Metastasis Of Squamous Cell Carcinoma Research Articles

Solitary renal metastasis of esophageal squamous cell carcinoma mimicking primary renal neoplasm – A case report and literature review

Solitary renal metastasis of esophageal squamous cell carcinoma mimicking primary renal neoplasm – A case report and literature review

A 18F-FDG PET/CT-based deep learning-radiomics-clinical model for prediction of cervical lymph node metastasis in esophageal squamous cell carcinoma.

To develop an artificial intelligence (AI)-based model using Radiomics, deep learning (DL) features extracted from 18F-fluorodeoxyglucose (18F-FDG) Positron emission tomography/Computed Tomography (PET/CT) images of tumor and cervical lymph node with clinical feature for predicting cervical lymph node metastasis (CLNM) in patients with esophageal squamous cell carcinoma (ESCC). The study included 300 ESCC patients from the First Affiliated Hospital of Zhengzhou University who were divided into a training cohort and an internal testing cohort with an 8:2 ratio. Another 111 patients from Shanghai Chest Hospital were included as the external cohort. For each sample, we extracted 428 PET/CT-based Radiomics features from the gross tumor volume (GTV) and cervical lymph node (CLN) delineated layer by layer and 256 PET/CT-based DL features from the maximum cross-section of GTV and CLN images We input these features into seven different machine learning algorithms and ultimately selected logistic regression (LR) as the model classifier. Subsequently, we evaluated seven models (Clinical, Radiomics, Radiomics-Clinical, DL-Clinical, DL-Radiomics, DL-Radiomics-Clinical) using Radiomics features, DL features and clinical feature. The DL-Radiomics-Clinical (DRC) model demonstrated higher AUC of 0.955 and 0.916 compared to the other six models in both internal and external testing cohorts respectively. The DRC model achieved the highest accuracy among the seven models in both the internal and external test sets, with scores of 0.951 and 0.892, respectively. Through the combination of Radiomics features and DL features from PET/CT imaging and clinical feature, we developed a predictive model exhibiting exceptional classification capabilities. This model can be considered as a non-invasive method for predication of CLNM in patients with ESCC. It might facilitate decision-making regarding to the extend of lymph node dissection, and to select candidates for postoperative adjuvant therapy.

Nicotine-induced CHRNA5 activation modulates CES1 expression, impacting head and neck squamous cell carcinoma recurrence and metastasis via MEK/ERK pathway

The mucosal epithelium of the head and neck region (including the oral cavity, nasal cavity, pharynx, nasopharynx, and larynx) is the primary site exposed to tobacco smoke, and its presence of nicotinic acetylcholine receptors (nAChRs) has been observed in the mucosal epithelial cells of this area. It remains unclear whether HNSC cells can migrate and invade through nAChR signaling. A model of HNSC cells exposed to nicotine is established. Cell proliferation following nicotine exposure is assessed using the CCK-8 assay, while migration and invasion are evaluated through wound healing and Transwell assays. The effects of CHRNA5 knockdown and overexpression are also investigated. Immunofluorescence staining is used to analyze CHRNA5 expression and localization, and clonogenic assays are performed to measure colony proliferation after CHRNA5 knockdown and overexpression. The interaction between CHRNA5 and CES1 is examined using molecular docking, co-immunoprecipitation, and immunofluorescence. Differentially expressed genes are subjected to pathway enrichment analysis, and MEK/ERK protein expression and phosphorylation are validated via western blot. Tumor formation assays are performed in nude mice using sh-CHRNA5 Cal27 cells, followed by western blot and immunohistochemical staining. Additionally, laryngeal and hypopharyngeal cancer tissues are analyzed through immunohistochemistry. Nicotine significantly enhanced the proliferation, migration, and invasion capabilities of head and neck tumor cells, including Cal27, Fadu, HN6, and Tu686 cells, through the expression of CHRNA5. Knockdown of CHRNA5 can reduce cell migration, invasion, and proliferation, whereas nicotine exposure can reverse this trend. Additionally, the mRNA and protein expression of CES1 decreases with the knockdown of CHRNA5, indicating a regulatory relationship between the two. Transcriptomics revealed that the knockdown of CHRNA5 is associated with the MEK/ERK signaling pathway. Further cellular- and tissue-level evidence confirmed that the levels of p-MEK/MEK, p-ERK/ERK, and CES1 decreased following knockdown of CHRNA5, a trend that nicotine can reverse. Nicotine promotes the proliferation, migration, and invasion of HNSC by upregulating CHRNA5 expression. Knockdown of CHRNA5 reduces these effects, which can be reversed by nicotine. Nicotine exposure activates CHRNA5, regulating CES1 expression via the MEK/ERK pathway, contributing to the recurrence and metastasis of head and neck squamous carcinoma.

Unexpected Findings: Cutaneous Metastasis in Squamous Cell Carcinoma of the Cervix – A Rare Case Report

Skin metastasis from squamous cell carcinoma of the uterine cervix is a rare occurrence with reported incidences ranging from 0.1% to 2%. This often indicates advanced-stage disease and poor prognosis. We present the case of a 50-year-old multiparous woman diagnosed with cervical squamous cell carcinoma FIGO stage 2A1 following a six-month history of abnormal uterine bleeding. Despite initial treatment with radical hysterectomy, the patient was noncompliant with postoperative radiotherapy and experienced disease recurrence manifesting as vaginal and cutaneous lesions. Subsequent chemotherapy failed to halt disease progression, leading to palliative care. The timing of skin metastasis onset following primary treatment is a crucial prognostic factor, with earlier appearances indicating poorer outcomes. Skin metastases are often preterminal, necessitating palliative care.

68Ga]Ga-FAPI04 Outperforms [18F]FDG PET/CT for Detecting Nodal Metastasis of Head and Neck Squamous Cell Carcinoma: A Single-Center Experience.

This study assesses fibroblast activated protein inhibitor (FAPI) targeted PET/CT imaging against [18F]FDG PET/CT (FDG PET) for detecting nodal involvement in head and neck squamous cell carcinoma (HNSCC), intending to improve diagnostic precision for metastatic lymph nodes and lay the groundwork for future investigations. Methods: Patients diagnosed with HNSCC were retrospectively enrolled. All patients underwent [68Ga]Ga-FAPI04 PET/CT (FAPI PET) and FDG PET within 6 d. Primary tumor, lymph nodes, and tracer uptake were visually and quantitatively compared. The metastatic lymph nodes were evaluated using patient-and lesion-based analyses, with biopsy or postoperative histopathological examination as the reference. Results: The cohort includes 24 patients (17 men, 7 women; mean age 60 ± 11.8 years) who underwent FDG and FAPI PET for preoperative diagnostic workup or restaging due to known recurrence of HNSCC. Lesions included 24 primary tumors, 54 cervical lymph nodes, and 5 metastases. Primary tumors exhibited significant uptake on both PET modalities (median maximum standardized uptake value [SUVmax]: FDG 19.4 ± 11.6, FAPI 16.9 ± 4.6), with no statistically significant difference (p > 0.5). For lymph nodes, FAPI and FDG PET showed median SUVmax of 9.18 ± 6.77 and 9.67 ± 6.5, respectively. The patient-based analysis found FDG PET sensitivity at 88.2% and FAPI PET at 94.1%, with FAPI PET specificity significantly higher (85.7% vs. 42.8% for FDG PET). Lesion-based analysis revealed FAPI PET sensitivity and specificity at 84.2% and 93.7%, respectively, contrasting FDG PET's at 81.5% and 25%, respectively. Conclusion: This study underscores the efficacy of FAPI PET in detecting primary tumors in HNSCC. Furthermore, FAPI PET shows improved specificity over FDG PET for metastatic lymph nodes advocating further investigations for integrating FAPI PET into HNSCC clinical protocols for its enhanced precision in detecting metastatic lymph nodes.

M2-like Macrophages-derived CCL17 Promotes Esophageal Squamous Cell Carcinoma Metastasis and Stemness via Activating CCR4-mediated ERK/PD-L1 Pathway.

High morbidity, high mortality and poor prognosis of esophageal squamous cell carcinoma (ESCC) highlights the urgent need for novel therapeutic strategies against ESCC. The current study addresses the precise role of M2-like macrophages-derived CCL17 in ESCC progression and to thoroughly elucidate the intrinsic molecular mechanisms. In this work, for functional experiments, Eca109 cells cultivated in M2-CM were treated with anti-IgG (50 μg/ml) or anti-CCL17 (50 μg/ml) to expound the tumorpromoting effects of M2-like macrophage-derived CCL17 in ESCC. Moreover, for rescue experiments, Eca109 cells were treated with CCL17 (50 ng/ml) and/or CCR4 antagonist AZD2098 (20 μM) to probe whether CCL17 could influence the malignant behaviors including migration, invasion and stemness of ESCC cells via activating CCR4/ERK/PD-L1 pathway. Markedly enhanced CCL17 secretion was observed in M2-like macrophages. CCL17 bound to CCR4 to activate ERK/PD-L1 signaling. M2-like macrophagesderived CCL17 facilitated ESCC cell migration and invasion and enhanced stemness characteristics of ESCC cells, which were partially reserved by AZD2098 treatment. The tumor-promoting effects of M2-like macrophages-derived CCL17 on ECSS was depended on the activation of CCR4/ERK/PD-L1 pathway. To conclude, M2-like macrophages-derived CCL17 could facilitate ESCC cell migration and invasion and enhance stemness characteristics of ESCC cells via activating CCR4/ERK/PD-L1 signaling.

18F-FDG PET/CT Findings of Isolated Renal Metastasis From Squamous Cell Lung Cancer.

We present the 18F-FDG PET/CT findings of a 64-year-old man with isolated renal metastasis. He had a history of radical surgery for squamous cell lung cancer 14 months ago, followed by chemotherapy and immunotherapy. The renal metastasis presented as a small focus of increased FDG uptake in the restaging 18F-FDG PET/CT scan, which was regarded as renal cortical tracer retention. The renal metastasis was more prominent on the second PET/CT performed 5 months later. The patient subsequently underwent radical nephrectomy, and histopathological examination confirmed the diagnosis of renal squamous cell carcinoma metastasis.

Lymph node metastasis determined miRNAs in esophageal squamous cell carcinoma.

There is no golden noninvasive and effective technique to diagnose lymph node metastasis (LNM) for esophageal squamous cell carcinoma (ESCC) patients. Here, a classifier was proposed consisting of miRNAs to screen ESCC patients with LNM from the ones without LNM. miRNA expression and clinical data files of 93 ESCC samples were downloaded from TCGA as the discovery set and 119 ESCC samples with similar dataset GSE43732 as the validation set. Differentially expressed miRNAs (DE-miRNAs) were analyzed between patients with LNM and without LNM. LASSO regression was performed for selecting the DE-miRNA pair to consist the classifier. To validate the accuracy and reliability of the classifier, the SVM and AdaBoost algorithms were applied. The CCK-8 and wound healing assay were used to evaluate the role of the miRNA in ESCC cells. There were 43 DE miRNAs between the LNM+ group and LNM- group. Among them, miR-224-5p, miR-99a-5p, miR-100-5p, miR-34c-5p, miR-503-5p, and miR-452-5p were identified by LASSO to establish the classifier. SVM and AdaBoost showed that the model could classify the ESCC patients with LNM from the ones without LNM precisely and reliably in 2 data sets. miR-224-5p in the classifier as the top contributor to discriminate the two groups of patients based on AdaBoost, promoted ESCC cell proliferation and migration in vitro. The classifier based on these 6 miRNAs could classify the ESCC patients with LNM from the ones without LNM successfully.

Therapeutic and Diagnostic Tactics for Metastases to the Lymph Nodes of the Neck without an Identified Primary Focus

Introduction. Metastatic squamous cell carcinoma from an unknown primary focus accounts for less than 5 % of malignant tumors in the head and neck. Improving the methods of diagnosis can reduce the incidence of this pathology. Materials and methods. A retrospective analysis of the results of diagnosis and treatment of 59 patients with metastasis to the lymph nodes of the neck without an identified primary focus was performed. The proportion of male patients was 86 % (51/59), female — 14 % (8/59). The average age of patients is 61 years. Squamous cell carcinoma prevailed — 79 % (47/59). Results. Metastatically affected lymph nodes were localized in 92 % of cases at levels II and III. The proportion of patients with stages N2, N3 prevailed — 55 % (abs. 26), 32 % (abs. 15), respectively. Overexpression of the P­16 protein in metastatically affected lymph nodes was detected in 70 %, PD­L1 in 48 %, and Epstein­Barr virus (EBV) in 6 %. Ipsilateral diagnostic palatine tonsillectomy of an apparently unchanged tonsil was performed in 15 % (9/59) of cases, revealing the primary site in one instance. Of the special treatment methods, complex and combined treatment prevailed — 55 % (abs. 26). Radiation therapy in an independent version was performed by 48 % of patients, while 76 % received the full course (abs. 16). Combined treatment (a course of Radiation therapy followed by chemotherapy) — in 7 % (abs. 3) 20 % of patients received polychemotherapy. Palliative immunotherapy (pembrolizumab 200 mg IV — 5 courses) was given to 1 patient. The average life expectancy was higher with complex treatment — it was 60 months (95 % CI 43.5–76.4), the median survival is 60 months. Discussion. The main methods of treatment of patients with metastases of squamous cell carcinoma without were radiation therapy in an independent version, as well as complex treatment. Ipsilateral diagnostic palatine tonsillectomy of an apparently unchanged tonsil was performed in 15 % (abs. 9), and allowed to identify the primary focus in 1 case.Conclusion. Metastasis to the lymph nodes of the neck without remains an urgent interdisciplinary problem. Prospective multicenter studies are required to improve and optimize the algorithms for diagnosis and treatment of these patients.

Single cell analysis revealed SFRP2 cancer associated fibroblasts drive tumorigenesis in head and neck squamous cell carcinoma

Understanding the mechanisms of invasion and metastasis in head and neck squamous cell carcinoma (HNSCC) is crucial for effective treatment, particularly in metastatic cases. In this study, we analyzed multicenter bulk sequencing and comprehensive single-cell data from 702,446 cells, leading to the identification of a novel subtype of cancer-associated fibroblasts (CAFs), termed Secreted Frizzled-Related Protein2 CAFs (SFRP2_CAFs). These cells, originating from smooth muscle cells, display unique characteristics resembling both myofibroblastic CAFs and inflammatory CAFs, and are linked to poorer survival outcomes in HNSCC patients. Our findings reveal significant interactions between SFRP2_CAFs and SPP1 tumor-associated macrophages, which facilitate tumor invasion and metastasis. Moreover, our research identifies Nuclear factor I/X (NFIX) as a key transcription factor regulating SFRP2_CAFs behavior, confirmed through gene regulatory network analysis and simulation perturbation.

Evaluation and treatment of cervical lymph node metastasis of head and neck squamous cell carcinoma

Evaluation and treatment of cervical lymph node metastasis of head and neck squamous cell carcinoma

The combination of p16 and Rb expression pattern is helpful to predict high-risk HPV infection and the primary site in lymph node metastases of squamous cell carcinoma

Identifying the primary site of metastatic squamous cell carcinoma in lymph nodes can be challenging. An immunohistochemistry (IHC) analysis recently revealed that high-risk human papillomavirus (HR-HPV)-associated oropharyngeal squamous cell carcinomas (OPSCCs) typically show overexpression of p16 protein and a partial loss pattern of Rb. Nevertheless, the status of these markers in metastatic lesions is still unclear. In this study, we examined p16 and Rb expression status by IHC and transcriptionally active HR-HPV infection by mRNA in situ hybridization in paired primary and metastatic SCC lesions. A total of 50 patients with OPSCCs (n=17), hypopharyngeal SCCs (n=16), laryngeal SCCs (n=6), or uterine cervical SCCs (n=11) were enrolled. HR-HPV and p16 were positive in 21/50 (42 %) and 23/50 (46 %) patients, respectively. Primary and metastatic lesions showed concordant results for those three markers in individual patients. Among the p16-positive patients (n=23), HPV-positive cases typically showed a partial loss of Rb (n=20) and, rarely, a complete loss of Rb (n=1), whereas HPV-negative cases showed preserved Rb expression (n=2). All 27 p16-negative cases lacked HPV infection, while preserved expression and complete loss of Rb were observed in 26 and 1 of the p16-negative cases, respectively. Compared to standalone p16, the combination of p16 overexpression and Rb-partial/complete loss showed equally excellent sensitivity and negative predictive value (each 100 %) as well as improved specificity (100 % versus 93.1 %) and positive predictive value (100 % versus 91.3 %). Our results suggest that combining p16 and Rb expression patterns may be helpful in screening for HR-HPV infection in metastatic lymph nodes and in estimating the primary site of SCC.

Supraclavicular lymph node metastasis should not be defined as regional lymph node metastasis in cervical and upper thoracic esophageal squamous cell carcinoma.

The importance of supraclavicular lymph node (SCLN) metastasis in cervical and upper thoracic esophageal squamous cell carcinoma (ESCC) has not been determined. The aim of the present study was to provide a detailed definition of the range of SCLN regions and to explore whether SCLNs should be considered as a regional lymph nodes for patients with cervical and upper thoracic ESCC. A retrospective analysis was performed on 230 patients with locally advanced cervical or upper thoracic ESCC who underwent radical radiotherapy and chemotherapy. The range of SCLN regions was defined in detail on contrast enhanced computed tomography images of the neck. According to whether the patient had lymph node metastasis in the supraclavicular region, the included patients were divided into two groups, and the survival differences and reasons for treatment failure between the two groups were analyzed. Of the 230 patients with ESCC, 71 (30.87%) exhibited lymph node metastases in the supraclavicular region. The median overall survival time of ESCC patients with and without SCLN metastasis was 17 and 30 months, respectively (P<0.001). After propensity score matching (PSM), the median overall survival time of ESCC patients with and without SCLN metastasis was 17 and 28 months, respectively (P<0.001). During the follow-up period, there were a total of 101 cases of failure of treatment in the irradiation field, 6 cases had esophageal metastasis in the non-irradiated field and 27 cases had regional lymph node metastasis in the non-irradiated field. In addition, there were 33 cases of metastasis to the distant lymph nodes or organs. There was no significant difference in the local treatment failure rate between the groups with or without SCLN metastasis in both the irradiation field and the non-irradiation field, but the probability of distant metastasis in the SCLN metastasis group was significantly higher than that in the group without SCLN metastasis (P=0.025). In conclusion, patients with cervical and upper thoracic ESCC with SCLN metastasis have a poor prognosis and the median overall survival time is closer to that of metastatic ESCC than ESCC with regional lymph node metastasis; therefore, SCLNs should not be defined as regional lymph nodes in patients with cervical and upper thoracic ESCC.

LNMAC Promotes Cervical Squamous Cell Carcinoma Lymphatic Metastasis via Epigenetic Regulation of FGF2-Induced Lymphangiogenesis.

The lymph node is the most common site of distant metastasis of cervical squamous cell carcinoma (CSCC), which elicits dismal prognosis and limited efficiency for treatment. Elucidation of the mechanisms underlying CSCC lymphatic metastasis would provide potential therapeutic strategies for nodal metastatic of CSCC. Here, based on in vivo lymphatic metastasis screening model, a circular RNA is identified that is termed as lymph node metastasis associated circRNA (LNMAC), is markedly upregulated in lymphatic metastatic CSCC and correlated with lymph node metastasis. Overexpression of LNMAC dramatically augments the metastatic capability of CSCC cells to the lymph node via inducing lymphangiogenesis. Mechanistically, LNMAC epigenetically upregulates fibroblast growth factor 2 (FGF2) expression by directly associating with histone acacetylase 1 (HDAC1), preventing Importin α6/8-mediated nuclear translocation of HDAC1 and eliciting histone H3K27ac-induced FGF2 transcriptional activation. Treatment with 3F12E7, an anti-FGF2 monoclonal antibody, effectively inhibits LNMAC-induced CSCC lymphatic metastasis. Taken together, these findings indicate that LNMAC plays a crucial role in FGF2-mediated lymphangiogenesis and lymphatic metastasis, highlighting that LNMAC might be a therapeutic target for lymph node metastasis in CSCC patients.

Upregulation of LY6K induced by FTO-mediated demethylation promotes the tumorigenesis and metastasis of oral squamous cell carcinoma via CAV-1-mediated ERK1/2 signaling activation.

Lymphocyte antigen 6 complex locus K (LY6K) has been demonstrated to play a significant role in cancers and identified as a therapeutic biomarker for head and neck squamous cell carcinoma. However, the role of LY6K in oral squamous cell carcinoma (OSCC) has not been explored. The current study discovered that LY6K was aberrantly upregulated in OSCC cell lines and tissues and that high LY6K expression significantly correlated with poorer survival of OSCC patients. Through stable knockdown of LY6K, we found that the growth, colony formation, migration, and invasion of OSCC cells were substantially suppressed. In addition, tumor growth and lung metastasis in vivo were effectively inhibited by LY6K depletion. Mechanically, LY6K binds with CAV-1 and activates CAV-1-mediated MAPK/ERK signaling to exert its oncogenic effects on OSCC. In addition, LY6K expression in OSCC was discovered to be regulated by FTO-mediated RNA N6-methyladenosine (m6A) modification in an IGF2BP1-dependent manner. Generally, LY6K expression was upregulated by FTO-mediated demethylation in OSCC, which promoted the tumorigenesis and metastasis of OSCC via activating the CAV-1-mediated ERK1/2 signaling pathway.

MiRNA-199b-5p suppresses of oral squamous cell carcinoma by targeting apical-basolateral polarity via Scribble/Lgl

In epithelial cells, Scribble forms cell-cell junctions and contribute to cell morphology and homeostasis by regulating apical-basolateral polarity in mammals and functions as a tumor suppressor in many carcinomas. The initial diagnosis of oral squamous cell carcinoma is important, and its prognosis is poor when accompanied by metastasis. However, research on the mechanisms of oral squamous cell carcinoma metastasis is insufficient. Herein, we showed that Scribble regulates the apical-basolateral polarity of oral squamous cell carcinoma by regulating lethal giant larvae 1, Scribble module and E-cadherin, the adhesion junction. The expression of lethal giant larvae 1 and E-cadherin decreased when the expression of Scribble was knocked down and their localization was completely disrupted in both the oral squamous cell carcinoma cell line and in vivo model. In particular, the Scribble was involved in oral squamous cell carcinoma metastasis via hsa-miR-199b-5p, which is a microenvironmental factor of hypoxia. The disruption of Scribble localization under hypoxic conditions, but its localization was maintained in miR-199b-5p oral squamous cell carcinoma cell lines and in vivo. These results suggest that Scribble functions as a tumor suppressor marker mediated by miR-199b-5p in oral squamous cell carcinoma.

LncOCMRL1 promotes oral squamous cell carcinoma growth and metastasis via the RRM2/EMT pathway

BackgroundLong noncoding RNAs (lncRNAs) are widely involved in cancer development and progression, but the functions of most lncRNAs have not yet been elucidated. Metastasis is the main factor restricting the therapeutic outcomes of various cancer types, including oral squamous cell carcinoma (OSCC). Therefore, exploring the key lncRNAs that regulate OSCC metastasis and elucidating their molecular mechanisms will facilitate the development of new strategies for effective OSCC therapy.MethodsWe analyzed the lncRNA expression profiles of tumor tissues from OSCC patients with and without cervical lymph node metastasis, and OSCC cell lines. We revealed high expression of oral squamous cell carcinoma metastasis-related lncRNA 1 (lncOCMRL1) in OSCC patient tumor tissues with lymph node metastasis and highly metastatic OSCC cell lines. The effects of lncOCMRL1 knockdown on the invasion, migration and proliferation abilities of OSCC cells were explored through qRT-PCR, Transwell, colony formation, and cell proliferation experiments. The mechanism by which lncOCMRL1 promotes OSCC metastasis and proliferation was explored through RNA pull-down, silver staining, mass spectrometry, RIP, and WB experiments. To increase its translational potential, we developed a reduction-responsive nanodelivery system to deliver siRNA for antitumor therapy.ResultsWe determined that lncOCMRL1 is highly expressed in OSCC metastatic tumor tissues and cells. Functional studies have shown that high lncOCMRL1 expression can promote the growth and metastasis of OSCC cells both in vivo and in vitro. Mechanistically, lncOCMRL1 could induce epithelial-mesenchymal transition (EMT) via the suppression of RRM2 ubiquitination and thereby promote the proliferation, invasion, and migration of OSCC cells. We further constructed reduction-responsive nanoparticles (NPs) for the systemic delivery of siRNAs targeting lncOCMRL1 and demonstrated their high efficacy in silencing lncOCMRL1 expression in vivo and significantly inhibited OSCC tumor growth and metastasis.ConclusionsOur results suggest that lncOCMRL1 is a reliable target for blocking lymph node metastasis in OSCC.

Preoperative dual-energy computed tomography and positron-emission tomography evaluation of lymph node metastasis in esophageal squamous cell carcinoma

Preoperative dual-energy computed tomography and positron-emission tomography evaluation of lymph node metastasis in esophageal squamous cell carcinoma

Neoteric Predictors for Lymph Node Metastasis in Early Oral Squamous Cell Carcinoma: Tumor Budding and Worst Pattern of Invasion

Neoteric Predictors for Lymph Node Metastasis in Early Oral Squamous Cell Carcinoma: Tumor Budding and Worst Pattern of Invasion

Development and validation of a CT-based deep learning radiomics signature to predict lymph node metastasis in oropharyngeal squamous cell carcinoma: a multicenter study.

Lymph node metastasis (LNM) is a pivotal determinant that influences the treatment strategies and prognosis for oropharyngeal squamous cell carcinoma (OPSCC) patients. This study aims to establish and verify a deep learning (DL) radiomics model for the prediction of LNM in OPSCCs using contrast-enhanced computed tomography (CECT). A retrospective analysis included 279 OPSCC patients from three institutions. CECT images were used for handcrafted (HCR) and DL feature extraction. Dimensionality reduction for HCR features used recursive feature elimination and least absolute shrinkage and selection operator algorithms, whereas DL feature dimensionality reduction used variance-threshold and recursive feature elimination algorithms. Radiomics signatures were constructed using support vector machine, decision tree, random forest, k-nearest neighbor, gaussian naive bayes classifiers and light gradient boosting machine. A combined model was then constructed using the screened DL, HCR, and clinical features. The area under the receiver operating characteristic curve (AUC) served to quantify the model's performance, and calibration curves were utilized to assess its calibration. The combined model exhibited robust performance, achieving AUC values of 0.909 (95% CI: 0.861-0.957) in the training cohort, 0.884 (95% CI: 0.800-0.968) in the internal validation cohort, and 0.865 (95% CI: 0.791-0.939) in the external validation cohort. It outperformed both the clinical model and best-performing radiomics model. Moreover, calibration was deemed satisfactory. The combined model based on CECT demonstrates the potential to predict LNM in OPSCCs preoperatively, offering a valuable tool for more precise and tailored treatment strategies. This study presents a novel combined model integrating clinical factors with deep learning radiomics, significantly enhancing preoperative LNM prediction in OPSCC.