Lung Cancer Dataset Research Articles

Minimum Dataset of Lung Cancer Patients: An Initial Step Towards Developing a Web-Based Personal Health Record

Background: Personal Health Records (PHR), which utilize advanced health information technology tools, play a crucial role in patient self-management and improving the control of chronic diseases such as lung cancer. To optimize the design of these systems, it is essential to determine the necessary data elements. Objectives: This study aims to identify the minimum dataset required for designing a web-based PHR for lung cancer patients. Methods: This descriptive, cross-sectional research was conducted in 2023. Initially, a lung cancer dataset was extracted through text analysis. In the next phase, a proposed minimum lung cancer dataset was formulated into a questionnaire containing 18 data groups, including 126 data elements. The dataset underwent expert validation in two phases using the Delphi technique. Data analysis was performed using SPSS version 26, with descriptive statistics employed. Results: The minimum web-based PHR dataset for lung cancer patients, consisting of 18 data groups (112 data elements), includes demographics, insurance information, emergency contact details, patient symptoms, tumor-related data, physician details, treatment information, patient-reported measurements, personal medical history, history of procedures and surgeries, visits, allergies, family history, medication information, test results, imaging data, dietary information, and educational materials. Conclusions: Based on the study findings, it is recommended that lung cancer data management encompass not only routine information but also additional dimensions such as allergies, tumor-related information, and dietary details. Collecting comprehensive and complete data can significantly enhance the treatment process and post-treatment follow-up.

Identification of Biomarkers and Molecular Pathways Implicated in Smoking and COVID-19 Associated Lung Cancer Using Bioinformatics and Machine Learning Approaches

Lung cancer (LC) is a significant global health issue, with smoking as the most common cause. Recent epidemiological studies have suggested that individuals who smoke are more susceptible to COVID-19. In this study, we aimed to investigate the influence of smoking and COVID-19 on LC using bioinformatics and machine learning approaches. We compared the differentially expressed genes (DEGs) between LC, smoking, and COVID-19 datasets and identified 26 down-regulated and 37 up-regulated genes shared between LC and smoking, and 7 down-regulated and 6 up-regulated genes shared between LC and COVID-19. Integration of these datasets resulted in the identification of ten hub genes (SLC22A18, CHAC1, ROBO4, TEK, NOTCH4, CD24, CD34, SOX2, PITX2, and GMDS) from protein-protein interaction network analysis. The WGCNA R package was used to construct correlation network analyses for these shared genes, aiming to investigate the relationships among them. Furthermore, we also examined the correlation of these genes with patient outcomes through survival curve analyses. The gene ontology and pathway analyses were performed to find out the potential therapeutic targets for LC in smoking and COVID-19 patients. Moreover, machine learning algorithms were applied to the TCGA RNAseq data of LC to assess the performance of these common genes and ten hub genes, demonstrating high performances. The identified hub genes and molecular pathways can be utilized for the development of potential therapeutic targets for smoking and COVID-19-associated LC.

Foundational Segmentation Models and Clinical Data Mining Enable Accurate Computer Vision for Lung Cancer.

This study aims to assess the effectiveness of integrating Segment Anything Model (SAM) and its variant MedSAM into the automated mining, object detection, and segmentation (MODS) methodology for developing robust lung cancer detection and segmentation models without post hoc labeling of training images. In a retrospective analysis, 10,000 chest computed tomography scans from patients with lung cancer were mined. Line measurement annotations were converted to bounding boxes, excluding boxes < 1cm or > 7cm. The You Only Look Once object detection architecture was used for teacher-student learning to label unannotated lesions on the training images. Subsequently, a final tumor detection model was trained and employed with SAM and MedSAM for tumor segmentation. Model performance was assessed on a manually annotated test dataset, with additional evaluations conducted on an external lung cancer dataset before and after detection model fine-tuning. Bootstrap resampling was used to calculate 95% confidence intervals. Data mining yielded 10,789 line annotations, resulting in 5403 training boxes. The baseline detection model achieved an internal F1 score of 0.847, improving to 0.860 after self-labeling. Tumor segmentation using the final detection model attained internal Dice similarity coefficients (DSCs) of 0.842 (SAM) and 0.822 (MedSAM). After fine-tuning, external validation showed an F1 of 0.832 and DSCs of 0.802 (SAM) and 0.804 (MedSAM). Integrating foundational segmentation models into the MODS framework results in high-performing lung cancer detection and segmentation models using only mined clinical data. Both SAM and MedSAM hold promise as foundational segmentation models for radiology images.

ABCG2 Gene Expression in Non-Small Cell Lung Cancer.

Background/Objectives: ATP-binding cassette subfamily G member 2 [ABCG2/breast cancer resistance protein (BCRP)] contributes to mechanisms of multidrug resistance (MDR) and is a marker of side population (SP) cells in human cancers. The primary objective of this study was to investigate the impact of ABCG2 gene expression on the non-small cell lung cancer (NSCLC) development, course of cancer disease, and patient prognosis using publicly available data. Obtained results were supplemented with assessment of ABCG2 expression in blood of NSCLC patients. Methods: The dataset of lung cancer was analyzed utilizing the TIMER 2.0, UALCAN, TNMplot, MEXPRESS, cBioPortal, MethSurv, KM Plotter, STRING, and ShinyGO 0.80 databases. Blood samples from 50 patients were assessed using the real-time PCR method. Results: The ABCG2 gene was expressed at a low level in NSCLC, and did not correlate with clinical aggressiveness of lung cancer. Higher ABCG2 expression improved overall survival, but only in LUAD. In addition, CpG sites located on the CpG island affecting the NSCLC patient's prognosis were indicated. In the case of our own laboratory results, the study did not reveal any changes in the ABCG2 expression levels in blood collected from patients at different time points during the diagnostic-therapeutic procedure. In the in silico analysis, most ABCG2 protein interactors were associated with the development of drug resistance. Conclusions: ABCG2 appears to have a particularly significant impact on the survival of patients with lung cancer and on the effect of immunotherapy related to immune cell infiltration. Presented findings may support personalized medicine strategies based on bioinformatics findings.

Using a patient-specific diffusion model to generate CBCT-based synthetic CTs for CBCT-guided adaptive radiotherapy.

Cone beam computed tomography (CBCT) can be used to evaluate the inter-fraction anatomical changes during the entire course for image-guided radiotherapy (IGRT). However, CBCT artifacts from various sources restrict the full application of CBCT-guided adaptive radiation therapy (ART). Inter-fraction anatomical changes during ART, including variations in tumor size and normal tissue anatomy, can affect radiation therapy (RT) efficacy. Acquiring high-quality CBCT images that accurately capture patient- and fraction-specific (PFS) anatomical changes is crucial for successful IGRT. To enhance CBCT image quality, we proposed PFS lung diffusion models (PFS-LDMs). The proposed PFS models use a pre-trained general lung diffusion model (GLDM) as a baseline, which is trained on historical deformed CBCT (dCBCT)-planning CT (pCT) paired data. For a given patient, a new PFS model is fine-tuned on a CBCT-deformed pCT (dpCT) pair after each fraction to learn the PFS knowledge for generating personalized synthetic CT (sCT) with quality comparable to pCT or dpCT. The learned PFS knowledge is the specific mapping relationships, including personal inter-fraction anatomical changes between personalized CBCT-dpCT pairs. The PFS-LDMs were evaluated on an institutional lung cancer dataset, quantified by mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and structural similarity index measure (SSIM) metrics. We also compared our PFS-LDMs with a mainstream GAN-based model, demonstrating that our PFS fine-tuning strategy could be applied to existing generative models. Our models showed remarkable improvements across all four evaluation metrics. The proposed PFS-LDMs outperformed the GLDM, demonstrating the effectiveness of our proposed fine-tuning strategy. The PFS model fine-tuned with CBCT images from four prior fractions, reduced the MAE from 103.95 to 15.96 Hounsfield units (HU), and increased the mean PSNR, NCC, and SSIM from 25.36dB to 33.57dB, 0.77 to 0.98, and 0.75 to 0.97, respectively. Applying our PFS fine-tuning strategy to a Cycle GAN model also showed improvements, with all four fine-tuned PFS Cycle GAN (PFS-CG) models outperforming the general Cycle GAN model. Overall, our proposed PFS fine-tuning strategy improved CBCT image quality compared to both the pre-correction and non-fine-tuned general models, with our proposed PFS-LDMs yielding better performance than the GAN-based model across all metrics. Our proposed PFS-LDMs significantly improve CBCT image quality with increased HU accuracy and fewer artifacts, thus better capturing inter-fraction anatomical changes. This lays the groundwork for enabling CBCT-based ART, which could enhance clinical efficiency and achieve personalized high-precision treatment by accounting for inter-fraction anatomical changes.

A Graph-Informed Modeling Framework Empowering Gene Pathway Discovery.

This study introduces a novel graph-informed modeling framework for improving the statistical analysis of gene expression data, particularly in the context of identifying differentially expressed gene pathways and gene expression-assisted disease classification in a high-dimensional data setting. By integrating gene regulatory network information into hypothesis testing for the difference between mean vectors and linear discriminant analysis, we aim to effectively capture and utilize previously validated external gene interaction information. Our method leverages a block-coordinate descent approach which enables us to incorporate mixed graph information into linear structural equation modeling, accommodating directed/undirected edges and potential cycles in gene regulatory networks. Extensive simulations under various data scenarios have demonstrated the effectiveness of our approach with improved power for gene pathway tests and disease classification over existing methods. An application to a lung cancer dataset from the Cancer Genome Atlas Program (TCGA) further exemplifies the potential of our graph-informed approach in empowering the detection of differentially expressed gene pathways and gene expression-based classification of different lung cancer stages. Our findings underscore the potential utility of incorporating gene regulatory network information in gene pathway analysis, setting the stage for future advancements in gene pathway discovery, disease diagnosis, and treatment strategies.

Human lung cancer classification and comprehensive analysis using different machine learning techniques.

Lung cancer is the most common causes of death among all cancer-related diseases. A lung scan examination of the patient is the primary diagnostic technique. This scan analysis pertains to an MRI, CT, or X-ray. The automated classification of lung cancer is difficult due to the involvement of multiple steps in imaging patients' lungs. In this manuscript, human lung cancer classification and comprehensive analysis using different machine learning techniques is proposed. Initially, the input images are gathered using lung cancer dataset. The proposed method processes these images using image-processing techniques, and further machine learning techniques are utilized for categorization. Seven different classifiers including the k-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), multinomial naive Bayes (MNB), stochastic gradient descent (SGD), random forest (RF), and multi-layer perceptron (MLP) classifier are used, which classifies the lung cancer as malignant and benign. The performance of the proposed approach is examined using performances metrics, like positive predictive value, accuracy, sensitivity, and f-score are evaluated. Among them, the performance of the MLP classifier provides 25.34%, 45.39%, 15.39%, 41.28%, 22.17%, and 12.12% higher accuracy than other KNN, SVM, DT, MNB, SGD, and RF respectively. RESEARCH HIGHLIGHTS: Lung cancer is a leading cause of cancer-related death. Imaging (MRI, CT, and X-ray) aids diagnosis. Automated classification of lung cancer faces challenges due to complex imaging steps. This study proposes human lung cancer classification using diverse machine learning techniques. Input images from lung cancer dataset undergo image processing and machine learning. Classifiers like k-nearest neighbors, support vector machine, decision tree, multinomial naive Bayes, stochastic gradient descent, random forest, and multi-layer perceptron (MLP) classify cancer types; MLP excels in accuracy.

Exploring time-to-event analysis models: A study of accelerated failure time and weighted least square estimation

Background: This study explores time-to-event analysis models, focusing on the comparison between accelerated failure time (AFT) and weighted least square estimation (WLSE) methods in analyzing survival data, emphasizing the challenge of heteroscedasticity in real-world datasets. Methods: Using the North Central Cancer Treatment Group (NCCTG) Lung Cancer dataset, five parametric AFT distributions (exponential, Weibull, log-logistic, log-normal, and generalized gamma) were evaluated. The log-likelihood method was utilized to calculate the AIC and BIC values for each distribution to determine the best fit model. Results: Among the different distributions tested, the Weibull distribution was identified as the best fit model based with the lowest AIC and BIC values of 2311.70 and 2318.56, respectively. This distribution played a crucial role in determining factors associated with the cancer data. Specifically, the variablecalories consumed at a meal (meal.cal) was associated with cancer patient recovery, with an estimate of 0.00004 and a standard error of 0.0002. Results indicated homoscedastic data through the Breusch-Pagan test. Moreover, the results demonstrated that when dealing with homoscedastic data, the Weibull AFT model outperformed WLSE in producing statistically significant effects and precise estimates. Conclusion: For data exhibiting homoscedasticity, the AFT method yielded superior results compared to WLSE in terms of statistical significance and precision. Therefore, it is advisable to employ AFT for homoscedastic data and WLSE for heteroscedastic data to enhance the accuracy of covariate effect estimates in survival analysis.

Dissection of intratumor microbiome–host interactions at single-cell level in lung cancer

The intratumor microbiome, one of the hallmarks of cancer, plays a crucial role in cancer progression through interaction with the host. However, the underlying mechanisms remain poorly understood. Herein, we investigated the heterogeneity of host–microbiome interactions at the single-cell level by integrating six single-cell transcriptomic lung cancer datasets using single-cell analysis of host–microbiome interactions (SAHMI). Our findings indicate that primary tumor tissues display a high proportion of fungi-associated cells, whereas metastatic brain tissues predominantly feature bacteria-associated cells. A distinct distribution of fungal and bacterial taxa across various cell types was observed. Notably, the presence of specific bacteria significantly influences the transcriptome of resident host cells, including T cells and macrophages, by modulating pathways related to ribosomal RNA (rRNA) processing, cellular responses to stress and stimuli, and the metabolism of RNA and proteins. Finally, specific cell-associated bacteria are significantly correlated with clinical features, such as lung cancer stages and smoking frequency. These single-cell insights into microbiome–host interactions facilitate our understanding of lung cancer development and progression, offering potential micro-ecological and diagnostic insights.

Proteogenomic characterization identifies clinical subgroups in EGFR and ALK wild-type never-smoker lung adenocarcinoma

Patients with lung adenocarcinoma who have never smoked (NSLA) and lack key driver mutations, such as those in the EGFR and ALK genes, face limited options for targeted therapies. They also tend to have poorer outcomes with immune checkpoint inhibitors than lung cancer patients who have a history of smoking. The proteogenomic profile of nonsmoking lung adenocarcinoma patients without these oncogenic driver mutations is poorly understood, which complicates the precise molecular classification of these cancers and highlights a significant area of unmet clinical need. This study analyzed the genome, transcriptome, and LC‒MS/MS-TMT-driven proteome data of tumors obtained from 99 Korean never-smoker lung adenocarcinoma patients. NSLA tumors without EGFR or ALK driver oncogenes were classified into four proteogenomic subgroups: proliferation, angiogenesis, immune, and metabolism subgroups. These 4 molecular subgroups were strongly associated with distinct clinical outcomes. The proliferation and angiogenesis subtypes were associated with a poorer prognosis, while the immune subtype was associated with the most favorable outcome, which was validated in an external lung cancer dataset. Genomic-wide impacts were analyzed, and significant correlations were found between copy number alterations and both the transcriptome and proteome for several genes, with enrichment in the ERBB, neurotrophin, insulin, and MAPK signaling pathways. Proteogenomic analyses suggested several targetable genes and proteins, including CDKs and ATR, as potential therapeutic targets in the proliferation subgroup. Upregulated cytokines, such as CCL5 and CXCL13, in the immune subgroup may serve as potential targets for combination immunotherapy. Our comprehensive proteogenomic analysis revealed the molecular subtypes of EGFR- and ALK-wild-type NSLA with significant unmet clinical needs.

CBCT-based synthetic CT image generation using a diffusion model for CBCT-guided lung radiotherapy.

Although cone beam computed tomography (CBCT) has lower resolution compared to planning CTs (pCT), its lower dose, higher high-contrast resolution, and shorter scanning time support its widespread use in clinical applications, especially in ensuring accurate patient positioning during the image-guided radiation therapy (IGRT) process. While CBCT is critical to IGRT, CBCT image quality can be compromised by severe stripe and scattering artifacts. Tumor movement secondary to respiratory motion also decreases CBCT resolution. In order to improve the image quality of CBCT, we propose a Lung Diffusion Model (L-DM) framework. Our proposed algorithm is based on a conditional diffusion model trained on pCT and deformed CBCT (dCBCT) image pairs to synthesize lung CT images from dCBCT images and benefit CBCT-based radiotherapy. dCBCT images were used as the constraint for the L-DM. The image quality and Hounsfield unit (HU) values of the synthetic CTs (sCT) images generated by the proposed L-DM were compared to three selected mainstream generation models. We verified our model in both an institutional lung cancer dataset and a selected public dataset. Our L-DM showed significant improvement in the four metrics of mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and structural similarity index measure (SSIM). In our institutional dataset, our proposed L-DM decreased the MAE from 101.47 to 37.87HU and increased the PSNR from 24.97 to 29.89 dB, the NCC from 0.81 to 0.97, and the SSIM from 0.80 to 0.93. In the public dataset, our proposed L-DM decreased the MAE from 173.65 to 58.95HU, while increasing the PSNR, NCC, and SSIM from 13.07 to 24.05 dB, 0.68 to 0.94, and 0.41 to 0.88, respectively. The proposed L-DM significantly improved sCT image quality compared to the pre-correction CBCT andthree mainstream generative models. Our model can benefit CBCT-based IGRT and other potential clinical applications as it increases the HU accuracy and decreases the artifacts from input CBCT images.

Tackling heterogeneity in medical federated learning via aligning vision transformers

Federated learning enables training models on distributed, privacy-sensitive medical imaging data. However, data heterogeneity across participating institutions leads to reduced model performance and fairness issues, especially for underrepresented datasets. To address these challenges, we propose leveraging the multi-head attention mechanism in Vision Transformers to align the representations of heterogeneous data across clients. By focusing on the attention mechanism as the alignment objective, our approach aims to improve both the accuracy and fairness of federated learning models in medical imaging applications. We evaluate our method on the IQ-OTH/NCCD Lung Cancer dataset, simulating various levels of data heterogeneity using Latent Dirichlet Allocation (LDA). Our results demonstrate that our approach achieves competitive performance compared to state-of-the-art federated learning methods across different heterogeneity levels and improves the performance of models for underrepresented clients, promoting fairness in the federated learning setting. These findings highlight the potential of leveraging the multi-head attention mechanism to address the challenges of data heterogeneity in medical federated learning.

Explainable lung cancer classification with ensemble transfer learning of VGG16, Resnet50 and InceptionV3 using grad-cam

Medical imaging stands as a critical component in diagnosing various diseases, where traditional methods often rely on manual interpretation and conventional machine learning techniques. These approaches, while effective, come with inherent limitations such as subjectivity in interpretation and constraints in handling complex image features. This research paper proposes an integrated deep learning approach utilizing pre-trained models—VGG16, ResNet50, and InceptionV3—combined within a unified framework to improve diagnostic accuracy in medical imaging. The method focuses on lung cancer detection using images resized and converted to a uniform format to optimize performance and ensure consistency across datasets. Our proposed model leverages the strengths of each pre-trained network, achieving a high degree of feature extraction and robustness by freezing the early convolutional layers and fine-tuning the deeper layers. Additionally, techniques like SMOTE and Gaussian Blur are applied to address class imbalance, enhancing model training on underrepresented classes. The model’s performance was validated on the IQ-OTH/NCCD lung cancer dataset, which was collected from the Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases over a period of three months in fall 2019. The proposed model achieved an accuracy of 98.18%, with precision and recall rates notably high across all classes. This improvement highlights the potential of integrated deep learning systems in medical diagnostics, providing a more accurate, reliable, and efficient means of disease detection.

Automated Lung Cancer Diagnosis Applying Butterworth Filtering, Bi-Level Feature Extraction, and Sparce Convolutional Neural Network to Luna 16 CT Images.

Accurate prognosis and diagnosis are crucial for selecting and planning lung cancer treatments. As a result of the rapid development of medical imaging technology, the use of computed tomography (CT) scans in pathology is becoming standard practice. An intricate interplay of requirements and obstacles characterizes computer-assisted diagnosis, which relies on the precise and effective analysis of pathology images. In recent years, pathology image analysis tasks such as tumor region identification, prognosis prediction, tumor microenvironment characterization, and metastasis detection have witnessed the considerable potential of artificial intelligence, especially deep learning techniques. In this context, an artificial intelligence (AI)-based methodology for lung cancer diagnosis is proposed in this research work. As a first processing step, filtering using the Butterworth smooth filter algorithm was applied to the input images from the LUNA 16 lung cancer dataset to remove noise without significantly degrading the image quality. Next, we performed the bi-level feature selection step using the Chaotic Crow Search Algorithm and Random Forest (CCSA-RF) approach to select features such as diameter, margin, spiculation, lobulation, subtlety, and malignancy. Next, the Feature Extraction step was performed using the Multi-space Image Reconstruction (MIR) method with Grey Level Co-occurrence Matrix (GLCM). Next, the Lung Tumor Severity Classification (LTSC) was implemented by using the Sparse Convolutional Neural Network (SCNN) approach with a Probabilistic Neural Network (PNN). The developed method can detect benign, normal, and malignant lung cancer images using the PNN algorithm, which reduces complexity and efficiently provides classification results. Performance parameters, namely accuracy, precision, F-score, sensitivity, and specificity, were determined to evaluate the effectiveness of the implemented hybrid method and compare it with other solutions already present in the literature.

A New Hybrid Adaptive Optimization Algorithm Based Wavelet Neural Network for Severity Level Prediction for Lung Cancer Dataset

A New Hybrid Adaptive Optimization Algorithm Based Wavelet Neural Network for Severity Level Prediction for Lung Cancer Dataset

Optimizing clinico-genomic disease prediction across ancestries: a machine learning strategy with Pareto improvement

BackgroundAccurate prediction of an individual’s predisposition to diseases is vital for preventive medicine and early intervention. Various statistical and machine learning models have been developed for disease prediction using clinico-genomic data. However, the accuracy of clinico-genomic prediction of diseases may vary significantly across ancestry groups due to their unequal representation in clinical genomic datasets.MethodsWe introduced a deep transfer learning approach to improve the performance of clinico-genomic prediction models for data-disadvantaged ancestry groups. We conducted machine learning experiments on multi-ancestral genomic datasets of lung cancer, prostate cancer, and Alzheimer’s disease, as well as on synthetic datasets with built-in data inequality and distribution shifts across ancestry groups.ResultsDeep transfer learning significantly improved disease prediction accuracy for data-disadvantaged populations in our multi-ancestral machine learning experiments. In contrast, transfer learning based on linear frameworks did not achieve comparable improvements for these data-disadvantaged populations.ConclusionsThis study shows that deep transfer learning can enhance fairness in multi-ancestral machine learning by improving prediction accuracy for data-disadvantaged populations without compromising prediction accuracy for other populations, thus providing a Pareto improvement towards equitable clinico-genomic prediction of diseases.

Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation.

Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions, especially for cohorts with different lung diseases. The attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This article presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network (FANN) and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization, and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19, and pulmonary fibrosis.

Optimizing double-layered convolutional neural networks for efficient lung cancer classification through hyperparameter optimization and advanced image pre-processing techniques.

Lung cancer remains a leading cause of cancer-related mortality globally, with prognosis significantly dependent on early-stage detection. Traditional diagnostic methods, though effective, often face challenges regarding accuracy, early detection, and scalability, being invasive, time-consuming, and prone to ambiguous interpretations. This study proposes an advanced machine learning model designed to enhance lung cancer stage classification using CT scan images, aiming to overcome these limitations by offering a faster, non-invasive, and reliable diagnostic tool. Utilizing the IQ-OTHNCCD lung cancer dataset, comprising CT scans from various stages of lung cancer and healthy individuals, we performed extensive preprocessing including resizing, normalization, and Gaussian blurring. A Convolutional Neural Network (CNN) was then trained on this preprocessed data, and class imbalance was addressed using Synthetic Minority Over-sampling Technique (SMOTE). The model's performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and ROC curve analysis. The results demonstrated a classification accuracy of 99.64%, with precision, recall, and F1-score values exceeding 98% across all categories. SMOTE significantly enhanced the model's ability to classify underrepresented classes, contributing to the robustness of the diagnostic tool. These findings underscore the potential of machine learning in transforming lung cancer diagnostics, providing high accuracy in stage classification, which could facilitate early detection and tailored treatment strategies, ultimately improving patient outcomes.

Lung Cancer Classification based on Auxiliary Classifier (WGAN) Optimised with HOA from CT Images

ABSTRACT The cancer diagnosis is currently experiencing an alteration of molecular biomarkers using s paradigm for the diagnostic panel. One of the most important genomic datasets showing genetic sequences is the classification of lung cancer. Many research studies have been conducted in this area, but none of them yields satisfied outcomes on account of lower classification accuracy. At first, the data are collected through the lung cancer dataset. Afterward, data are fed into pre-processing. The pre-processing segment removes the noise and enhances the input images utilising Dynamic Context-Sensitive Filtering. The pre-processing output is fed to the feature extraction segment. Here, four statistical features are extracted based on the Force Invariant Improved Feature Extraction Model. The extracting features are fed to the feature segmentation segment. Lung cancer images can segment the ROI region using Adaptive Density-Based Spatial Clustering. After that, the segmentation features are given to ACWGAN for effectively categorizing cancer and non-cancer of the lung cancer Hence, the Hunter–prey optimisation algorithm is employed to optimise the ACWGAN classifier. It classifies the lung cancer images accurately. The LCC-ACWGAN-HPOA-CTI algorithm is activated in MATLAB under the lung cancer database. The performance of the LCC-ACWGAN-HPOA-CTI approach shows higher accuracy and lower computation time than those of the existing methods.

A critical assessment of using ChatGPT for extracting structured data from clinical notes.

Existing natural language processing (NLP) methods to convert free-text clinical notes into structured data often require problem-specific annotations and model training. This study aims to evaluate ChatGPT's capacity to extract information from free-text medical notes efficiently and comprehensively. We developed a large language model (LLM)-based workflow, utilizing systems engineering methodology and spiral "prompt engineering" process, leveraging OpenAI's API for batch querying ChatGPT. We evaluated the effectiveness of this method using a dataset of more than 1000 lung cancer pathology reports and a dataset of 191 pediatric osteosarcoma pathology reports, comparing the ChatGPT-3.5 (gpt-3.5-turbo-16k) outputs with expert-curated structured data. ChatGPT-3.5 demonstrated the ability to extract pathological classifications with an overall accuracy of 89%, in lung cancer dataset, outperforming the performance of two traditional NLP methods. The performance is influenced by the design of the instructive prompt. Our case analysis shows that most misclassifications were due to the lack of highly specialized pathology terminology, and erroneous interpretation of TNM staging rules. Reproducibility shows the relatively stable performance of ChatGPT-3.5 over time. In pediatric osteosarcoma dataset, ChatGPT-3.5 accurately classified both grades and margin status with accuracy of 98.6% and 100% respectively. Our study shows the feasibility of using ChatGPT to process large volumes of clinical notes for structured information extraction without requiring extensive task-specific human annotation and model training. The results underscore the potential role of LLMs in transforming unstructured healthcare data into structured formats, thereby supporting research and aiding clinical decision-making.