Objectives
Neoadjuvant targeted therapy has emerged as a promising treatment strategy for locally aggressive thyroid cancer. Its impact on tumor and adjacent tissues remains a nascent area of study. ...Here we report on a series of six subjects with locally advanced thyroid cancer and recurrent laryngeal nerve (RLN) paralysis who experienced recovery of RLN function with neoadjuvant treatment and describe the morphologic and electrophysiologic characteristics of these recovered nerves.
Methods
This is a multicenter retrospective review. Descriptive analysis was conducted to examine the following parameters for recovered nerves: (1) nerve morphology, characterized as Type A (involving epineurium only) versus Type B (extending beyond epineurium); (2) proximal stimulability (normal vs. abnormal vs. absent); and (3) surgical management (resection vs. preservation).
Results
Six subjects with unilateral VFP were identified. Median time to return of VF mobility was 3 months (range 2–13.5). All nerves (100%) were noted to have Type A morphology at surgery. Proximal stimulability was normal in four subjects (66.7%), abnormal in one (16.7%), and absent in one (16.7%). Nerves that had improvement of function through neoadjuvant therapy were able to be surgically preserved in five subjects (83.3%).
Conclusions
This represents the first characterization of RLNs that have recovered function with neoadjuvant treatment of locally advanced thyroid cancer. Although much remains unknown, our findings indicate carcinomatous neural invasion is a reversible process and recovered nerves may demonstrate normal morphology and electrophysiologic activity.
Level of Evidence
4 Laryngoscope, 134:3415–3419, 2024
Objective
We aimed to establish an artificial intelligence (AI) model to identify parathyroid glands during endoscopic approaches and compare it with senior and junior surgeons' visual estimation.
...Methods
A total of 1,700 images of parathyroid glands from 166 endoscopic thyroidectomy videos were labeled. Data from 20 additional full‐length videos were used as an independent external cohort. The YOLO V3, Faster R‐CNN, and Cascade algorithms were used for deep learning, and the optimal algorithm was selected for independent external cohort analysis. Finally, the identification rate, initial recognition time, and tracking periods of PTAIR (Artificial Intelligence model for Parathyroid gland Recognition), junior surgeons, and senior surgeons were compared.
Results
The Faster R‐CNN algorithm showed the best balance after optimizing the hyperparameters of each algorithm and was updated as PTAIR. The precision, recall rate, and F1 score of the PTAIR were 88.7%, 92.3%, and 90.5%, respectively. In the independent external cohort, the parathyroid identification rates of PTAIR, senior surgeons, and junior surgeons were 96.9%, 87.5%, and 71.9%, respectively. In addition, PTAIR recognized parathyroid glands 3.83 s ahead of the senior surgeons (p = 0.008), with a tracking period 62.82 s longer than the senior surgeons (p = 0.006).
Conclusions
PTAIR can achieve earlier identification and full‐time tracing under a particular training strategy. The identification rate of PTAIR is higher than that of junior surgeons and similar to that of senior surgeons. Such systems may have utility in improving surgical outcomes and also in accelerating the education of junior surgeons.
Level of Evidence
3 Laryngoscope, 132:2516–2523, 2022
PTAIR is an artificial intelligence algorithm to identify parathyroid glands in the endoscopic thyroid. Artificial intelligence biopsies are on the horizon for us.
The recurrent laryngeal nerve (RLN) can be injured during thyroid surgery, which can negatively affect a patient's quality of life. The impact of intraoperative anatomic variations of the RLN on ...nerve injury remains unclear. Objectives of this study were to (1) better understand the detailed surgical anatomic variability of the RLN with a worldwide perspective; (2) establish potential correlates between intraoperative RLN anatomy and electrophysiologic responses; and (3) use the information to minimize complications and assure accurate and safe intraoperative neuromonitoring (IONM).
A large international registry database study with prospectively collected data was conducted through the International Neural Monitoring Study Group (INMSG) evaluating 1000 RLNs at risk during thyroid surgery using a specially designed online data repository. Monitored thyroid surgeries following standardized IONM guidelines were included. Cases with bulky lymphadenopathy, IONM failure, and failed RLN visualization were excluded. Systematic evaluation of the surgical anatomy of the RLN was performed using the International RLN Anatomic Classification System. In cases of loss of signal (LOS), the mechanism of neural injury was identified, and functional evaluation of the vocal cord was performed.
A total of 1000 nerves at risk (NARs) were evaluated from 574 patients undergoing thyroid surgery at 17 centers from 12 countries and 5 continents. A higher than expected percentage of nerves followed an abnormal intraoperative trajectory (23%). LOS was identified in 3.5% of NARs, with 34% of LOS nerves following an abnormal intraoperative trajectory. LOS was more likely in cases of abnormal nerve trajectory, fixed splayed or entrapped nerves (including at the ligament of Berry), extensive neural dissection, cases of cancer invasion, or when lateral lymph node dissection was needed. Traction injury was found to be the most common form of RLN injury and to be less recoverable than previous reports.
Multicenter international studies enrolling diverse patient populations can help reshape our understanding of surgical anatomy during thyroid surgery. There can be significant variability in the anatomic and intraoperative characteristics of the RLN, which can impact the risk of neural injury.
Background
The use of ultrasound‐guided ablation procedures to treat both benign and malignant thyroid conditions is gaining increasing interest. This document has been developed as an international ...interdisciplinary evidence‐based statement with a primary focus on radiofrequency ablation and is intended to serve as a manual for best practice application of ablation technologies.
Methods
A comprehensive literature review was conducted to guide statement development and generation of best practice recommendations. Modified Delphi method was applied to assess whether statements met consensus among the entire author panel.
Results
A review of the current state of ultrasound‐guided ablation procedures for the treatment of benign and malignant thyroid conditions is presented. Eighteen best practice recommendations in topic areas of preprocedural evaluation, technique, postprocedural management, efficacy, potential complications, and implementation are provided.
Conclusions
As ultrasound‐guided ablation procedures are increasingly utilized in benign and malignant thyroid disease, evidence‐based and thoughtful application of best practices is warranted.
Background:
Cytopathological evaluation of thyroid fine-needle aspiration biopsy (FNAB) specimens can fail to raise preoperative suspicion of medullary thyroid carcinoma (MTC). The Afirma ...RNA-sequencing MTC classifier identifies MTC among FNA samples that are cytologically indeterminate, suspicious, or malignant (Bethesda categories III–VI). In this study we report the development and clinical performance of this MTC classifier.
Methods:
Algorithm training was performed with a set of 483 FNAB specimens (21 MTC and 462 non-MTC). A support vector machine classifier was developed using 108 differentially expressed genes, which includes the 5 genes in the prior Afirma microarray-based MTC cassette.
Results:
The final MTC classifier was blindly tested on 211 preoperative FNAB specimens with subsequent surgical pathology, including 21 MTC and 190 non-MTC specimens from benign and malignant thyroid nodules independent from those used in training. The classifier had 100% sensitivity (21/21 MTC FNAB specimens correctly called positive; 95% confidence interval CI = 83.9–100%) and 100% specificity (190/190 non-MTC FNAs correctly called negative; CI = 98.1–100%). All positive samples had pathological confirmation of MTC, while all negative samples were negative for MTC on surgical pathology.
Conclusions:
The RNA-sequencing MTC classifier accurately identified MTC from preoperative thyroid nodule FNAB specimens in an independent validation cohort. This identification may facilitate an MTC-specific preoperative evaluation and resulting treatment.
Background
The preservation of parathyroid glands is crucial in endoscopic thyroid surgery to prevent hypocalcemia and related complications. However, current methods for identifying and protecting ...these glands have limitations. We propose a novel technique that has the potential to improve the safety and efficacy of endoscopic thyroid surgery.
Purpose
Our study aims to develop a deep learning model called PTAIR 2.0 (Parathyroid gland Artificial Intelligence Recognition) to enhance parathyroid gland recognition during endoscopic thyroidectomy. We compare its performance against traditional surgeon‐based identification methods.
Materials and methods
Parathyroid tissues were annotated in 32 428 images extracted from 838 endoscopic thyroidectomy videos, forming the internal training cohort. An external validation cohort comprised 54 full‐length videos. Six candidate algorithms were evaluated to select the optimal one. We assessed the model's performance in terms of initial recognition time, identification duration, and recognition rate and compared it with the performance of surgeons.
Results
Utilizing the YOLOX algorithm, we developed PTAIR 2.0, which demonstrated superior performance with an AP50 score of 92.1%. The YOLOX algorithm achieved a frame rate of 25.14 Hz, meeting real‐time requirements. In the internal training cohort, PTAIR 2.0 achieved AP50 values of 94.1%, 98.9%, and 92.1% for parathyroid gland early prediction, identification, and ischemia alert, respectively. Additionally, in the external validation cohort, PTAIR outperformed both junior and senior surgeons in identifying and tracking parathyroid glands (p < 0.001).
Conclusion
The AI‐driven PTAIR 2.0 model significantly outperforms both senior and junior surgeons in parathyroid gland identification and ischemia alert during endoscopic thyroid surgery, offering potential for enhanced surgical precision and patient outcomes.
Experience with targeted neoadjuvant treatment for locoregionally advanced thyroid cancer is nascent.
Multicenter retrospective case series examining targeted neoadjuvant treatment for locoregionally ...advanced thyroid cancer. The primary outcome was change in surgical morbidity as measured by two metrics developed for use in clinical trials to characterize surgical complexity and morbidity. Secondary outcomes included percentage of patients proceeding to surgery and percentage receiving an R0/R1 resection.
Seventeen patients with varied molecular alterations, pathologies, and treatment regimens were included. Mean surgical complexity scores decreased between time points for baseline and postneoadjuvant treatment, postneoadjuvant treatment and surgery, and between baseline and surgery. Eleven patients (64.7%) underwent surgical resection, with 10 (58.8%) receiving an R0/R1 resection.
Neoadjuvant treatment of advanced thyroid cancer improves resectability and decreases the morbidity of required surgical procedures. However, treatment is not uniformly effective.
Background
Recurrent laryngeal nerve (RLN) invasion by thyroid carcinoma represents an advanced disease status with potentially significant co‐morbidity.
Methods
In a retrospective single‐center ...study, we included patients with invaded RLNs operated on while using nerve monitoring techniques. We studied pre‐, intra‐, and postoperative parameters associated with postoperative vocal cord paralysis (VCP); 5‐year recurrence‐free survival (RFS); and 5‐year overall survival (OS) in addition to two subgroup analyses of postoperative VCP in patients without preoperative VCP and based on source of RLN invasion.
Results
Of 65 patients with 66 nerves‐at‐risk, 39.3% reported preoperative voice complaints. Preoperative VCP was documented in 43.5%. The RLN was invaded by primary tumor in 59.3% and nodal metastasis in 30.5%. Papillary thyroid carcinoma was the most common pathologic subtype (80%). After 6 months, 81.8% had VCP. Complete tumor resection of the RLN was not associated with 5‐year RFS (p = 0.24) or 5‐year OS (p = 0.9). Resecting the RLN did not offer statistically significant benefit on 5‐year RFS (p = 0.5) or 5‐year OS (p = 0.38). Radioactive Iodine (RAI) administration was associated with improvement in 5‐year RFS (p = 0.006) and 5‐year OS (p = 0.004). Patients without preoperative VCP had higher IONM amplitude compared with patients with VCP. After a mean follow‐up of 65.8 months, 35.9% of patients had distant metastases, whereas 36.4% had recurrence.
Conclusion
Preoperative VCP accompanies less than half of patients with RLN invasion. Invaded RLNs may have existent electrophysiologic stimulability. Complete tumor resection and RLN resection were not associated with better 5‐year RFS or OS, but postoperative RAI was.
Level of Evidence
4 Laryngoscope, 132:2285–2292, 2022
After our coauthors described the first remote‐access parathyroidectomy (RAP) series in 2000, several other approaches were developed. No systematic review has been performed to classify and evaluate ...RAP techniques. We performed a literature search using PubMed and Cochrane Library (CENTRAL). A total of 71 studies met our inclusion/exclusion criteria. RAP can be categorized into five approaches: (1) endoscopic and robotic axillary, (2) anterior chest, (3) transoral, (4) retroauricular, and (5) a combination of these approaches. The limited data in the literature suggest that the cure rates and safety of RAP are in no way inferior to those of open parathyroidectomy. Each approach has its advantages and disadvantages, and the recommendations for the selection of each approach are listed. The selection of approach methods might depend on the surgeon's experience and familiarity and the patient's preference and disease status.
The recently published 2021 guidelines for the management of patients with anaplastic thyroid cancer from the American Thyroid Association provide updated recommendations and guidance for the ...treatment of this rare but lethal thyroid cancer and incorporate significant advances since the initial guidelines were published in 2012. In particular, the focus on prompt cytopathologic and immunohistochemical diagnosis with the identification of potentially actionable genomic/molecular targets affirms the central and key role of pathologists and cytopathologists in not only the diagnosis but also the management of these patients.
