A prediction model based on DNA methylation biomarkers and radiological characteristics for identifying malignant from benign pulmonary nodules

Promising predictive molecular biomarkers for cervical cancer (Review)

Cervical cancer (CC) constitutes a serious public health problem. Vaccination and screening programs have notably reduced the incidence of CC worldwide by >80%; however, the mortality rate in low‑income countries remains high. The staging of CC is a determining factor in therapeutic strategies: The clinical management of early stages of CC includes surgery and/or radiotherapy, whereas radiotherapy and/or concurrent chemotherapy are the recommended therapeutic strategies for locally advanced CC. The histopathological characteristics of tumors can effectively serve as prognostic markers of radiotherapy response; however, the efficacy rate of radiotherapy may significantly differ among cancer patients. Failure of radiotherapy is commonly associated with a higher risk of recurrence, persistence and metastasis; therefore, radioresistance remains the most important and unresolved clinical problem. This condition highlights the importance of precision medicine in searching for possible predictive biomarkers to timely identify patients at risk of treatment response failure and provide tailored therapeutic strategies according to genetic and epigenetic characteristics. The present review aimed to summarize the evidence that supports the role of several proteins, methylation markers and non‑coding RNAs as potential predictive biomarkers for CC.

A novel multimodal prediction model based on DNA methylation biomarkers and low-dose computed tomography images for identifying early-stage lung cancer

Objective

DNA methylation alterations are early events in carcinogenesis and immune signalling in lung cancer. This study aimed to develop a model based on short stature homeobox 2 gene (SHOX2)/prostaglandin E receptor 4 gene (PTGER4) DNA methylation in plasma, appearance subtype of pulmonary nodules (PNs) and low-dose computed tomography (LDCT) images to distinguish early-stage lung cancers.

Methods

We developed a multimodal prediction model with a training set of 257 individuals. The performance of the multimodal prediction model was further validated in an independent validation set of 42 subjects. In addition, we explored the association between SHOX2/PTGER4 DNA methylation and driver gene mutations in lung cancer based on data from The Cancer Genome Atlas (TCGA) portal.

Results

There were significant differences between the early-stage lung cancers and benign groups in the methylation levels. The area under a receiver operator characteristic curve (AUC) of SHOX2 in patients with solid nodules, mixed ground-glass opacity nodules and pure ground-glass opacity nodules were 0.693, 0.497 and 0.864, respectively, while the AUCs of PTGER4 were 0.559, 0.739 and 0.619, respectively. With the highest AUC of 0.894, the novel multimodal prediction model outperformed the Mayo Clinic model (0.519) and LDCT-based deep learning model (0.842) in the independent validation set. Database analysis demonstrated that patients with SHOX2/PTGER4 DNA hypermethylation were enriched in TP53 mutations.

Conclusions

The present multimodal prediction model could more efficiently distinguish early-stage lung cancer from benign PNs. A prognostic index based on DNA methylation and lung cancer driver gene alterations may separate the patients into groups with good or poor prognosis.

Smart Sensors and Microtechnologies in the Precision Medicine Approach against Lung Cancer

BACKGROUND AND RATIONALE

The therapeutic interventions against lung cancer are currently based on a fully personalized approach to the disease with considerable improvement of patients' outcome. Alongside continuous scientific progresses and research investments, massive technologic efforts, innovative challenges, and consolidated achievements together with research investments are at the bases of the engineering and manufacturing revolution that allows a significant gain in clinical setting.

AIM AND METHODS

The scope of this review is thus to focus, rather than on the biologic traits, on the analysis of the precision sensors and novel generation materials, as semiconductors, which are below the clinical development of personalized diagnosis and treatment. In this perspective, a careful revision and analysis of the state of the art of the literature and experimental knowledge is presented.

RESULTS

Novel materials are being used in the development of personalized diagnosis and treatment for lung cancer. Among them, semiconductors are used to analyze volatile cancer compounds and allow early disease diagnosis. Moreover, they can be used to generate MEMS which have found an application in advanced imaging techniques as well as in drug delivery devices.

CONCLUSIONS

Overall, these issues represent critical issues only partially known and generally underestimated by the clinical community. These novel micro-technology-based biosensing devices, based on the use of molecules at atomic concentrations, are crucial for clinical innovation since they have allowed the recent significant advances in cancer biology deciphering as well as in disease detection and therapy. There is an urgent need to create a stronger dialogue between technologists, basic researchers, and clinicians to address all scientific and manufacturing efforts towards a real improvement in patients' outcome. Here, great attention is focused on their application against lung cancer, from their exploitations in translational research to their application in diagnosis and treatment development, to ensure early diagnosis and better clinical outcomes.

The presence of circulating genetically abnormal cells in blood predicts risk of lung cancer in individuals with indeterminate pulmonary nodules

PURPOSE

Computed tomography is the standard method by which pulmonary nodules are detected. Greater than 40% of pulmonary biopsies are not lung cancer and therefore not necessary, suggesting that improved diagnostic tools are needed. The LungLB™ blood test was developed to aid the clinical assessment of indeterminate nodules suspicious for lung cancer. LungLB™ identifies circulating genetically abnormal cells (CGACs) that are present early in lung cancer pathogenesis.

METHODS

LungLB™ is a 4-color fluorescence in-situ hybridization assay for detecting CGACs from peripheral blood. A prospective correlational study was performed on 151 participants scheduled for a pulmonary nodule biopsy. Mann-Whitney, Fisher's Exact and Chi-Square tests were used to assess participant demographics and correlation of LungLB™ with biopsy results, and sensitivity and specificity were also evaluated.

RESULTS

Participants from Mount Sinai Hospital (n = 83) and MD Anderson (n = 68), scheduled for a pulmonary biopsy were enrolled to have a LungLB™ test. Additional clinical variables including smoking history, previous cancer, lesion size, and nodule appearance were also collected. LungLB™ achieved 77% sensitivity and 72% specificity with an AUC of 0.78 for predicting lung cancer in the associated needle biopsy. Multivariate analysis found that clinical and radiological factors commonly used in malignancy prediction models did not impact the test performance. High test performance was observed across all participant characteristics, including clinical categories where other tests perform poorly (Mayo Clinic Model, AUC = 0.52).

CONCLUSION

Early clinical performance of the LungLB™ test supports a role in the discrimination of benign from malignant pulmonary nodules. Extended studies are underway.

Clinical Scores, Biomarkers and IT Tools in Lung Cancer Screening-Can an Integrated Approach Overcome Current Challenges?

As most lung cancer (LC) cases are still detected at advanced and incurable stages, there are increasing efforts to foster detection at earlier stages by low dose computed tomography (LDCT) based LC screening. In this scoping review, we describe current advances in candidate selection for screening (selection phase), technical aspects (screening), and probability evaluation of malignancy of CT-detected pulmonary nodules (PN management). Literature was non-systematically assessed and reviewed for suitability by the authors. For the selection phase, we describe current eligibility criteria for screening, along with their limitations and potential refinements through advanced clinical scores and biomarker assessments. For LC screening, we discuss how the accuracy of computerized tomography (CT) scan reading might be augmented by IT tools, helping radiologists to cope with increasing workloads. For PN management, we evaluate the precision of follow-up scans by semi-automatic volume measurements of CT-detected PN. Moreover, we present an integrative approach to evaluate the probability of PN malignancy to enable safe decisions on further management. As a clear limitation, additional validation studies are required for most innovative diagnostic approaches presented in this article, but the integration of clinical risk models, current imaging techniques, and advancing biomarker research has the potential to improve the LC screening performance generally.

Evaluating Histological Subtypes Classification of Primary Lung Cancers on Unenhanced Computed Tomography Based on Random Forest Model

Lung cancer is the leading cause of cancer-related death in many countries, and an accurate histopathological diagnosis is of great importance in subsequent treatment. The aim of this study was to establish the random forest (RF) model based on radiomic features to automatically classify and predict lung adenocarcinoma (ADC), lung squamous cell carcinoma (SCC), and small cell lung cancer (SCLC) on unenhanced computed tomography (CT) images. Eight hundred and fifty-two patients (mean age: 61.4, range: 29-87, male/female: 536/316) with preoperative unenhanced CT and postoperative histopathologically confirmed primary lung cancers, including 525 patients with ADC, 161 patients with SCC, and 166 patients with SCLC, were included in this retrospective study. Radiomic features were extracted, selected, and then used to establish the RF classification model to analyse and classify primary lung cancers into three subtypes, including ADC, SCC, and SCLC according to histopathological results. The training (446 ADC, 137 SCC, and 141 SCLC) and testing cohorts (79 ADC, 24 SCC, and 25 SCLC) accounted for 85% and 15% of the whole datasets, respectively. The prediction performance of the RF classification model was evaluated by F1 scores and the receiver operating characteristic (ROC) curve. On the testing cohort, the areas under the ROC curve (AUC) of the RF model in classifying ADC, SCC, and SCLC were 0.74, 0.77, and 0.88, respectively. The F1 scores achieved 0.80, 0.40, and 0.73 in ADC, SCC, and SCLC, respectively, and the weighted average F1 score was 0.71. In addition, for the RF classification model, the precisions were 0.72, 0.64, and 0.70; the recalls were 0.86, 0.29, and 0.76; and the specificities were 0.55, 0.96, and 0.92 in ADC, SCC, and SCLC. The primary lung cancers were feasibly and effectively classified into ADC, SCC, and SCLC based on the combination of RF classification model and radiomic features, which has the potential for noninvasive predicting histological subtypes of primary lung cancers.

Establishment of a malignancy and benignancy prediction model of sub-centimeter pulmonary ground-glass nodules based on the inflammation-cancer transformation theory

Background

In recent years, Chinese clinicians are frequently encountered by patients with multiple lung nodules and these intensity ground-glass nodules (GGNs) are usually small in size and some of them have no spicule sign. In addition, early lung cancer is diagnosed in large numbers of non-heavy smokers and individuals with no caner history. Obviously, the Mayo model is not applicable to these patients. The aim of the present study is to develop a new and more applicable model that can predict malignancy or benignancy of pulmonary GGNs based on the inflammation-cancer transformation theory.

Materials and methods

Included in this study were patients who underwent surgical resection or lung puncture biopsy of GGNs in Shanghai 10th People’s Hospital between January 1, 2018 and May 31, 2021 with the inclusion criterion of the maximum diameter of GGN < 1.0 cm. All the included patients had their pulmonary GGNs diagnosed by postoperative pathology. The patient data were analyzed to establish a prediction model and the predictive value of the model was verified.

Results

Altogether 100 GGN patients who met the inclusion criteria were included for analysis. Based on the results of logistic stepwise regression analysis, a mathematical predication equation was established to calculate the malignancy probability as follows: Malignancy probability rate (p) = ex/(1 + ex); p > 0.5 was considered as malignant and p ≤ 0.5 as benign, where x = 0.9650 + [0.1791 × T helper (Th) cell] + [0.2921 × mixed GGN (mGGN)] + (0.4909 × vascular convergence sign) + (0.1058 × chronic inflammation). According to this prediction model, the positive prediction rate was 73.3% and the negative prediction rate was 100% versus the positive prediction rate of 0% for the Mayo model.

Conclusion

By focusing on four major factors (chronic inflammation history, human Th cell, imaging vascular convergence sign and mGGNs), the present prediction model greatly improves the accuracy of malignancy or benignancy prediction of sub-centimeter pulmonary GGNs. This is a breakthrough innovation in this field.