UNASSIGNED: Magnetic resonance imaging (MRI) is a routinely used imaging modality for pre-treatment radiologic evaluation of tongue carcinoma, providing accurate information regarding the extent of the disease.
UNASSIGNED: To investigate the role of MRI-derived depth of invasion and tumor thickness evaluation in squamous cell carcinoma of the tongue, and to assess if any correlation exists between depth of invasion, tumor thickness, nodal metastasis, muscles, and space involved.
UNASSIGNED: Thirty-three patients with oral squamous cell carcinoma of the tongue who had undergone pre-treatment MRI and excisional biopsy were included. The tumor thickness (TT) and depth of invasion (DOI) were evaluated on MRI and histopathologic images.
UNASSIGNED: The relation between different methodologies for assessing showed a very high correlation for the tumor tissue thickness (r = 0.99, p < 0.05) and depth of invasion (r = 0.82, p < 0.05). The tumor thickness and the depth of invasion increased with the loss of differentiation in the carcinoma histopathologically. As the depth of invasion increases, the extent of the spread of the carcinoma to tongue musculature, lingual septum, and spaces also increases.
UNASSIGNED: The present study has depicted a high correlation between the tumor thickness and the depth of invasion between MRI and histopathological findings and is the first of its kind to correlate DOI to the invasiveness of the disease.

OBJECTIVE: This study evaluates the efficacy of two advanced Large Language Models (LLMs), OpenAI\'s ChatGPT 4 and Google\'s Gemini Advanced, in providing treatment recommendations for head and neck oncology cases. The aim is to assess their utility in supporting multidisciplinary oncological evaluations and decision-making processes.
METHODS: This comparative analysis examined the responses of ChatGPT 4 and Gemini Advanced to five hypothetical cases of head and neck cancer, each representing a different anatomical subsite. The responses were evaluated against the latest National Comprehensive Cancer Network (NCCN) guidelines by two blinded panels using the total disagreement score (TDS) and the artificial intelligence performance instrument (AIPI). Statistical assessments were performed using the Wilcoxon signed-rank test and the Friedman test.
RESULTS: Both LLMs produced relevant treatment recommendations with ChatGPT 4 generally outperforming Gemini Advanced regarding adherence to guidelines and comprehensive treatment planning. ChatGPT 4 showed higher AIPI scores (median 3 [2-4]) compared to Gemini Advanced (median 2 [2-3]), indicating better overall performance. Notably, inconsistencies were observed in the management of induction chemotherapy and surgical decisions, such as neck dissection.
CONCLUSIONS: While both LLMs demonstrated the potential to aid in the multidisciplinary management of head and neck oncology, discrepancies in certain critical areas highlight the need for further refinement. The study supports the growing role of AI in enhancing clinical decision-making but also emphasizes the necessity for continuous updates and validation against current clinical standards to integrate AI into healthcare practices fully.

Three-dimensional (3D) ultrasound can assess the margins of resected tongue carcinoma during surgery. Manual segmentation (MS) is time-consuming, labour-intensive, and subject to operator variability. This study aims to investigate use of a 3D deep learning model for fast intraoperative segmentation of tongue carcinoma in 3D ultrasound volumes. Additionally, it investigates the clinical effect of automatic segmentation. A 3D No New U-Net (nnUNet) was trained on 113 manually annotated ultrasound volumes of resected tongue carcinoma. The model was implemented on a mobile workstation and clinically validated on 16 prospectively included tongue carcinoma patients. Different prediction settings were investigated. Automatic segmentations with multiple islands were adjusted by selecting the best-representing island. The final margin status (FMS) based on automatic, semi-automatic, and manual segmentation was computed and compared with the histopathological margin. The standard 3D nnUNet resulted in the best-performing automatic segmentation with a mean (SD) Dice volumetric score of 0.65 (0.30), Dice surface score of 0.73 (0.26), average surface distance of 0.44 (0.61) mm, Hausdorff distance of 6.65 (8.84) mm, and prediction time of 8 seconds. FMS based on automatic segmentation had a low correlation with histopathology (r = 0.12, p = 0.67); MS resulted in a moderate but insignificant correlation with histopathology (r = 0.4, p = 0.12, n = 16). Implementing the 3D nnUNet yielded fast, automatic segmentation of tongue carcinoma in 3D ultrasound volumes. Correlation between FMS and histopathology obtained from these segmentations was lower than the moderate correlation between MS and histopathology.

Cancer of the tongue is an uncommon cancer site, with only 31,378 cases in the SEER 1975-2017 database, fewer than 1% of all reported cancers. This article updates trends in incidence, prevalence, short and long-term survival and mortality of tongue carcinoma.

To compare postoperative complications, functional rehabilitation, surgical outcomes of the radial artery forearm free flap (RAFFF) and split thickness skin graft (STSG) reconstruction of postsurgical defect in T2 lesions of cancer oral cavity. Observational Prospective comparative study. Academic tertiary referral centre. In our study of forty four patients, after tumour resection, half underwent reconstruction using RAFFF (Group I) and another half by STSG (Group II). All of the patients were followed postoperatively to determine and compare their functional outcomes related to donor site and recipient site complications, speech, deglutition and mouth opening. The speech intelligibility and deglutition were each assessed using Articulation Handicap Index and Vedio-fluoroscopy using the Functional oral intake scale. Operative time for STSG reconstruction was shorter at 2.2 ± 0.97 SD hours compared to 5.9 ± 1.24 SD hours for RAFFF reconstruction. Hospital stay was 8.3 ± 1.19 SD days for STSG patients and 12.6 ± 1.7 SD days for RAFFF patients. The functional outcomes of speech quality and swallowing were near comparable in both groups but the donor site complications were significant in the RAFFF group. Operative time, hospital stay and donor site complications are both significantly reduced with the STSG as opposed to RAFF. Functional and oncologic results of both methods are near comparable. To conclude, STSG can be used for reconstruction of the post-surgical defects in T2 lesions of the tongue.

The aim of this study was to investigate the correlation between pre-treatment inflammatory biomarkers and the post-operative depth of invasion (DOI) and worst pattern of invasion (WPOI) in early-stage oral tongue squamous cell carcinoma (OTSCC) by means of positive sentinel lymph node biopsy (SLNB). A retrospective analysis of patients affected by cN0 T1-T2 OTSCC who had undergone an SLNB at the National Cancer Institute of Naples was performed. The patients were studied using an evaluation of the pre-treatment neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammatory index (SII), and a histopathological analysis of the DOI and WPOI. The statistical analysis showed that among the prognostic biomarkers, the NLR was a significant predictor of high WPOI values (p = 0.002). The cut-off NLR value was 2.52 with a probability of developing a positive sentinel lymph node biopsy (SLNB) of 30.3%. In contrast, the DOI value was 5.20 with a probability of developing a positive SLNB of 31.82%. Regarding the WPOI, increasing the WPOI class increased the likelihood of a positive SLNB occurrence, and a positive significant correlation was found between the WPOI and SLNB (Csp = 0.342; p < 0.001). Pre-treatment NLR, together with post-surgical DOI and WPOI, can be a reliable predictor of occult neck metastasis in patients affected by early-stage OTSCC with a clinically negative neck. Further prospective studies with a larger series will be needed to confirm the results obtained and to better define the NLR, WPOI and DOI cut-off values in order for elective neck dissection to be recommended in relation to a clinically negative neck.

Magnetic resonance imaging (MRI) is an integral part of the evaluation of local and regional disease in tongue squamous cell carcinoma prior to surgery. The aim of this study was to evaluate the accuracy of MRI in assessing tumour dimensions, as well as the impact of the time-lag from diagnostic biopsy on the accuracy of MRI. The medical records of 64 patients with tongue carcinoma were reviewed retrospectively. Tumour maximum diameter and tumour depth of invasion were compared between pathology and MRI (T1- and T2-weighted). MRI-derived maximum tumour diameter and depth of invasion correlated strongly with histopathology: T1-weighted (r = 0.700 and r = 0.813, respectively) and T2-weighted (r = 0.734 and r = 0.834, respectively). A significant correlation was found between measurements on T1 and T2 MRI for both parameters (P = 0.955 and P = 0.984, respectively). The accuracy rate of MRI for T-staging of early tumours was low: 10% for T1 tumours; 39.3% for T2 tumours. A time-lag of less than 2 weeks between the diagnostic biopsy and MRI adversely affected the correlation of tumour dimensions. MRI is a reliable tool for evaluating tongue carcinoma; however, it overestimates early tumours. A 2-week delay after diagnostic biopsy is desired before completing an MRI. Alternatively, if logistics allow, a pre-biopsy MRI is preferred, especially for T1-T2 tumours.

UNASSIGNED: To analyze the results of patients treated with perioperative interstitial brachytherapy (ISBT) in tongue carcinoma (TC).
UNASSIGNED: From April 2009 to May 2015, 43 squamous cell carcinoma consecutive patients diagnosed with TC were treated with limited partial glossectomy and perioperative ISBT, using high-dose-rate (HDR). Twenty- seven patients were treated by brachytherapy (BT), and sixteen received BT as a complement to subsequent external beam radiotherapy (EBRT) after results of lymph node dissection. Median age was 66 years. Distribution by stage, included 10 patients stage I, 14 stage II, 10 stage III, and 9 stage IV. Eighteen patients had negative margins, nineteen margin involvement, and in six cases, the margin was < 5 mm.
UNASSIGNED: With a median follow-up of 54 months, LC at 3 and 5 years was 87% and 84%, respectively. LC was 95% at five years in patients with clear margins, and 75% with involved margins. LC in N0 patients treated with BT was 83% at 5 years, and in patients N+ with posterior EBRT treatment, LC was 86%. By tumor size, we found one local relapse in 13 cases T1, in 5 of 27 patients T2 was found, and no local relapse T3 with LC of 87%, 70%, and 100% respectively at five years. Regional control (RC) was 81% at 3 and 5 years. We found a metastasis-free survival of 91% at 3- and 5-year. Twenty-three patients have died, 11 of them due to other causes, with overall survival of 56% at three years and 53% at five years.
UNASSIGNED: Combined treatment with conservative surgery and ISBT shows similar results to radical surgery or RT alone, allowing a more patient-tailored approach, with good organ function preservation and cosmetic outcomes.

BACKGROUND: To evaluate the diagnostic performance of [¹⁸F]fluorodeoxyglucose positron emission tomography/computed tomography ([¹⁸F]FDG-PET/CT) scan in detecting local recurrences in patients with surgically treated oral tongue squamous cell cancer (OTSCC).
METHODS: Eighty-seven patients who had undergone surgery for OTSCC were monitored clinically and [¹⁸F]FDGPET/CT and magnetic resonance (MR). PET uptakes were classified as functional (Type A), suspicious (Type B), or highly suggestive of local recurrence (Type C). A multidisciplinary team (MDT) evaluated case-by-case the surveillance strategy based on PET uptake.
RESULTS: Fifty-nine patients presented FDG-PET uptake during follow-up: this report was significantly more frequent in patients who received flap reconstruction than in those without (73% vs 50%; p = 0.05). In 13 patients with Type A (n = 1), Type B (n = 9), and Type C (n = 3) uptakes an additional MR was considered preferable and discovered recurrence in 12.PET-CT had 9 true positives, 17 false positives, 71 true negatives, and no false-negative, resulting in sensitivity, specificity, positive (PPV) and negative predictive values (NPV) of 100%, 80.7%, 34.6%, and 100%.
CONCLUSIONS: The present results demonstrated a change in diagnostic strategy, as decided by the MDT, in about one-fifth of patients. The results should prompt in designing a rational surveillance schedule in surgically treated OTSCC.

OBJECTIVE: This study aimed to clarify the accuracy of intraoral ultrasonography (US), computed tomography (CT), and magnetic resonance imaging (MRI) in preoperative image depth of invasion (DOI) measurement of T1/T2 tongue cancer through comparison with histopathological measurements.
METHODS: Imaging of the primary lesions was performed at our hospital; the lesions were classified into T1 and T2 based on the 8th edition of the AJCC/UICC, and surgery performed. There was histopathological confirmation of lesions as squamous cell carcinoma in 48 patients with tongue cancer. T3 and T4 cases, cases in which preoperative chemotherapy and radiation therapy were performed, and cases where biopsy was performed before imaging were excluded. The radiological DOI in US, CT, and MRI and the histopathological DOI as base were comparatively investigated and statistical analyses were performed by Bland-Altman analysis and Spearman\'s rank correlation coefficient.
RESULTS: Bland-Altman analysis showed that the US radiological DOI was overestimated by an average of 0.2 mm compared to the histopathological DOI, while CT and MRI radiological DOI were overestimated by an average of 2-3 mm. The comparison of CT and MRI revealed that the difference between the MRI and histopathological DOI, as well as the 95% limit of agreement, were smaller than those of the CT radiological DOI.
CONCLUSIONS: US is the most accurate preoperative diagnostic tool for T1 and T2 squamous cell carcinoma; CT and MRI tend to have an overestimation of about 2-3 mm and so caution is required.