Precise and automated lung cancer cell classification using deep neural network with multiscale features and model distillation.

Lung diseases globally impose a significant pathological burden and mortality rate, particularly the differential diagnosis between adenocarcinoma, squamous cell carcinoma, and small cell lung carcinoma, which is paramount in determining optimal treatment strategies and improving clinical prognoses. Faced with the challenge of improving diagnostic precision and stability, this study has developed an innovative deep learning-based model. This model employs a Feature Pyramid Network (FPN) and Squeeze-and-Excitation (SE) modules combined with a Residual Network (ResNet18), to enhance the processing capabilities for complex images and conduct multi-scale analysis of each channel's importance in classifying lung cancer. Moreover, the performance of the model is further enhanced by employing knowledge distillation from larger teacher models to more compact student models. Subjected to rigorous five-fold cross-validation, our model outperforms existing models on all performance metrics, exhibiting exceptional diagnostic accuracy. Ablation studies on various model components have verified that each addition effectively improves model performance, achieving an average accuracy of 98.84% and a Matthews Correlation Coefficient (MCC) of 98.83%. Collectively, the results indicate that our model significantly improves the accuracy of disease diagnosis, providing physicians with more precise clinical decision-making support.

Purulent Pericarditis as the First Manifestation of Esophageal Carcinoma.

INTRODUCTION: Purulent pericarditis secondary to esophago-pericardial fistula is a serious complication that has been previously reported in patients with esophageal cancer treated with radio/chemotherapy and esophageal stenting. However, the presence of esophago-pericardial fistula as the first manifestation of advanced carcinoma of the esophagus is exceedingly infrequent. We report the case of a 61-year-old male who presented with sepsis, cardiac tamponade and septic shock who was found to have an esophago-pericardial fistula secondary to squamous carcinoma of the esophagus. Emergency pericardiocentesis was performed with subsequent hemodynamic improvement. The drained pericardial fluid was purulent in nature and cultures were positive for Streptococcus anginosus. A CT scan followed by upper gastrointestinal endoscopy with tissue biopsy confirmed the diagnosis of squamous cell carcinoma of the esophagus. A self-expanding covered stent was endoscopically placed to exclude the fistula and restore the esophageal lumen. In this report, we discuss some aspects related to the diagnosis and management of this serious clinical entity.

Use of digital strategies in the diagnosis of oral squamous cell carcinoma: a scoping review.

Telediagnosis uses information and communication technologies to support diagnosis, shortening geographical distances. It helps make decisions about various oral lesions. The objective of this scoping review was to map the existing literature on digital strategies to assist in the diagnosis of oral squamous cell carcinoma. this review was structured based on the 5-stage methodology proposed by Arksey and O'Malley, the Joanna Briggs Institute Manual for Evidence Synthesis and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews. The methods were registered on the Open Science Framework. The research question was: What digital strategies have been used to assist in the diagnosis of oral squamous cell carcinoma? The search was conducted on PubMed/MEDLINE, Scopus, Web of Science, Embase, and ScienceDirect. Inclusion criteria comprised studies on telediagnosis, teleconsultation or teleconsultation mediated by a professional and studies in English, without date restrictions. The search conducted in June 2023 yielded 1,798 articles, from which 16 studies were included. Telediagnosis was reported in nine studies, involving data screening through applications, clinical images from digital cameras, mobile phones or artificial intelligence. Histopathological images were reported in four studies. Both, telediagnosis and teleconsultation, were mentioned in seven studies, utilizing images and information submission services to platforms, WhatsApp or applications. One study presented teleconsultations involving slides and another study introduced teleconsultation mediated by a professional. Digital strategies telediagnosis and teleconsultations enable the histopathological diagnosis of oral cancer through clinical or histopathological images. The higher the observed diagnostic agreement, the better the performance of the strategy.

Human epididymal protein 4 and its combined detection show good diagnostic value in lung cancer: A retrospective study.

OBJECTIVES: This study aimed to assess the diagnostic value of human epididymal protein 4 (HE4), a potential novel biomarker for lung cancer, and its combined detection with five other conventional biomarkers in lung cancer diagnosis and subtyping. METHODS: In this retrospective study, 115 lung cancer patients, 50 patients with benign pulmonary disease, and 50 healthy controls were included. Serum HE4, progastrin-releasing peptide (ProGRP), squamous cell carcinoma (SCC) antigen, cytokeratin-19 fragment (CYFRA21-1), neuron-specific enolase (NSE), and carcinoembryonic antigen (CEA) were analyzed using the electrochemiluminescence immunoassay and chemiluminescence immunoassay. The receiver operating characteristic curve was performed to analyze the diagnostic efficacy of individual biomarkers in identifying both lung cancer and its histologic subtypes. RESULTS: All six biomarkers showed significantly elevated levels in the lung cancer group compared to both benign pulmonary disease and control groups (P < 0.05). Among the biomarkers evaluated, HE4 exhibited the highest diagnostic performance for lung cancer, lung adenocarcinoma, and lung squamous cell carcinoma with area under the curve (AUC) values of 0.921, 0.891, and 0.937, respectively. ProGRP was the optimal biomarker for small cell lung cancer with an AUC of 0.973. The combination of all six biomarkers yielded the largest AUCs in the diagnosis of lung cancer subtypes (0.937 for lung adenocarcinoma, 0.998 for lung squamous cell carcinoma, and 0.985 for small cell lung cancer). Furthermore, specific combinations, such as HE4 + CEA, HE4 + SCC, and ProGRP + HE4 + NSE, showed strong diagnostic performance in lung cancer. CONCLUSIONS: HE4 and its combined detection held substantial clinical significance in the diagnosis of lung cancer and its histologic subtyping, especially for lung adenocarcinoma and lung squamous cell carcinoma.

Photodynamic application in diagnostic procedures and treatment of non-melanoma skin cancers.

OPINION STATEMENT: Skin tumors commonly seen in dermatology are involved in all layers of the skin and appendages. While biopsy of affected skin remains an essential method to confirm diagnosis and to predicate tumor prognosis, it has its limitations. Recently, photodynamic diagnosis (PDD) has demonstrated high sensitivity in detecting affected skin and mucosal tissues, providing valuable guidance for precision surgery to resect skin and mucosal tumors. In this review, we summarized the literatures concerning the applications of PDD in diagnostic process and treatment of skin and mucosal conditions such as actinic keratoses (AK), basal cell carcinoma (BCC), squamous cell carcinoma (SCC), Bowen's disease (BD) and extramammary Paget's disease (EMPD). The findings suggest that PDD holds substantial promise for expanding clinical applications and deserves further research exploration.

[Severe Conjunctival and Corneal Epithelial Dysplasia: A Case Series]. / Schwere konjunktivale und korneale epitheliale Dysplasie: eine Fallserie.

BACKGROUND/OBJECTIVES: Ocular surface squamous neoplasia (OSSN) are among the most frequent non-pigmented malignancies of the ocular surface. They have a wide range of histological characteristics - ranging from mild epithelial dysplasia to invasive carcinoma of the squamous cells of the cornea. They may be restricted to the conjunctiva or also involve the cornea. As there are no leading symptoms in the early stages, diagnosis may be very delayed in patients who do not receive regular ophthalmological treatment. The present case series describes clinical and histological data on OSSN and includes clinical and histological data on OSSN, including possible clinical presentations, important risk factors, special histological and cytological features and therapeutic options. METHODS: Retrospective case series of patients with histologically confirmed severe epithelial dysplasia of the conjunctiva and cornea consistent with OSSN who presented to the Department of Ophthalmology in Basel University Hospital. The analysis covered demographic data, symptoms, diagnostic testing (photo documentation, brush biopsy), treatment and cytological and/or histological material and findings. RESULTS: We report on five patients aged between 41 and 92 years at the time of diagnosis. The histological findings in all patients included severe epithelial dysplasia, but with a heterogenous clinical presentation. In all cases, the lesion started in the conjunctiva, but traversed the limbus and extended to the cornea. The primary treatment was always surgical removal. In one patient, this had to be repeated several times due to recurrent metaplasia and was complemented by subsequent mitomycin C therapy. The clinical outcome ranged between total restitution of the original state to inevitable enucleation. CONCLUSION: The clinical presentation of OSSN is highly heterogenous, so that the initial diagnosis is difficult. There are no official guidelines for treatment, so that the treatment of choice varied between clinics. Regular ophthalmological follow-ups are recommended, even after complete surgical excision. Possible relevant concomitant diseases and risk factors must be identified before therapy.

Oral Cavity Squamous Cell Carcinoma: Review of Pathology, Diagnosis, and Management.

Squamous cell carcinoma of the oral cavity presents a significant global health burden, primarily due to risk factors such as tobacco smoking, smokeless tobacco use, heavy alcohol consumption, and betel quid chewing. Common clinical manifestations of oral cavity cancer include visible lesions and sores, often accompanied by pain in advanced stages. Diagnosis relies on a comprehensive assessment involving detailed history, physical examination, and biopsy. Ancillary imaging studies and functional evaluations aid in accurate staging and facilitate treatment planning. Prognostic information is obtained from histopathological factors, such as tumor grade, depth of invasion, lymphovascular invasion, and perineural invasion. Notably, lymph node metastasis, found in approximately half of the patients, carries significant prognostic implications. Effective management necessitates a multidisciplinary approach to optimize patient outcomes. Surgical resection is the backbone of treatment, aimed at complete tumor removal while preserving functional outcomes. Adjuvant therapies, including radiation and chemotherapy, are tailored according to pathological factors. Further work in risk stratification and treatment is necessary to optimize outcomes in squamous cell carcinoma of the oral cavity.

Six-Gene Signature for Differential Diagnosis and Therapeutic Decisions in Non-Small-Cell Lung Cancer-A Validation Study.

Non-small-cell lung cancer (NSCLC) poses a challenge due to its heterogeneity, necessitating precise histopathological subtyping and prognostication for optimal treatment decision-making. Molecular markers emerge as a potential solution, overcoming the limitations of conventional methods and supporting the diagnostic-therapeutic interventions. In this study, we validated the expression of six genes (MIR205HG, KRT5, KRT6A, KRT6C, SERPINB5, and DSG3), previously identified within a 53-gene signature developed by our team, utilizing gene expression microarray technology. Real-time PCR on 140 thoroughly characterized early-stage NSCLC samples revealed substantial upregulation of all six genes in squamous cell carcinoma (SCC) compared to adenocarcinoma (ADC), regardless of clinical factors. The decision boundaries of the logistic regression model demonstrated effective separation of the relative expression levels between SCC and ADC for most genes, excluding KRT6C. Logistic regression and gradient boosting decision tree classifiers, incorporating all six validated genes, exhibited notable performance (AUC: 0.8930 and 0.8909, respectively) in distinguishing NSCLC subtypes. Nevertheless, our investigation revealed that the gene expression profiles failed to yield predictive value regarding the progression of early-stage NSCLC. Our molecular diagnostic models manifest the potential for an exhaustive molecular characterization of NSCLC, subsequently informing personalized treatment decisions and elevating the standards of clinical management and prognosis for patients.

Assessing Circulating Tumour DNA (ctDNA) as a Biomarker for Anal Cancer Management: A Systematic Review.

This systematic review investigates the potential of circulating tumour DNA (ctDNA) as a predictive biomarker in the management and prognosis of squamous cell carcinoma of the anal canal (SCCA). PubMed, EMBASE, and Cochrane Central Registry of Controlled Trials were searched until 7 January 2024. Selection criteria included research articles exploring ctDNA in the context of anal cancer treatment response, recurrence risk assessment, and consideration of salvage surgery. A total of eight studies were therefore included in the final review, examining a total of 628 patients. These studies focused on three main themes: SCCA diagnosis and staging, treatment response, and patient outcomes. Significant heterogeneity was observed in terms of patient cohort, study methodology, and ctDNA biomarkers. Four studies provided information on the sensitivity of ctDNA biomarkers in SCCA, with a range of 82-100%. Seven studies noted a correlation between pre-treatment ctDNA levels and SCCA disease burden, suggesting that ctDNA could play a role as a biomarker for the staging of SCCA. Across all seven studies with paired pre- and post-treatment ctDNA samples, a trend was seen towards decreasing ctDNA levels post-treatment, with specific identification of a 'fast elimination' group who achieve undetectable ctDNA levels prior to the end of treatment and may be less likely to experience treatment failure. Residual ctDNA detection post-treatment was associated with poorer patient prognosis. This systematic review identifies the broad potential of ctDNA as a useful and decisive tool in the management of SCCA. Further analysis of ctDNA biomarkers that include larger patient cohorts is required in order to clearly evaluate their potential role in clinical decision-making processes.

Sentinel lymph node biopsy versus observation in high risk cutaneous squamous cell carcinoma of head and neck: a propensity score matching analysis.

Sentinel lymph node biopsy (SLNB) has gained considerable attention in the management of head and neck cutaneous squamous cell carcinoma (HNcSCC). The aim of this study was to compare the oncologic outcomes between observation and SLNB in cN0 high-risk HNcSCC patients. We retrospectively enrolled patients from the SEER database and evaluated the impact of observation versus SLNB on disease-specific survival (DSS) and overall survival (OS) using a Propensity Score Matching (PSM) analysis. A total of 9804 patients were included, with 1169 cases treated by SLNB. Successful retrieval of the sentinel lymph node was achieved in 1130 procedures. After PSM and subsequent multivariate analysis, SLNB was found to be an independent predictor for improved DSS, with a hazard ratio of 0.70 (95% confidence interval: 0.56-0.86). In patients presenting with two or three high-risk factors, SLNB was associated with better DSS (p = 0.021 and p = 0.044), but similar OS (p = 0.506 and p = 0.801) when compared to observation. However, in patients exhibiting four high-risk factors, SLNB demonstrated significantly improved DSS (p = 0.040) and OS (p = 0.028) compared to observation. Our findings suggest that SLNB is a highly feasible technique in HNcSCC and provides significant survival benefits. It is strongly recommended in patients with two or more high-risk factors, as it can help guide treatment decisions and improve patient outcomes.

Applying Machine Learning for Enhanced MicroRNA Analysis: A Companion Risk Tool for Oral Squamous Cell Carcinoma in Standard Care Incisional Biopsy.

Machine learning analyses within the realm of oral cancer outcomes are relatively underexplored compared to other cancer types. This study aimed to assess the performance of machine learning algorithms in identifying oral cancer patients, utilizing microRNA expression data. In this study, we implemented this approach using a panel of oral cancer-associated microRNAs sourced from standard incisional biopsy specimens to identify cases of oral squamous cell carcinomas (OSCC). For the model development process, we used a dataset comprising 30 OSCC and 30 histologically normal epithelium (HNE) cases. We initially trained a logistic regression prediction model using 70 percent of the dataset, while reserving the remaining 30 percent for testing. Subsequently, the model underwent hyperparameter tuning resulting in enhanced performance metrics. The hyperparameter-tuned model exhibited high accuracy (0.894) and ROC AUC (0.898) in predicting OSCC. Testing the model on cases of potentially malignant disorders (OPMDs) revealed that leukoplakia with mild dysplasia was predicted as having a high risk of progressing to OSCC, emphasizing machine learning's advantage over histopathology in detecting early molecular changes. These findings underscore the necessity for further refinement, incorporating a broader set of variables to enhance the model's predictive capabilities in assessing the risk of oral potentially malignant disorders.

Update on Oral and Oropharyngeal Cancers: A guide for oral health care providers.

Oral squamous cell carcinomas (OSCC) signs and symptoms may be first identified by dental hygienists during routine extra and intra-oral examinations. A comprehensive extra-oral and intra-oral examination during regular dental hygiene assessment is paramount to identifying oral potentially malignant disorders (OPMD) and cancerous lesions for timely referral and treatment. Integrating a systematic list of questions during the medical and dental assessment along with careful visual and tactile examinations is critical to identifying OPMDs and cancerous lesions. Understanding the relationship between oropharyngeal squamous cell carcinomas (OPSCC) and Human Papilloma Virus (HPV) and how vaccination can prevent HPV-related OPSCC is critical to providing evidence-based recommendations and care. The purpose of this report is to provide an update on current epidemiological trends of OSCC and OPSCC rates in the United States (US) and provide the latest evidence on what dental hygienists must know to improve health outcomes and mitigate the consequences of undiagnosed cancer. This report considers enduring challenges with the annual rise in OPSCC rates and the public health burden of HPV-related cancers in the US. Emphasis on regular, quality continuing education about OSCC and OPSCC is emphasized along with recommendations for evidence-based training.

Near-infrared hyperspectral imaging and robust statistics for in vivo non-melanoma skin cancer and actinic keratosis characterisation.

One of the most common forms of cancer in fair skinned populations is Non-Melanoma Skin Cancer (NMSC), which primarily consists of Basal Cell Carcinoma (BCC), and cutaneous Squamous Cell Carcinoma (SCC). Detecting NMSC early can significantly improve treatment outcomes and reduce medical costs. Similarly, Actinic Keratosis (AK) is a common skin condition that, if left untreated, can develop into more serious conditions, such as SCC. Hyperspectral imagery is at the forefront of research to develop non-invasive techniques for the study and characterisation of skin lesions. This study aims to investigate the potential of near-infrared hyperspectral imagery in the study and identification of BCC, SCC and AK samples in comparison with healthy skin. Here we use a pushbroom hyperspectral camera with a spectral range of ≈ 900 to 1600 nm for the study of these lesions. For this purpose, an ad hoc platform was developed to facilitate image acquisition. This study employed robust statistical methods for the identification of an optimal spectral window where the different samples could be differentiated. To examine these datasets, we first tested for the homogeneity of sample distributions. Depending on these results, either traditional or robust descriptive metrics were used. This was then followed by tests concerning the homoscedasticity, and finally multivariate comparisons of sample variance. The analysis revealed that the spectral regions between 900.66-1085.38 nm, 1109.06-1208.53 nm, 1236.95-1322.21 nm, and 1383.79-1454.83 nm showed the highest differences in this regard, with <1% probability of these observations being a Type I statistical error. Our findings demonstrate that hyperspectral imagery in the near-infrared spectrum is a valuable tool for analyzing, diagnosing, and evaluating non-melanoma skin lesions, contributing significantly to skin cancer research.

Diagnosis and therapy of actinic keratosis.

Actinic keratosis (AK) is considered a chronic and recurring in situ skin neoplasia, with a possible transformation into invasive squamous cell carcinoma (SCC). Among others, predominant risk factors for development of AK are UV-light exposure and immunosuppression. Basal epidermal keratinocyte atypia (AK I) and proliferation (PRO score) seem to drive malignant transformation, rather than clinical appearance of AK (Olsen I-III). Due to the invasiveness of punch biopsy, those histological criteria are not regularly assessed. Non-invasive imaging techniques, such as optical coherence tomography (OCT), reflectance confocal microscopy (RCM) and line-field confocal OCT (LC-OCT) are helpful to distinguish complex cases of AK, Bowen's disease, and SCC. Moreover, LC-OCT can visualize the epidermis and the papillary dermis at cellular resolution, allowing real-time PRO score assessment. The decision-making for implementation of therapy is still based on clinical risk factors, ranging from lesion- to field-targeted and ablative to non-ablative regimens, but in approximately 85% of the cases a recurrence of AK can be observed after a 1-year follow-up. The possible beneficial use of imaging techniques for a non-invasive follow-up of AK to detect recurrence or invasive progression early on should be subject to critical evaluation in further studies.

NMR and MS reveal characteristic metabolome atlas and optimize esophageal squamous cell carcinoma early detection.

Metabolic changes precede malignant histology. However, it remains unclear whether detectable characteristic metabolome exists in esophageal squamous cell carcinoma (ESCC) tissues and biofluids for early diagnosis. Here, we conduct NMR- and MS-based metabolomics on 1,153 matched ESCC tissues, normal mucosae, pre- and one-week post-operative sera and urines from 560 participants across three hospitals, with machine learning and WGCNA. Aberrations in 'alanine, aspartate and glutamate metabolism' proved to be prevalent throughout the ESCC evolution, consistently identified by NMR and MS, and reflected in 16 serum and 10 urine metabolic signatures in both discovery and validation sets. NMR-based simplified panels of any five serum or urine metabolites outperform clinical serological tumor markers (AUC = 0.984 and 0.930, respectively), and are effective in distinguishing early-stage ESCC in test set (serum accuracy = 0.994, urine accuracy = 0.879). Collectively, NMR-based biofluid screening can reveal characteristic metabolic events of ESCC and be feasible for early detection (ChiCTR2300073613).

Prognosis and prognostic factors of lung cancer complications in patients with rheumatoid arthritis.

AIM: To clarify the prognosis and prognostic factors for lung cancer in patients with rheumatoid arthritis (RA). METHODS: In this retrospective longitudinal study, we investigated the medical records of patients with RA among 1422 patients diagnosed with lung cancer and registered in a hospital-based cancer registry between January 2013 and May 2022. The Kaplan-Meier method and Cox proportional hazards model were used to analyze survival and identify predictive factors. RESULTS: Of 26 patients with RA complicated with lung cancer (median age, 69 years), the 2-year overall survival rates for stages I-II were 90%-100%, and those for stages III-IV were 20%, respectively. Positivity of anti-citrullinated protein/peptide antibody, smoking history, interstitial lung disease, poorly controlled RA, stage III and IV lung cancer, histological types other than adenocarcinoma and squamous cell carcinoma, and RF ≧ 50 IU/mL were associated with increased mortality. After the surgical resection of stage I and II lung cancer, 5 of the 16 patients experienced cancer recurrence after resumption of RA treatment, and the histology of the recurrent cancers was mostly squamous cell carcinoma. CONCLUSIONS: Early detection of lung cancer is needed, especially in patients with RA who have a history of smoking, seropositivity, or interstitial lung disease. Even after surgical resection, it should be noted that squamous cell carcinoma is prone to recurrence.

Perineural Infiltration: A Comprehensive Review of Diagnostic, Prognostic, and Therapeutic Implications.

ABSTRACT: Perineural infiltration refers to a neoplastic cell involvement in, around, and through the nerves. It is considered as one of the neoplastic dissemination pathways. Thus, its identification is crucial to establish the prognosis of some malignant skin neoplasms, such as squamous cell carcinoma, and explains the locally aggressive behavior of cutaneous neoplasms, such as microcystic adnexal carcinoma. We have conducted a review of malignant and benign skin tumors in which perineural infiltration has been described, and we also discuss some histopathological findings that may simulate perineural infiltration.