Prognostic factors for recurrence of locally advanced differentiated thyroid cancer

Natural History and Prognostic Model of Untreated Papillary Thyroid Cancer: A SEER Database Analysis

PURPOSE

This investigation leveraged the SEER database to delve into the progression patterns of PTC when left untreated. Furthermore, it aimed to devise and authenticate a nomogram for prognosis prediction for such patients.

METHODS

We extracted data from the SEER database, focusing on PTC-diagnosed individuals from 2004-2020. To discern disease progression intervals, median survival times across stages were gauged, and the disease progression time was estimated by subtracting the median survival time of a more severe stage from its preceding stage. Prognostic determinants in the training set were pinpointed using both univariate and multivariate Cox regression. Using these determinants, a prognostic nomogram was crafted.

RESULTS

In untreated PTC patients, those in stages I and II had a favorable prognosis, with 10-year overall survival rates of 86.34% and 66.03%, respectively. Patients in stages III and IV had a relatively poorer prognosis. The median survival time of stage III, stage IVA, stage IVB and stage IVC patients was 108months, 43 months, 20 months and 8 months, respectively. The deduced progression intervals from stages III-IVC were 65, 23, and 12 months. In the training set, age, tumor stage, gender, and marital status were identified as independent risk factors influencing the prognosis of untreated PTC, and a nomogram was constructed using these variables.

CONCLUSION

In the absence of treatment intervention, early-stage PTC progressed slowly with an overall favorable prognosis. However, in mid to advanced-stage PTC, as tumor stage increased, disease progression accelerated, and prognosis gradually worsened. Age, tumor stage, marital status, and gender were independent risk factors influencing the prognosis of untreated PTC, and the nomogram based on these factors demonstrated good prognostic capability.

Initial clinical and treatment patterns of advanced differentiated thyroid cancer: ERUDIT study

Background

Up to 30% of differentiated thyroid cancer (DTC) will develop advanced-stage disease (aDTC) with reduced overall survival (OS).

Objective

The aim of this study is to characterize initial diagnosis of aDTC, its therapeutic management, and prognosis in Spain and Portugal.

Methods

A multicentre, longitudinal, retrospective study of adult patients diagnosed with aDTC in the Iberian Peninsula was conducted between January 2007 and December 2012. Analyses of baseline characteristics and results of initial treatments, relapse- or progression-free survival ((RP)FS) from first DTC diagnosis, OS, and prognostic factors impacting the evolution of advanced disease were evaluated.

Results

Two hundred and thirteen patients (median age: 63 years; 57% female) were eligible from 23 hospitals. Advanced disease presented at first diagnosis (de novo aDTC) included 54% of patients, while 46% had relapsed from early disease (recurrent/progressive eDTC). At initial stage, most patients received surgery (98%) and/or radioiodine (RAI) (89%), with no differences seen between median OS (95% CI) (10.4 (7.3-15.3) years) and median disease-specific-survival (95% CI) (11.1 (8.7-16.2) years; log-rank test P = 0.4737). Age at diagnosis being <55 years was associated with a lower risk of death (Wald chi-square (Wc-s) P < 0.0001), while a poor response to RAI to a higher risk of death ((Wc-s) P < 0.05). In the eDTC cohort, median (RP)FS (95% CI) was of 1.7 (1.0-2.0) years after RAI, with R0/R1 surgeries being the only common significant favourable factor for longer (RP)FS and time to aDTC ((Wc-s) P < 0.05).

Conclusion

Identification of early treatment-dependent prognostic factors for an unfavourable course of advanced disease is possible. An intensified therapeutic attitude may reverse this trend and should be considered in poor-performing patients. Prospective studies are required to confirm these findings.

Is there a relationship between preoperative cytological diagnosis and evolution in patients with differentiated thyroid carcinoma? A retrospective study

Objective

Cytological analysis and Bethesda classification of thyroid nodules is the standard method of diagnosing differentiated thyroid carcinoma (DTC). However, even for nodules with a non-malignant cytological diagnosis, there is a not insignificant risk of cancer. There are doubts whether this lack of certainty would influence patient prognosis. Our aim was to compare patients with DTC, classified according to the preoperative cytological diagnosis, regarding their evolution.

Methods

A retrospective study was carried out with 108 DTC patients submitted to total thyroidectomy (TT) between 2009 and 2015, divided into three groups according to preoperative cytological diagnosis (Bethesda classification): classes I/II, III/IV, and V/VI. Groups were compared for evolution considering response to treatment at last evaluation as well as time disease free. Statistical analysis used ANOVA, chi squared, and Kaplan-Meier curves with p<0.05 considered significant.

Results

Groups differed for time between nodule puncture and TT [in months; V/VI (2.35 ± 2.48) < III/IV (7.32 ± 6.34) < I/II (13.36 ± 8.9); p < 0.0001]. There was no significant difference between groups for evolution at final evaluation (disease free status; classes I/II: 71.4%; classes III/IV: 60%; classes V/VI: 66.6%; p = 0.7433), as well as time disease free (in months; classes I/II: 34.57 ± 25.82; classes III/IV: 38.04 ± 26.66; classes V/VI: 30.84 ± 26.34; p = 0.3841).

Conclusion

DTC patients classified according to preoperative cytological diagnosis did not differ for evolution. Although patients with non-malignant cytological diagnoses were submitted to TT later, this did not affect the evolution of the cases.

Does Locally Advanced Thyroid Cancer Have Different Features? Results from a Single Academic Center

Background: Despite the fact that the majority of thyroid cancers are indolent, 15% of patients with well-differentiated carcinoma including papillary thyroid carcinoma (PTC) present with locally advanced thyroid cancer (LATC) at diagnosis. The current study analyzes a cohort of patients with LATC focusing on their risk for local recurrence, distant metastases, and overall survival. Materials and methods: From January 2010 to December 2020, 65 patients with LATC were retrieved, including 42 cases with preoperative cytological samples. BRAF^V600E and TERT mutations were performed on both cytology and histopathology specimens in this cohort. Results: Among the 65 cases, 42 (65%) were women. The median age was 60.1 years. Histological diagnoses included 25 (38.4%) with classic PTC and 30 (46.1%) aggressive variants of PTC, mostly tall cell variant (17 cases, 26.1%). Multifocality was seen in 33 cases (50.8%). All patients had nodal metastases. The most common site of extrathyroidal extension was the recurrent laryngeal nerve (69.2%). Staging revealed 21 cases were stage I, none were stage II, 33 were stage III, and 7 were stage IVa and 4 stage IVb. No differences were found between well and poorly/undifferentiated thyroid cancers. Conclusion: These data suggest that locally advanced thyroid cancers, including variants of PTC, exhibit a more aggressive biological course and should accordingly be more assertively managed.

[Efficacy and tolerance of salvage curative radiotherapy for patients with cervical relapse of differentiated thyroid carcinoma]

PURPOSE

Radiation therapy is often the last resource treatment for cervical relapse in iodine refractory differentiated thyroid cancer. We present locoregional control data in patients with cervical relapse treated with curative intent radiation therapy with or without concomitant carboplatin.

MATERIAL AND METHODS

This monocentric retrospective study gathered data on patients with differentiated thyroid carcinoma - vesicular or papillary - in relapse after thyroidectomy who received a curative intent cervical radiation therapy. Locoregional progression free survival (LRPFS), progression free survival (PFS), overall survival (OS) were gathered as well as acute and chronic adverse events assessed with the CTCAE v4.

RESULTS

Thirty-nine patients were consecutively included between 2005 and 2019. The median follow-up was 36.6months. Fifteen patients (38%) had a locoregional relapse, locoregional control at 2years was 66.7%. The median LRPFS was 48months [32.9-not reached] and the median overall survival 49months [38.8-not reached]. In multivariate analysis, initial incomplete resection was associated with poorer OS (HR: 24.39 [3.57-166.78], P=0.00113) and LRPFS (HR: 33.91 [4.46-257.61], P=0.00066), extra nodal spread was associated with poorer LRPFS (HR: 13.45 [1.81-99,76], P=0.011). ECOG performance status was associated with OS (HR: 5.11 [1.57-16.66], P=0.00688). Carboplatin association with radiation therapy was not associated with improved survivals (OS: P=0.34, LRPFS: P=0.84). The rate of acute grade 3 toxicities was 14%.

CONCLUSION

Salvage cervical radiation therapy was associated with a locoregional control of 66.7% at 2years with a reasonable toxicity rate. Carboplatin association with radiation therapy did not improve locoregional control nor overall survival in comparison with radiotherapy alone.

Outcomes of Tracheal Resections in Well-Differentiated Thyroid Cancer-A case series and meta-analysis

BACKGROUND

Tracheal invasion in thyroid cancer is a well-known form of advanced disease. There is an ongoing controversy over outcomes of tracheal shaving in this situation. The aim of this study was to compare the results of tracheal shaving to radical resections in patients with low-volume tracheal involvement.

METHODS

An institutional case series and a meta-analysis was conducted. All studies that included patients diagnosed with well-differentiated thyroid cancer (WDTC) and tracheal invasion were analyzed. Patients with low-volume tracheal invasion (according to the Shin classification) were extracted from the various studies and subsequently included in this study. The outcomes of tracheal shaving and radical resection were consolidated and compared. All recurrences and mortality over 10 years of follow-up were calculated using the Kaplan-Meier method.

RESULTS

Institutional case series included 22 patients diagnosed with WDTC and tracheal invasion that underwent resection. There was one case of recurrence (4.5%) during the follow-up period and no mortality. The meta-analysis yielded a total of 284 patients from six studies who met the inclusion criteria. The 10-year overall survival was 82.4% for the shave group and 80.8% for the resection group. The combined Kaplan-Meier curves revealed no statistically significant difference between the two techniques (hazard ratio [HR] = 0.86, P = .768). The combined 10-year local control rate of the shave group was 90.2%.

CONCLUSIONS

The outcomes of tracheal shaving in low-volume invasion are similar to more aggressive forms of tracheal resections. Shave resection is oncologically safe in carefully selected WDTC patients demonstrating minimal tracheal invasion.

Tracheal Resection in the Management of Thyroid Cancer: An Evidence-Based Approach

OBJECTIVE

Determine the effect of patient demographics and surgical approach on patient outcomes after tracheal resection in the management of thyroid cancer.

STUDY DESIGN

Systematic review and meta-analysis.

METHODS

Systematic review of literature was performed using PubMed, Embase, and Cochrane Library to identify patients with thyroid carcinoma who underwent tracheal resection. Pooled estimates for patient demographics, presenting findings, complications, and outcomes are determined using random-effects meta-analyses.

RESULTS

Ninety-six relevant studies encompassing 1,179 patients met inclusion criteria. Meta-analysis pooled rates of complications: 1.7% (confidence interval [CI] 0.8-2.5; P < .001; I² = 1.85%) airway complications, 2.8% (CI 1.6-3.9; P < .001; I² = 13.34%) bilateral recurrent laryngeal nerve paralysis, 2.2% (CI 1.2-3.1; P < .001; I² = 6.72%) anastomotic dehiscence. Circumferential resection pooled estimates major complications, locoregional recurrence, distal recurrence, overall survival: 14.1% (CI 8.3-19.9; P < .001; I² = 35.26%), 15% (CI 9.6-20.3; P < .001; I² = 38.2%), 19.7% (CI 13.7-25.8; P < .001; I² = 28.83%), 74.5% (CI 64.4-84.6; P < .001; I² = 85.07%). Window resection estimates: 19.8% (CI 6.9-32.8; P < .001; I² = 18.83%) major complications, 25.6% (CI 5.1-46.1; P < .014; I² = 84.68%) locoregional recurrence, 15.6% (CI 9.7-21.5; P < .001; I² = 0%) distal recurrence, 77.1% (CI 58-96.2; P < .001; I² = 78.77%) overall survival.

CONCLUSION

Management of invasive thyroid carcinoma may require tracheal resection to achieve locoregional control. Nevertheless, postoperative complications are not insignificant, and therefore this risk cannot be overlooked when counseling patients perioperatively. Laryngoscope, 131:932-946, 2021.

Immediate Ansa Cervicalis-to-Recurrent Laryngeal Nerve Anastomosis for the Management of Recurrent Laryngeal Nerve Infiltration by a Differentiated Thyroid Carcinoma

OBJECTIVES

The optimal surgical approach to treat recurrent laryngeal nerve (RLN) infiltration by differentiated thyroid cancer (DTC) remains a subject of debate. This study explored the feasibility and efficiency of immediate ansa cervicalis nerve (ACN)-to-RLN anastomosis for the management of RLN infiltration by DTC.

MATERIAL AND METHODS

Fifty-three patients who underwent immediate ACN-to-RLN anastomosis during DTC extirpation were enrolled in the present study. Thirty-seven cases presented with unilateral vocal cord paralysis before the operation (Group A), and another 16 patients presented with normal vocal cord mobility preoperatively (Group B). Multidimensional assessments, videostroboscopy, voice assessment, and laryngeal electromyography (LEMG) were performed preoperatively and postoperatively.

RESULTS

All videostroboscopy, voice assessment and LEMG parameters in Group A deteriorated 1 month after the operation and improved 1 year after the operation compared with preoperative data. In Group B, all parameters 1 year after the operation improved significantly compared with the corresponding parameters 1 month after the operation. LEMG in Group A and B provided substantial evidence for the maturation of neural regeneration from ACN and demonstrated that the laryngeal muscles were reinnervated successfully by this procedure.

CONCLUSIONS

If the RLN is infiltrated by DTC, immediate ACN-to-RLN anastomosis during complete excision of DTC could restore satisfactory phonatory function and does not compromise oncological radicality.

Head and Neck Cancer Detection in Digitized Whole-Slide Histology Using Convolutional Neural Networks

Primary management for head and neck cancers, including squamous cell carcinoma (SCC), involves surgical resection with negative cancer margins. Pathologists guide surgeons during these operations by detecting cancer in histology slides made from the excised tissue. In this study, 381 digitized, histological whole-slide images (WSI) from 156 patients with head and neck cancer were used to train, validate, and test an inception-v4 convolutional neural network. The proposed method is able to detect and localize primary head and neck SCC on WSI with an AUC of 0.916 for patients in the SCC testing group and 0.954 for patients in the thyroid carcinoma testing group. Moreover, the proposed method is able to diagnose WSI with cancer versus normal slides with an AUC of 0.944 and 0.995 for the SCC and thyroid carcinoma testing groups, respectively. For comparison, we tested the proposed, diagnostic method on an open-source dataset of WSI from sentinel lymph nodes with breast cancer metastases, CAMELYON 2016, to obtain patch-based cancer localization and slide-level cancer diagnoses. The experimental design yields a robust method with potential to help create a tool to increase efficiency and accuracy of pathologists detecting head and neck cancers in histological images.

Hyperspectral imaging for head and neck cancer detection: specular glare and variance of the tumor margin in surgical specimens

Head and neck squamous cell carcinoma (SCC) is primarily managed by surgical cancer resection. Recurrence rates after surgery can be as high as 55%, if residual cancer is present. Hyperspectral imaging (HSI) is evaluated for detection of SCC in ex-vivo surgical specimens. Several machine learning methods are investigated, including convolutional neural networks (CNNs) and a spectral-spatial classification framework based on support vector machines. Quantitative results demonstrate that additional data preprocessing and unsupervised segmentation can improve CNN results to achieve optimal performance. The methods are trained in two paradigms, with and without specular glare. Classifying regions that include specular glare degrade the overall results, but the combination of the CNN probability maps and unsupervised segmentation using a majority voting method produces an area under the curve value of 0.81 [0.80, 0.83]. As the wavelengths of light used in HSI can penetrate different depths into biological tissue, cancer margins may change with depth and create uncertainty in the ground truth. Through serial histological sectioning, the variance in the cancer margin with depth is investigated and paired with qualitative classification heat maps using the methods proposed for the testing group of SCC patients. The results determined that the validity of the top section alone as the ground truth may be limited to 1 to 2 mm. The study of specular glare and margin variation provided better understanding of the potential of HSI for the use in the operating room.

Microscopically positive surgical margins and local recurrence in thyroid cancer. A meta-analysis

BACKGROUND

Microscopically positive surgical margins are a prognostic factor of recurrence in advanced thyroid carcinoma. However, information on early and completely resected thyroid tumors is scarce. Some studies do not identify any association between positive margin and local recurrence. The objective of this study was to perform a meta-analysis to measure the association of microscopically positive surgical margins and local recurrence in patients who underwent total thyroidectomy.

METHODS

Clinical trials assessing the association between microscopically positive surgical margin and local recurrence in patients with early-stage, well-differentiated thyroid carcinoma who underwent total thyroidectomy were evaluated. The outcome measured was local recurrence in the thyroid bed. A systematic review and meta-analysis was done using a random-effects model.

RESULTS

Six studies with 7696 patients were identified. Methodological quality was good, and we did not identify statistical heterogeneity or publication bias. The risk difference for microscopically positive surgical margin and local recurrence was 0% (95% CI 0 to 1).

CONCLUSION

Meta-analysis did not find a statistically significant association between microscopically positive surgical margin and local recurrence in this population. A finding of microscopically positive surgical margin in the absence of other adverse factors is not an indication for adjuvant treatment.

Cancer Detection Using Hyperspectral Imaging and Evaluation of the Superficial Tumor Margin Variance with Depth

Head and neck squamous cell carcinoma (SCCa) is primarily managed by surgical resection. Recurrence rates after surgery can be as high as 55% if residual cancer is present. In this study, hyperspectral imaging (HSI) is evaluated for detection of SCCa in ex-vivo surgical specimens. Several methods are investigated, including convolutional neural networks (CNNs) and a spectral-spatial variant of support vector machines. Quantitative results demonstrate that additional processing and unsupervised filtering can improve CNN results to achieve optimal performance. Classifying regions that include specular glare, the average AUC is increased from 0.73 [0.71, 0.75 (95% confidence interval)] to 0.81 [0.80, 0.83] through an unsupervised filtering and majority voting method described. The wavelengths of light used in HSI can penetrate different depths into biological tissue, while the cancer margin may change with depth and create uncertainty in the ground-truth. Through serial histological sectioning, the variance in cancer-margin with depth is also investigated and paired with qualitative classification heat maps using the methods proposed for the testing group SCC patients.

Immediate Surgery Might Be a Better Option for Subcapsular Thyroid Microcarcinomas

For high-risk papillary thyroid microcarcinomas (PTMCs), immediate surgery is recommended. This study aimed to evaluate the location of PTMCs in the thyroid lobe and determine whether location is associated with an aggressive biology and the necessity of immediate surgery. This retrospective study included 288 patients who underwent initial surgery for PTMC. Clinical data were extracted. Subcapsular thyroid microcarcinomas (STMs) and nonsubcapsular thyroid microcarcinomas (NSTMs), distinguished by ultrasound, were compared in terms of tumour size, extrathyroidal extension, cervical lymph node metastasis, and multifocality. The preoperative ultrasound features predictive of recurrent laryngeal nerve (RLN) involvement were assessed. There were no statistical differences in tumour size (P = 0.985), multifocality (P = 0.866), lymph node metastases to the central compartment (P = 0.154), or lateral lymph node metastases (P = 0.929) between STM and NSTM groups. Macroscopic extrathyroidal extension was exclusively found in the STM group. For assessing RLN involvement, the sensitivity, specificity, and positive predictive value of the presence of an abnormal thyroid capsule margin between the STM and the presumed RLN course, assessed on preoperative ultrasonography images, were 100%, 43.3%, and 43.3%, respectively. Immediate surgery appears to be a better option than conservative treatment for these high-risk STM patients.

Current controversies and future directions in the diagnosis and management of differentiated thyroid cancers

Despite the development of novel diagnostic, surgical, and chemotherapeutic approaches to differentiated thyroid cancers (DTCs), the diagnosis and management of these tumors remains controversial. The most recent American Thyroid Association (ATA) guidelines, released in 2015, reflect a recent shift towards less aggressive management for patients with DTCs. However, many clinicians have expressed concern that more conservative management will put patients at risk for disease recurrence and metastasis. In particular, the management of indeterminate nodules on fine needle aspiration (with special attention to genetic and epigenetic markers of malignancy), the extent of surgery for known differentiated cancers, the role of adjuvant radioactive iodine (RAI) therapy, and novel targeted treatments with tyrosine kinase inhibitors (TKIs) represent current areas of uncertainty and opportunities for future research. In this review, we examine the current state of the art in these areas, and address some of the questions that remain.

Secondary tracheal tumors: a systematic review

BACKGROUND

Secondary tracheal tumors arise from mural invasion by primary tumors in adjacent organs, metastatic lymph nodes or blood-born metastasis from distant sites. This systematic review aims to assess the presentation, management options, and clinical outcomes of these uncommon non-tracheal malignancies.

METHODS

Electronic searches of the MEDLINE database were performed to identify case series and individual case reports of tracheal invasion by primary non-tracheal tumors or metastatic disease. All English-language studies with available abstracts or articles containing primary data were included.

RESULTS

From 1978 to 2017, a total of 160 case reports or case series identified 2,242 patients with invasion of the trachea by tumors of adjacent organs (n=1,853) or by metastatic lymph nodes or hematogenous spread (n=389). Common primary sites of origin were thyroid, esophagus, and lung, and the most common presentation was metachronous (range of interval: 0 to 564 months) with dyspnea, neck mass, voice change and/or hemoptysis. A majority of patients in case reports (77.9%) and case series (66.0%) underwent resection and the most common reported operation was segmental tracheal resection. Fewer patients underwent bronchoscopic intervention (21.7%) and radiation was used in 32.2% of patients. Complications after bronchoscopic treatment included bleeding, granulation tissue, and retained secretions, while anastomotic leak, unplanned tracheostomy, and new recurrent laryngeal nerve paralysis were observed after surgical resection. The rate of 30-day mortality was low (0.01-1.80%). Median survival was higher in patients with thyroid malignancy and in patients who underwent surgical management. Follow-up time ranged from 0.03 to 183 months.

CONCLUSIONS

Patients with tracheal invasion by metastatic or primary non-tracheal malignancies should be assessed for symptoms, tumor grade, tumor recurrence and concurrent metastases to decide on optimal surgical, bronchoscopic or noninterventional therapy. Clinical experience suggests that palliative endoscopic intervention for tracheal obstruction by metastasis-bearing lymph nodes is underreported.

Tumor Margin Classification of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks

One of the largest factors affecting disease recurrence after surgical cancer resection is negative surgical margins. Hyperspectral imaging (HSI) is an optical imaging technique with potential to serve as a computer aided diagnostic tool for identifying cancer in gross ex-vivo specimens. We developed a tissue classifier using three distinct convolutional neural network (CNN) architectures on HSI data to investigate the ability to classify the cancer margins from ex-vivo human surgical specimens, collected from 20 patients undergoing surgical cancer resection as a preliminary validation group. A new approach for generating the HSI ground truth using a registered histological cancer margin is applied in order to create a validation dataset. The CNN-based method classifies the tumor-normal margin of squamous cell carcinoma (SCCa) versus normal oral tissue with an area under the curve (AUC) of 0.86 for inter-patient validation, performing with 81% accuracy, 84% sensitivity, and 77% specificity. Thyroid carcinoma cancer-normal margins are classified with an AUC of 0.94 for inter-patient validation, performing with 90% accuracy, 91% sensitivity, and 88% specificity. Our preliminary results on a limited patient dataset demonstrate the predictive ability of HSI-based cancer margin detection, which warrants further investigation with more patient data and additional processing techniques to optimize the proposed deep learning method.

Optical Biopsy of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks

Successful outcomes of surgical cancer resection necessitate negative, cancer-free surgical margins. Currently, tissue samples are sent to pathology for diagnostic confirmation. Hyperspectral imaging (HSI) is an emerging, non-contact optical imaging technique. A reliable optical method could serve to diagnose and biopsy specimens in real-time. Using convolutional neural networks (CNNs) as a tissue classifier, we developed a method to use HSI to perform an optical biopsy of ex-vivo surgical specimens, collected from 21 patients undergoing surgical cancer resection. Training and testing on samples from different patients, the CNN can distinguish squamous cell carcinoma (SCCa) from normal aerodigestive tract tissues with an area under the curve (AUC) of 0.82, 81% accuracy, 81% sensitivity, and 80% specificity. Additionally, normal oral tissues can be sub-classified into epithelium, muscle, and glandular mucosa using a decision tree method, with an average AUC of 0.94, 90% accuracy, 93% sensitivity, and 89% specificity. After separately training on thyroid tissue, the CNN differentiates between thyroid carcinoma and normal thyroid with an AUC of 0.95, 92% accuracy, 92% sensitivity, and 92% specificity. Moreover, the CNN can discriminate medullary thyroid carcinoma from benign multi-nodular goiter (MNG) with an AUC of 0.93, 87% accuracy, 88% sensitivity, and 85% specificity. Classical-type papillary thyroid carcinoma is differentiated from benign MNG with an AUC of 0.91, 86% accuracy, 86% sensitivity, and 86% specificity. Our preliminary results demonstrate that an HSI-based optical biopsy method using CNNs can provide multi-category diagnostic information for normal head-and-neck tissue, SCCa, and thyroid carcinomas. More patient data are needed in order to fully investigate the proposed technique to establish reliability and generalizability of the work.