Machine Learning in Laryngoscopy Analysis: A Proof of Concept Observational Study for the Identification of Post-Extubation Ulcerations and Granulomas.

OBJECTIVE: Computer-aided analysis of laryngoscopy images has potential to add objectivity to subjective evaluations. Automated classification of biomedical images is extremely challenging due to the precision required and the limited amount of annotated data available for training. Convolutional neural networks (CNNs) have the potential to improve image analysis and have demonstrated good performance in many settings. This study applied machine-learning technologies to laryngoscopy to determine the accuracy of computer recognition of known laryngeal lesions found in patients post-extubation. METHODS: This is a proof of concept study that used a convenience sample of transnasal, flexible, distal-chip laryngoscopy images from patients post-extubation in the intensive care unit. After manually annotating images at the pixel-level, we applied a CNN-based method for analysis of granulomas and ulcerations to test potential machine-learning approaches for laryngoscopy analysis. RESULTS: A total of 127 images from 25 patients were manually annotated for presence and shape of these lesions-100 for training, 27 for evaluating the system. There were 193 ulcerations (148 in the training set; 45 in the evaluation set) and 272 granulomas (208 in the training set; 64 in the evaluation set) identified. Time to annotate each image was approximately 3 minutes. Machine-based analysis demonstrated per-pixel sensitivity of 82.0% and 62.8% for granulomas and ulcerations respectively; specificity was 99.0% and 99.6%. CONCLUSION: This work demonstrates the feasibility of machine learning via CNN-based methods to add objectivity to laryngoscopy analysis, suggesting that CNN may aid in laryngoscopy analysis for other conditions in the future.

Interarytenoid botulinum toxin A injection for the treatment of vocal process granuloma.

OBJECTIVES: To report on the efficacy and adverse effects of interarytenoid botulinum toxin A injection for the treatment of vocal process granuloma. METHODS: A retrospective chart review was conducted of eight patients with vocal process granuloma resistant to anti-reflux therapy who underwent interarytenoid botulinum toxin A injection. The mean dosage of botulinum toxin A injected was 6.56 U. RESULTS: Fifty per cent of patients had complete regression of the lesion and 50 per cent had partial regression. The main side effects were breathiness (n = 4), voice breaks (n = 1) and aspiration (n = 1). CONCLUSION: Interarytenoid botulinum toxin A injection for the treatment of vocal process granuloma is an effective mode of therapy, with transient vocal and swallowing side effects.

Evaluation of narrow band imaging in the assessment of laryngeal granuloma.

Laryngeal granulomas belong to common complications following trans-oral laser microsurgery (TLM). The aim of this study was to evaluate NBI in the differentiation between granuloma-like lesions and local tumor recurrence. 154 consecutive patients after TLM due to early laryngeal cancer were enrolled. In the group, a monthly follow-up including NBI endoscopy was performed. Moderate and severe dysplasia, carcinoma in situ and invasive cancer were defined as positive histology, laryngeal granuloma and other benign laryngeal lesions as negative histology and premalignant lesions as suspicious histology. In 47/154 (31%) cases, granuloma-like lesion (GLL) was found. Patients with GLL were divided into two groups based on the NBI classification. In all patients, the microvascular pattern in NBI was compared with the final histology. In group A, with suspicious, perpendicular vessels, 13/13 (100%) samples were positive. In group B, with normal vascular pattern 3/34 (9%) samples were positive and 31/34 (91%) samples were negative. There was a significant correlation between the positive NBI vascular pattern and the final histology (p = 0.00001). Sensitivity, specificity, accuracy of NBI were as follows: 81%, 100%, 94%, respectively.Based on our results, NBI can reliably differentiate between postoperative laryngeal granuloma and local tumor recurrence. In such a manner, this method is very helpful in the follow-up of tumor patients.

Post-transplantation laryngeal actinomycosis.

A case of laryngeal actinomycosis occurred after bone marrow transplantation was reported. The patient was a 14-year-old girl who had a history of bone marrow transplantation for the treatment of acute lymphocytic leukemia 4month before the onset of the disease. She was referred to our hospital complaining persistent sore throat since 2weeks ago. Fiberscopic observation proved the presence of white tumor-like mass on her right arytenoid of the larynx. As CT image demonstrated that the mass was localized at the arytenoid region with central low-density area surrounded by granulation tissue, we underwent biopsy under local anesthesia. Excision of the mass proved it to be a soft granulation including sulfur granules. Oral administration of amoxicillin 750mg per day was initiated as a postoperative medication. On day 17, histological study confirmed that the tumor-like mass was Actinomyces granuloma, and therefore amoxicillin administration continued. The medication was effective to subside the disease and the arytenoid lesion healed on day 31. Amoxicillin was further administered until day 70 to prevent recurrence. At 6month after the biopsy, she was free from the disease.

Conservative Treatment versus Surgery for Laryngeal Contact Granuloma: A Prospective Study.

AIMS: To confirm the efficacy of conservative treatment for laryngeal contact granuloma and identify factors influencing treatment outcome. METHODS: In this prospective study, patients with laryngeal contact granuloma were divided into a group receiving conservative treatment and a group undergoing surgery. Efficacy was assessed by analyzing the complete response after a 48-week follow-up. The association of treatment outcome with clinical factors was then evaluated. RESULTS: In total, 61 patients, 43 in the group receiving conservative treatment and 18 in the group undergoing surgery, were analyzed, and the complete response rate was 72.1% and 38.9%, respectively. Both univariate analysis and multivariate analysis revealed that treatment modality (p1 = 0.015, p2 = 0.043), voice abuse (p1 = 0.010, p2 = 0.010), and the size of the granuloma (p1 = 0.031, p2 = 0.020) were significantly associated with the complete response of laryngeal contact granuloma. Kaplan-Meier curves showed that alcohol consumption (p = 0.031), voice abuse (p < 0.001), and granuloma size (p = 0.025) were significantly related to the complete response of conservative treatment. CONCLUSIONS: This prospective study strengthens the argument for conservative treatment (instead of surgery) as the first choice for laryngeal contact granuloma. The results also suggest that voice abuse, alcohol consumption, and the size of the granuloma may predict treatment outcome.

Massive Idiopathic Oropharyngeal and Laryngeal Granulomatosis on FDG PET/CT.

Idiopathic granulomatosis is a rare entity and has varied manifestations and imaging findings. A 44-year-old woman with sore throat and worsening dyspnea had multiple oropharyngeal and supraglottic masses on laryngoscopic examination. FDG PET/CT demonstrated diffuse tumor-like mucosal/submucosal lesions with intense uptake involving the oropharynx, supraglottis, and hypopharynx. Surgical biopsy showed chronically inflamed granulation tissue without malignancy, necrosis, or vasculitis. All stains were negative for any organisms. The image highlights the necessity of including granulomatosis as a differential from malignancy in interpretation of FDG PET/CT showing diffuse mucosal/submucosal oropharyngeal and/or laryngeal lesions but without established diagnosis.

The prevalence and factors associate with vocal nodules in general population: Cross-sectional epidemiological study.

The purpose of this study was to analyze the prevalence of vocal nodules and to identify factors related with an increased risk for vocal nodules.This study was conducted using data from the Korean National Health and Nutrition Examination Survey 2008 to 2011. The subjects consisted of 19,636 men and women aged ≥19 years. Related factors such as age, marital status, incomes, and education level were assessed in individual interviews, and health-related behaviors including smoking, alcohol, and activity were assessed with self-administered questionnaires. Also, examination survey such as laryngoscopy examination, basic physical examination, and blood sampling was conducted.The prevalence of vocal nodules was 1.31% (n = 258). Among variable factors, age, education level, and voice disorder were related with the presence of vocal nodules (P < 0.05). Other factors including sex, alcohol, smoking, physical activities, hypertension, obesity, waist circumference and metabolic syndrome, hypercholesterolemia, serum calcium, and vitamin D did not show any meaningful relationship with the presence of vocal nodules.This result may help reduce the incidence of vocal nodules and offer proper management for patients with vocal nodules, and may also facilitate efficient allocation of public health resources.

Laryngeal granuloma in experimental rats with gastroesophageal reflux disease and mechanically injured vocal cord mucosa.

OBJECTIVE: This study was undertaken to elucidate the mechanisms underlying laryngeal granuloma formation in a rat model of gastroesophageal reflux disease (GERD) with mechanically injured vocal cord mucosa. METHODS: The rat model of GERD was surgically created by tying the pyloric sphincter and ligating the transitional region between the forestomach and the glandular portion (limiting ridge). The control rats received only a midline incision. In all the animals, a plastic bar was inserted into the trachea, and moved vertically thrice in 3 seconds to cause mechanical injury of the vocal cord mucosa. The rats were sacrificed 2 weeks postsurgically, and their pharynx and larynx were observed histologically. RESULTS: Granulomas were observed in the vocal cord mucosa of the GERD group (3 of 5 animals); they presented a similar pathological structure to that of human laryngeal granulomas. In contrast, only abrasions and blisters were observed on the vocal cord mucosa in the control group (all 5 animals). CONCLUSIONS: The development of laryngeal granuloma may involve both mechanical injury and gastric acid reflux.

Retrospective analysis of the clinical course for intubation vs. unspecified laryngeal granulomas.

Intubation laryngeal granulomas (ILGs) are a well-known complication of endotracheal intubation. Cases other than ILGs can be categorized as unspecified laryngeal granulomas (ULGs) since their etiologies are often difficult to confirm. We intended to clarify clinical features of both ILGs and ULGs and that anticoagulant medication could cause the formation and delayed healing of ILGs in terms of wound-healing delay. We compared the results of our treatment of ILGs (n = 16) and ULGs (n = 47) treated between 1998 and 2009 to characterize these patients. The clinical course, treatment (medical vs. surgical), indications for surgical resection, treatment outcome, and use of anticoagulants for preexisting disease were reviewed and compared between these two groups. The resolution rate was significantly better in ILGs (p < .05). Five ILGs and seven ULGs were surgically resected. The main reason for resection was airway obstruction and the need for histological assessment, respectively. The use of anticoagulants was significantly higher in ILGs than ULGs (8/16 vs. 4/47, p < .01). The resolution period was significantly longer in the ILGs patients with anticoagulant medication compared to that in the ILGs patients without anticoagulant medication (152 ± 101 days vs. 76 ± 44 days, p < .05). ILGs may have different clinical course from ULGs, especially in terms of the resolution period. Moreover, administration of anticoagulants may deter healing of small injury due to intubation. Patients taking anticoagulants should be managed carefully during the perioperative period to prevent the occurrence of ILGs.

Identification and characterization of a novel genetic mutation with prolonged QT syndrome in an unexplained postoperative death.

INTRODUCTION: The human ether-à-go-go-related gene (hERG) encodes the α-subunit of a cardiac potassium channel. Various mutations of hERG, including missense mutations, have been reported to cause long QT syndrome (LQTS) and severe arrhythmic disorders such as sudden cardiac death. We identified a novel hERG frameshift mutation (hERG(ΔAT)) in the S5-pore region from a LQTS patient who died suddenly and analyzed its genetic profile and the molecular and electrophysiological behaviors of the protein product to assess the pathogenicity of hERG(ΔAT). METHODS AND RESULTS: We performed direct sequencing of hERG and evaluated its transcript level by using a whole blood sample from the patient. We performed immunoblotting, immunocytochemistry, and patch-clamp recordings of HEK-293 T cells transfected with hERG(ΔAT), wild-type hERG (hERG(WT)), or both. The patient demonstrated an AT deletion (c.1735_1736del) in hERG and a decrease in hERG mRNA transcripts. HEK-293 T cells showed lower production and cell surface expression of hERG(ΔAT) compared with hERG(WT) protein. In addition, the hERG(∆AT) protein failed to form functional channels, while the activation kinetics of functional channels, presumably consisting of hERG(WT) subunits, were unaffected. CONCLUSION: The ΔAT mutation may decrease the number of functional hERG channels by impairing the posttranscriptional and posttranslational processing of the mutant product. This decrease may partly explain the cardiac symptoms of the patient who was heterozygous for hERG(ΔAT).

Zinc sulfate therapy of vocal process granuloma.

Vocal process granuloma is a benign lesion that occurs on the arytenoid cartilage. It tends to recur locally, and there is a great diversity of methods to treat it. Here, we reviewed the effects of zinc sulfate therapy program in 16 patients with vocal process granulomas. Eleven patients had a history of trauma or laryngeal intubation and five patients had unknown origin. Eleven had recurrence after one to three failed surgeries, and the others had no prior treatment. Symptoms included hoarseness, sore throat, lump sensation in the throat and cough that apparently improved. The granulomas did not recur for at least 1 year. No complications occurred. For vocal process granuloma, zinc sulfate therapy is good either as an initial or compensatory treatment.

Three-dimensional conformal radiation therapy for refractory laryngeal granuloma.

AIMS AND BACKGROUND: The etiology of laryngeal granulomas is often multifactorial and the benefit of pharmacological therapy remains unclear. Anti-reflux treatment is only effective in granulomas definitely induced by gastroesophageal reflux. Steroid inhalation has shown favorable results but it is unclear whether it shortens the healing process. Surgical excision is associated with high recurrence rates. The aim of this study was to evaluate the role of 3-dimensional conformal radiation therapy (3DCRT) in the treatment of refractory laryngeal granuloma. METHODS AND STUDY DESIGN: The study was a retrospective review including all patients presenting to the Department of Radiation Oncology at Xijing Hospital from January 2004 to March 2007. We studied a total of 15 cases of refractory laryngeal granuloma that had recurred ≥2 times. Patients had previously been managed with voice rest, corticosteroids, antibiotics, antacids, surgery and botulinum toxin. All patients accepted surgical excision and immediate adjuvant 3DCRT at a total dose of 15 Gy over 5 days. RESULTS: All patients were successfully treated with surgery and 3DCRT. There has been no granuloma recurrence in 3 years of follow-up. CONCLUSIONS: 3DCRT is a safe and effective therapy for refractory laryngeal granulomas, especially when other methods have failed.

Inhaled triamcinolone with proton pump inhibitor for treatment of vocal process granulomas: a series of 67 granulomas.

OBJECTIVES: We sought to analyze the outcomes of vocal process granulomas treated with proton pump inhibitors and inhaled triamcinolone acetonide. METHODS: We reviewed the medical records of patients with a diagnosis of contact granuloma or vocal process granuloma between 1995 and 2008. Data included age, gender, intubation history, reflux history, lesion location, previous treatment methods, treatment course, and recurrence. All patients were treated with daily or twice-daily protein pump inhibitors and inhaled triamcinolone acetonide (300 microg 3 times a day). RESULTS: Sixty-seven granulomas were diagnosed in 54 patients: 13 bilateral and 41 unilateral. Twenty patients, including all 11 women, had a recent history of intubation. Sixty-two granulomas in 50 patients were treated with triamcinolone and a proton pump inhibitor. Of the 57 granulomas that completed treatment, 5 (9%) did not respond (mean follow-up, 50 weeks; range, 30.3 to 78.3 weeks), 13 (22%) partially responded (mean follow-up, 11 weeks; range, 3 to 30 weeks), and 40 (69%) completely responded (mean follow-up, 21 weeks; range, 5.9 to 84.6 weeks). Three cases had recurrence: 2 nonresponders and 1 complete responder. One patient developed oral thrush. CONCLUSIONS: In this study, vocal process granulomas occurred more frequently in men, whereas women developed granulomas only after intubation. The anti-inflammatory action of inhaled triamcinolone combined with antireflux proton pump inhibitors successfully treats most vocal process granulomas with low rates of side effects and recurrence.