PET/CT findings and dose distribution during radiotherapy in T1N0M0-T2N0M0 glottic cancer.

OBJECTIVE: To investigate the positron emission tomography/computed tomography (PET/CT) findings of T1/T2N0M0 glottic cancer (hereafter referred to as T1/T2) and dose distribution in radiotherapy. SUBJECTS AND METHODS: We retrospectively collected data from patients diagnosed with T1/T2N0M0 glottic cancer who received radiotherapy. The extent of fluorine-18-fluorodeoxyglucose (18F-FDG) accumulation in primary tumors, maximum standardized uptake value (SUVmax), total lesion glycolysis (TLG), tumor volume of primary tumors on PET/CT were compared. Furthermore, the tumor identified on PET/CT was incorporated into the radiotherapy plans. A dummy plan (radiation field 6x6cm, prescription point facing the vertebral body, maximum dose ≤107%, T1/T2 66Gy/33 fractions) was developed for three-dimensional conformal radiotherapy, and the dose distribution of primary tumors was calculated. RESULTS: Twenty-nine patients (27 men and two women) were included; their mean age was 67.2±15.0 years. Increased 18F-FDG accumulation in primary tumors was observed on PET/CT in 22/29 (78.5%; T1: 14/21 [67%], T2: 8/8 [100%]) patients. The median SUVmax, TLG, and primary tumor volume were significantly different between T1 and T2 (SUVmax, T1: 4.56 vs. T2: 8.43, P=0.035; TLG, T1: 1.01 vs. T2: 3.71 SUVxmL, P<0.01; primary tumor volume, T1: 0.38mL vs. T2: 0.80mL, P=0.01). At a TLG cut-off value of 3.470, the area under the curve was 0.875, sensitivity was 0.875, and specificity was 0.929 for T1-T2 differentiation. In 20 patients with 18F-FDG accumulation, the minimum radiation dose was significantly different between T1 and T2 (66Gy vs. 64Gy, P<0.01) at the same 66Gy prescription. The minimum radiation dose and primary tumor volume show the correlation value (r=-0.516, P=0.02). CONCLUSION: In glottic cancer, T1 and T2 can be differentiated by the extent of 18F-FDG accumulation in primary tumors on PET/CT. The minimum radiation dose rate decreases as volume increases.

Assessment and validation of glottic motion using cone-beam CT and real-time cine MRI.

PURPOSE: This study aimed to assess the margin for the planning target volume (PTV) using the Van Herk formula. We then validated the proposed margin by real-time magnetic resonance imaging (MRI). METHODS: An analysis of cone-beam computed tomography (CBCT) data from early glottic cancer patients was performed to evaluate organ motion. Deformed clinical target volumes (CTV) after rigid registration were acquired using the Velocity program (Varian Medical Systems, Palo Alto, CA, USA). Systematic (Σ) and random errors (σ) were evaluated. The margin for the PTV was defined as 2.5 Σ + 0.7 σ according to the Van Herk formula. To validate this margin, we accrued healthy volunteers. Sagittal real-time cine MRI was conducted using the ViewRay system (ViewRay Inc., Oakwood Village, OH, USA). Within the obtained sagittal images, the vocal cord was delineated. The movement of the vocal cord was summed up and considered as the internal target volume (ITV). We then assessed the degree of overlap between the ITV and the PTV (vocal cord plus margins) by calculating the volume overlap ratio, represented as (ITV∩PTV)/ITV. RESULTS: CBCTs of 17 early glottic patients were analyzed. Σ and σ were 0.55 and 0.57 for left-right (LR), 0.70 and 0.60 for anterior-posterior (AP), and 1.84 and 1.04 for superior-inferior (SI), respectively. The calculated margin was 1.8 mm (LR), 2.2 mm (AP), and 5.3 mm (SI). Four healthy volunteers participated for validation. A margin of 3 mm (AP) and 5 mm (SI) was applied to the vocal cord as the PTV. The average volume overlap ratio between ITV and PTV was 0.92 (range 0.85-0.99) without swallowing and 0.77 (range 0.70-0.88) with swallowing. CONCLUSION: By evaluating organ motion by using CBCT, the margin was 1.8 (LR), 2.2 (AP), and 5.3 mm (SI). The margin acquired using CBCT fitted well in real-time cine MRI. Given that swallowing during radiotherapy can result in a substantial displacement, it is crucial to consider strategies aimed at minimizing swallowing and related motion.

How reliable is assessment of true vocal cord-arytenoid unit mobility in patients affected by laryngeal cancer? a multi-institutional study on 366 patients from the ARYFIX collaborative group.

PURPOSE: In clinical practice the assessment of the "vocal cord-arytenoid unit" (VCAU) mobility is crucial in the staging, prognosis, and choice of treatment of laryngeal squamous cell carcinoma (LSCC). The aim of the present study was to measure repeatability and reliability of clinical assessment of VCAU mobility and radiologic analysis of posterior laryngeal extension. METHODS: In this multi-institutional retrospective study, patients with LSCC-induced impairment of VCAU mobility who received curative treatment were included; pre-treatment endoscopy and contrast-enhanced imaging were collected and evaluated by raters. According to their evaluations, concordance, number of assigned categories, and inter- and intra-rater agreement were calculated. RESULTS: Twenty-two otorhinolaryngologists evaluated 366 videolaryngoscopies (total evaluations: 2170) and 6 radiologists evaluated 237 imaging studies (total evaluations: 477). The concordance of clinical rating was excellent in only 22.7% of cases. Overall, inter- and intra-rater agreement was weak. Supraglottic cancers and transoral endoscopy were associated with the lowest inter-observer reliability values. Radiologic inter-rater agreement was low and did not vary with imaging technique. Intra-rater reliability of radiologic evaluation was optimal. CONCLUSIONS: The current methods to assess VCAU mobility and posterior extension of LSCC are flawed by weak inter-observer agreement and reliability. Radiologic evaluation was characterized by very high intra-rater agreement, but weak inter-observer reliability. The relevance of VCAU mobility assessment in laryngeal oncology should be re-weighted. Patients affected by LSCC requiring imaging should be referred to dedicated radiologists with experience in head and neck oncology.

Isoprognostic functional CT map for open partial horizontal laryngectomy.

PURPOSE: To identify a radiological map of laryngeal subsites whose involvement by the tumor could predict patients' functional outcomes after open partial horizontal laryngectomy (OPHL). METHODS: The present retrospective analysis concerned 96 patients with glottic squamous cell carcinoma, who were radiologically staged with contrast-enhanced neck CT scans before undergoing supracricoid or supratracheal laryngectomy. A radiological map of patients' functional risk was developed by considering the distribution of functional outcomes in relation to the laryngeal subsites involved. The functional outcomes considered were: (i) decannulation at discharge; (ii) time to removal of the nasogastric feeding tube (NFT); (iii) postoperative complication rate; and (iv) length of hospital stay. RESULTS: Involvement of the anterior supraglottis was related to a longer need for NFT, and a longer hospital stay (p = 0.003, and p = 0.003, respectively). Involvement of the posterior glottis negatively affected the time to decannulation, and the likelihood of postoperative complications (p = 0.000, and p = 0.002, respectively). CONCLUSIONS: Anterior glottic small tumors (without significant subglottic and/or supraglottic extension) are related to the best functional outcomes after OPHL, since the suprahyoid epiglottis and both the arytenoids are likely to be spared.

Transoral laser microsurgery for T1 glottic cancer with anterior commissure: Identifying clinical and radiological variables that predict oncological outcome.

PURPOSE: The involvement of the anterior commissure (AC) is regarded to be a risk factor for poor results after transoral laser microsurgery (TLM) for early glottic cancer. The objective of this study was to determine how AC-related clinical and radiological factors affected oncological outcomes in a cohort of patients with T1 stage early glottic carcinoma involving the anterior commissure who were treated with TLM with negative surgical margins. METHODS: Retrospective analysis was performed on clinical, radiological, and follow-up data of patients consecutively treated with TLM at a tertiary academic center between November 2011 and August 2021 for T1 glottic squamous cell carcinoma involving the anterior commissure. Recurrence-free survival (RFS), local control with laser alone (LCL), laryngeal preservation (LP), and overall survival (OS) rates (Kaplan-Meier) were the primary outcome metrics. RESULTS: In our series, 5-year OS probability was 75.1%, RFS was 64.8%, LCL was 73.8%, and LP was 83.4%. OS and RFS were higher in patients with early stages of AC pattern than in patients with advanced stage (p = 0.004, p = 0.034, respectively). Vertical extension ratio was found to be associated with OS and RFS (p = 0.023, p = 0.001, respectively), and thyroid cartilage interlaminar angle with LCL by multiple Cox regression analysis (p = 0.041). CONCLUSION: TLM remains a valuable treatment option for AC involvement. AC3 type involvement and elevated vertical extension ratio were associated with negative prognosis. There have been signs that thyroid cartilage with a narrow angle increases recurrence. Alternative modalities should be kept in mind in the treatment decision of these cases.

Improved delineation with diffusion weighted imaging for laryngeal and hypopharyngeal tumors validated with pathology.

OBJECTIVE: This study aims to determine the added value of a geometrically accurate diffusion-weighted (DW-) MRI sequence on the accuracy of gross tumor volume (GTV) delineations, using pathological tumor delineations as a ground truth. METHODS: Sixteen patients with laryngeal or hypopharyngeal carcinoma were included. After total laryngectomy, the specimen was cut into slices. Photographs of these slices were stacked to create a 3D digital specimen reconstruction, which was registered to the in vivo imaging. The pathological tumor (tumorHE) was delineated on the specimen reconstruction. Six observers delineated all tumors twice: once with only anatomical MR imaging, and once (a few weeks later) when DW sequences were also provided. The majority voting delineation of session one (GTVMRI) and session two (GTVDW-MRI), as well as the clinical target volumes (CTVs), were compared to the tumorHE. RESULTS: The mean tumorHE volume was 11.1 cm3, compared to a mean GTVMRI volume of 18.5 cm3 and a mean GTVDW-MRI volume of 15.7 cm3. The median sensitivity (tumor coverage) was comparable between sessions: 0.93 (range: 0.61-0.99) for the GTVMRI and 0.91 (range: 0.53-1.00) for the GTVDW-MRI. The CTV volume also decreased when DWI was available, with a mean CTVMR of 47.1 cm3 and a mean CTVDW-MRI of 41.4 cm3. Complete tumor coverage was achieved in 15 and 14 tumors, respectively. CONCLUSION: GTV delineations based on anatomical MR imaging tend to overestimate the tumor volume. The availability of the geometrically accurate DW sequence reduces the GTV overestimation and thereby CTV volumes, while maintaining acceptable tumor coverage.

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.

The added value of radiomics in determining patient responsiveness to laryngeal preservation strategies.

PURPOSE OF REVIEW: Laryngeal cancer (LC) is a highly aggressive malignancy of the head and neck and represents about 1-2% of cancer worldwide.Treatment strategies for LC aim both to complete cancer removal and to preserve laryngeal function or maximize larynx retention.Predicting with high precision response to induction chemotherapy (IC) is one of the main fields of research when considering LC, since this could guide treatment strategies in locally advanced LC. RECENT FINDINGS: Radiomics is a noninvasive method to extract quantitative data from the whole tumor using medical imaging. This signature could represent the underlying tumor heterogeneity and phenotype.During the last five years, some studies have highlighted the potential of radiomics in the pretreatment assessment of LC, in the prediction of response to IC, and in the early assessment of response to radiation therapy. Although these represent promising results, larger multicentric studies are demanded to validate the value of radiomics in this field. SUMMARY: The role of radiomics in laryngeal preservation strategies is still to be defined. There are some early promising studies, but the lack of validation and larger multicentric studies limit the value of the papers published in the literature and its application in clinical practice.

Correlation of narrow-band imaging findings using the Ni and European Laryngeal Society classification systems during in-office flexible laryngoscopy with histopathology.

OBJECTIVE: This study used the European Laryngeal Society (2016) and Ni (2011 and 2019) classifications for narrow-band imaging and correlated the findings with histopathology. METHODS: Retrospective analysis was conducted by retrieving data of patients who underwent micro-laryngoscopy for suspicious glottic lesions. The narrow-band imaging findings were classified using both classification systems. Retrieved histopathology report findings were correlated with narrow-band imaging data. RESULTS: Using the European Laryngeal Society and Ni classifications, 37 (69.8 per cent) and 35 (66 per cent) patients, respectively, were suspected to have malignant lesions. Upon histopathology, 37 (69.8 per cent) lesions were malignant. Sensitivity, specificity, positive predictive value, negative predictive value and accuracy using the European Laryngeal Society classification were 91.9 per cent, 81.3 per cent, 91.9 per cent, 81.3 per cent and 88.7 per cent, and using the Ni classification were 91.9 per cent, 93.8 per cent, 97.1 per cent, 83.3 per cent and 92.5 per cent, respectively. CONCLUSION: The Ni classification had better specificity and accuracy. The European Laryngeal Society classification is simple to use and may serve as a useful screening tool. For optimum results, both European Laryngeal Society and Ni classifications may be used together, in that order.

The influence of clinical experience on reliable evaluation of pharyngeal and laryngeal lesions: comparison of high-definition laryngoscopy using narrow band imaging with fibre-optic laryngoscopy.

BACKGROUND: Fibre-optic laryngoscopy is still widely used in daily clinical practice; however, high-definition laryngoscopy using narrow band imaging could be more reliable in characterising pharyngeal and laryngeal lesions. METHODS: Endoscopic videos were assessed in a tertiary referral hospital by 12 observers with different levels of clinical experience. Thirty pairs of high-definition laryngoscopy with narrow band imaging and fibre-optic laryngoscopy videos were judged twice, with an interval of two to four weeks, in a random order. Inter- and intra-observer reliability, sensitivity and specificity were calculated in terms of detecting a malignant lesion and a specific histological entity, for beginners, trained observers and experts. RESULTS: Using high-definition laryngoscopy with narrow band imaging, inter-observer reliability for detecting malignant lesions increased from moderate to substantial in trained observers and experts (high-definition laryngoscopy with narrow band imaging κ = 0.66 and κ = 0.77 vs fibre-optic laryngoscopy κ = 0.51 and κ = 0.56, for trained observers and experts respectively) and sensitivity increased by 16 per cent. CONCLUSION: Inter-observer reliability increased with the level of clinical experience, especially when using high-definition laryngoscopy with narrow band imaging.

CT of the Larynx: Is an Additional High-Resolution Acquisition Necessary for Diagnostic Accuracy?

BACKGROUND AND PURPOSE: Diagnostic CT of the larynx is historically performed with a protocol that combines a standard neck CT with dedicated imaging through the larynx. Multichannel CT scanners, however, allow high-resolution reformatted images of the larynx to be created directly from the initial neck acquisition data. The purpose of this study was to determine whether reformatted laryngeal images derived from a standard neck CT acquisition provide information comparable with that of separate dedicated high-resolution laryngeal images. MATERIALS AND METHODS: The CT protocol for suspected laryngeal masses at our institution consists of a standard neck acquisition followed by a second acquisition focused on the larynx. We enrolled 200 patients who had undergone this protocol for a suspected laryngeal mass. Two head and neck radiologists independently reviewed each of the 200 scans twice. In one session, the entire scan was available, while in the other session, only images derived from the standard neck acquisition were available. The main outcome variable was the frequency of discrepant tumor staging between the interpretation sessions. No pathologic reference standard was used. RESULTS: Radiologist A had discrepant staging in 45 of the 200 scans (23%; 95% CI, 17%-29%). Radiologist B had discrepant staging in 42 of the 200 scans (21%; 95% CI, 16%-27%). Fifty-three of the 87 discrepancies (61%) reflected improper downstaging of the laryngeal tumor on standard images alone, while the other 34 (39%) had improper upstaging on standard images alone. CONCLUSIONS: Reformatted images from our institution's standard neck CT acquisition were less accurate than dedicated images of the larynx for analysis of laryngeal tumor extension. Focused images of the larynx were needed to optimize interpretation.

[Diagnostic efficiency of transcutaneous ultrasound scanning and Dopplerography in laryngeal pathology]. / Diagnosticheskaya effektivnost' ul'trazvukovogo skanirovaniya i doplerografii pri patologii gortani.

OBJECTIVE: To assess the efficiency and the place of grey scale ultrasound and color Doppler sonography of the larynx in the diagnosis of laryngeal pathology. MATERIAL AND METHODS: A prospective blind cohort examination in B-mode laryngeal ultrasound (LUS) and color Doppler imaging (CDI) with linear scanning transducer 7-15 MHz was performed in 120 patients aged from 6 months to 52 years (average age 7.6±5.8 years, Me 6 year) and in 40 patients without laryngeal pathology (average age 7.0±5.0 years). The patients presented with complaints of voice and/or stridor. The diagnosis was verified by followed laryngoscopy. RESULTS: Laryngeal papillomas, hemangiomas, scarring and vocal fold's nodules were identified as hyperechoic formations. Color Doppler sonography made it possible to visualize them better: small formations were highlighted in color and the space around the large ones was colored. There were paradoxical movements of the hyperechoic arytenoid cartilages during inspiration to the anterior commissure in patients with laryngomalacia. Color Doppler ultrasonography revealed changes during phonation in patients with functional dysphonia. The sensitivity and specificity of LUS were 58% (95% CI 48-66) and 98% (95% CI 87-99) compared with laryngoscopy in the detection of laryngeal pathology, but laryngeal CDI - 81% (95% CI 72-87) and 98% (95% CI 87-99) respectively. CONCLUSION: Ultrasound of the larynx in B-mode has a diagnostic efficiency of 67.5%, and in CDI mode - 85% for ruling in laryngeal pathologies compared to laryngoscopy. So, this method is a modern affordable, non-invasive and informative diagnostic tool for the detection of laryngeal diseases, especially in those cases, when it is impossible to carry out a laryngoscopy.

Prognostic value of interim CT-based peritumoral and intratumoral radiomics in laryngeal and hypopharyngeal cancer patients undergoing definitive radiotherapy.

BACKGROUND AND PURPOSE: We aimed to investigate the prognostic value of peritumoral and intratumoral computed tomography (CT)-based radiomics during the course of radiotherapy (RT) in patients with laryngeal and hypopharyngeal cancer (LHC). MATERIALS AND METHODS: A total of 92 eligible patients were 1:1 randomly assigned into training and validation cohorts. Pre-RT and mid-RT radiomic features were extracted from pre-treatment and interim CT. LASSO-Cox regression was used for feature selection and model construction. Time-dependent area under the receiver operating curve (AUC) analysis was applied to evaluate the models' prognostic performances. Risk stratification ability on overall survival (OS) and progression-free survival (PFS) were assessed using the Kaplan-Meier method and Cox regression. The associations between radiomics and clinical parameters as well as circulating lymphocyte counts were also evaluated. RESULTS: The mid-RT peritumoral (AUC: 0.77) and intratumoral (AUC: 0.79) radiomic models yielded better performance for predicting OS than the pre-RT intratumoral model (AUC: 0.62) in validation cohort. This was confirmed by Kaplan-Meier analysis, in which risk stratification depended on the mid-RT peritumoral (p = 0.009) and intratumoral (p = 0.003) radiomics could be improved for OS, in comparison to the pre-RT intratumoral radiomics (p = 0.199). Multivariate analysis identified mid-RT peritumoral and intratumoral radiomic models as independent prognostic factors for both OS and PFS. Mid-RT peritumoral and intratumoral radiomics were correlated with treatment-related lymphopenia. CONCLUSION: Mid-RT peritumoral and intratumoral radiomic models are promising image biomarkers that could have clinical utility for predicting OS and PFS in patients with LHC treated with RT.

Concordance between head and neck MRI and histopathology in detecting laryngeal subsite invasion among patients with laryngeal cancer.

BACKGROUND: Accuracy of head and neck MRI (HN-MRI) in predicting tumor invasion of laryngeal site/subsites in patients with laryngeal cancer prior to laryngectomy is poorly evaluated in the literature. Therefore, we aim to evaluate the diagnostic value of HN-MRI in accurate pre-operative estimation of tumor invasion to laryngeal subsites in patients with laryngeal cancer. METHODS: Patients with laryngeal cancer who underwent HN-MRI for cancer staging and underwent total laryngectomy between 2008 and 2021 were included. Sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy of HN-MRI in predicting tumor invasion of laryngeal subsites were calculated based on concordance between the HN-MRI and histopathological results. RESULTS: One hundred and thirty-seven patients underwent total laryngectomy [primary: 82/137(60%), salvage 55/137(40%)]. The utilization of HN-MRI resulted in the downstaging of 16/137 (11.6%) patients and the upstaging of 8/137 (5.8%) patients. For the whole cohort, there was a significant discordance between HN-MRI and histopathology for T-category; out of 116 cT4a disease, 102(87.9%) were confirmed to have pT4a disease, and out of 17 cT3 disease, 9(52.9%) were confirmed to have pT3 disease, p < 0.001. The MRI overall diagnostic accuracy of predicting tumor invasion was 91%, 92%, 82%, 87%, 72%, 76%, 65% and 68% for base of tongue, arytenoid, vocal cord, posterior commissure, pre-epiglottic space, cricoid cartilage, inner thyroid cortex, and subglottis, respectively. CONCLUSIONS: In patients with laryngeal cancer undergoing total laryngectomy, HN-MRI demonstrates promising accuracy in predicting tumor invasion of specific laryngeal subsites (e.g., base of tongue). Our findings showed the potential of HN-MRI as a valuable tool for pre-operative planning and treatment decision-making in this patient population.

Contact Endoscopy - Narrow Band Imaging (CE-NBI) data set for laryngeal lesion assessment.

The endoscopic examination of subepithelial vascular patterns within the vocal fold is crucial for clinicians seeking to distinguish between benign lesions and laryngeal cancer. Among innovative techniques, Contact Endoscopy combined with Narrow Band Imaging (CE-NBI) offers real-time visualization of these vascular structures. Despite the advent of CE-NBI, concerns have arisen regarding the subjective interpretation of its images. As a result, several computer-based solutions have been developed to address this issue. This study introduces the CE-NBI data set, the first publicly accessible data set that features enhanced and magnified visualizations of subepithelial blood vessels within the vocal fold. This data set encompasses 11144 images from 210 adult patients with pathological vocal fold conditions, where CE-NBI images are annotated using three distinct label categories. The data set has proven invaluable for numerous clinical assessments geared toward diagnosing laryngeal cancer using Optical Biopsy. Furthermore, given its versatility for various image analysis tasks, we have devised and implemented diverse image classification scenarios using Machine Learning (ML) approaches to address critical clinical challenges in assessing laryngeal lesions.

The importance of preoperative and perioperative Narrow Band Imaging endoscopy in the diagnosis of pre-tumor and tumor lesions of the larynx.

INTRODUCTION: Narrow band imaging (NBI) is an endoscopic imaging method intended for the diagnosis of mucosal lesions of the larynx that are not visible in white-light endoscopy, but are typical of pre-tumor and tumor lesions of the larynx. THE PURPOSE OF THE STUDY: To compare preoperative/perioperative white light endoscopy and NBI endoscopy with the results of histopathological examinations in pre-tumor and tumor lesions of the larynx. METHODS: A prospective study, over a period of five years (5/2018-5/2023), included 87 patients with laryngeal lesions aged 24-80 years. We evaluated preoperative/ perioperative white light and NBI endoscopy, established a working prehistological diagnosis, and compared this with the definitive histopathological results of laryngeal biopsies. RESULTS: In relation to the definitive histology score, a statistically significant correlation was found between the evaluation of the finding and the definitive histology for preoperative and perioperative white light endoscopy and NBI endoscopy (p < 0.001). Both methods showed higher precision when used perioperatively. CONCLUSION: NBI endoscopy is an optical method that allows us to improve the diagnosis of laryngeal lesions, perform a controlled perioperative biopsy, and refine the surgical scope. The NBI endoscopy is a suitable method for the diagnosis of early cancerous lesions of the larynx. The use of preoperative/perioperative NBI endoscopy allowed us to achieve a high level of agreement correlation (p < 0.001) between the prehistological working diagnosis and the final histopathological result. The NBI method proves its application in the diagnosis of pre-tumor and tumor lesions of the larynx.

The usefulness of machine-learning-based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features for predicting prognosis in patients with laryngeal cancer.

OBJECTIVE: To examine whether machine learning (ML) analyses involving clinical and 18F-FDG-PET-based radiomic features are helpful in predicting prognosis in patients with laryngeal cancer. METHODS: This retrospective study included 49 patients with laryngeal cancer who underwent18F-FDG-PET/CT before treatment, and these patients were divided into the training (n = 34) and testing (n = 15) cohorts.Seven clinical (age, sex, tumor size, T stage, N stage, Union for International Cancer Control stage, and treatment) and 40 18F-FDG-PET-based radiomic features were used to predict disease progression and survival. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were used for predicting disease progression. Two ML algorithms (cox proportional hazard and random survival forest [RSF] model) considering for time-to-event outcomes were used to assess progression-free survival (PFS), and prediction performance was assessed by the concordance index (C-index). RESULTS: Tumor size, T stage, N stage, GLZLM_ZLNU, and GLCM_Entropy were the five most important features for predicting disease progression.In both cohorts, the naïve Bayes model constructed by these five features was the best performing classifier (training: AUC = 0.805; testing: AUC = 0.842). The RSF model using the five features (tumor size, GLZLM_ZLNU, GLCM_Entropy, GLRLM_LRHGE and GLRLM_SRHGE) exhibited the highest performance in predicting PFS (training: C-index = 0.840; testing: C-index = 0.808). CONCLUSION: ML analyses involving clinical and 18F-FDG-PET-based radiomic features may help predict disease progression and survival in patients with laryngeal cancer. ADVANCES IN KNOWLEDGE: ML approach using clinical and 18F-FDG-PET-based radiomic features has the potential to predict prognosis of laryngeal cancer.

Interpretable Computer Vision to Detect and Classify Structural Laryngeal Lesions in Digital Flexible Laryngoscopic Images.

OBJECTIVE: To localize structural laryngeal lesions within digital flexible laryngoscopic images and to classify them as benign or suspicious for malignancy using state-of-the-art computer vision detection models. STUDY DESIGN: Cross-sectional diagnostic study SETTING: Tertiary care voice clinic METHODS: Digital stroboscopic videos, demographic and clinical data were collected from patients evaluated for a structural laryngeal lesion. Laryngoscopic images were extracted from videos and manually labeled with bounding boxes encompassing the lesion. Four detection models were employed to simultaneously localize and classify structural laryngeal lesions in laryngoscopic images. Classification accuracy, intersection over union (IoU) and mean average precision (mAP) were evaluated as measures of classification, localization, and overall performance, respectively. RESULTS: In total, 8,172 images from 147 patients were included in the laryngeal image dataset. Classification accuracy was 88.5 for individual laryngeal images and increased to 92.0 when all images belonging to the same sequence (video) were considered. Mean average precision across all four detection models was 50.1 using an IoU threshold of 0.5 to determine successful localization. CONCLUSION: Results of this study showed that deep neural network-based detection models trained using a labeled dataset of digital laryngeal images have the potential to classify structural laryngeal lesions as benign or suspicious for malignancy and to localize them within an image. This approach provides valuable insight into which part of the image was used by the model to determine a diagnosis, allowing clinicians to independently evaluate models' predictions.