ABSTRACT
PURPOSE: Recent breakthroughs in natural language processing and machine learning, exemplified by ChatGPT, have spurred a paradigm shift in healthcare. Released by OpenAI in November 2022, ChatGPT rapidly gained global attention. Trained on massive text datasets, this large language model holds immense potential to revolutionize healthcare. However, existing literature often overlooks the need for rigorous validation and real-world applicability. METHODS: This head-to-head comparative study assesses ChatGPT's capabilities in providing therapeutic recommendations for head and neck cancers. Simulating every NCCN Guidelines scenarios. ChatGPT is queried on primary treatments, adjuvant treatment, and follow-up, with responses compared to the NCCN Guidelines. Performance metrics, including sensitivity, specificity, and F1 score, are employed for assessment. RESULTS: The study includes 68 hypothetical cases and 204 clinical scenarios. ChatGPT exhibits promising capabilities in addressing NCCN-related queries, achieving high sensitivity and overall accuracy across primary treatment, adjuvant treatment, and follow-up. The study's metrics showcase robustness in providing relevant suggestions. However, a few inaccuracies are noted, especially in primary treatment scenarios. CONCLUSION: Our study highlights the proficiency of ChatGPT in providing treatment suggestions. The model's alignment with the NCCN Guidelines sets the stage for a nuanced exploration of AI's evolving role in oncological decision support. However, challenges related to the interpretability of AI in clinical decision-making and the importance of clinicians understanding the underlying principles of AI models remain unexplored. As AI continues to advance, collaborative efforts between models and medical experts are deemed essential for unlocking new frontiers in personalized cancer care.
Subject(s)
Adjuvants, Immunologic , Head and Neck Neoplasms , Humans , Benchmarking , Clinical Decision-Making , Head and Neck Neoplasms/therapy , Artificial IntelligenceABSTRACT
PURPOSE: In laryngeal squamous cell carcinoma (LSCC) treated with transoral laser microsurgery (TOLMS), the status of margins significantly affected local control. When a positive or close margin is present, there is no ubiquitous consensus regarding further treatments. The rationale of the present systematic review and meta-analysis is to investigate the survival impact of the status of the margins in patients affected by LSCC treated with TOLMS. DATA SOURCES: PubMed, EMBASE, and Cochrane Library. METHODS: We performed a systematic search, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Inclusion criteria were: patients affected by LSCC, staged according to the American Joint Committee on Cancer Staging System and treated by TOLMS without any previous treatment; margins status (close, positive, negative) and the adjusted hazard ratios (aHRs) with 95% confidence intervals (CIs) of overall survival, disease-specific survival, and disease-free survival has to be reported. RESULTS: Nine studies were deemed eligible for the qualitative analysis, and 3 for the quantitative analysis to investigate the association between margin status and OS. The cumulative number of patients was 3130. The sample size ranged from 96 to 747 patients. The follow-up period ranged from 0 to 201 months. The meta-analysis results show that positive margins have an aHR of 1.30 yet with CI range (0.56 to 2.97). CONCLUSIONS: Our current meta-analysis results are unable to definitively assess the real impact of resection margins on OS. Few authors provide accurate data regarding position and types of margins. Further prospective or high-quality studies are required.
ABSTRACT
PURPOSE: Informative image selection in laryngoscopy has the potential for improving automatic data extraction alone, for selective data storage and a faster review process, or in combination with other artificial intelligence (AI) detection or diagnosis models. This paper aims to demonstrate the feasibility of AI in providing automatic informative laryngoscopy frame selection also capable of working in real-time providing visual feedback to guide the otolaryngologist during the examination. METHODS: Several deep learning models were trained and tested on an internal dataset (n = 5147 images) and then tested on an external test set (n = 646 images) composed of both white light and narrow band images. Four videos were used to assess the real-time performance of the best-performing model. RESULTS: ResNet-50, pre-trained with the pretext strategy, reached a precision = 95% vs. 97%, recall = 97% vs, 89%, and the F1-score = 96% vs. 93% on the internal and external test set respectively (p = 0.062). The four testing videos are provided in the supplemental materials. CONCLUSION: The deep learning model demonstrated excellent performance in identifying diagnostically relevant frames within laryngoscopic videos. With its solid accuracy and real-time capabilities, the system is promising for its development in a clinical setting, either autonomously for objective quality control or in conjunction with other algorithms within a comprehensive AI toolset aimed at enhancing tumor detection and diagnosis.
Subject(s)
Deep Learning , Laryngoscopy , Humans , Laryngoscopy/methods , Video Recording , Feasibility Studies , Laryngeal Diseases/diagnosis , Laryngeal Diseases/diagnostic imagingABSTRACT
Introduction: The increasing population of survivors of head and neck carcinomas is becoming more conspicuous. Consequently, the pivotal role of quality of life, particularly elucidated through the assessment of dysphagia and dysphonia, is progressively influencing the decision-making process. The current study aims to assess whether VITOM 3D could offer a comparable post-treatment quality of life to traditional approaches for patients with laryngeal cancer and oro-hypopharyngeal cancer. Methods: A case series of laryngeal cancer and oro-hypopharyngeal cancer patients treated either with an exoscopic-assisted surgical setup and with conventional treatments (transoral microsurgery and radio-chemotherapy) at the Otolaryngology Unit of IRCCS San Martino Hospital, Genoa, is presented. The post-treatment quality of life of the two cohorts were compared through the administration of the University of Washington Quality of Life Questionnaire, Voiceik Handicap Index-10, M.D. Anderson Dysphagia Inventory were administrated to both cohorts of patients. Results: In the laryngeal cancer group, a total of 79 patients were included. Of these, 50.1% underwent transoral exoscope-assisted surgery, while 49.9% underwent primary transoral microscopic-assisted surgical approach. No significant differences were observed in terms of the University of Washington Quality of Life Questionnaire and Voice Handicap Index-10 between the two subgroups. Conversely, in the oro-hypopharyngeal cancer group, 43 patients were included. Of these, 37.2% underwent primary transoral exoscope-assisted surgery, while 62.8% received (chemo)radiotherapy. No notable differences were reported in terms of the University of Washington Quality of Life Questionnaire and M.D. Anderson Dysphagia Inventory between the transoral exoscope-assisted surgery and (chemo)radiotherapy subgroups. Conclusions: Assessments of quality of life, conducted through the University of Washington Quality of Life Questionnaire questionnaire, dysphonia evaluations using the Voice Handicap Index-10, and dysphagia assessments employing the M.D. Anderson Dysphagia Inventory questionnaire, demonstrate analogous outcomes between conventional treatment modalities and transoral interventions utilizing the 3D exoscope.
ABSTRACT
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.
Subject(s)
Deep Learning , Laryngeal Neoplasms , Laryngoscopy , Narrow Band Imaging , Humans , Laryngoscopy/methods , Narrow Band Imaging/methods , Laryngeal Neoplasms/diagnostic imaging , Laryngeal Neoplasms/surgery , Laryngeal Neoplasms/pathology , Retrospective Studies , Video Recording , Male , Female , Middle Aged , Light , AgedABSTRACT
BACKGROUND: Transoral robotic surgery (TORS) performed after neoadjuvant chemotherapy (NAC) is a promising treatment for advanced-stage oropharyngeal carcinoma (OPSCC) able to reduce the adjuvant therapy administration rate. METHODS: A retrospective bi-centric study was conducted to analyze NAC + TORS versus upfront TORS patients. A 1:1 propensity score matching was used to compare the two groups. RESULTS: Among the 300 patients with stage III-IV OPSCC, 204 patients were matched for comparing NAC + TORS versus upfront TORS. Between the two groups, no significant difference was observed in recurrences and in survival for RFS, OS, and DSS. In the NAC + TORS p16-positive population, adjuvant therapy could be spared in 51% versus 16% in the upfront surgery cohort (p < 0.001) due to the lower frequency of pathological risk factors after NAC. CONCLUSIONS: NAC followed by TORS for locoregionally advanced OPSCC demonstrated to achieve non-inferior survival outcomes to upfront surgery, while in the p16-positive population allowed to significantly spare adjuvant therapy.
ABSTRACT
OBJECTIVE: The prognostic value of depth of invasion (DOI) in oral squamous cell cancer carcinoma and cutaneous melanoma is well established, while there is a lack of reports investigating the role of DOI in laryngeal cancer. This study aims to explore the association of glottic cancer DOI with other established pathological risk factors and nodal metastasis and evaluate the feasibility of measuring DOI preoperatively using tomographic imaging. METHODS: The medical records of glottic cancer patients treated between 2015 and 2020 in a single tertiary referral center were screened retrospectively. Pathologically measured DOI (pDOI) value was also reviewed and registered. Preoperative computer tomography (CT) was used to obtain the radiological DOI (rDOI) measured by two dedicated radiologists. Their inter-rated agreement was assessed and the correlation between pDOI and rDOI was calculated. pDOI association with the main pathology report features was assessed with univariable analysis. Cox univariable and multivariable models were used to explore the role of pDOI on survival. RESULTS: Ninety-one patients had pDOI data available, of which 59 also had rDOI data. A strong concordance between the two radiologists was found (concordance correlation coefficient = 0.96); rDOI and pDOI were highly and significantly correlated (R = 0.85; p < 0.001). pDOI was significantly higher in patients with perineural invasion (PNI; p < 0.001), lymphovascular invasion (LVI; p < 0.001), and nodal metastasis (p < 0.001). pDOI was associated with disease-free survival at univariable analysis (p = 0.04) while it did not show a significant impact (p = 0.10) at multivariable analysis. CONCLUSION: Glottic carcinoma DOI correlates with PNI, LVI, and nodal metastasis and it can be reliably assessed in a preoperative setting using CT imaging. LEVEL OF EVIDENCE: 3 Laryngoscope, 134:3230-3237, 2024.
Subject(s)
Glottis , Laryngeal Neoplasms , Neoplasm Invasiveness , Tomography, X-Ray Computed , Humans , Laryngeal Neoplasms/pathology , Laryngeal Neoplasms/surgery , Laryngeal Neoplasms/diagnostic imaging , Laryngeal Neoplasms/mortality , Male , Female , Glottis/pathology , Glottis/diagnostic imaging , Glottis/surgery , Retrospective Studies , Middle Aged , Aged , Prognosis , Preoperative Care/methods , Feasibility Studies , Lymphatic Metastasis/diagnostic imaging , Lymphatic Metastasis/pathology , Aged, 80 and over , AdultABSTRACT
OBJECTIVE: The aim of this study is to analyze oncologic outcomes and complications rate after common or internal carotid artery (CCA/ICA) resection for head and neck squamous cell carcinoma (HNSCC). METHODS: This study was conducted in conformity with the PRISMA statement. A systematic review and pooled analysis was performed for overall survival (OS), disease specific survival (DSS) (primary outcomes), and perioperative death rate (secondary outcome). RESULTS: A total of 276 patients (males: 76.7%, n = 191/249) with a median age of 59 years (n = 239/276; 95% CI 55.0-61.7) who underwent CCA/ICA resection for HNSCC were included. The median follow-up time was 11 months (n = 276). Estimated pooled OS rates (95% CI) at 1 and 2 years were 52.7% (46.9-59.2) and 29.8% (24.3-36.5), respectively. The median OS (95% CI) was 14 months (12-17). Estimated pooled DSS rates (95% CI) at 1 and 2 years were 58.6% (52.7-65.2) and 34.6% (28.5-41.9), respectively. The median DSS (95% CI) was 16 months (14-19). The perioperative death rate was 6.9% (n = 19/276). CONCLUSIONS: CCA/ICA resection should be considered as a treatment option for accurately selected patients. Multicentric prospective studies are recommended to develop a predictive score guiding the decision-making process.