Integrating lipid metabolite analysis with MRI-based transformer and radiomics for early and late stage prediction of oral squamous cell carcinoma.

BACKGROUND: Oral Squamous Cell Carcinoma (OSCC) presents significant diagnostic challenges in its early and late stages. This study aims to utilize preoperative MRI and biochemical indicators of OSCC patients to predict the stage of tumors. METHODS: This study involved 198 patients from two medical centers. A detailed analysis of contrast-enhanced T1-weighted (ceT1W) and T2-weighted (T2W) MRI were conducted, integrating these with biochemical indicators for a comprehensive evaluation. Initially, 42 clinical biochemical indicators were selected for consideration. Through univariate analysis and multivariate analysis, only those indicators with p-values less than 0.05 were retained for model development. To extract imaging features, machine learning algorithms in conjunction with Vision Transformer (ViT) techniques were utilized. These features were integrated with biochemical indicators for predictive modeling. The performance of model was evaluated using the Receiver Operating Characteristic (ROC) curve. RESULTS: After rigorously screening biochemical indicators, four key markers were selected for the model: cholesterol, triglyceride, very low-density lipoprotein cholesterol and chloride. The model, developed using radiomics and deep learning for feature extraction from ceT1W and T2W images, showed a lower Area Under the Curve (AUC) of 0.85 in the validation cohort when using these imaging modalities alone. However, integrating these biochemical indicators improved the model's performance, increasing the validation cohort AUC to 0.87. CONCLUSION: In this study, the performance of the model significantly improved following multimodal fusion, outperforming the single-modality approach. CLINICAL RELEVANCE STATEMENT: This integration of radiomics, ViT models, and lipid metabolite analysis, presents a promising non-invasive technique for predicting the staging of OSCC.

Quantum dots in noninvasive imaging of oral squamous cell carcinomas: A scoping literature review.

ABSTRACT: The current scoping review's objective was to outline existing applications, recent breakthroughs, and quantum dots' applicability in imaging of oral squamous cell cancer. Quantum dots are nanometric semiconductor crystals with customizable optical characteristics and intense, stable fluorescence suited for bioimaging and labeling. We used the Preferred reporting items for systematic reviews and meta-analyses (PRISMA) recommendations for conducting our systematic search. An analysis of the properties and applications of quantum dots in noninvasive detection of oral squamous cell cancer is presented in this study, which comprehensively explores the available evidence. Following searches in the databases PubMed, Ovid SP, and Cochrane using the search terms quantum dots AND oral squamous cell cancer, 55 published publications were chosen for this review. The review identified a total of eight papers that met the criteria. In noninvasive detection of oral squamous cell carcinoma, quantum dots have the potential to offer an array of therapeutic and diagnostic applications. Furthermore, quantum dots emit near-infrared and visible light, which is advantageous in biological imaging since it reduces light dispersion and absorption of tissue. The future may see quantum dots become a popular noninvasive imaging technique for oral squamous cell cancer. The number of studies accessible is quite limited, and further research is required.

Update on Pathologic Conditions, Imaging Findings, Prevention, and Management of Human Papillomavirus-related Neoplasms.

Human papillomavirus (HPV) is the most common sexually transmitted infection that proliferates in the squamous epithelium and is the most common source of viral-related neoplasms. Low-risk subtypes (HPV-6 and -11) cause respiratory papillomas (laryngeal, tracheal, and bronchial) and condyloma acuminata of the penis, anus, and perineal region (anogenital warts). High-risk subtypes (HPV-16, -18, -31, and -33) are responsible for oropharyngeal squamous cell carcinoma (SCC) that involves the tongue base, tonsils, posterior pharyngeal wall, and larynx and malignancies of the anogenital region (cancers of the cervix, vagina, vulva, penis, and anal canal). Recent studies have increasingly shown a favorable treatment response and substantial differences in the overall prognosis associated with HPV-associated oropharyngeal cancers. Given this fact, oropharyngeal, cervical, and penile SCCs are classified as HPV-associated and HPV-independent cancers in the current World Health Organization classification. Imaging is essential in the early detection, diagnosis, and staging of HPV-associated cancers. Imaging also helps assess treatment response and postoperative complications and is used for long-term surveillance. HPV-associated oropharyngeal SCCs have well-defined borders and solid and cystic nodal metastases at imaging. Updated screening and vaccination guidelines are currently available that have great potential to decrease the overall disease burden and help control this worldwide public health concern. Novel therapeutic strategies, such as immunotherapies, are being explored, and imaging biomarkers that can predict treatment response and prognosis are being investigated; radiologists play a pivotal role in these efforts. ©RSNA, 2024 Supplemental material is available for this article.

Imaging in Ocular Surface Squamous Cell Carcinoma: There's More to PET/CT Than Meets the Eye.

ABSTRACT: A 56-year-old woman presenting with swelling, redness, and pain in the left eye, initially treated with topical therapy for conjunctival squamous neoplasia, developed visual loss with progression of swelling in the left eye over the next year. Patient was referred for imaging as she also had significant weight loss and palpable neck swellings. Whole-body 18 F-FDG PET/CT revealed hypermetabolic left eye lesion; metastases in bilateral submandibular glands; cervical, mediastinal, and axillary lymph nodes; and a right lung nodule. Patient was diagnosed with ocular surface squamous cell carcinoma with metastases and started on systemic chemotherapy (cisplatin, paclitaxel, and 5-fluorouracil).

False-Positive Bone Pitfall Lesion and Collateral Circulation: Don't Miss the True-Positive Lesion.

ABSTRACT: We report the case of a patient followed up for squamous cell carcinoma of the buccal floor with lymph node involvement. The initial staging PET/CT revealed bone foci that were not definitively pathological in the context of a regional collateral circulation secondary to a defibrillator. A new monitoring examination, conducted due to the rapid local progression, revealed a dissociated evolution of the bone uptake adjacent to the collateral circulation, some confirming false-positives, but one indicating a real metastasis. This case illustrates that bone uptakes without morphological lesions adjacent to a collateral circulation are not easily interpretable.

CT-based delta-radiomics nomogram to predict pathological complete response after neoadjuvant chemoradiotherapy in esophageal squamous cell carcinoma patients.

BACKGROUND: This study developed a nomogram model using CT-based delta-radiomics features and clinical factors to predict pathological complete response (pCR) in esophageal squamous cell carcinoma (ESCC) patients receiving neoadjuvant chemoradiotherapy (nCRT). METHODS: The study retrospectively analyzed 232 ESCC patients who underwent pretreatment and post-treatment CT scans. Patients were divided into training (n = 186) and validation (n = 46) sets through fivefold cross-validation. 837 radiomics features were extracted from regions of interest (ROIs) delineations on CT images before and after nCRT to calculate delta values. The LASSO algorithm selected delta-radiomics features (DRF) based on classification performance. Logistic regression constructed a nomogram incorporating DRFs and clinical factors. Receiver operating characteristic (ROC) and area under the curve (AUC) analyses evaluated nomogram performance for predicting pCR. RESULTS: No significant differences existed between the training and validation datasets. The 4-feature delta-radiomics signature (DRS) demonstrated good predictive accuracy for pCR, with α-binormal-based and empirical AUCs of 0.871 and 0.869. T-stage (p = 0.001) and differentiation degree (p = 0.018) were independent predictors of pCR. The nomogram combined the DRS and clinical factors improved the classification performance in the training dataset (AUCαbin = 0.933 and AUCemp = 0.941). The validation set showed similar performance with AUCs of 0.958 and 0.962. CONCLUSIONS: The CT-based delta-radiomics nomogram model with clinical factors provided high predictive accuracy for pCR in ESCC patients after nCRT.

Explainable prediction model for the human papillomavirus status in patients with oropharyngeal squamous cell carcinoma using CNN on CT images.

Several studies have emphasised how positive and negative human papillomavirus (HPV+ and HPV-, respectively) oropharyngeal squamous cell carcinoma (OPSCC) has distinct molecular profiles, tumor characteristics, and disease outcomes. Different radiomics-based prediction models have been proposed, by also using innovative techniques such as Convolutional Neural Networks (CNNs). Although some of these models reached encouraging predictive performances, there evidence explaining the role of radiomic features in achieving a specific outcome is scarce. In this paper, we propose some preliminary results related to an explainable CNN-based model to predict HPV status in OPSCC patients. We extracted the Gross Tumor Volume (GTV) of pre-treatment CT images related to 499 patients (356 HPV+ and 143 HPV-) included into the OPC-Radiomics public dataset to train an end-to-end Inception-V3 CNN architecture. We also collected a multicentric dataset consisting of 92 patients (43 HPV+ , 49 HPV-), which was employed as an independent test set. Finally, we applied Gradient-weighted Class Activation Mapping (Grad-CAM) technique to highlight the most informative areas with respect to the predicted outcome. The proposed model reached an AUC value of 73.50% on the independent test. As a result of the Grad-CAM algorithm, the most informative areas related to the correctly classified HPV+ patients were located into the intratumoral area. Conversely, the most important areas referred to the tumor edges. Finally, since the proposed model provided additional information with respect to the accuracy of the classification given by the visualization of the areas of greatest interest for predictive purposes for each case examined, it could contribute to increase confidence in using computer-based predictive models in the actual clinical practice.

Basaloid squamous cell carcinoma clinically and radiologically masquerading as a head and neck paraganglioma: a case report and review of the literature.

BACKGROUND: This paper reports the first case of basaloid squamous cell carcinoma clinically and radiologically masquerading as a head and neck paraganglioma. CASE PRESENTATION: A 66-year-old Sinhalese male with unilateral hearing impairment and 7th-12th (excluding 11th) cranial nerve palsies was diagnosed radiologically with a head and neck paraganglioma by magnetic resonance imaging of the brain, which revealed a hypointense and hyperintense punctate mass centered at the jugular fossa with intracranial extension. The ascending pharyngeal artery, recognized as the major feeder, was embolized by percutaneous embolization following digital subtraction angiography. Gross total resection of the tumor was followed by an uneventful postoperative recovery. Combined immunohistochemistry and histopathological morphology revealed a basaloid squamous cell carcinoma, following which the patient completed radiotherapy and is at 3-month follow-up currently. CONCLUSION: This case report discusses the diagnostic pitfalls and management challenges of this rare entity on the basis of prior evidence, as well as a literature review and clinical and surgical analysis.

Epidemiology and Survival of Malignant Central Airway Obstruction in Lung Cancer Identified on Cross-Sectional Imaging.

BACKGROUND: The prevalence of malignant central airway obstruction at diagnosis and its 5-year incidence are largely unknown, as are basic epidemiological data pertaining to this serious condition. To address these data limitations, we retrospectively collected data from the cohort of patients diagnosed with lung cancer at our institution in 2015 and followed cohort patients 5 years forward, until 2020. METHODS: We reviewed index PET/CT or CT scans at the time of lung cancer diagnosis to identify the presence, subtype, and severity of malignant central airway obstruction as well as progression/development over the next 5 years. RESULTS: The prevalence of malignant central airway obstruction affecting the airway lumen by 25% or greater was 17%, and its 5-year incidence of development was 8.2%. Notable associations from the multivariate analysis included a younger age and a stepwise increase in obstruction with increasing stage of disease. Squamous cell carcinoma and small-cell lung cancer were the 2 histologic subtypes with the strongest association with obstruction. The presence of malignant central airway obstruction either at time of diagnosis or on follow-up imaging was associated with significantly shortened survival (multivariate Cox proportional HR for MCAO=1.702, P<0.001). CONCLUSION: This study provides the first systematic characterization of fundamental epidemiological data on malignant central airway obstructions at a tertiary cancer center in the United States. This data is important to inform research directions and funding efforts of this serious complication. It also serves as a baseline value against which to compare for future studies.

Letter to the editor regarding, "Beneath the surface: A systematic review on intraoperative imaging techniques for deep margin assessment in oral squamous cell carcinoma".

Surgical methods for oral squamous cell carcinoma have the potential to improve patient outcomes with the integration of modern imaging tools for deep margin evaluation. This articlesummarises the potential benefits of MRI, FMI, and ultrasound modalities for improving surgical accuracy, based on a wide range of research. Theuses of intraoperative imaging in oral pathology are also covered, along with difficulties including ethical and technological constraints. Important insights to direct future research and implementation efforts in the field of oral cancer surgery are provided, which also examines implications for clinical education and innovation.

Beneath the surface: A systematic review on intraoperative imaging techniques for deep margin assessment in oral squamous cell carcinoma.

Resection margins of oral squamous cell carcinoma (SCC) are often inadequate. A systematic review on clinical intraoperative whole-specimen imaging techniques to obtain adequate deep resection margins in oral SCC is lacking. Such a review may render better alternatives for the current insufficient intraoperative techniques: palpation and frozen section analyses (FSA). This review resulted in ten publications investigating ultrasound (US), four investigating fluorescence, and three investigating MRI. Both US and fluorescence were able to image the tumor intraorally and perform ex-vivo imaging of the resection specimen. Fluorescence was also able to image residual tumor tissue in the wound bed. MRI could only be used on the ex-vivo specimen. The 95 % confidence intervals for sensitivity and specificity were large, due to the small sample sizes for all three techniques. The sensitivity and specificity of US for identifying < 5 mm margins ranged from 0 % to 100 % and 60 % to 100 %, respectively. For fluorescence, this ranged from 0 % to 100 % and 76 % to 100 %, respectively. For MRI, this ranged from 7 % to 100 % and 81 % to 100 %, respectively. US, MRI and fluorescence are the currently available imaging techniques that can potentially be used intraoperatively and which can image the entire tumor-free margin, although they have insufficient sensitivity for identifying < 5 mm margins. Further research on larger cohorts is needed to improve the sensitivity by determining cut-off points on imaging for inadequate margins. This improves the number of adequate resections of oral SCC's and pave the way for routine clinical implementation of these techniques.

Diagnostic accuracy of contrast-enhanced computed tomography in assessing bone invasion in patients with oral squamous cell carcinoma.

OBJECTIVES: This study aimed to evaluate the diagnostic accuracy of contrast-enhanced computed tomography (CT) in detecting bone invasion in oral squamous cell carcinoma (OSCC) patients and to explore clinicopathological factors associated with its reliability. MATERIALS AND METHODS: 417 patients underwent preoperative contrast-enhanced CT followed by radical surgery. The presence or absence of bone invasion served as the outcome variable, with histopathologic examination of the resection specimen considered the gold standard. Statistical analyses, comprising correlation analyses and the determination of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were conducted. RESULTS: CT exhibited 76.85% sensitivity, 82.20% specificity, 47.14% PPV, and 89.67% NPV. False-positive and false-negative rates were 11.27% and 5.99%, respectively. Artifacts affected assessment in 44 patients, but not in those with bone invasion. Tumor size, depth of invasion (DOI), tumor localization at the upper jaw, lymphatic invasion, and perineural invasion correlated with incorrect identification of bone invasion (Chi-square, p < 0.05). CONCLUSIONS: Despite utilizing thin-section CT, notable false-positive and false-negative results persisted. Patients with T3 tumors, DOI ≥ 10 mm, or upper jaw tumors are at higher risk for misidentification of bone invasion. Combining multiple methods may enhance diagnostic accuracy, and the integration of artificial intelligence or tracking electrolyte disturbances by tumor depth profiling shows promise for further assessment of bone invasion before histopathology. CLINICAL RELEVANCE: Surgeons should consider these insights when planning tumor resection. Supplementary imaging may be warranted in cases with high risk factors for misidentification. Further methodological advancements are crucial for enhancing diagnostic precision.

A Case of Incidentally Discovered Congenital Complete Pericardial Defect during Lobectomy for Lung Cancer: A Case Report and Literature Review.

An 82-year-old male patient underwent a left upper lobectomy with anterolateral thoracotomy for lung cancer. Although a complete left-pericardial defect was observed during surgery, the pericardial repair was not performed because the left lower lobe remained and the heart was considered stable. Postoperative pathological examination revealed primary synchronous double-lung squamous-cell carcinoma (pathological stage pT2a(2)N0M0 stage IB). He was discharged without complications on postoperative day 8. Leftward displacement of the heart and left diaphragmatic elevation, suspected of phrenic-nerve paralysis, were found in the chest X-ray after discharge. However, the patient's overall condition remained unaffected at the 5-month postoperative follow-up. To assess the need for pericardial repair, we compared cases of complete pericardial defects observed during lobectomy or pneumonectomy reported in the literature. Only one of 12 cases occurred postoperative death despite pericardial repair, and that case combined pectus excavatum and pericardial defects. Our assessment indicated that pericardial repair might not be necessary, excluding complex cases.

Oral cavity cancer and its pre-treatment radiological evaluation: A pictorial overview.

PURPOSE: Oral cavity cancer, primarily squamous cell carcinoma (SCC), is a prevalent malignancy globally, necessitating accurate clinical assessment and staging to enable effective treatment planning. Diagnosis requires biopsy and is followed by surgical resection and reconstruction as the primary therapeutic modality. Imaging plays a pivotal role during this process, aiding in the evaluation of tumour extent, nodal involvement and distant metastases. However, despite its value, both radiologists and clinicians must recognise its inherent limitations. METHODS: This pictorial review article aims to illustrate the application of various imaging modalities in the pre-treatment evaluation of oral cavity SCC and highlights potential pitfalls. It underscores the importance of understanding the anatomical subsites of the oral cavity, the diverse patterns of spread tumours exhibit at each site, alongside the role of imaging in facilitating informed management strategies, while also acknowledging its limitations. RESULTS: The review delves into fundamentals of current staging including nodal involvement, while, emphasising imaging strategies and potential limitations. Finally, it touches on the potential of novel radiomic techniques in characterising tumours and predicting treatment response. CONCLUSIONS: Pre-treatment oral cavity cancer staging reflects an ongoing quest for enhanced diagnostic accuracy and prognostic prediction. Recognising the value of imaging alongside its limitations fosters a multidisciplinary approach to treatment planning, ultimately improving patient outcomes.

Fully automated 3D machine learning model for HPV status characterization in oropharyngeal squamous cell carcinomas based on CT images.

BACKGROUND: Human papillomavirus (HPV) status plays a major role in predicting oropharyngeal squamous cell carcinoma (OPSCC) survival. This study assesses the accuracy of a fully automated 3D convolutional neural network (CNN) in predicting HPV status using CT images. METHODS: Pretreatment CT images from OPSCC patients were used to train a 3D DenseNet-121 model to predict HPV-p16 status. Performance was evaluated by the ROC Curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. RESULTS: The network achieved a mean AUC of 0.80 ± 0.06. The best-preforming fold had a sensitivity of 0.86 and specificity of 0.92 at the Youden's index. The PPV, NPV, and F1 scores are 0.97, 0.71, and 0.82, respectively. CONCLUSIONS: A fully automated CNN can characterize the HPV status of OPSCC patients with high sensitivity and specificity. Further refinement of this algorithm has the potential to provide a non-invasive tool to guide clinical management.

Nomogram based on MRI and clinical features to predict progression-free survival in patients with stage IIIC1r cervical squamous cell carcinoma: A two-center study.

PURPOSE: To develop a nomogram based on MRI and clinical features to predict progression-free survival (PFS) of 2018 FIGO stage ⅢC1r cervical squamous cell carcinoma (CSCC). METHODS: 144 consecutive patients with stage ⅢC1r CSCC from two independent institutions were stratified into training cohort (from Institution 1, n=100) and independent validation cohort (from Institution 2, n=44). Univariate and multivariate Cox regression analyses of MRI and clinical features before treatment were performed to determine independent risk factors for PFS in training cohort. Nomogram was developed based on them. Concordance index (C-index), calibration curves, and receiver operating characteristic (ROC) analyses were performed to assess and validate the nomogram. RESULTS: In training cohort, 2009 FIGO stage, maximum length of the primary tumor, short diameter and roundness index of the maximum metastatic lymph node were independent risk factors of PFS in patients with stage IIIC1r CSCC (all P-values < 0.05). Nomogram based on them to predict 1- and 3-year PFS achieved C-indexes of 0.835 (95% confidence interval (CI): 0.809-0.862) and 0.789 (95%CI: 0.683-0.895) in the training and validation cohorts, respectively. Areas under ROC curves for the nomogram to predict 1- and 3-year PFS were 0.891 (95%CI: 0.829-0.954), 0.921 (95%CI: 0.861-0.981) in training cohort, and 0.902 (95%CI: 0.803-0.999), 0.885 (95%CI: 0.778-0.992) in validation cohort, respectively. Calibration curves indicated the nomogram predictions were in good agreement with actual observations. CONCLUSIONS: The nomogram based on MRI and clinical features has high accuracy and stability in predicting PFS of patients with stage IIIC1r CSCC.

Potential Efficacy of 68 Ga-Trivehexin PET/CT and Immunohistochemical Validation of αvß6 Integrin Expression in Patients With Head and Neck Squamous Cell Carcinoma and Pancreatic Ductal Adenocarcinoma.

PURPOSE: αvß6 integrin is exclusively expressed in epithelial cells and is upregulated in many carcinomas, such as pancreatic ductal adenocarcinomas (PDACs) and head and neck squamous cell carcinomas (H&NSCCs). Trivehexin is a recently synthesized trimerized αvß6 integrin selective nonapeptide, which can be labeled with a positron emitter like 68 Ga. This is a pilot study to assess the potential role of 68 Ga-Trivehexin PET/CT in patients with H&NSCC and PDAC and their correlation with αvß6 integrin expression by the tumor tissue on immunohistochemistry (IHC). PATIENTS AND METHODS: Thirty-two patients with suspected H&NSCC (n = 20) or PDAC (n = 12) underwent whole-body 68 Ga-Trivehexin PET/CT and 18 F-FDG PET/CT scans on 2 separate days. All 32 patients underwent biopsy from the tumor site for histopathological diagnosis and IHC for αvß6 integrin expression. The degree of αvß6 integrin expression on IHC was scored using the immunoreactive score and modified 4-point immunoreactive score classification. RESULTS: The 68 Ga-Trivehexin PET images demonstrated increased tracer uptake (mean SUV max 5.9 ± 3.3) in the primary and metastatic lesions with good lesion delineation in 8 out of the 9 cases of PDACs. However, FDG PET showed increased tracer uptake in 7 cases (6.2 ± 2.6). Among various cases of H&NSCC, increased uptakes of 68 Ga-Trivehexin (6.6 ± 4.5) and 18 F-FDG (12.7 ± 6.7) were seen in 17 out of the 18 patients. The 2 cases of inflammatory changes with suspected disease recurrence showed increased tracer uptake in 18 F-FDG PET (7.98 ± 3.1) and no significant uptake in 68 Ga-Trivehexin PET (2.2 ± 0.34).IHC showed higher expression of αvß6 integrins in lesions with higher uptake of 68 Ga-Trivehexin. A higher sensitivity, specificity, and accuracy of 68 Ga-Trivehexin PET over 18 F-FDG PET was seen for detection of primary and metastatic lesions. CONCLUSIONS: 68 Ga-Trivehexin is a promising noninvasive molecular imaging agent for tumors expressing αvß6 integrin, especially in cases where 18 F-FDG PET/CT scan may be suboptimal due to its low uptake, or due to its nonspecific uptake around tumor sites.