Detection Of Lung Cancer Research Articles

Design of novel convolution neural network model for lung cancer detection by using sensitivity maps

<p>Despite the existence of numerous models for detecting lung cancer, there is still room for achieving higher levels of accuracy. In this paper, a maximum sensitivity neural network (MSNN) has been proposed. As the name suggests, the model aims to achieve high sensitivity and offers a viable remedy to minimize the number of false positive in oder to improve the overall accuracy for lung cancer detection. The MSNN model is a promising model since it can efficiently interpret grayscale lung computed tomography (CT) scan images as inputs and can be trained using just a few images also. This model has surpassed previous deep learning models by obtaining a remarkable sensitivity of 94.6% and an accuracy of 96.9%. A sensitivity map is created, offering important insights into the critical regions for finding malignant nodules. This innovative method has shown outstanding performance in identifying lung cancer with a low false positive rate which can increase the accuracy of medical diagnoses.</p>

Gender-specific outcomes of low-dose computed tomography screening for lung cancer detection: A retrospective study in Chinese never-smoker population.

Low-dose computed tomography (LDCT) has emerged as a pivotal tool for detecting lung cancer among ever-smokers. This study aims to evaluate the gender-specific outcomes of LDCT screening within the Chinese never-smoking population. We conducted a single-center, retrospective cohort study, which analyzed LDCT screening outcomes for 42,018 asymptomatic participants. Specifically, we focused on assessing gender-specific differences in the prevalence of pulmonary nodules, and the incidence of lung cancer diagnosis among never-smokers. Among the 42,018 eligible participants, 41.50% were females and 58.50% were males. Most participants were non-smokers (77.57%), with a significantly higher proportion of non-smokers among females than males (99.33% vs. 62.14%). Pulmonary nodules were identified in 2.66% of participants, with a higher prevalence in females (2.99%) than males (2.43%) (p < 0.001). Non-smoking females had a higher incidence of positive nodules than non-smoking males (2.98% vs. 2.38%, p < 0.001). Invasive biopsies were performed in 334 individuals with nodules, confirming lung cancer in 258 cases. The majority of these cancer cases were non-smokers (212), with non-smoking females showing a higher incidence (0.85%) compared to males (0.43%) (p < 0.001). There was no significant difference in the false-positive rates between non-smoking females (0.14%) and males (0.13%). Multivariate analysis showed that never-smoking women were more likely to undergo biopsies (OR 1.65, p = 0.0016) and had a higher, though not statistically significant, probability of lung cancer diagnosis (OR 1.84, p = 0.06). This study elucidates sex-based differences within the Chinese population, revealing a higher prevalence of pulmonary nodules and lung cancers among non-smoking females. These findings offer valuable reference for both clinical practice and future research initiatives.

Automatic Lung Cancer Detection Using Computed Tomography Based on Chan Vese Segmentation and SENET

Automatic Lung Cancer Detection Using Computed Tomography Based on Chan Vese Segmentation and SENET

Emphysema and lung cancer risk.

With increasing significance of lung cancer screening programs, it is essential to determine the group of participants, who would benefit the most from screening. In our study, we aimed to establish the correlation between lung emphysema and lung cancer risk. The study design was cross-sectional. Low-dose computed tomography (LDCT) scans of 896 subjects from MOLTEST-BIS lung cancer screening program, including 100 subjects with detected lung cancer, were visually evaluated for the presence, type and severity of emphysema. Quantitative emphysema evaluation was performed with Siemens syngo.via Pulmo 3D application. Visually detected presence of centrilobular emphysema (CLE) correlated with male gender (P=0.02), age (P<0.001) and pack-years of smoking (P=0.004), as well as with quantitative assessment of Emphysema Index (EI) (P=0.008), and with emphysema clusters of given size (Clas 1-4) Clas 1, Clas 3 and Clas 4 (P<0.001). Visually assessed severity grade of emphysema correlated with age (P<0.001), pack-years of smoking history (P=0.002) and EI (P<0.001). There was a correlation between lung cancer occurrence and pack-years (P<0.001), age (P<0.001), and presence of CLE (P<0.001) but no correlation with gender (P=0.88) and EI (P=0.32) was found. In the logistic regression model pack-years, age, qualitative severity of CLE and Clas 1 were significant factors correlated with lung cancer occurrence (P<0.001). Qualitative and quantitative emphysema evaluation correlate with each other. Both, presence and severity of CLE correlate with higher incidence of lung cancer. Severity of visually assessed emphysema, age and pack-years of smoking are significant predictors of lung cancer occurrence.

Robotic-assisted bronchoscopy: a narrative review of systems.

Robotic-assisted bronchoscopy (RAB) has emerged as an advanced technology for lung cancer diagnosis. This review explores the three approved robotic bronchoscopy systems: Ion™ Endoluminal (Intuitive Surgical, Sunnyvale, CA, USA), Monarch™ (Johnson & Johnson, Redwood City, CA, USA), and Galaxy System™ (Noah Medical, San Carlos, CA, USA), and their different operational systems. This narrative review aims to summarize their findings and outcomes for sampling peripheral pulmonary lesions (PPL) suspected of lung cancer. A search in PubMed and Google Scholar databases was conducted for articles and abstracts published between January 2018 to May 2024 using the terms "robotic bronchoscopy" or "robotic-assisted bronchoscopy" for biopsy of PPL. Lung cancer is the leading cause of cancer-related mortality. The introduction of RAB aims to improve the feasibility and safety of sampling PPL. Current literature describes high diagnostic yields with low risk of complications, allowing concurrent hilar and mediastinal staging within the same procedure. RAB can potentially improve early diagnosis and treatment of pulmonary malignancies and survival rate in long term, while progressing towards therapeutic applications in the near future. As RAB evolves, its potential as a "one-stop shop" for diagnosis, staging, and treatment can positively impact lung cancer detection, focusing on improved patient-centered outcomes and reducing multiple diagnostic and therapeutic procedures.

Vision Transformer Based Effective Model for Early Detection and Classification of Lung Cancer

Vision Transformer Based Effective Model for Early Detection and Classification of Lung Cancer

Application of artificial intelligence in lung cancer screening: A real-world study in a Chinese physical examination population.

With the rapid increase of chest computed tomography (CT) images, the workload faced by radiologists has increased dramatically. It is undeniable that the use of artificial intelligence (AI) image-assisted diagnosis system in clinical treatment is a major trend in medical development. Therefore, in order to explore the value and diagnostic accuracy of the current AI system in clinical application, we aim to compare the detection and differentiation of benign and malignant pulmonary nodules between AI system and physicians, so as to provide a theoretical basis for clinical application. Our study encompassed a cohort of 23 336 patients who underwent chest low-dose spiral CT screening for lung cancer at the Health Management Center of West China Hospital. We conducted a comparative analysis between AI-assisted reading and manual interpretation, focusing on the detection and differentiation of benign and malignant pulmonary nodules. The AI-assisted reading exhibited a significantly higher screening positive rate and probability of diagnosing malignant pulmonary nodules compared with manual interpretation (p < 0.001). Moreover, AI scanning demonstrated a markedly superior detection rate of malignant pulmonary nodules compared with manual scanning (97.2% vs. 86.4%, p < 0.001). Additionally, the lung cancer detection rate was substantially higher in the AI reading group compared with the manual reading group (98.9% vs. 90.3%, p < 0.001). Our findings underscore the superior screening positive rate and lung cancer detection rate achieved through AI-assisted reading compared with manual interpretation. Thus, AI exhibits considerable potential as an adjunctive tool in lung cancer screening within clinical practice settings.

Enhanced adsorption of lung cancer biomarkers using Biphenyl-Derived quantum dots

This study explores the interaction between biphenyl quantum dot (BP-B2B1) and lung cancer biomarkers (LCBs), specifically methanal, ethanal, and propanal. The investigation involves optimizing the structures of BP-B2B1 and its doped variants (with B, N, O, P, S, and Si) to assess their stability and electronic properties. Natural bond orbital (NBO) analysis reveals significant charge transfer from BP-B2B1 and its doped forms to the LCBs upon adsorption, indicating enhanced interaction. Optical properties are examined through shifts in absorption spectra and excited states, showing that doping affects the electronic structure and interaction with LCBs. Non-covalent interaction (NCI) analysis provides insights into the nature of the interactions, identifying predominant van der Waals forces between BP-B2B1 and the LCBs. The results demonstrate that dopants enhance the binding and electronic response of BP-B2B1 to LCBs, highlighting its potential for use in biosensing applications for lung cancer detection.

The Promising Role of Artificial Intelligence in Navigating Lung Cancer Prognosis

Incorporating AI in lung cancer management is a disruptive innovation that has improved diagnosis accuracy, prognosis prediction and treatment modalities. In this literature review, we seek to identify the role of artificial intelligence (AI) and machine learning (ML) in lung cancer detection, diagnosis and treatment between 2010 and 2023. A total of 55 studies were selected systematically from databases such as IEEE Xplore, Scopus and PubMed via a PRISMA-based approach. The analysis reveals that artificial intelligence (AI) techniques, specifically convolutional neural networks (CNNs) and natural language processing (NLP), highly improve the precision of initial detection and imaging of lung cancer. Also, CNN distinguishes between benign and malignant nodules, thus aiding early diagnosis and reducing unnecessary biopsies. On the other hand, NLP is utilized to extract relevant clinical information from electronic health records and unstructured medical texts, thereby enhancing the understanding of patient histories and improving treatment planning. Sensitive and specific scores usually higher than standard techniques characterize these technologies. Results show that traditional statistical approaches couldn’t match AI models whose predictive accuracies are outstanding while providing better care to patients through personalised treatment plans. Furthermore, multi-omics data analysis for personalised treatment planning and clinical decision-making optimisation via Clinical Decision Support Systems (CDSS) powered by AI are some ways artificial intelligence has exhibited its potential in this area. Given this, future studies should aim to fine-tune AI algorithms, improve data integration, and address ethical issues promoting responsible use of AI technologies in clinical practice settings. Despite these advances, data quality, model interpretability, and integration into clinical workflows persist. This review demonstrates the demand for continued research and collaboration from different disciplines so that the complete possibilities of AI in fighting lung cancer may be realised.

Clinical utility of repeated rebiopsy for EGFR T790M mutation detection in non-small cell lung cancer.

In cases where rebiopsy fails to find the epidermal growth factor receptor (EGFR) T790M mutation, the criteria for selecting patients for repeated rebiopsy remains unclear. This study aimed to assess the impact of repeated rebiopsy on T790M mutation detection in non-small cell lung cancer (NSCLC) patients. Patients with advanced EGFR-mutated NSCLC between January 2018 and December 2021 at three-referral hospitals in South Korea underwent retrospective review. Of 682 patients who had rebiopsy after disease progression, T790M mutation status was assessed in plasma circulating tumor DNA (ctDNA) and/or tumor tissues. The overall T790M positivity rate increased from 40.8% after the first rebiopsy to 52.9% following multiple rebiopsies in the entire study population. Longer duration of initial EGFR TKI use (OR 1.792, ≥8 months vs. <8 months, p=0.004), better EGFR TKI responses (OR 1.611, complete or partial response vs. stable disease, p=0.006), presence of bone metastasis (OR 2.286, p<0.001) were correlated with higher T790M positivity. Longer EGFR TKI use and better responses increased T790M positivity in repeated tissue rebiopsy, while bone metastasis favored liquid rebiopsy. Additionally, T790M status has been shown to be positive over time through repeated rebiopsies ranging from several months to years, suggesting its dynamic nature. In this study, among patients who initially tested negative for T790M in rebiopsy, repeated rebiopsies uncovered an additional 23.5% T790M positivity. Particularly, it is suggested that repeated rebiopsies may be valuable for patients with prolonged EGFR TKI usage, better responses to treatment, and bone metastasis.

Lung cancer detection

Lung cancer detection

AI-Enhanced Lung Cancer Prediction: A Hybrid Model's Precision Triumph.

Lung cancer is considered one of the most dangerous cancers, with a 5-year survival rate, ranking the disease among the top three deadliest cancers globally. Effectively combating lung cancer requires early detection for timely targeted interventions. However, ensuring early detection poses a major challenge, giving rise to innovative approaches. The emergence of artificial intelligence offers revolutionary solutions for predicting cancer. While marking a significant healthcare shift, the imperative to enhance artificial intelligence models remains a focus, particularly in precision medicine. This study introduces a hybrid deep learning model, incorporating Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory Networks (BiLSTM), designed for lung cancer detection from patients' medical notes. Comparative analysis with the MIMIC IV dataset reveals the model's superiority, achieving an MCC of 96.2% with an Accuracy of 98.1%, and outperforming LSTM and BioBERT with an MCC of 93.5 %, an accuracy of 97.0% and MCC of 95.5 with an accuracy of 98.0% respectively. Another comprehensive comparison was conducted with state-of-the-art results using the Yelp Review Polarity dataset. Remarkably, our model significantly outperforms the compared models, showcasing its superior performance and potential impact in the field. This research signifies a significant stride toward precise and early lung cancer detection, emphasizing the ongoing necessity for Artificial Intelligence model refinement in precision medicine.

Performance analysis of lung cancer detection and classification using efficientNet: a deep learning model

Performance analysis of lung cancer detection and classification using efficientNet: a deep learning model

Deep learning-based computerized diagnosis of lung cancer

The Deep-Learning (DL) technique is capturing increasingly flexible in the sector of processing medical images. Rapid and precise lung cancer detection requirements a standardized computer-aided diagnostic (CAD) architecture. For a quick and reliable detection of lung cancer, a standardized CAD framework is required. High-risk patients are advised by the National Lung Screening Trial to undertake standard screenings with low-dose CT to support the early detection of cancer and decrease the consequence of lung cancer death. In this paper, a lung CT scan and probabilistic bilateral convolutional neural networks (PB-CNN)-based automated diagnosis system for lung cancer are developed. The PB-CNN models were trained using sample cases from the LUNA16 dataset. We used existing techniques, such as Decision Trees (DT), Artificial Neural Networks (ANN) and K-Nearest Neighbors (KNN) to detect lung cancer. We employed accuracy, precision, recall, and f-measure in our experimental investigation. The proposed PB-CNN is automatically detecting lung cancer, yielding an acceptable performance.

"Enhancing Lung Cancer Detection: A Comparative Analysis of CNN and RNN Models on X-Ray Image Data"

"Enhancing Lung Cancer Detection: A Comparative Analysis of CNN and RNN Models on X-Ray Image Data"

Innovations in Early Lung Cancer Detection: Tracing the Evolution and Advancements in Screening.

Lung cancer mortality rates, particularly non-small cell lung cancer (NSCLC), continue to present a significant global health challenge, and the adoption of lung cancer screening remains limited, often influenced by inequities in access to healthcare. Despite clinical evidence demonstrating the efficacy of annual screening with low-dose computed tomography (LDCT) and recommendations from medical organizations including the U.S. Preventive Services Task Force (USPSTF), the national lung cancer screening uptake remains around 5% among eligible individuals. Advancements in the clinical management of NSCLC have recently become more personalized with the implementation of blood-based biomarker testing. Extensive research into tumor-derived cell-free DNA (cfDNA) through fragmentation offers a novel method for improving early lung cancer detection. This review assesses the screening landscape, explores obstacles to lung cancer screening, and discusses how a plasma whole genome fragmentome test (pWGFrag-Lung) can improve lung cancer screening participation and adherence.

Retrospective evaluation of plasma protein tumour markers for early lung cancer detection

BackgroundBlood-based biomarkers might help lung cancer diagnosis. A panel of serum tumour markers (TM) has been validated for hospital referrals due to clinical suspicion of lung cancer. We have compared plasma from a cohort enriched for early-stage lung cancer, including controls from a healthy population cohort.MethodsTM assays for CEA, CYFRA 21-1, CA15.3, ProGRP and SCC were run on a Roche Elecsys 2010 Immunoassay Analyser for a retrospective, nested case-control cohort from the Liverpool Lung Project. The primary endpoints were the sensitivity and specificity of a pre-defined TM panel using published thresholds.ResultsExcept for ProGRP, TM levels were significantly higher in cases and ROC AUC values demonstrated significant discriminant power. Accuracy and levels were higher for late-stage cancers, except for ProGRP which was highest in stage 1 cancers. Although providing similar sensitivity (82.4% vs 88.5%), TMs performed worse for specificity (39.3% vs 82%) and overall (Youden’s Index 0.22 vs 0.77) and this was not improved by threshold optimisation or binary logistic regression.ConclusionsAlthough the TMs were associated with lung cancer status and discriminatory with a high sensitivity when combined, performance was compromised in early-stage disease, which casts some doubt on utility in the screening setting.

Frightening symptom hemoptysis: Analysis of etiology, mortality, and treatment outcomes in a large cohort from the chest disease center in Turkiye

Aims: Hemoptysis can indicate serious, potentially life-threatening conditions. The etiology varies by region and can include tuberculosis (TB) in developing countries and malignancies in developed regions. Methods: This retrospective cohort study reviewed medical records of 400 hospitalized hemoptysis patients between June 2012 and March 2016. Data collected included patient demographics, comorbidities, hemoptysis volume, diagnostic tests, treatments, and outcomes. Survival rates and readmissions were tracked for 2-6 years post-discharge. Results: Of the 400 patients, 88 (22%) were female and 312 (78%) were male. The leading causes of hemoptysis were bronchiectasis (14%), sequela of tuberculosis (TB sequelae; 19%), and malignancy (22.8%). The most common causes in male patients were lung cancer (27.2%) and TB sequelae (21.8%). Bronchiectasis accounted for 28.4% of cases in female patients, followed by drug-induced hemoptysis at 14.8%. The in-hospital mortality rate was 1% (n = 4), with severe hemoptysis present in all four patients who died during admission for hemoptysis. The 2–6-year survival rate was 70.8% for women and 56.1% for men (p = 0.005). The factors found to significantly worsen mortality risk were lung malignancy, age &gt;65, diabetes, and chronic obstructive pulmonary disease (COPD). Conclusion: Overall, lung cancer was found to be the leading cause of hemoptysis, with bronchiectasis being the leading cause in female patients and malignancy in male patients. Close monitoring of male patients is crucial due to higher mortality risk. Careful assessment of patients with hemoptysis having comorbidities such as diabetes and COPD is required due to the reduced survival rates associated with these conditions. Early detection and intervention for lung cancer is essential to optimize the prognosis of affected individuals.

A Hybrid Lung Cancer Model for Diagnosis and Stage Classification from Computed Tomography Images

Pulmonary cancers at early stages is difficult but crucial for patient survival. Therefore, it is essential to develop an intelligent, autonomous, and accurate lung cancer detection system that shows great reliability compared to previous systems and research. In this study, we have developed an innovative lung cancer detection system known as the Hybrid Lung Cancer Stage Classifier and Diagnosis Model (Hybrid-LCSCDM). This system simplifies the complex task of diagnosing lung cancer by categorizing patients into three classes: normal, benign, and malignant, by analyzing computed tomography (CT) scans using a two-part approach: First, feature extraction is conducted using a pre-trained model called VGG-16 for detecting key features in lung CT scans indicative of cancer. Second, these features are then classified using a machine learning technique called XGBoost, which sorts the scans into three categories. A dataset, IQ-OTH/NCCD - Lung Cancer, is used to train and evaluate the proposed model to show its effectiveness. The dataset consists of the three aforementioned classes containing 1190 images. Our suggested strategy achieved an overall accuracy of 98.54 %, while the classification precision among the three classes was 98.63 %. Considering the accuracy, recall, and precision as well as the F1-score evaluation metrics, the results indicated that when using solely computed tomography scans, the proposed (Hybrid-LCSCDM) model outperforms all previously published models.

In-training and private physicians' knowledge, attitudes, practices and perceived barriers on the utilization of low dose chest CT scan as lung cancer screening for high-risk patients in a tertiary hospital: Single center experience.

150 Background: Lung cancer is the leading cause of cancer-related deaths worldwide. Aside from smoking cessation efforts and guidelines from all proficient panels, utilizing Low dose CT scan (LDCT) of the chest as lung cancer screening (LCS) has been poorly adopted. Methods: This was conducted after institutional review board approval. The respondents were handed hard copy or electronic consent forms and survey questionnaire depending on the platform of their choice. Results: Majority of the respondents were in-training female physicians with median age of 31 years old who specialized in Internal Medicine practicing between 1-5 years who catered to more than 10 patients per week in outpatient clinics. Nearly half of the respondents answered that the recommended frequency for lung cancer screening (LCS) for high-risk individuals is done bi-annually. Majority agreed that lung cancer screening is effective in decreasing lung cancer mortality and morbidity. Most respondents have initiated discussion about the risks and benefits of low dose chest CT scan (LDCT) as lung cancer screening among eligible high-risk patients. However, most of the respondents disagreed that lung cancer screening is cost effective. The top three perceived barriers on the utilization of Low dose chest CT scan as lung cancer screening reported in descending order revealed that it is not cost-effective, some forgets to screen patients and lung cancer screening has the potential to cause mental anguish or anxiety to patients. Conclusions: This study recommends conducting further studies exploring the socio-economic burden and impact assessment of lung cancer in the Philippines to enable translation of more meaningful strategies for local and national lung cancer screening access, health policies and financing. Promoting continuous lung cancer screening forums, lectures and information dissemination of annual LDCT of the chest among high risk patients will encourage and strengthen interdepartmental and multidisciplinary referral and collaboration in increasing earlier detection of lung cancer and decreasing related morbidity and mortality.