Visibility of esophageal squamous cell carcinoma under iodine staining on texture and color enhancement imaging.

Objective: Iodine staining on white light imaging (WLI) is the gold standard for detecting and demarcating esophageal squamous cell carcinoma (ESCC). We examined the effects of texture and color enhancement imaging (TXI) on improving the endoscopic visibility of ESCC under iodine staining. Methods: Twenty ESCC lesions that underwent endoscopic submucosal dissection were retrospectively included. The color difference between ESCC and the surrounding mucosa (ΔEe) on WLI, TXI, and narrow-band imaging was assessed, and ΔEe under 1% iodine staining on WLI and TXI. Furthermore, the visibility grade determined by endoscopists was evaluated on each imaging. Result: The median ΔEe was greater on TXI than on WLI (14.53 vs. 10.71, respectively; p < 0.005). Moreover, the median ΔEe on TXI under iodine staining was greater than the median ΔEe on TXI and narrow-band imaging (39.20 vs. 14.53 vs. 16.42, respectively; p < 0.005 for both). A positive correlation in ΔEe under iodine staining was found between TXI and WLI (correlation coefficient = 0.61, p < 0.01). Moreover, ΔEe under iodine staining on TXI in each lesion was greater than the corresponding ΔEe on WLI. The visibility grade assessed by endoscopists on TXI was also significantly greater than that on WLI under iodine staining (p < 0.01). Conclusions: The visibility of ESCC after iodine staining was greater on TXI than on WLI.

Metabolism score and machine learning models for the prediction of esophageal squamous cell carcinoma progression.

The incomplete prediction of prognosis in esophageal squamous cell carcinoma (ESCC) patients is attributed to various therapeutic interventions and complex prognostic factors. Consequently, there is a pressing demand for enhanced predictive biomarkers that can facilitate clinical management and treatment decisions. This study recruited 491 ESCC patients who underwent surgical treatment at Huashan Hospital, Fudan University. We incorporated 14 blood metabolic indicators and identified independent prognostic indicators for overall survival through univariate and multivariate analyses. Subsequently, a metabolism score formula was established based on the biochemical markers. We constructed a nomogram and machine learning models utilizing the metabolism score and clinically significant prognostic features, followed by an evaluation of their predictive accuracy and performance. We identified alkaline phosphatase, free fatty acids, homocysteine, lactate dehydrogenase, and triglycerides as independent prognostic indicators for ESCC. Subsequently, based on these five indicators, we established a metabolism score that serves as an independent prognostic factor in ESCC patients. By utilizing this metabolism score in conjunction with clinical features, a nomogram can precisely predict the prognosis of ESCC patients, achieving an area under the curve (AUC) of 0.89. The random forest (RF) model showed superior predictive ability (AUC = 0.90, accuracy = 86%, Matthews correlation coefficient = 0.55). Finally, we used an RF model with optimal performance to establish an online predictive tool. The metabolism score developed in this study serves as an independent prognostic indicator for ESCC patients.

Correlation of PD-L1 expression with CD8+ T cells and oxidative stress-related molecules NRF2 and NQO1 in esophageal squamous cell carcinoma.

Oxidative stress and the immune microenvironment both contribute to the pathogenesis of esophageal squamous cell carcinoma (ESCC). However, their interrelationships remain poorly understood. We aimed to examine the status of key molecules involved in oxidative stress and the immune microenvironment, as well as their relationships with each other and with clinicopathological features and prognosis in ESCC. The expression of programmed death-ligand 1 (PD-L1), CD8, nuclear factor erythroid-2 related factor-2 (NRF2), and NAD(P)H quinone oxidoreductase 1 (NQO1) was detected using immunohistochemistry in tissue samples from 176 patients with ESCC. We employed both combined positive score (CPS) and tumor proportion score (TPS) to evaluate PD-L1 expression and found a positive correlation between CPS and TPS. Notably, PD-L1 expression, as assessed by either CPS or TPS, was positively correlated with both NRF2 nuclear score and NQO1 score in stage II-IV ESCC. We also observed a positive correlation between the density of CD8+ T cells and PD-L1 expression. Furthermore, high levels of PD-L1 CPS, but not TPS, were associated with advanced TNM stage and lymph node metastases. Moreover, both PD-L1 CPS and the nuclear expression of NRF2 were found to be predictive of shorter overall survival in stage II-IV ESCC. By using the Mandard-tumor regression grading (TRG) system to evaluate the pathological response of tumors to neoadjuvant chemotherapy (NACT), we found that the TRG-5 group had higher NRF2 nuclear score, PD-L1 CPS, and TPS in pre-NACT biopsy samples compared with the TRG-3 + 4 group. The NQO1 scores of post-NACT surgical specimens were significantly higher in the TRG-5 group than in the TRG 3 + 4 group. In conclusion, the expression of PD-L1 is associated with aberrant NRF2 signaling pathway, advanced TNM stage, lymph node metastases, and unfavorable prognosis. The dysregulation of PD-L1 and aberrant activation of the NRF2 signaling pathway are implicated in resistance to NACT. Our findings shed light on the complex interrelationships between oxidative stress and the immune microenvironment in ESCC, which may have implications for personalized therapies and improved patient outcomes.

Role of elective neck dissection in cT2N0 maxillary sinus squamous cell carcinoma.

Our objective was to examine the impact of elective neck dissection (END) on the prognosis of patients with cT2N0 maxillary sinus squamous cell carcinoma (MS-SCC) and to determine factors that predict the occurrence of occult metastasis in this patient population. A retrospective analysis was conducted using data from the SEER database. Patients with cT2N0 MS-SCC were included in the study and divided into two groups: those who received END and those who did not. The impact of END on disease-specific survival (DSS) and overall survival (OS) was assessed using propensity score matching. Multivariate logistic regression analysis was performed to determine predictors for occult metastasis. A total of 180 patients were included in the study, with 40 cases receiving END. Following propensity score matching, patients treated with END and those without showed similar DSS and OS rates. Occult metastasis was observed in 9 patients, corresponding to a rate of 22.5%. High-grade tumors were independently associated with a higher risk of occult metastasis compared to low-grade tumors (hazard ratio 1.52, 95% confidence interval 1.17-2.00). cT2 MS-SCC carries an occult metastasis rate of 22.5%, with histologic grade being the primary determinant of occult metastasis. END does not confer a significant survival benefit in this patient population.

A novel bispecific peptide targeting PD-1 and PD-L1 with combined antitumor activity of T-cells derived from the patients with TSCC.

Programmed death-1 (PD-1) and programmed death ligand-1 (PD-L1) are key immune checkpoints (ICs) that critically influence immunotherapy. Tumor resistance to single IC-targeting drugs has increased interest in dual-target drugs, which have shown feasibility for cancer treatment. In this study, we aimed to develop dual-target peptide drugs targeting the PD-1/PD-L1 pathway and to evaluate their efficacy compared to functional antibodies in enhancing the cytotoxicity of human T cells against tongue squamous carcinoma cell lines. Through sequence analysis and peptide truncation, we modified a pre-existing peptide named nABPD-1 targeting PD-1. Subsequently, we obtained two novel peptides named nABPD-2 and nABPD-3, with nABPD-2 showing an enhanced affinity for human PD-1 protein compared to nABPD-1. Importantly, nABPD-2 exhibited dual-targeting capability, possessing a high affinity for both PD-L1 and PD-1. Furthermore, nABPD-2 effectively promoted the cytotoxicity of human T cells against tongue squamous carcinoma cell lines, surpassing the efficacy of anti-PD-1 or anti-PD-L1 functional antibodies alone. Considering that nABPD-2 has lower production costs and dose requirements, it can potentially be used in therapeutic applications.

[Retracted] Galectin­3 blockade suppresses the growth of cetuximab­resistant human oral squamous cell carcinoma.

Following the publication of this paper, it was drawn to the Editor's attention by a concerned reader that the colony formation assay data shown in Fig. 4C on p. 6 were strikingly similar to data appearing in different form in other articles written by different authors at different research institutes, which had already been published. Owing to the fact that the contentious data in the above article had already been published prior to its submission to Molecular Medicine Reports, the Editor has decided that this paper should be retracted from the Journal. After having been in contact with the authors, they accepted the decision to retract the paper. The Editor apologizes to the readership for any inconvenience caused. [Molecular Medicine Reports 24: 685, 2021; DOI: 10.3892/mmr.2021.12325].

The Effects of ML385 on Head and Neck Squamous Cell Carcinoma: Implications for NRF2 Inhibition as a Therapeutic Strategy.

Head and neck squamous cell carcinoma (HNSCC) affects squamous cells in the head and neck region and is currently ranked as the sixth most common cancer worldwide. NF-E2-related factor 2 (NRF2) plays a crucial role in cellular protection and defence mechanisms and NRF2 over-expression has been linked to various cancers; however, its role in the response of HNSCC cells remains elusive. We investigated the effects of ML385, a selective NRF2 inhibitor, on HNSCC to understand the underlying molecular mechanisms, and to assess the potential of ML385 as a therapeutic agent. We treated HNSCC cell lines with ML385 and observed a significant reduction in the expression of NRF2 and its downstream target, heme oxygenase-1 (HO-1), using Western blotting. We evaluated its effects on various cellular processes, including cell proliferation, cloning, migration, and wound healing, in HNSCC cell lines. ML385 treatment substantially reduced NRF2 expression, promoting a decrease in the investigated cellular activities. Additionally, we examined changes in the expression of cell-cycle-related proteins and found that ML385 induced cell cycle arrest at the G1/S phase in HNSCC cell lines. Our findings suggest that ML385 can regulate cell cycle progression, inhibit HNSCC growth, and have potential as a therapeutic agent for HNSCC.

Therapeutic Approaches for Non-Melanoma Skin Cancer: Standard of Care and Emerging Modalities.

Skin cancer encompasses a range of cutaneous malignancies, with non-melanoma skin cancers (NMSCs) being the most common neoplasm worldwide. Skin exposure is the leading risk factor for initiating NMSC. Ultraviolet (UV) light induces various genomic aberrations in both tumor-promoting and tumor-suppressing genes in epidermal cells. In conjunction with interactions with a changed stromal microenvironment and local immune suppression, these aberrations contribute to the occurrence and expansion of cancerous lesions. Surgical excision is still the most common treatment for these lesions; however, locally advanced or metastatic disease significantly increases the chances of morbidity or death. In recent years, numerous pharmacological targets were found through extensive research on the pathogenic mechanisms of NMSCs, leading to the development of novel treatments including Hedgehog pathway inhibitors for advanced and metastatic basal cell carcinoma (BCC) and PD-1/PD-L1 inhibitors for locally advanced cutaneous squamous cell carcinoma (cSCC) and Merkel cell carcinoma (MCC). Despite the efficacy of these new drugs, drug resistance and tolerability issues often arise with long-term treatment. Ongoing studies aim to identify alternative strategies with reduced adverse effects and increased tolerability. This review summarizes the current and emerging therapies used to treat NMSC.

The Role of SCARA5 as a Potential Biomarker in Squamous Cell Carcinoma of the Lung.

Lung cancer is the leading cause of cancer-related deaths in the western world. Squamous cell carcinoma is one of the most common histological subtypes of this malignancy. For squamous cell carcinoma of the lung (LSCC), prognostic and predictive markers still are largely missing. In a previous study, we were able to show that the expression of THSD7A shows an association with unfavorable prognostic parameters in prostate cancer. There is also a link to a high expression of FAK. There is incidence that SCARA5 might be the downstream gene of THSD7A. Furthermore, there is evidence that SCARA5 interacts with FAK. We were interested in the role of SCARA5 as a potential biomarker in LSCC. Furthermore, we wanted to know whether SCARA5 expression is linked to THSD7A positivity and to the expression level of FAK. For this reason, we analyzed 101 LSCC tumors by immunohistochemistry. Tissue microarrays were utilized. No significant association was found between SCARA5 expression and overall survival or clinicopathological parameters. There was also no significant association between THSD7A positivity and SCARA5 expression level. Moreover, no significant association was found between FAK expression level and SCARA5 expression level. SCARA5 seems not to play a major role as a biomarker in squamous cell carcinoma of the lung.

Multi-Wavelength Raman Differentiation of Malignant Skin Neoplasms.

Raman microspectroscopy has become an effective method for analyzing the molecular appearance of biomarkers in skin tissue. For the first time, we acquired in vitro Raman spectra of healthy and malignant skin tissues, including basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), at 532 and 785 nm laser excitation wavelengths in the wavenumber ranges of 900-1800 cm-1 and 2800-3100 cm-1 and analyzed them to find spectral features for differentiation between the three classes of the samples. The intensity ratios of the bands at 1268, 1336, and 1445 cm-1 appeared to be the most reliable criteria for the three-class differentiation at 532 nm excitation, whereas the bands from the higher wavenumber region (2850, 2880, and 2930 cm-1) were a robust measure of the increased protein/lipid ratio in the tumors at both excitation wavelengths. Selecting ratios of the three bands from the merged (532 + 785) dataset made it possible to increase the accuracy to 87% for the three classes and reach the specificities for BCC + SCC equal to 87% and 81% for the sensitivities of 95% and 99%, respectively. Development of multi-wavelength excitation Raman spectroscopic techniques provides a versatile non-invasive tool for research of the processes in malignant skin tumors, as well as other forms of cancer.

Efficacy and Safety of Salvage-line Nivolumab Monotherapy for Advanced Esophageal Squamous Cell Carcinoma: Comparison of 240 mg Versus 480 mg Doses.

BACKGROUND: Nivolumab monotherapy is the standard second-line treatment for advanced esophageal squamous cell carcinoma (ESCC) after failure of platinum-based chemotherapy without anti-PD-1 antibody. Fixed dosing with 240 mg every 2 weeks was approved initially, followed by fixed dosing with 480 mg every 4 weeks based on pharmacokinetics data. However, information on the comparative efficacy and safety of the two doses remains limited. METHODS: We compared progression-free survival (PFS), overall survival (OS), objective response rate (ORR), and the incidence of adverse events (AEs) between the two doses in 117 patients who received second-line (n = 85) or later-line (n = 32) nivolumab monotherapy at our institution between January 2016 and December 2021. RESULTS: In the second-line group, patient characteristics for the 240 mg and 480 mg groups were as follows (240 mg vs. 480 mg): performance status (PS) 0/1/2 was 34/61/5% vs. 54/42/4%, and prior fluoropyrimidine plus platinum therapy (FP) was 81.3% vs. 42.3%. In the later-line group, the characteristics were: PS 0/1/2 was 28/60/12% vs. 14/86/0%, and prior FP was 60.0% vs. 42.8%. ORR was 11.9 vs. 24.0% in the second-line group (p = 0.19) and 0 vs. 14.3% in the later-line group (p = 0.22). Median PFS was 1.7 vs. 4.1 months on second-line (hazard ratio [HR] 0.60, 95% confidence interval [CI] 0.35-1.01, p = 0.056) and 1.4 vs. 1.8 months on later-line (HR 0.58, 95% CI 0.23-1.46, p = 0.25); AEs of any grade were observed in 58.3 vs. 69.7%, respectively. CONCLUSIONS: The efficacy and safety of the two doses of nivolumab monotherapy were comparable in patients with advanced ESCC.

The Role of Biomarkers in HPV-Positive Head and Neck Squamous Cell Carcinoma: Towards Precision Medicine.

Head and neck cancer (HNC) represents a significant global health challenge, with squamous cell carcinomas (SCCs) accounting for approximately 90% of all HNC cases. These malignancies, collectively referred to as head and neck squamous cell carcinoma (HNSCC), originate from the mucosal epithelium lining the larynx, pharynx, and oral cavity. The primary risk factors associated with HNSCC in economically disadvantaged nations have been chronic alcohol consumption and tobacco use. However, in more affluent countries, the landscape of HNSCC has shifted with the identification of human papillomavirus (HPV) infection, particularly HPV-16, as a major risk factor, especially among nonsmokers. Understanding the evolving risk factors and the distinct biological behaviors of HPV-positive and HPV-negative HNSCC is critical for developing targeted treatment strategies and improving patient outcomes in this complex and diverse group of cancers. Accurate diagnosis of HPV-positive HNSCC is essential for developing a comprehensive model that integrates the molecular characteristics, immune microenvironment, and clinical outcomes. The aim of this comprehensive review was to summarize the current knowledge and advances in the identification of DNA, RNA, and protein biomarkers in bodily fluids and tissues that have introduced new possibilities for minimally or non-invasive cancer diagnosis, monitoring, and assessment of therapeutic responses.

Extended Follow-Up Outcomes from Pooled Prospective Studies Evaluating Efficacy of Interstitial Alpha Radionuclide Treatment for Skin and Head and Neck Cancers.

The initial favorable efficacy and safety profile for Alpha DaRT have been demonstrated (NCT04377360); however, the longer-term safety and durability of the treatment are unknown. This pooled analysis of four prospective trials evaluated the long-term safety and efficacy of Alpha DaRT for the treatment of head and neck or skin tumors. A total of 81 lesions in 71 patients were treated across six international institutions, with a median follow-up of 14.1 months (range: 2-51 months). Alpha DaRT sources were delivered via a percutaneous interstitial technique and placed to irradiate the tumor volume with the margin. The sources were removed two to three weeks following implantation. A complete response was observed in 89% of treated lesions (n = 72) and a partial response in 10% (n = 8). The two-year actuarial local recurrence-free survival was 77% [95% CI 63-87]. Variables, including recurrent versus non-recurrent lesions, baseline tumor size, or histology, did not impact long-term outcomes. Twenty-seven percent of patients developed related acute grade 2 or higher toxicities, which resolved with conservative measures. No grade 2 or higher late toxicities were observed. These data support the favorable safety profile of Alpha DaRT, which is currently being explored in a pivotal US trial.

Efficacy of Cisplatin-CXCR4 Antagonist Combination Therapy in Oral Cancer.

Cisplatin is a platinum-based compound that is widely used for treating inoperable oral squamous cell carcinoma (OSCC) in Japan; however, resistance to cisplatin presents a challenge and innovative approaches are required. We aimed to investigate the therapeutic potential of targeting the chemokine receptor CXCR4, which is involved in angiogenesis and tumor progression, using the CXCR4 inhibitor AMD3100, in combination with cisplatin. AMD3100 induced necrosis and bleeding in OSCC xenografts by inhibiting angiogenesis. We investigated the combined ability of AMD3100 plus cisplatin to enhance the antitumor effect in cisplatin-resistant OSCC. An MTS assay identified HSC-2 cells as cisplatin-resistant cells in vitro. Mice treated with the cisplatin-AMD combination exhibited the most significant reduction in tumor volume, accompanied by extensive hemorrhage and necrosis. Histological examination indicated thin and short tumor vessels in the AMD and cisplatin-AMD groups. These results indicated that cisplatin and AMD3100 had synergistic antitumor effects, highlighting their potential for vascular therapy of refractory OSCC. Antitumor vascular therapy using cisplatin combined with a CXCR4 inhibitor provides a novel strategy for addressing cisplatin-resistant OSCC.

Mohs Micrographic Surgery for Cutaneous Squamous Cell Carcinoma.

BACKGROUND: The first-line treatment of the localized form of cutaneous squamous cell carcinoma (cSCC) remains surgical excision. Either conventional excision (CE) with margins or Mohs micrographic surgery (MMS) may be preferred, depending on the risk factors of cSCC, the characteristics of the tumor, and the available technical facilities. METHODS: This article presents a systematic review of the current literature spanning from 1974 to 2023, comparing outcomes of cSCC treated with MMS versus cSCC treated with conventional excision. RESULTS: Out of the 6821 records identified through the database search, a total of 156 studies were screened, of which 10 were included in the review. The majority of the included studies showed that treatment of cSCC with MMS consistently exhibits a significantly lower risk of recurrence compared to treatment with CE. In addition, MMS is emerging as the preferred technique for the resection of cSCC located in aesthetically or functionally challenging anatomical areas. CONCLUSION: The studies generally demonstrate that MMS is a safer and more effective treatment of cSCC than CE. Nevertheless, outcomes such as recurrence rates and cost-effectiveness should be assessed more precisely, in order to allow for a more tailored approach in determining the appropriate indication for the use of MMS.

Immunological Signatures for Early Detection of Human Head and Neck Squamous Cell Carcinoma through RNA Transcriptome Analysis of Blood Platelets.

Although there has been a reduction in head and neck squamous cell carcinoma occurrence, it continues to be a serious global health concern. The lack of precise early diagnostic biomarkers and postponed diagnosis in the later stages are notable constraints that contribute to poor survival rates and emphasize the need for innovative diagnostic methods. In this study, we employed machine learning alongside weighted gene co-expression network analysis (WGCNA) and network biology to investigate the gene expression patterns of blood platelets, identifying transcriptomic markers for HNSCC diagnosis. Our comprehensive examination of publicly available gene expression datasets revealed nine genes with significantly elevated expression in samples from individuals diagnosed with HNSCC. These potential diagnostic markers were further assessed using TCGA and GTEx datasets, demonstrating high accuracy in distinguishing between HNSCC and non-cancerous samples. The findings indicate that these gene signatures could revolutionize early HNSCC identification. Additionally, the study highlights the significance of tumor-educated platelets (TEPs), which carry RNA signatures indicative of tumor-derived material, offering a non-invasive source for early-detection biomarkers. Despite using platelet and tumor samples from different individuals, our results suggest that TEPs reflect the transcriptomic and epigenetic landscape of tumors. Future research should aim to directly correlate tumor and platelet samples from the same patients to further elucidate this relationship. This study underscores the potential of these biomarkers in transforming early diagnosis and personalized treatment strategies for HNSCC, advocating for further research to validate their predictive and therapeutic potential.

C-Reactive Protein Kinetic as a Potential Predictive and Prognostic Factor during Treatment with Checkpoint Inhibitors in R/M-HNSCC.

Introduction The kinetic of C-reactive protein (CRP) in the early phase of therapy with checkpoint inhibitors (CPI) and its prognostic value has already been investigated in several tumor entities. In particular, flare dynamics have been described as a positive prognostic parameter. The aim of this retrospective study is to examine the extent to which such an application can also be transferred to patients with recurrent or metastatic squamous cell carcinoma of the head and neck region (R/M-HNSCC). Material and Methods All patients treated with CPI for R/M-HNSCC at our clinic between 2018 and 2023 were included (n = 44). Demographic, clinical, histopathologic and laboratory data were extracted from the digital patient records and statistically analyzed. We then examined the CRP kinetic using two previously published classifications and proposed a new classification ourselves. Subsequently, correlation analyses were performed with the overall survival (OS) of the patients. Results Of the two CRP kinetic classifications previously published, only one showed a correlation with the result of the first re-staging, and neither showed a correlation with the OS of R/M-HNSCC patients. Our new CRP kinetic classification showed a significant association with OS in R/M-HNSCC patients (p = 0.05). In a multivariate analysis, our CRP kinetic classification (p = 0.007) and the outcome of the first re-staging (p = 0.002) were significant independent factors for OS. Discussion Our novel CRP kinetic classification significantly correlates with OS in R/M-HNSCC patients, indicating a potential prognostic marker. Existing classifications from other cancer entities showed limited prognostic significance, emphasizing the need for tailored markers. For validation, however, testing on larger R/M-HNSCC patient collectives is necessary.

Citrullinated Histone H3, a Marker for Neutrophil Extracellular Traps, Is Associated with Poor Prognosis in Cutaneous Squamous Cell Carcinoma Developing in Patients with Recessive Dystrophic Epidermolysis Bullosa.

Recessive dystrophic epidermolysis bullosa (RDEB) is a rare severe hereditary skin disease characterized by skin and mucosa fragility, resulting in blister formation. The most severe complication in RDEB patients is the development of cutaneous squamous cell carcinoma (SCC), leading to premature death. There is a great deal of evidence suggesting a permissive tumor microenvironment (TME) as a driver of SCC development in RDEB patients. In a cohort of RDEB patients, we characterized the immune profiles of RDEB-SCCs and compared them with clinical, histopathological, and prognostic features. RDEB-SCCs were subdivided into four groups based on their occurrence (first onset or recurrences) and grading according to clinical, histopathological parameters of aggressiveness. Thirty-eight SCCs from 20 RDEB patients were analyzed. Five RDEB patients experienced an unfavorable course after the diagnosis of the first SCC, with early recurrence or metastasis, whereas 15 patients developed multiple SCCs without metastasis. High-risk primary RDEB-SCCs showed a higher neutrophil-to-lymphocyte ratio in the tumor microenvironment and an increased proportion of neutrophil extracellular traps (NETs). Additionally, citrullinated histone H3, a marker of NETs, was increased in the serum of RDEB patients with high-risk primary SCC, suggesting that this modified form of histone H3 may serve as a potential blood marker of unfavorable prognosis in RDEB-SCCs.

Deep learning-based hyperspectral technique identifies metastatic lymph nodes in oral squamous cell carcinoma-A pilot study.

AIMS: To establish a system based on hyperspectral imaging and deep learning for the detection of cancer cells in metastatic lymph nodes. MAIN METHODS: The continuous sections of metastatic lymph nodes from 45 oral squamous cell carcinoma (OSCC) patients were collected. An improved ResUNet algorithm was established for deep learning to analyze the spectral curve differences between cancer cells and lymphocytes, and that between tumor tissue and normal tissue. KEY FINDINGS: It was found that cancer cells, lymphocytes, and erythrocytes in the metastatic lymph nodes could be distinguished basing hyperspectral image, with overall accuracy (OA) as 87.30% and average accuracy (AA) as 85.46%. Cancerous area could be recognized by hyperspectral image and deep learning, and the average intersection over union (IOU) and accuracy were 0.6253 and 0.7692, respectively. SIGNIFICANCE: This study indicated that deep learning-based hyperspectral techniques can identify tumor tissue in OSCC metastatic lymph nodes, achieving high accuracy of pathological diagnosis, high work efficiency, and reducing work burden. But these are preliminary results limited to a small sample.