Browse
Submit Data
Databases
API
Help

Dataset Information

23 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Using deep learning to identify the recurrent laryngeal nerve during thyroidectomy.

ABSTRACT: Surgeons must visually distinguish soft-tissues, such as nerves, from surrounding anatomy to prevent complications and optimize patient outcomes. An accurate nerve segmentation and analysis tool could provide useful insight for surgical decision-making. Here, we present an end-to-end, automatic deep learning computer vision algorithm to segment and measure nerves. Unlike traditional medical imaging, our unconstrained setup with accessible handheld digital cameras, along with the unstructured open surgery scene, makes this task uniquely challenging. We investigate one common procedure, thyroidectomy, during which surgeons must avoid damaging the recurrent laryngeal nerve (RLN), which is responsible for human speech. We evaluate our segmentation algorithm on a diverse dataset across varied and challenging settings of operating room image capture, and show strong segmentation performance in the optimal image capture condition. This work lays the foundation for future research in real-time tissue discrimination and integration of accessible, intelligent tools into open surgery to provide actionable insights.

SUBMITTER: Gong J

PROVIDER: S-EPMC8275665 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

How the Severity and Mechanism of Recurrent Laryngeal Nerve Dysfunction during Monitored Thyroidectomy Impact on Postoperative Voice.

Project description:Intraoperative neuromonitoring can qualify and quantify RLN function during thyroid surgery. This study investigated how the severity and mechanism of RLN dysfunction during monitored thyroid surgery affected postoperative voice. This retrospective study analyzed 1021 patients that received standardized monitored thyroidectomy. Patients had post-dissection RLN(R2) signal <50%, 50-90% and >90% decrease from pre-dissection RLN(R1) signal were classified into Group A-no/mild, B-moderate, and C-severe RLN dysfunction, respectively. Demographic characteristics, RLN injury mechanisms(mechanical/thermal) and voice analysis parameters were recorded. More patients in the group with higher severity of RLN dysfunction had malignant pathology results (A/B/C = 35%/48%/55%, p = 0.017), received neck dissection (A/B/C = 17%/31%/55%, p < 0.001), had thermal injury (p = 0.006), and had asymmetric vocal fold motion in long-term postoperative periods (A/B/C = 0%/8%/62%, p < 0.001). In postoperative periods, Group C patients had significantly worse voice outcomes in several voice parameters in comparison to Group A/B. Thermal injury was associated with larger voice impairments compared to mechanical injury. This report is the first to discuss the severity and mechanism of RLN dysfunction and postoperative voice in patients who received monitored thyroidectomy. To optimize voice and swallowing outcomes after thyroidectomy, avoiding thermal injury is mandatory, and mechanical injury must be identified early to avoid a more severe dysfunction.

| S-EPMC8582531 | biostudies-literature

Protective Effects of Intraoperative Nerve Monitoring (IONM) for Recurrent Laryngeal Nerve Injury in Thyroidectomy: Meta-analysis.

Project description:Recurrent laryngeal nerve (RLN) injury is an intractable complication of thyroidectomy. Intraoperative nerve monitoring (IONM) was designed to prevent RLN injury. However, the results concerning the protective effect of IONM on RLN injury are still controversial. We searched all eligible databases from 1980 to 2017. Meta-analysis was performed to evaluate the effect of IONM on RLN injury. Sensitivity analysis was also conducted to check the stability of our results. There were 34 studies included in the analysis. Overall analysis found a significant decrease in total injury (RR = 0.68, 95%CI: 0.55 to 0.83), transient injury (RR = 0.71, 95%CI: 0.57 to 0.88), and permanent injury (RD = -0.0026, 95%CI: -0.0039 to -0.0012) with IONM. Subgroup analysis found IONM played a preventive role of total, transient and permanent injury in patients undergoing bilateral thyroidectomy. IONM also reduced the incidence of total and transient injury for malignancy cases. Operations with IONM were associated with fewer total and transient RLN injuries in operation volume < 300 NARs per year and fewer total and permanent RLN injuries in operation volume ≥ 300 NARs per year. The application of IONM could reduce the RLN injury of thyroidectomy. Particularly, we recommend routine IONM for use in bilateral operations and malignancy operations.

| S-EPMC5958090 | biostudies-literature

Intraoperative recurrent laryngeal nerve monitoring using endotracheal electromyography during parathyroidectomy for secondary hyperparathyroidism.

Project description:ObjectiveTo investigate the factors associated with adherence of an enlarged parathyroid gland to the recurrent laryngeal nerve (RLN) and the effectiveness of intraoperative neural monitoring (IONM).MethodsThis single-center retrospective study involved samples from 197 consecutive patients (394 RLNs; 733 parathyroid glands) who underwent parathyroidectomy and transcervical thymectomy between September 2010 and December 2014. The presence of parathyroid gland adhesion to the RLN and the clinical characteristics of patients with and without nerve adhesion were recorded. All patients underwent intraoperative monitoring of the electromyographic responses of the vocal cords using the endotracheal NIM-Response 3.0 system. The patients' postoperative clinical outcomes were recorded.ResultsParathyroid gland adhesion to the RLN was significantly associated with maximum gland diameter (>15 mm), weight (>500 mg), and the presence of nodular hyperplasia. IONM demonstrated a sensitivity of 97.8%, specificity of 43.5%, and accuracy of 94.7% for detecting nerve damage. Parathyroid gland adhesion to 17 RLNs occurred in 3 cases (17.6%) of vocal cord paralysis, whereas the 377 glands without nerve adhesion resulted in vocal cord paralysis in 20 cases (5.3%).ConclusionOur findings demonstrated the effectiveness of IONM using endotracheal electromyography in patients who underwent parathyroidectomy for secondary hyperparathyroidism.

| S-EPMC7989137 | biostudies-literature

Bilateral recurrent laryngeal nerve paralysis diagnosed using dynamic digital radiography during the COVID-19 pandemic.

Project description:Dynamic digital radiography (DDR) is a motion-detecting technique with high temporal resolution. Flexible laryngoscopy is a common modality for the observation of the larynx; however, it generates aerosol. DDR is an easy and less risky screening test for the diagnosis of recurrent laryngeal nerve paralysis during the COVID-19 pandemic.

| S-EPMC9309747 | biostudies-literature

Animal Study to Evaluate the Effect of Carbon Dioxide Insufflation on Recurrent Laryngeal Nerve Function in Transoral Endoscopic Thyroidectomy.

Project description:Data with regard to potential recurrent laryngeal nerve (RLN) compromise caused by intra-neck CO2 insufflation during transoral endoscopic thyroidectomy vestibular approach (TOETVA) are missing. RLN electromyographic (EMG) profiles, metabolic and hemodynamic parameters (oxygen saturation, heart rate, blood pressure, experimental time, CO2 partial pressure, pH, O2 partial pressure), central venous pressure (CVP), airpocket temperature and pressure were recorded in a TOETVA animal model. Twelve pigs were randomly divided into different groups according to increasing CO2 insufflation pressures. Nerves segments were then collected for histopathology. Significant variation of metabolic and hemodynamic parameters were registered when CO2 insufflation pressures increased x3 and x5 the baseline parameters. Combined EMG amplitude drop and latency increase also were documented. There was no significant change in the intraluminal temperature. RLNs structure were preserved with normal axons, no fibrosis, and no vacuolization and without loss of myelinated fibers during the experiment. RLN EMG profiles (but not histology) were altered when CO2 insufflation pressures increased.

| S-EPMC6597721 | biostudies-literature

Continuous intraoperative neuromonitoring of the recurrent laryngeal nerve during lung operations.

Project description:BackgroundThe recurrent laryngeal nerve (RLN), especially on the left side, is particularly vulnerable during lung operations. Therefore, continuous intraoperative neuromonitoring (cIONM) would be desirable. With the use of a double-lumen tube (DLT) for single-lung ventilation, there is some uncertainty where the recording electrode should be positioned. The aim of this study was to assess the feasibility of this technique and to predict the ideal position of a single recording electrode.MethodsPatients scheduled to undergo left thoracotomy due to pulmonary pathologies, two adhesive electrodes were affixed consecutively above the proximal cuff of the DLT prior to intubation for a precise location of the recording from the vocal cords. Following thoracotomy, the vagus nerve alongside the aortic arch was exposed. A continuous stimulation probe (Saxophone® electrode, Dr. Langer Medical, Waldkirch, Germany) was placed around the nerve. The signals of the respective electrode were recorded and analyzed with regard to previously defined limits of positive signaling.ResultsStrong signals with an amplitude of at least 165 µV were recorded in 18 of 20 patients. In these patients 100% of the signals were recorded via the distally located electrode. An additional signal was recorded via the proximal electrode in four patients. cIONM was found to be a safe and reproducible technique.ConclusionsThe described technique enables the use of cIONM of the RLN throughout the entire course of the surgical procedure.

| S-EPMC10482653 | biostudies-literature

Management of Recurrent Laryngeal Nerve Injury During Radiofrequency Ablation of Thyroid Nodules.

Project description: Not available

| S-EPMC8984510 | biostudies-literature

The current state of intermittent intraoperative neural monitoring for prevention of recurrent laryngeal nerve injury during thyroidectomy: a PRISMA-compliant systematic review of overlapping meta-analyses.

Project description:PurposeRecurrent laryngeal nerve (RLN) injury is one of the most common and detrimental complications following thyroidectomy. Intermittent intraoperative nerve monitoring (I-IONM) has been proposed to reduce prevalence of RLN injury following thyroidectomy and has gained increasing acceptance in recent years.MethodsA comprehensive database search was performed, and data from eligible meta-analyses meeting the inclusion criteria were extracted. Transient, permanent, and overall RLN injuries were the primary outcome measures. Quality assessment via AMSTAR, heterogeneity appraisal, and selection of best evidence was performed via a Jadad algorithm.ResultsEight meta-analyses met the inclusion criteria. Meta-analyses included between 6 and 23 original studies each. Via utilization of the Jadad algorithm, the selection of best evidence resulted in choosing of Pisanu et al. (Surg Res 188:152-161, 2014). Five out of eight meta-analyses demonstrated non-significant (p > 0.05) RLN injury reduction with the use of I-IONM versus nerve visualization alone.ConclusionsTo date, I-IONM has not achieved a significant level of RLN injury reduction as shown by the meta-analysis conducted by Pisanu et al. (Surg Res 188:152-161, 2014). However, most recent developments of IONM technology including continuous vagal IONM and concept of staged thyroidectomy in case of loss of signal on the first side in order to prevent bilateral RLN injury may provide additional benefits which were out of the scope of this study and need to be assessed in further prospective multicenter trials.

| S-EPMC5437188 | biostudies-literature

Clinical classification of recurrent laryngeal nerve palsy

Project description: Not available

| S-EPMC10570980 | biostudies-literature

Microarray Analysis Gene Expression Profiles in Laryngeal Muscle After Recurrent Laryngeal Nerve Injury

Project description:The pathophysiology of recurrent laryngeal nerve (RLN) transection injury is rare in that it is characteristically followed by a high degree of spontaneous reinnervation, with reinnervation of the laryngeal adductor complex (AC) preceding that of the abducting posterior cricoarytenoid (PCA) muscle. Here, we aim to elucidate the differentially expressed myogenic factors following RLN injury that may be at least partially responsible for the spontaneous reinnervation. F344 male rats underwent RLN injury or sham surgery (n=12). One week after RLN injury, larynges were harvested following euthanasia. mRNA was extracted from PCA and AC muscles bilaterally, and microarray analysis was performed using a full rat genome array. Microarray analysis of denervated AC and PCA muscles demonstrated dramatic differences in gene expression profiles, with 205 individual probes that were differentially expressed between the denervated AC and PCA muscles, and only 14 genes with similar expression patterns. The differential expression patterns of the AC and PCA suggest different mechanisms of reinnervation. The PCA showed the gene patterns of Wallerian degeneration, while the AC expressed the gene patterns of reinnervation by adjacent axonal sprouting. This finding may reveal important therapeutic targets applicable to RLN and other peripheral nerve injuries. Compare mRNA expression from injured tissue (recurrent laryngeal nerve transection injury) to normal tissue from two tissues laryngeal adductor complex and posterior cricoarytenoid muscles.

2016-07-01 | E-GEOD-72361 | biostudies-arrayexpress

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data