Donald Gregory Farwell

Background: Metastatic lymph node (MLN) detection remains a major clinical challenge in head and neck cancer, as nodal involvement is strongly associated with poor prognosis and directly affects treatment planning. Previous approaches typically rely on cropped lymph node (LN) regions or tumor contours for MLN identification, requiring substantial expert annotation during preprocessing and relying solely on imaging information. As a result, small or low-contrast metastatic nodes may be missed, while benign lymph nodes may be incorrectly identified as metastatic due to overlapping imaging characteristics. To address these limitations, we propose a multimodal learning framework that integrates anatomical and metabolic features from head and neck PET/CT images with biochemical features derived from FLIm for patient-level MLN prediction, without requiring manual lymph node cropping or tumor contouring during inference. Methods: To enable robust imaging representation learning, a region-aware PET/CT network based on a merging-diverging architecture was first pretrained on the HECKTOR 2022 dataset and then fine-tuned on the institutional cohort. In parallel, FLIm point-wise measurements with clinical variables were encoded using a multilayer perceptron (MLP) and aggregated into subject-level representations. To effectively combine these modalities, two multimodal fusion strategies were evaluated at the decoder stage, including cube-based fusion and squeeze-and-excitation (SE)-based fusion. The proposed strategies were evaluated on a cohort of 53 patients. Results: Compared with the single-modality baselines, both multimodal fusion strategies achieved better patient-level MLN prediction. The PET/CT-only segmentation-driven model and FLIm-only model reached balanced accuracies of 0.815 and 0.665, with AUCs of 0.828 and 0.614, respectively. Cube-based fusion improved balanced accuracy and AUC to 0.827 and 0.850, respectively, while channel-wise SE-based fusion achieved the best overall performance, with a balanced accuracy of 0.839 and an AUC of 0.872. Conclusions: These results suggest that multimodal integration may improve patient-level MLN prediction compared with single-modality approaches. Given the limited sample size, these findings should be interpreted as hypothesis-generating and require validation in larger, independent patient cohorts.

Objectives: Early detection and accurate diagnosis of lymph node metastasis (LNM) in head and neck cancer (HNC) are crucial for enhancing patient prognosis and survival rates. Current imaging methods have limitations, necessitating new evaluation of new diagnostic techniques. This study investigates the potential of combining pre-operative CT and intra-operative fluorescence lifetime imaging (FLIm) to enhance LNM prediction in HNC using primary tumor signatures. Methods: CT and FLIm data were collected from 46 HNC patients. A total of 42 FLIm features and 924 CT radiomic features were extracted from the primary tumor site and fused. A support vector machine (SVM) model with a radial basis function kernel was trained to predict LNM. Hyperparameter tuning was conducted using 10-fold nested cross-validation. Prediction performance was evaluated using balanced accuracy (bACC) and the area under the ROC curve (AUC). Results: The model, leveraging combined CT and FLIm features, demonstrated improved testing accuracy (bACC: 0.71, AUC: 0.79) over the CT-only (bACC: 0.58, AUC: 0.67) and FLIm-only (bACC: 0.61, AUC: 0.72) models. Feature selection identified that a subset of 10 FLIm and 10 CT features provided optimal predictive capability. Feature contribution analysis identified high-pass and low-pass wavelet-filtered CT images as well as Laguerre coefficients from FLIm as key predictors. Conclusions: Combining CT and FLIm of the primary tumor improves the prediction of HNC LNM compared to either modality alone. Significance: This study underscores the potential of combining pre-operative radiomics with intra-operative FLIm for more accurate LNM prediction in HNC, offering promise to enhance patient outcomes.

Background: This study evaluated whether fluorescence lifetime imaging (FLIm), coupled with standard diagnostic workups, could enhance primary lesion detection in patients with p16+ head and neck squamous cell carcinoma of the unknown primary (HNSCCUP).Methods: FLIm was integrated into transoral robotic surgery to acquire optical data on six HNSCCUP patients' oropharyngeal tissues. An additional 55‐patient FLIm dataset, comprising conventional primary tumors, trained a machine learning classifier; the output predicted the presence and location of HNSCCUP for the six patients. Validation was performed using histopathology.Results: Among the six HNSCCUP patients, p16+ occult primary was surgically identified in three patients, whereas three patients ultimately had no identifiable primary site in the oropharynx. FLIm correctly detected HNSCCUP in all three patients (ROC‐AUC: 0.90 ± 0.06), and correctly predicted benign oropharyngeal tissue for the remaining three patients. The mean sensitivity was 95% ± 3.5%, and specificity 89% ± 12.7%.Conclusions: FLIm may be a useful diagnostic adjunct for detecting HNSCCUP.

Background: Novel, non-invasive diagnostic biomarkers that facilitate early intervention in head and neck cancer are urgently needed. Polyamine metabolites have been observed to be elevated in numerous cancer types and correlated with poor prognosis. The aim of this study was to assess the concentration of polyamines in the saliva and urine from head and neck cancer (HNC) patients, compared to healthy controls. Methods: Targeted metabolomic analysis was performed on saliva and urine from 39 HNC patient samples and compared to 89 healthy controls using a quantitative, targeted liquid chromatography mass spectrometry approach. Results: The metabolites N¹-acetylspermine (ASP), N⁸-acetylspermidine (ASD) and N¹,N¹²-diacetylspermine (DAS) were detected at significantly different concentrations in the urine of HNC patients as compared to healthy controls. Only ASP was detected at elevated levels in HNC saliva as compared to healthy controls. Conclusion: These data suggest that assessment of polyamine-based metabolite biomarkers within the saliva and urine warrants further investigation as a potential diagnostic in HNC patients.

Objectives/Hypothesis To evaluate the safety and potential efficacy of autologous muscle‐derived cells (AMDCs) for the treatment of swallowing impairment following treatment for oropharynx cancer. Study Design Prospective, phase I, open label, clinical trial. Methods Oropharynx cancer survivors disease free ≥2 years post chemoradiation were recruited. All patients had swallowing impairment but were not feeding tube dependent (Functional Oral Intake Scale [FOIS] ≥ 5). Muscle tissue (50–250 mg) was harvested from the vastus lateralis and 150 × 10⁶ AMDCs were prepared (Cook MyoSite Inc., Pittsburgh, PA). The cells were injected into four sites throughout the intrinsic tongue musculature. Participants were followed for 24 months. The primary outcome measure was safety. Secondary endpoints included objective measures on swallowing fluoroscopy, oral and pharyngeal pressure, and changes in patient‐reported outcomes. Results Ten individuals were enrolled. 100% (10/10) were male. The mean age of the cohort was 65 (±8.87) years. No serious adverse event occurred. Mean tongue pressure increased significantly from 26.3 (±11.1) to 31.8 (±9.5) kPa (P = .017). The mean penetration‐aspiration scale did not significantly change from 5.6 (±2.1) to 6.8 (±1.8), and the mean FOIS did not significantly change from 5.4 (±0.5) to 4.6 (±0.7). The incidence of pneumonia was 30% (3/10) and only 10% (1/10) experienced deterioration in swallowing function throughout 2 years of follow‐up. The mean eating assessment tool (EAT‐10) did not significantly change from 24.1 (±5.57) to 21.3 (±6.3) (P = .12). Conclusion Results of this phase I clinical trial demonstrate that injection of 150 × 10⁶ AMDCs into the tongue is safe and may improve tongue strength, which is durable at 2 years. A blinded placebo‐controlled trial is warranted. Level of Evidence Level 3 Laryngoscope, 2021

Syphilis may present with a myriad of oral manifestations in the primary, secondary, and tertiary stages, and may be confused with malignancy. Despite a rise in the incidence of syphilis, tertiary syphilis is exceedingly rare. Tertiary syphilis gummas usually affect the hard palate, while tongue involvement is very rare. A 55-year-old male with extensive smoking and alcohol use was referred for malignancy evaluation with an ulcerative mass creating a tongue cleft, and a positron emission tomography scan suggestive for malignancy. Biopsy results demonstrated no carcinoma but histology demonstrated granulomatous inflammation. Further laboratory results demonstrated elevated rapid plasma reagin titers with Treponema pallidum immunoglobulin G antibodies present. The patient was diagnosed with tertiary syphilis, received appropriate antibiotic therapy, and had healing of the tongue with a persistent cleft. Syphilis may mimic many disease processes. As such, it is important to include this disease in the differential of an unusual tongue lesion. An oral lesion may be the first sign of infection.