) and DE-GA groups (OS: 2-yr: 76 %, 5-yr: 50 %; DSS: 2-yr: 81 %, 5-yr: 79 %).

CONCLUSION

FLB in the outpatient setting demonstrates a high diagnostic accuracy, is safe, accelerates the diagnostic process and has no negative effects on clinical outcome compared to DE-GA. Therefore, FLB should be considered as the standard diagnostic procedure in patients suspected of laryngopharyngeal cancer.

Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning

OBJECTIVE

To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos.

METHODS

A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos.

RESULTS

A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos.

CONCLUSION

SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement.

LEVEL OF EVIDENCE

III Laryngoscope, 134:2826-2834, 2024.