Sputum cytology in suspected cases of carcinoma of lung (Sputum cytology a poor man's bronchoscopy!)

Omics-based deep learning approaches for lung cancer decision-making and therapeutics development

Lung cancer has been the most common and the leading cause of cancer deaths globally. Besides clinicopathological observations and traditional molecular tests, the advent of robust and scalable techniques for nucleic acid analysis has revolutionized biological research and medicinal practice in lung cancer treatment. In response to the demands for minimally invasive procedures and technology development over the past decade, many types of multi-omics data at various genome levels have been generated. As omics data grow, artificial intelligence models, particularly deep learning, are prominent in developing more rapid and effective methods to potentially improve lung cancer patient diagnosis, prognosis and treatment strategy. This decade has seen genome-based deep learning models thriving in various lung cancer tasks, including cancer prediction, subtype classification, prognosis estimation, cancer molecular signatures identification, treatment response prediction and biomarker development. In this study, we summarized available data sources for deep-learning-based lung cancer mining and provided an update on recent deep learning models in lung cancer genomics. Subsequently, we reviewed the current issues and discussed future research directions of deep-learning-based lung cancer genomics research.

Detection of early (T1) lung cancers and lepidic adenocarcinomas in sputum and bronchial cytology

BACKGROUND

The lung is an extensively epithelialized organ, producing ample exfoliated material for sputum and bronchial cytology. In view of the updates in the World Health Organization classification of early (T1/≤ 3 cm) lung cancer with respect to adenocarcinomas with lepidic pattern, this study retrospectively reviews sputum and bronchial cytology paired with resection-confirmed lung cancers.

METHODS

A computerized search for all lung resection specimens of carcinomas over a 20-year period was performed. Cytologic diagnoses of corresponding sputum and bronchial cytology were classified into five-tiered categories (C1-insufficient/inadequate, C2-benign, C3-atypia, C4-suspicious and C5-malignant). Reports and slides of the resection specimen were reviewed for reclassification of T1 cancers.

RESULTS

Totally 472 and 383 sputum and bronchial cytology specimens respectively were included. Sensitivity for T1 lesions on sputum cytology were 10.6 %, 2.1 % and 0.5 % at cutoffs of atypia/C3, suspicious/C4 and malignant/C5 categories, lower than bronchial cytology (35.1 %, 15.5 %, 8.1 %; p < 0.001). T1 lesions correlated with lower detection rates, whereas squamous cell carcinoma histology, larger size and bronchial invasion were associated with increased detection rates in sputum and bronchial cytology (p < 0.050). Detection rates for abrasive bronchial cytology (brushing) were overall higher (p = 0.018- < 0.001), but on subgroup comparison, non-abrasive (aspiration, lavage and washing) cytology demonstrated favorable trends (p = 0.063-0.088) in detecting T1 lesions. Adenocarcinomas with lepidic pattern had lower suspicious/C4 (p = 0.040) or above and malignant/C5 (p = 0.019), but not atypia/C3 or above (p = 0.517) rates.

CONCLUSIONS

Most adenocarcinomas with lepidic pattern are only diagnosed as atypia/C3 on cytology. With its modest sensitivity, interpretation of negative and indeterminate cytology results mandates caution.

Novel Screening Tools for Lung Cancer

Screening with low-dose computed tomography has been shown to decrease lung cancer mortality. However, the issues of low detection rates and false positive results remain, highlighting the need for adjunctive tools in lung cancer screening. To this end, researchers have investigated easily applicable, minimally invasive tests with high validity. We herein review some of the more promising novel markers utilizing plasma, sputum, and airway samples.

Can combined non-invasive methods improve diagnosis of lung cancer?

Background

Lung cancer is the most common malignancy in both gender. Early diagnosis is needed to reduce morbidity and mortality. There is a debate about the most accurate investigating modality for the diagnosis of lung cancer.

Methods

It is a retrospective cohort analysis to determine whether an approach of combined contrast-enhanced computed tomography (CECT) thorax with bronchoscopy method has higher sensitivity and specificity than combined CECT thorax with sputum cytology method. Records of patients with lung cancer who had visited the hospital within the last 6 months were retrospectively analyzed for their diagnostic modality. SPSS version 19 software was used for statistical analysis of the data. CECT scan thorax, bronchoscopy, and sputum cytology for lung cancer patients were analyzed. The CECT thorax plus bronchoscopy method was compared with the CECT thorax plus sputum cytology method. Their sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in diagnosing lung cancer were analyzed.

Results

Sixty-two patients were considered, including 62.9% males with a mean age of 55.5 years. In patients diagnosed with lung cancer, CECT thorax combined with bronchoscopy method was found to have a sensitivity of 96.67% than CECT thorax combined with sputum cytology method with a sensitivity of 90% and the difference in sensitivity between all individual approaches as well as the combined method was statistically significant with a P = 0.00001 and Chi-square value of 86.5909 owing to the low sensitivity of sputum cytology. CECT thorax combined with sputum cytology approach had a better specificity than CECT thorax combined with bronchoscopy.

Conclusion

Combined CECT thorax with sputum cytology method has a better specificity in diagnosing lung cancer than combined CECT thorax with bronchoscopy method.

A 56-Year-Old Man With Chronic Cough, Hemoptysis, and a Left Lower Lobe Infiltrate

CASE PRESENTATION

A 56-year-old man presented to the lung nodule clinic with abnormal chest imaging prompted by a chronic cough and hemoptysis. Approximately 2.5 years earlier, while kneeling beside his car fixing a flat tire, he fell backwards while holding the tire cap in his mouth, causing him to inhale sharply and aspirate the cap. He immediately developed an intractable cough productive of flecks of blood. He presented to an emergency room but left before being seen because of a long wait time and his lack of health-care insurance. He self-medicated for severe cough and chest discomfort with codeine, eventually developing a dependency. Approximately 3 weeks after aspirating the tire cap, his cough became productive, and he developed fever and chills. His symptoms improved transiently with antibiotics and additional narcotics. Ultimately, his chronic cough with intermittent hemoptysis affected his ability to work, and 30 months later he sought medical attention and was diagnosed with pneumonia and reactive airway disease. He was prescribed doxycycline, steroids, inhaled albuterol, and dextromethorphan, with initial improvement, but his symptoms recurred multiple times despite quitting smoking, leading to repeated medication courses.

Molecular sputum analysis for the diagnosis of lung cancer

Lung cancer is the leading cause of cancer mortality rate worldwide, mainly because of the presence of metastatic disease at the time of diagnosis. Early detection of lung cancer improves prognosis, and towards this end, large screening trials in high-risk individuals have been conducted since the past century. Despite all efforts, the need for novel (complementary) lung cancer diagnostic and screening methods still exists. In this review, we focus on the assessment of lung cancer-related biomarkers in sputum in the past decennium. Besides cytology, mutation and microRNA analysis, special attention has been paid to DNA promoter hypermethylation, of which all available literature is summarised without time restriction. A model is proposed to aid in the distinction between diagnostic and risk markers. Research on the use of sputum for non-invasive detection of early-stage lung cancer has brought new insights and advanced molecular techniques. The sputum shows a promising potential for routine diagnostic and possibly screening purposes.

Advances in cytopathology for lung cancer: the impact and challenges of new technologies

Despite recent advances in treatment modalities, the survival rate of patients with lung cancer has not significantly improved. Therefore, new avenues are being explored in the era of evolving personalized patient management by early detection. Cytology is now the mainstay to address the diagnostic needs of pulmonary malignancies. Cytology specimens deliver diagnostic results equivalent to tissue biopsies. Fine-needle aspirations are equally useful to perform diagnostic, predictive, and prognostic immunohistochemical markers and molecular analysis. This article reviews the main new technologies that produced this revolution. The new role of the cytopathologist in this time of interdisciplinary care is also discussed.