[Diagnosis of benign laryngeal tumors using neural network]. / Diagnostika dobrokachestvennykh novoobrazovanii gortani s primeneniem neiroseti.

The article describes our experience in developing and training an artificial neural network based on artificial intelligence algorithms for recognizing the characteristic features of benign laryngeal tumors and variants of the norm of the larynx based on the analysis of laryngoscopy pictures obtained during the examination of patients. During the preparation of data for training the neural network, a dataset was collected, labeled and loaded, consisting of 1471 images of the larynx in digital formats (jpg, bmp). Next, the neural network was trained and tested in order to recognize images of the norm and neoplasms of the larynx. The developed and trained artificial neural network demonstrated an accuracy of 86% in recognizing of benign laryngeal tumors and variants of the norm of the larynx. The proposed technology can be further used in practical healthcare to control and improve the quality of diagnosis of laryngeal pathologies.

[Study on the difference and clinical value of serum amino acids in patients with laryngeal squamous cell carcinoma].

Objective:To detect the differences in types and levels of amino acids in the peripheral serum of patients with laryngeal squamous cell carcinoma and non-tumor patients, and explore their relationship with clinical parameters of laryngeal squamous cell carcinoma as well as their clinical value in diagnosis. Methods:High-performance liquid chromatography-tandem mass spectrometry（HPLC-MS） was employed to detect the serum amino acid contents and levels of 62 patients diagnosed with laryngeal carcinoma and 141 non-tumor patients at the First Affiliated Hospital of Jinzhou Medical University between September 2018 and February 2021. The study compared the differences in 22 non-essential and essential amino acids found in the serum between the experimental group and the control group. An ROC curve and risk scoring formula of multivariate linear logic regression model was utilized to evaluate the efficiency of serum amino acids in the early diagnosis of laryngeal carcinoma. Results:There were significant differences in the contents of fourteen types of amino acids between the experimental and control groups, with thirteen amino acids showing higher levels in the experimental group（P<0.05）. Seven of these amino acids were essential, including phenylalanine, threonine, leucine, valine, histidine, tyrosine, and citrulline. The other six amino acids were non-essential, including arginine, asparagine, cysteine, glycine, ornithine, and proline. Interestingly, the content of homocysteine in the experimental group was lower than that in the control group（P=0.024）. Further analysis showed that patients with laryngeal squamous cell carcinoma in TNM stage Ⅰ and Ⅱ had higher serum methionine levels compared to those in stages Ⅲ and Ⅳ（P=0.026）. In addition, the content of serum histidine was higher in patients with poorly differentiated squamous cell carcinoma compared to those with well-differentiated squamous cell carcinoma（P=0.041）. The level of asparagine in the serum of patients with laryngeal squamous cell carcinoma older than 64 years old was lower than that in patients younger than 64 years old（P=0.033）. The level of tryptophan in the serum of patients with a smoking history was lower than that in patients without a smoking history（P=0.033）. The level of citrulline in the serum of patients with a history of alcohol consumption was higher than that in patients with no history of alcohol consumption（P=0.003）. ROC curve analysis showed that out of the 14 different amino acids between the experimental and control groups, citrulline and cysteine were relatively effective as independent factors in the diagnosis of laryngeal squamous cell carcinoma, with an AUC of 0.856 and 0.850, respectively. Arginine was the most sensitive factor in the diagnosis of laryngeal squamous cell carcinoma（AUC=0.855）. However, citrulline alone had the highest specificity（0.830） in the diagnosis of laryngeal squamous cell carcinoma, and the combination of 12 amino acids significantly improved the diagnostic efficiency of laryngeal squamous cell carcinoma, with an AUC of 0.946, sensitivity of 0.887, and specificity of 0.894. A risk score formula for a multivariate logistic regression model was established based on the differential amino acid content in the serum. The risk score of laryngeal squamous cell carcinoma group was higher than that of the non-tumor group（P<0.001）. The AUC of risk score in the diagnosis of laryngeal squamous cell carcinoma was 0.953 with sensitivity and specificity of 0.957 and 0.855. Conclusion:This study found that there are differences in the contents of 14 amino acids among which 13 amino acids were increased in serum of patients with laryngeal squamous cell carcinoma, and were associated with age, clinical stage, pathological differentiation, smoking, and drinking. Combined detection of 12 amino acids can improve the diagnostic efficiency of laryngeal squamous cell carcinoma and serve as potential markers for the auxiliary diagnosis of laryngeal squamous cell carcinoma using peripheral blood samples. Additionally, the established risk score model was found to be more effective in the diagnosis of laryngeal squamous cell carcinoma, indicating its important potential value as an auxiliary diagnostic tool.

Identification and bioinformatic characterization of a serum miRNA signature for early detection of laryngeal squamous cell carcinoma.

BACKGROUND: The growing understanding of cancer biology and the establishment of new treatment modalities has not yielded the expected results in terms of survival for Laryngeal Squamous Cell Cancer (LSCC). Early diagnosis, as well as prompt identification of patients with high risk of relapse would ensure greater chance of therapeutic success. However, this goal remains a challenge due to the absence of specific biomarkers for this neoplasm. METHODS: Serum samples from 45 LSCC patients and 23 healthy donors were collected for miRNA expression profiling by TaqMan Array analysis. Additional 20 patients and 42 healthy volunteers were included for the validation set, reaching an equal number of clinical samples for each group. The potential diagnostic ability of the such identified three-miRNA signature was confirmed by ROC analysis. Moreover, each miRNA was analyzed for the possible correlation with HNSCC patients' survival and TNM status by online databases Kaplan-Meier (KM) plotter and OncomiR. In silico analysis of common candidate targets and their network relevance to predict shared biological functions was finally performed by PANTHER and GeneMANIA software. RESULTS: We characterized serum miRNA profile of LSCC patients identifying a novel molecular signature, including miR-223, miR-93 and miR-532, as circulating marker endowed with high selectivity and specificity. The oncogenic effect and the prognostic significance of each miRNA was investigated by bioinformatic analysis, denoting significant correlation with OS. To analyse the molecular basis underlying the pro-tumorigenic role of the signature, we focused on the simultaneously regulated gene targets-IL6ST, GTDC1, MAP1B, CPEB3, PRKACB, NFIB, PURB, ATP2B1, ZNF148, PSD3, TBC1D15, PURA, KLF12-found by prediction tools and deepened for their functional role by pathway enrichment analysis. The results showed the involvement of 7 different biological processes, among which inflammation, proliferation, migration, apoptosis and angiogenesis. CONCLUSIONS: In conclusion, we have identified a possible miRNA signature for early LSCC diagnosis and we assumed that miR-93, miR-223 and miR-532 could orchestrate the regulation of multiple cancer-related processes. These findings encourage the possibility to deepen the molecular mechanisms underlying their oncogenic role, for the desirable development of novel therapeutic opportunities based on the use of short single-stranded oligonucleotides acting as non-coding RNA antagonists in cancer.

Synchronous laryngeal cancer.

Multiple primary cancers are usually defined as primary malignant tumors of different histological origins in one person. Synchronous cancers are defined as two or more primary cancers diagnosed in the same patient at the same time or within six months after identifying the first tumor, and those cancers that develop at more than a six-month interval are termed as metachronous multiple primary cancers. Our study comprised of a patient with synchronous laryngeal cancer with double localizations. The case was solved through surgical excision of the tumors. Histopathological and immunohistochemistry examinations revealed synchronous laryngeal cancer. Laryngeal cancer should usually be managed through surgical resection, followed by oncological treatment.

[Primary laryngeal lymphoma: a case report]. / Lymphome primitif laryngé: à propos d'un cas.

Primary laryngeal lymphoma is rare, accounting for less than 1% of all laryngeal cancers. Treatment depends on the stage and severity of the disease. We here report the exceptional case of a 64-year-old woman, non-smoker, suffering from dysphagia for solids and a foreign body sensation. Laryngoscopy and biopsies revealed polyploid tumor of the left epiglottic fold. The diagnosis of diffuse large B-cell lymphoma was made. The patient underwent chemotherapy followed by radiotherapy, with significant improvement at 2-year follow-up, with no local recurrence. Due to the rarity of this disease and the variety of symptoms, the optimal management strategy for this type of cancer is controversial, requiring a specific diagnostic and therapeutic approach.

A large, locally aggressive giant cell tumour arising from the laryngeal cartilage: A Rare Case Report.

Giant cell tumour is a growth predominantly found in long bones of the body. Giant cell tumour has a rare occurrence in the head and neck. A case of a 31 year old male with no known comorbidities at the ENT Department, Shifa International Hospital, Islamabad presented with anterior neck swelling and hoarseness of voice. Patient was diagnosed as having Giant Cell Tumour of Larynx (GTCL) proven on FNA cytology and post-operative biopsy. GCTL is an uncommon entity with only 45 reported cases in the world.

Laryngeal schwannoma masquerading as malignancy.

Laryngeal schwannoma is a rare type of neurogenous tumour with a non-specific presentation. We present a case of a middle-aged man with issues of hoarseness, globus sensation and intermittent episodes of throat pain. The Hopkins examination showed right vocal fold irregularity with fullness in the right ventricle. The contrast-enhanced CT neck revealed an ill-defined lesion with contrast uptake extending into the paraglottic region with no neck node involvement. Considering the clinical presentation of hoarseness, throat pain and globus with imaging revealing contrast enhancement of lesion, direct laryngoscopy and biopsy were planned to rule out malignancy. Intraoperatively, a well-defined submucosal capsulated swelling became apparent after incision and dissection of the mucosa over the right vocal fold. A complete excision of the swelling was done with microlaryngeal instruments without tracheostomy. The histopathological report was suggestive of schwannoma. The literature review discusses clinical presentation, location, imaging features and management strategy.

Identification of a Novel Five-Gene Prognostic Model for Laryngeal Cancer Associated with Mitophagy Using Integrated Bioinformatics Analysis and Experimental Verification.

Laryngeal cancer (LC) is a prevailing tumor with a high mortality rate. The pivotal role of mitophagy in LC is acknowledged; however, a comprehensive analysis of the corresponding genes has not been conducted. In the present study, we proposed a prognostic model consisting of mitophagy-related genes in LC. Clinical information and transcriptome profiling of patients with LC and mitophagy-related genes were retrieved from open-source databases. Gene set variation analysis (GSVA) and Weighted Gene Co-expression Network Analysis (WGCNA) were used to identify core mitophagy-related genes and construct gene co-expression networks. Functional enrichment analysis was employed to analyze the enriched regulatory pathways of the mitophagy-related genes. Kaplan-Meier curves (KM), Cox, and LASSO regression were applied to explore their prognostic effects. Finally, quantitative real-time PCR (RT-qPCR) further verified the bioinformatics prediction. A total of 45 genes related to mitochondrial pathways was collected. GSVA analysis demonstrated that these genes in tumor samples mainly referred to the mitochondrial pathway. Among these genes, five mitophagy-related-gene signatures (CERCAM, CHPF, EPHX3, EXT2, and MED15) were further identified to construct the prognostic model. KM and Cox regression analyses indicated that this model had an accurate prognostic prediction for LC. RT-qPCR showed that CERCAM, CHPF, EXT2, and MED15 expression were upregulated, and EPHX3 level was decreased in LC cells. The present study established a five-mitophagy-related-gene model that can predict the prognosis of LC patients, thus laying the foundation for a better understanding and potential advancements in clinical treatments for LC.

Exosomes multiplex profiling, a promising strategy for early diagnosis of laryngeal cancer.

BACKGROUND: Exosomes are nanosized vesicles released from all cells into surrounding biofluids, including cancer cells, and represent a very promising direction in terms of minimally invasive approaches to early disease detection. They carry tumor-specific biological contents such as DNA, RNA, proteins, lipids, and sugars, as well as surface molecules that are able to pinpoint the cellular source. By the above criteria, exosomes may be stratified according to the presence of tissue and disease-specific signatures and, due to their stability in such biofluids as plasma and serum, they represent an indispensable source of vital clinical insights from liquid biopsies, even at the earliest stages of cancer. Therefore, our work aimed to isolate and characterize LCa patients' derived exosomes from serum by Flow Cytometry in order to define a specific epitope signature exploitable for early diagnosis. METHODS: Circulating exosomes were collected from serum collected from 30 LCa patients and 20 healthy volunteers by the use of antibody affinity method exploiting CD63 specific surface marker. Membrane epitopes were then characterized by Flow cytometry multiplex analysis and compared between LCa Patients and Healthy donors. Clinical data were also matched to obtain statistical correlation. RESULTS: A distinct overexpression of CD1c, CD2, CD3, CD4, CD11c, CD14, CD20, CD44, CD56, CD105, CD146, and CD209 was identified in LCa patients compared to healthy controls, correlating positively with tumor presence. Conversely, CD24, CD31, and CD40, though not overexpressed in tumor samples, showed a significant correlation with nodal involvement in LCa patients (p < 0.01). CONCLUSION: This approach could allow us to set up a cost-effective and less invasive liquid biopsy protocol from a simple blood collection in order to early diagnose LCa and improve patients' outcomes and quality of life.

Laryngeal Cancer Screening During Flexible Video Laryngoscopy Using Large Computer Vision Models.

OBJECTIVE: Develop an artificial intelligence assisted computer vision model to screen for laryngeal cancer during flexible laryngoscopy. METHODS: Using laryngeal images and flexible laryngoscopy video recordings, we developed computer vision models to classify video frames for usability and cancer screening. A separate model segments any identified lesions on the frames. We used these computer vision models to construct a video stream annotation system. This system classifies findings from flexible laryngoscopy as "potentially malignant" or "probably benign" and segments any detected lesions. Additionally, the model provides a confidence level for each classification. RESULTS: The overall accuracy of the flexible laryngoscopy cancer screening model was 92%. For cancer screening, it achieved a sensitivity of 97.7% and a specificity of 76.9%. The segmentation model attained an average precision at a 0.50 intersection-over-union of 0.595. The confidence level for positive screening results can assist clinicians in counseling patients regarding the findings. CONCLUSION: Our model is highly sensitive and adequately specific for laryngeal cancer screening. Segmentation helps endoscopists identify and describe potential lesions. Further optimization is required to enable the model's deployment in clinical settings for real-time annotation during flexible laryngoscopy.

Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study.

OBJECTIVE: To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL). METHODS: The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance. RESULTS: In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740-0.811) and 0.720 (95 % CI 0.684-0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798-0.940) and 0.851 (95 % CI 0.756-0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743-0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682-0.755) to 0.808 (95 % CI 0.775-0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608-0.686) to 0.807 (95 % CI 0.773-0.837) for junior otolaryngologists. CONCLUSIONS: The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.

A Rare Case of Laryngeal Mantle Cell Lymphoma.

This case report describes an 80-year-old woman presenting to her primary care practitioner after several months of a persistent globus sensation and throat fullness.

Subglottic Mass With Hoarseness and Difficulty Breathing.

A man in his 70s was referred for a 5-cm submandibular mass, hoarseness, and difficulty breathing with no cough, blood in sputum, or dysphagia. What is your diagnosis?

[Epidemiological features papillomatosis of the larynx in adults: a literature review]. / Epidemiologicheskie osobennosti papillomatoza gortani u vzroslykh (obzor literatury).

The literature review presents current data on the epidemiology, drug, and surgical treatment of laryngeal papillomatosis in adults. Possible prospects for further study of the prevalence and incidence of the disease and provoking factors of recurrence of the disease for the development of possible preventive measures are considered.

[Laryngeal carcinosarcoma]. / Kartsinosarkoma gortani.

A clinical case of a rare malignant tumor of the larynx, carcinosarcoma, is described. The features of the clinical picture, diagnostic methods: instrumental and morphological are presented.

Non-squamous Cancers of the Larynx.

PURPOSE OF REVIEW: Although non-squamous tumors of the larynx are really rare, they may not always be viewed from the same perspective in the multidisciplinary treatment approach once the diagnosis is made. In this review, non-squamous tumors of the larynx and current approaches in treatment will be discussed. RECENT FINDINGS: When the studies and meta-analyses presented in the last 5 years are evaluated, it is seen that these tumors usually show non-specific symptoms. Due to their submucosal location, the stage of the disease at the time of diagnosis is often advanced. In the literature, treatment may vary in these particular cases. The majority of non-squamous tumors of the larynx includes minor salivary gland tumors, neuroendocrine carcinomas, sarcomas, cartilage tumors, and malignant melanomas. Once treating a patient with these diagnoses, it should be kept in mind that the histopathological subtype is almost as important as the stage of the tumor.

Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis.

Voice change is often the first sign of laryngeal cancer, leading to diagnosis through hospital laryngoscopy. Screening for laryngeal cancer solely based on voice could enhance early detection. However, identifying voice indicators specific to laryngeal cancer is challenging, especially when differentiating it from other laryngeal ailments. This study presents an artificial intelligence model designed to distinguish between healthy voices, laryngeal cancer voices, and those of the other laryngeal conditions. We gathered voice samples of individuals with laryngeal cancer, vocal cord paralysis, benign mucosal diseases, and healthy participants. Comprehensive testing was conducted to determine the best mel-frequency cepstral coefficient conversion and machine learning techniques, with results analyzed in-depth. In our tests, laryngeal diseases distinguishing from healthy voices achieved an accuracy of 0.85-0.97. However, when multiclass classification, accuracy ranged from 0.75 to 0.83. These findings highlight the challenges of artificial intelligence-driven voice-based diagnosis due to overlaps with benign conditions but also underscore its potential.

Diagnostic and prognostic nomograms for laryngeal carcinoma patients with lung metastasis: a SEER-based study.

PURPOSE: To establish two nomograms to quantify the risk of lung metastasis (LM) in laryngeal carcinoma (LC) and predict the overall survival of LC patients with LM. METHODS: Totally 9515 LC patients diagnosed histologically from 2000 to 2019 were collected from the Surveillance, Epidemiology, and End Results database. The independent diagnostic factors for LM in LC patients and prognostic factors for LC patients with LM were identified by logistic and Cox regression analysis, respectively. Nomograms were established based on regression coefficients and evaluated by receiver operating characteristic curve, calibration curves, and decision curve analysis. RESULTS: Patients with supraglottis, higher pathological grade, higher N stage, and distant metastasis (bone, brain, or liver) were more likely to have LM (P < 0.05). Chemotherapy, surgery and radiotherapy were independent factors of the overall survival of LC patients with LM (P < 0.05). The area under curve of diagnostic nomogram were 0.834 and 0.816 in the training and validation cohort respectively. For the prognostic nomogram, the area under curves of 1-, 2-, and 3-years were 0.735, 0.734, and 0.709 in the training cohort and 0.705, 0.803, and 0.809 in the validation cohort. The calibration curves and decision curve analysis indicated good performance of the nomograms. CONCLUSION: Distant metastasis (bone, brain, or liver) and N stage should be considered for prediction of LM in LC patients. Chemotherapy is the most significant influencing prognostic factor improving the survival of LC patients with LM. Two nomograms may benefit for providing better precautionary measures and treatment decision.

Extraskeletal Ewing's sarcoma of supraglottis: A rare case report.

Ewing's Sarcoma family of tumors is a group of small round tumor cells. Ewing's sarcoma majority occurs in bone, accounts about 10 % of primary bone tumors. Extraskeletal Ewing's sarcoma (ESS) is unusual and commonly seen in trunk, paravertebral, and chest wall region. It is rarely seen in head and neck region, accounting to 2-3 %. In head and neck region, ESS is seen in nasal or oral cavities, sinuses. EES originating in the larynx is very rare. Here, we report a 22 years old female having the complaints of change in voice and noisy breathing who was diagnosed as a case of EES of supraglottis. As the disease progressed during the time of diagnosis, she had to undergo emergency tracheostomy. The disease was inoperable so she received neoadjuvant chemotherapy followed by radiation followed by adjuvant chemotherapy. At present she is symptomatically better. The aim of this report is to put forward the rare site of Ewing's Sarcoma and highlighting the early diagnosis in suspected case with IHC, providing effective multimodality treatment.