Malignant Pulmonary Nodules Research Articles

The effectiveness of deep learning model in differentiating benign and malignant pulmonary nodules on spiral CT.

Pulmonary nodule, one of the most common clinical phenomena, is an irregular circular lesion with a diameter of ⩽ 3 cm in the lungs, which can be classified as benign or malignant. Differentiating benign and malignant pulmonary nodules has an essential effect on clinical medical diagnosis. To explore the clinical value and diagnostic effects of the lung nodule classification and segmentation algorithm based on deep learning in differentiating benign and malignant pulmonary nodules. A deep learning model with a fine-grained classification manner for the discrimination of pulmonary models in Dr.Wise Lung Analyzer. This study retrospectively enrolled 120 patients with pulmonary nodules detected by chest spiral CT from March 2021 to September 2022 in the radiology department of Ninghai First Hospital. The DL-based method and physicians' accuracy, sensitivity, and specificity results were compared using the pathological results as the gold standard. The ROC curve of the deep learning model was plotted, and the AUCs were calculated. On 120 CT images, pathologically diagnosed 81 malignant nodules and 122 benign modules. The AUCs of radiologists' diagnostic approach and DL-base method for differentiating patients were 0.62 and 0.81; radiologists' diagnostic approach and DL-base method achieved AUCs of 0.75 and 0.90 for benign and malignant pulmonary nodules differentiate. The accuracy, sensitivity, and specificity with the deep learning model were 73.33%, 78.75%, and 62.50%, respectively, while the accuracy, sensitivity, and specificity with the physician's diagnosis were 63.33%, 66.25%, and 57.500. There was no significant difference between the diagnosis results of the proposed DL-based method and the radiologists' diagnostic approach in differentiating benign and malignant lung nodules on spiral CT (P< 0.05).

PET/CT radiomics and deep learning in the diagnosis of benign and malignant pulmonary nodules: progress and challenges

Lung cancer is currently the leading cause of cancer-related deaths, and early diagnosis and screening can significantly reduce its mortality rate. Since some early-stage lung cancers lack obvious clinical symptoms and only present as pulmonary nodules (PNs) in imaging examinations, accurately determining the benign or malignant nature of PNs is crucial for improving patient survival rates. 18F-FDG PET/CT is important in diagnosing PNs, but its specificity needs improvement. Radiomics can provide information beyond traditional visual assessment, overcoming its limitations by extracting high-throughput quantitative features from medical images. Radiomics features based on 18F-FDG PET/CT and deep learning methods have shown great potential in the noninvasive diagnosis of PNs. This paper reviews the latest advancements in these methods and discusses their contributions to improving diagnostic accuracy and the challenges they face.

An Integrated Nomogram Combining Deep Learning and Radiomics for Predicting Malignancy of Pulmonary Nodules Using CT-Derived Nodules and Adipose Tissue: AMulticenter Study.

Correctly distinguishing between benign and malignant pulmonary nodules can avoid unnecessary invasive procedures. This study aimed to construct a deep learning radiomics clinical nomogram (DLRCN) for predicting malignancy of pulmonary nodules. One thousand and ninety-eight patients with 6-30 mm pulmonary nodules who received histopathologic diagnosis at 3 centers were included and divided into a primary cohort (PC), an internal test cohort (I-T), and two external test cohorts (E-T1, E-T2). The DLRCN was built by integrating adipose tissue radiomics features, intranodular and perinodular deep learning features, and clinical characteristics for diagnosing malignancy of pulmonary nodules. The least absolute shrinkage and selection operator (LASSO) was used for feature selection. The performance of DLRCN was assessed with respect to its calibration curve, area under the curve (AUC), and decision curve analysis (DCA). Furthermore, we compared it with three radiologists. The net reclassification improvement (NRI), integrated discrimination improvement (IDI), and subgroup analysis were also taken into account. The incorporation of adipose tissue radiomics features led to significant NRI and IDI (NRI = 1.028, p < 0.05, IDI = 0.137, p < 0.05). In the I-T, E-T1, and E-T2, the AUCs of DLRCN were 0.946 (95% CI: 0.936, 0.955), 0.948 (95% CI: 0.933, 0.963) and 0.962 (95% CI: 0.945, 0.979), The calibration curve revealed good predictive accuracy between the actual probability and predicted probability (p > 0.05). DCA showed that the DLRCN was clinically useful. Under equal specificity, the sensitivity of DLRCN increased by 8.6% compared to radiologist assessments. The subgroup analysis conducted on adipose tissue radiomics features further demonstrated their supplementary value in determining the malignancy of pulmonary nodules. The DLRCN demonstrated good performance in predicting the malignancy of pulmonary nodules, which was comparable to radiologist assessments. The adipose tissue radiomics features have notably enhanced the performance of DLRCN.

Highly Sensitive and Specific Panels of Plasma Exosomal microRNAs for Identification of Malignant Pulmonary Nodules.

With wide application of computed tomography (CT) in early lung cancer screening, solitary pulmonary nodules (SPNs) are frequently detected. Due to their high etiological diversity and potential for malignancy, rapid and accurate identification and malignant SPNs are crucial in the clinical management. In the present study, plasma exosomal microRNAs were identified and evaluated as sensitive and specific indicators for malignant SPNs. Exosomal miRNAs isolated from the plasmas of pathologically confirmed patients with SPN (four malignant and four benign, designated as the screening set) were subjected for high throughput sequencing and eight candidate miRNAs were selected. The pre-operation plasma levels of the candidate miRNAs in 77 patients with SPN (48 malignant and 29 benign, designated as the identification set) were detected by quantitative PCR, five miRNAs were identified as potential biomarkers for malignant SPNs, and the diagnostic values of the five miRNAs each alone or combined were then analyzed by AUROC analysis. The prediction values of the identified miRNAs were further evaluated in 95 patients with SPN (double blind, 74 malignant and 21 benign, designated as the validation set). High-throughput sequencing identified 45 miRNAs with statistical differences between benign and malignant SPNs. Among the eight candidate miRNAs in the identification set, miR-1-3p alone had the best diagnostic value, with the sensitivities and specificities of 89.6% and 100% for malignant SPNs. Unexpectedly, when miR-1-3p was combined with miR-99a-5p, both the sensitivity and specificity reached 100% for malignant SPNs. miR-1-3p+miR-125b-5p and miR-1-3p+miR-218-5p were also good indicators of malignant SPNs with sensitivities of 95.8% and 97.9%, specificities of 100% and 96.6%. Further analysis of these microRNA combinations in the validation set indicated that the PPV were 91.4%, 97.4%, and 93.5% and the NPV were 100%, 100%, and 88.9% for miR-1-3p+miR-99a-5p, miR-1-3p+miR-218-5p, and miR-1-3p+miR-125b-5p, with the sensitivities were 100%, 100%, and 97.3% and the specificities were 66.7%, 90.5%, and 76.2% for miR-1-3p+miR-99a-5p, miR-1-3p+miR-218-5p, and miR-1-3p+miR-125b-5p, respectively. Through high throughput sequencing, qPCR determination of plasma microRNAs and AUROC analysis, miR-1-3p combined with miR-99a-5p, miR-125b-5p, or miR-218-5p have been found to be sensitive and specific indicators of malignant SPNs in both the identification and validation sets. Our results indicate that the panels of plasma miRNAs can be used as diagnostic biomarkers for malignant SPNs.

Enhancing the differential diagnosis of small pulmonary nodules: a comprehensive model integrating plasma methylation, protein biomarkers, and LDCT imaging features

BackgroundAccurate differentiation between malignant and benign pulmonary nodules, especially those measuring 5–10 mm in diameter, continues to pose a significant diagnostic challenge. This study introduces a novel, precise approach by integrating circulating cell-free DNA (cfDNA) methylation patterns, protein profiling, and computed tomography (CT) imaging features to enhance the classification of pulmonary nodules.MethodsBlood samples were collected from 419 participants diagnosed with pulmonary nodules ranging from 5 to 30 mm in size, before any disease-altering procedures such as treatment or surgical intervention. High-throughput bisulfite sequencing was used to conduct DNA methylation profiling, while protein profiling was performed utilizing the Olink proximity extension assay. The dataset was divided into a training set and an independent test set. The training set included 162 matched cases of benign and malignant nodules, balanced for sex and age. In contrast, the test set consisted of 46 benign and 49 malignant nodules. By effectively integrating both molecular (DNA methylation and protein profiling) and CT imaging parameters, a sophisticated deep learning-based classifier was developed to accurately distinguish between benign and malignant pulmonary nodules.ResultsOur results demonstrate that the integrated model is both accurate and robust in distinguishing between benign and malignant pulmonary nodules. It achieved an AUC score 0.925 (sensitivity = 83.7%, specificity = 82.6%) in classifying test set. The performance of the integrated model was significantly higher than that of individual methylation (AUC = 0.799, P = 0.004), protein (AUC = 0.846, P = 0.009), and imaging models (AUC = 0.866, P = 0.01). Importantly, the integrated model achieved a higher AUC of 0.951 (sensitivity = 83.9%, specificity = 89.7%) in 5–10 mm small nodules. These results collectively confirm the accuracy and robustness of our model in detecting malignant nodules from benign ones.ConclusionsOur study presents a promising noninvasive approach to distinguish the malignancy of pulmonary nodules using multiple molecular and imaging features, which has the potential to assist in clinical decision-making.Trial registration: This study was registered on ClinicalTrials.gov on 01/01/2020 (NCT05432128). https://classic.clinicaltrials.gov/ct2/show/NCT05432128.

Serum exosomal small nucleolar RNA (snoRNA) signatures as a predictive biomarker for benign and malignant pulmonary nodules

Low-dose CT (LDCT) is increasingly recognized as the preferred method for detecting pulmonary nodules. However, distinguishing whether a nodule is benign or malignant often necessitates repeated scans or invasive tissue sampling procedures. Therefore, there is a pressing need for non-invasive techniques to minimize unnecessary interventions. This study aim to investigate the expression profile of exosomal snoRNA in the serum of patients with benign and malignant pulmonary nodules. We identified a total of 278 snoRNAs in serum exosomes, revealing significant differences in snoRNA levels between patients with malignant and benign nodules. Specifically, the upregulated snoRNAs U78 and U37 were validated through qRT-PCR and were found significantly elevated in the serum of patients with malignant pulmonary nodules, positioning them as promising biomarkers for the early detection of lung cancer. This study underscores the potential of serum exosomal U78 and U37 as critical tools for assessing the risk of pulmonary nodules identified through CT screening.

Assessment of solitary pulmonary nodules using dual-layer spectral detector computed tomography.

We aim to quantitatively investigate the difference between benign and malignant solid pulmonary nodules that appeared on dual-energy spectral computed tomography, and assess the diagnostic accuracy of several parameters derived from computed tomography in differentiating malignant from benign pulmonary nodules. Between September 2021 and December 2022, spectral images of 71 patients (male:female = 44:27, mean age = 71.0 years) confirmed by pathology were retrospectively analyzed in the venous phase. Patients were classified into the malignant group and the benign group. The iodine concentration values of the nodules, normalized iodine concentration of the nodules to the neighboring vessels, virtual monochromatic images of 40 and 80 keV, and slope of the spectral curve were calculated and compared between the benign and malignant groups. Receiver operating characteristic curves and the area under the curve were performed to assess the diagnostic performance of the above parameters. Both virtual monochromatic images and iodine concentration maps prove to be highly useful in differentiating benign and malignant pulmonary nodules. The malignant pulmonary nodules have higher iodine density and slope of the spectral curve than the benign lesions. The combined model of iodine density and curve slope with an optimal cutoff of 0.39 (area under the curve = 0.82) yielded a sensitivity of 95% and a specificity of 63%. Contrast-enhanced dual-energy spectral computed tomography allows promising capability of distinguishing malignant from benign lesions, potential for avoiding unnecessary invasive procedure or surgery.

Prediction of benign and malignant ground glass pulmonary nodules based on multi-feature fusion of attention mechanism.

The purpose of this study was to develop and validate a new feature fusion algorithm to improve the classification performance of benign and malignant ground-glass nodules (GGNs) based on deep learning. We retrospectively collected 385 cases of GGNs confirmed by surgical pathology from three hospitals. We utilized 239 GGNs from Hospital 1 as the training and internal validation set, and 115 and 31 GGNs from Hospital 2 and Hospital 3, respectively, as external test sets 1 and 2. Among these GGNs, 172 were benign and 203 were malignant. First, we evaluated clinical and morphological features of GGNs at baseline chest CT and simultaneously extracted whole-lung radiomics features. Then, deep convolutional neural networks (CNNs) and backpropagation neural networks (BPNNs) were applied to extract deep features from whole-lung CT images, clinical, morphological features, and whole-lung radiomics features separately. Finally, we integrated these four types of deep features using an attention mechanism. Multiple metrics were employed to evaluate the predictive performance of the model. The deep learning model integrating clinical, morphological, radiomics and whole lung CT image features with attention mechanism (CMRI-AM) achieved the best performance, with area under the curve (AUC) values of 0.941 (95% CI: 0.898-0.972), 0.861 (95% CI: 0.823-0.882), and 0.906 (95% CI: 0.878-0.932) on the internal validation set, external test set 1, and external test set 2, respectively. The AUC differences between the CMRI-AM model and other feature combination models were statistically significant in all three groups (all p<0.05). Our experimental results demonstrated that (1) applying attention mechanism to fuse whole-lung CT images, radiomics features, clinical, and morphological features is feasible, (2) clinical, morphological, and radiomics features provide supplementary information for the classification of benign and malignant GGNs based on CT images, and (3) utilizing baseline whole-lung CT features to predict the benign and malignant of GGNs is an effective method. Therefore, optimizing the fusion of baseline whole-lung CT features can effectively improve the classification performance of GGNs.

Deep learning-based CT image for pulmonary nodule classification with intrathoracic fat: A multicenter study

Correctly distinguishing between benign and malignant pulmonary nodules can avoid unnecessary invasive procedures. However, existing models exhibit a deficiency in the study of fat regions. We aim to create a multimodal deep learning nomogram (DLN) using pulmonary nodule and intrathoracic fat (ITF) features to distinguish between benign and malignant nodules and further demonstrate that intrathoracic fat can enhance the performance of lung cancer prediction models. A segmentation methodology was devised for precisely delineating intranodular and perinodular region (IPN). The Swin Transformer was used for feature extraction. The least absolute shrinkage and selection operator (LASSO) regression was employed for feature selection. The nomogram integrating IPN and ITF signatures revealed better diagnostic accuracy than IPN signature alone (net reclassification improvement = 0.134, P<0.05, and integrated discrimination improvement = 0.078, P<0.05). In the internal test cohort, DLN obtained an area under the curve (AUC) of 0.913 (95 % CI: 0.870, 0.952). In the external test cohort, the AUC was 0.906 (95 % CI: 0.867, 0.938). There was no significant difference between the calibrated curve and perfectly calibrated curve in all cohorts (P>0.05). Decision curve analysis showed that the DLN was clinically useful. The DLN demonstrated substantial diagnostic value for distinguishing between benign and malignant pulmonary nodules. The incorporation of the ITF signature has enhanced the performance of DLN.

Lung nodule classification using radiomics model trained on degraded SDCT images

Background and ObjectiveLow-dose computed tomography (LDCT) screening has shown promise in reducing lung cancer mortality; however, it suffers from high false positive rates and a scarcity of available annotated datasets. To overcome these challenges, we propose a novel approach using synthetic LDCT images generated from standard-dose CT (SDCT) scans from the LIDC-IDRI dataset. Our objective is to develop and validate an interpretable radiomics-based model for distinguishing likely benign from likely malignant pulmonary nodules. MethodsFrom a total of 1010 CT images (695 SDCTs and 315 LDCTs), we degraded SDCTs in the sinogram domain and obtained 1950 nodules as the training set. The 675 nodules from the LDCTs were stratified into 50%-50% partitions for validation and testing. Radiomic features were extracted from nodules, and three feature sets were assessed using: a) only shape and size (SS) features, b) all features but SS features, and c) all features. A systematic pipeline was developed to optimize the feature set and evaluate multiple machine learning models. Models were trained using degraded SDCT, validated and tested on the LDCT nodules. ResultsTraining a logistic regression model using three SS features yielded the most promising results, achieving on the test set mean balanced accuracy, sensitivity, specificity, and AUC-ROC scores of 0.81, 0.76, 0.85, and 0.87, respectively. ConclusionsOur study demonstrates the feasibility and effectiveness of using synthetic LDCT images for developing a relatively accurate radiomics-based model in lung nodule classification. This approach addresses challenges associated with LDCT screening, offering potential implications for improving lung cancer detection and reducing false positives.

Predicting malignant potential of solitary pulmonary nodules in patients with COVID-19 infection: a comprehensive analysis of CT imaging and tumor markers

ObjectiveTo analyze the value of combining computed tomography (CT) with serum tumor markers in the differential diagnosis of benign and malignant solitary pulmonary nodules (SPNs).MethodsThe case data of 267 patients diagnosed with SPNs in the First Affiliated Hospital of Zhengzhou University from March 2020 to January 2023 were retrospectively analyzed. All individuals diagnosed with coronavirus disease 2019 (COVID-19) were confirmed via respiratory specimen viral nucleic acid testing. The included cases underwent CT, serum tumor marker testing and pathological examination. The diagnostic efficacy and clinical significance of CT, serum tumor marker testing and a combined test in identifying benign and malignant SPNs were analyzed using pathological histological findings as the gold standard. Finally, a nomogram mathematical model was established to predict the malignant probability of SPNs.ResultsOf the 267 patients with SPNs, 91 patients were not afflicted with COVID-19, 36 exhibited malignant characteristics, whereas 55 demonstrated benign features. Conversely, within the cohort of 176 COVID-19 patients presenting with SPNs, 62 were identified as having malignant SPNs, and the remaining 114 were diagnosed with benign SPNs. CT scans revealed statistically significant differences between the benign and malignant SPNs groups in terms of CT values (P<0.001), maximum nodule diameter (P<0.001), vascular convergence sign (P<0.001), vacuole sign (P = 0.0007), air bronchogram sign (P = 0.0005), and lobulation sign (P = 0.0005). Malignant SPNs were associated with significantly higher levels of carcinoembryonic antigen (CEA) and neuron-specific enolase (NSE) compared to benign SPNs (P < 0.05), while no significant difference was found in carbohydrate antigen 125 (CA125) levels (P = 0.054 for non-COVID-19; P = 0.072 for COVID-19). The sensitivity (95.83%), specificity (95.32%), and accuracy (95.51%) of the comprehensive diagnosis combining serum tumor markers and CT were significantly higher than those of CT alone (70.45%, 79.89%, 76.78%) or serum tumor marker testing alone (56.52%, 73.71%, 67.79%) (P < 0.05). A visual nomogram predictive model for malignant pulmonary nodules was constructed.ConclusionCombining CT with testing for CEA, CA125, and NSE levels offers high diagnostic accuracy and sensitivity, enables precise differentiation between benign and malignant nodules, particularly in the context of COVID-19, thereby reducing the risk of unnecessary surgical interventions.

GC-WIR : 3D global coordinate attention wide inverted ResNet network for pulmonary nodules classification

PurposeCurrently, deep learning methods for the classification of benign and malignant lung nodules encounter challenges encompassing intricate and unstable algorithmic models, limited data adaptability, and an abundance of model parameters.To tackle these concerns, this investigation introduces a novel approach: the 3D Global Coordinated Attention Wide Inverted ResNet Network (GC-WIR). This network aims to achieve precise classification of benign and malignant pulmonary nodules, leveraging its merits of heightened efficiency, parsimonious parameterization, and robust stability.MethodsWithin this framework, a 3D Global Coordinate Attention Mechanism (3D GCA) is designed to compute the features of the input images by converting 3D channel information and multi-dimensional positional cues. By encompassing both global channel details and spatial positional cues, this approach maintains a judicious balance between flexibility and computational efficiency. Furthermore, the GC-WIR architecture incorporates a 3D Wide Inverted Residual Network (3D WIRN), which augments feature computation by expanding input channels. This augmentation mitigates information loss during feature extraction, expedites model convergence, and concurrently enhances performance. The utilization of the inverted residual structure imbues the model with heightened stability.ResultsEmpirical validation of the GC-WIR method is performed on the LUNA 16 dataset, yielding predictions that surpass those generated by previous models. This novel approach achieves an impressive accuracy rate of 94.32%, coupled with a specificity of 93.69%. Notably, the model’s parameter count remains modest at 5.76M, affording optimal classification accuracy.ConclusionFurthermore, experimental results unequivocally demonstrate that, even under stringent computational constraints, GC-WIR outperforms alternative deep learning methodologies, establishing a new benchmark in performance.

A Multi-Task Model for Pulmonary Nodule Segmentation and Classification.

In the computer-aided diagnosis of lung cancer, the automatic segmentation of pulmonary nodules and the classification of benign and malignant tumors are two fundamental tasks. However, deep learning models often overlook the potential benefits of task correlations in improving their respective performances, as they are typically designed for a single task only. Therefore, we propose a multi-task network (MT-Net) that integrates shared backbone architecture and a prediction distillation structure for the simultaneous segmentation and classification of pulmonary nodules. The model comprises a coarse segmentation subnetwork (Coarse Seg-net), a cooperative classification subnetwork (Class-net), and a cooperative segmentation subnetwork (Fine Seg-net). Coarse Seg-net and Fine Seg-net share identical structure, where Coarse Seg-net provides prior location information for the subsequent Fine Seg-net and Class-net, thereby boosting pulmonary nodule segmentation and classification performance. We quantitatively and qualitatively analyzed the performance of the model by using the public dataset LIDC-IDRI. Our results show that the model achieves a Dice similarity coefficient (DI) index of 83.2% for pulmonary nodule segmentation, as well as an accuracy (ACC) of 91.9% for benign and malignant pulmonary nodule classification, which is competitive with other state-of-the-art methods. The experimental results demonstrate that the performance of pulmonary nodule segmentation and classification can be improved by a unified model that leverages the potential correlation between tasks.

Clinical value of peripheral blood miR-21 and miR-486 combined with CT forearly cancer diagnosis in pulmonary nodulessmoking

PurposeThis study aimed to investigate the clinical significance of combining peripheral blood miR-21 and miR-486 with CT for the early cancer diagnosis in pulmonary nodules.MethodsA total of 215 patients diagnosed with isolated pulmonary nodules with a history of smoking were selected as researchsubjects. 30 healthy volunteers with a history of smoking were recruitedas the control group.The selection of subjectswas based on the presence of isolated pulmonary nodules detected on chest CT scans. The training set consisted of 65 patients with lung nodules and 30 healthy smokers, while the verification setincluded 150 patients with lung nodules.ResultsCompared with the control group, the plasma expression level of miR-210 was significantly higher in the group of patients with benign pulmonary nodules (P < 0.05). The level of miR-486-5p was lower in patients with malignant pulmonary nodules compared to those with benign pulmonary nodules (P < 0.05). Moreover, the plasma level of miR-210was higher in patients with malignant pulmonary nodules compared to those with benign pulmonary nodules and healthy smokers (P < 0.05). The combination of miR-21 and miR-486 yielded an AUC of 0.865, which was significantly higher than any other gene combination (95%CI: 0.653–0.764, P < 0.05).ConclusionsThis study offered preliminary evidence supporting the use of peripheral blood miR-21 and miR-486, combined with CT scans, as potential biomarkers for the early cancer diagnosis in lung nodules.

Multimodal Deep Learning Network for Differentiating Between Benign and Malignant Pulmonary Ground Glass Nodules.

This study aimed to establish a multimodal deep-learning network model to enhance the diagnosis of benign and malignant pulmonary ground glass nodules [GGNs]. Retrospective data on pulmonary GGNs were collected from multiple centers across China, including North, Northeast, Northwest, South, and Southwest China. The data were divided into a training set and a validation set in an 8:2 ratio. In addition, a GGN dataset was also obtained from our hospital database and used as the test set. All patients underwent chest computed tomography [CT], and the final diagnosis of the nodules was based on postoperative pathological reports. The Residual Network [ResNet] was used to extract imaging data, the Word2Vec method for semantic information extraction, and the Self Attention method for combining imaging features and patient data to construct a multimodal classification model. Then, the diagnostic efficiency of the proposed multimodal model was compared with that of existing ResNet and VGG models and radiologists. The multicenter dataset comprised 1020 GGNs, including 265 benign and 755 malignant nodules, and the test dataset comprised 204 GGNs, with 67 benign and 137 malignant nodules. In the validation set, the proposed multimodal model achieved an accuracy of 90.2%, a sensitivity of 96.6%, and a specificity of 75.0%, which surpassed that of the VGG [73.1%, 76.7%, and 66.5%] and ResNet [78.0%, 83.3%, and 65.8%] models in diagnosing benign and malignant nodules. In the test set, the multimodal model accurately diagnosed 125 [91.18%] malignant nodules, outperforming radiologists [80.37% accuracy]. Moreover, the multimodal model correctly identified 54 [accuracy, 80.70%] benign nodules, compared to radiologists' accuracy of 85.47%. The consistency test comparing radiologists' diagnostic results with the multimodal model's results in relation to postoperative pathology showed strong agreement, with the multimodal model demonstrating closer alignment with gold standard pathological findings [Kappa=0.720, P<0.01]. The multimodal deep learning network model exhibited promising diagnostic effectiveness in distinguishing benign and malignant GGNs and, therefore, holds potential as a reference tool to assist radiologists in improving the diagnostic accuracy of GGNs, potentially enhancing their work efficiency in clinical settings.

Metabolic reprogramming-related gene classifier distinguishes malignant from the benign pulmonary nodules

The current existing classifiers for distinguishing malignant from benign pulmonary nodules is limited by effectiveness or clinical practicality. In our study, we aimed to develop and validate a gene classifier for lung cancer diagnosis. To identify the genes involved in this process, we used the weighted gene co-expression network analysis to analyze gene expression datasets from Gene Expression Omnibus (GEO). We identified the three most relevant modules associated with malignant nodules and performed functional enrichment analysis on them. The results indicated significant involvement in metabolic, immune-related, cell cycle, and viral-related processes. All three modules showed enrichment in metabolic reprogramming pathways. Based on these genes, we intersected genes from the three modules with metabolic reprogramming-related genes and further intersected with differentially expressed genes to get 78 genes. After machine learning algorithms and manual selection, we finally got a nine-gene classifier consisting of SEC24D, RPSA, PSME3, PSMD8, PSMB7, NCOA1, MED12, LPCAT1, and AKR1C3. Our developed and validated classifier-based model demonstrated good discrimination, with an area under the curve (AUC) of 0.763 in the development cohort, 0.744 in the internal validation cohort, and 0.718 in the external validation cohort, and outperformed previous clinical models. Moreover, the addition of nodule size improved the predictive capability of the classifier. We further verify the expression of the gene in the classifier using TCGA lung cancer samples and found eight of the genes showed significant differential expression in lung adenocarcinoma while all nine genes showed significant differential expression in lung squamous carcinoma. Our findings underscore the significance of metabolic reprogramming pathways in patients with malignant pulmonary nodules, and our gene classifier can assist clinicians in differentiating benign from malignant pulmonary nodules in clinical settings.

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.

Deep Learning Radiomics Features of Mediastinal Fat and Pulmonary Nodules on Lung CT Images Distinguish Benignancy and Malignancy.

This study investigated the relationship between mediastinal fat and pulmonary nodule status, aiming to develop a deep learning-based radiomics model for diagnosing benign and malignant pulmonary nodules. We proposed a combined model using CT images of both pulmonary nodules and the fat around the chest (mediastinal fat). Patients from three centers were divided into training, validation, internal testing, and external testing sets. Quantitative radiomics and deep learning features from CT images served as predictive factors. A logistic regression model was used to combine data from both pulmonary nodules and mediastinal adipose regions, and personalized nomograms were created to evaluate the predictive performance. The model incorporating mediastinal fat outperformed the nodule-only model, with C-indexes of 0.917 (training), 0.903 (internal testing), 0.942 (external testing set 1), and 0.880 (external testing set 2). The inclusion of mediastinal fat significantly improved predictive performance (NRI = 0.243, p < 0.05). A decision curve analysis indicated that incorporating mediastinal fat features provided greater patient benefits. Mediastinal fat offered complementary information for distinguishing benign from malignant nodules, enhancing the diagnostic capability of this deep learning-based radiomics model. This model demonstrated strong diagnostic ability for benign and malignant pulmonary nodules, providing a more accurate and beneficial approach for patient care.

Non-invasive diagnosis of pulmonary nodules by circulating tumor DNA methylation: A prospective multicenter study

BackgroundWith the popularization of computed tomography, more and more pulmonary nodules (PNs) are being detected. Risk stratification of PNs is essential for detecting early-stage lung cancer while minimizing the overdiagnosis of benign nodules. This study aimed to develop a circulating tumor DNA (ctDNA) methylation-based, non-invasive model for the risk stratification of PNs. MethodsA blood-based assay (“LUNG-TRAC”) was designed to include novel lung cancer ctDNA methylation markers identified from in-house reduced representative bisulfite sequencing data and known markers from the literature. A stratification model was trained based on 183 ctDNA samples derived from patients with benign or malignant PNs and validated in 62 patients. LUNG-TRAC was further single-blindly tested in a single- and multi-center cohort. ResultsThe LUNG-TRAC model achieved an area under the curve (AUC) of 0.810 (sensitivity = 74.4 % and specificity = 73.7 %) in the validation set. Two test sets were used to evaluate the performance of LUNG-TRAC, with an AUC of 0.815 in the single-center test (N = 61; sensitivity = 67.5 % and specificity = 76.2 %) and 0.761 in the multi-center test (N = 95; sensitivity = 50.7 % and specificity = 80.8 %). The clinical utility of LUNG-TRAC was further assessed by comparing it to two established risk stratification models: the Mayo Clinic and Veteran Administration models. It outperformed both in the validation and the single-center test sets. ConclusionThe LUNG-TRAC model demonstrated accuracy and consistency in stratifying PNs for the risk of malignancy, suggesting its utility as a non-invasive diagnostic aid for early-stage peripheral lung cancer. Clinical trial registrationwww.clinicaltrials.gov (NCT03989219).

A Multi-Modal Machine Learning Methodology for Predicting Solitary Pulmonary Nodule Malignancy in Patients Undergoing PET/CT Examination

This study explores a multi-modal machine-learning-based approach to classify solitary pulmonary nodules (SPNs). Non-small cell lung cancer (NSCLC), presenting primarily as SPNs, is the leading cause of cancer-related deaths worldwide. Early detection and appropriate management of SPNs are critical to improving patient outcomes, necessitating efficient diagnostic methodologies. While CT and PET scans are pivotal in the diagnostic process, their interpretation remains prone to human error and delays in treatment implementation. This study proposes a machine-learning-based network to mitigate these concerns, integrating CT, PET, and manually extracted features in a multi-modal manner by integrating multiple image modalities and tabular features). CT and PET images are classified by a VGG19 network, while additional SPN features in combination with the outputs of VGG19 are processed by an XGBoost model to perform the ultimate diagnosis. The proposed methodology is evaluated using patient data from the Department of Nuclear Medicine of the University Hospital of Patras in Greece. We used 402 patient cases with human annotations to internally validate the model and 96 histopathological-confirmed cases for external evaluation. The model exhibited 97% agreement with the human readers and 85% diagnostic performance in the external set. It also identified the VGG19 predictions from CT and PET images, SUVmax, and diameter as key malignancy predictors. The study suggests that combining all available image modalities and SPN characteristics improves the agreement of the model with the human readers and the diagnostic efficiency.