Development and validation of a preoperative CT-based radiomic nomogram to predict pathology invasiveness in patients with a solitary pulmonary nodule: a machine learning approach, multicenter, diagnostic study

Clinical applications of radiomics and deep learning in breast and lung cancer: A narrative literature review on current evidence and future perspectives

Radiomics, analysing quantitative features from medical imaging, has rapidly become an emerging field in translational oncology. Radiomics has been investigated in several neoplastic malignancies as it might allow for a non-invasive tumour characterization and for the identification of predictive and prognostic biomarkers. Over the last few years, evidence has been accumulating regarding potential clinical applications of machine learning in many crucial moments of cancer patients' history. However, the incorporation of radiomics in clinical decision-making process is still limited by low data reproducibility and study variability. Moreover, the need for prospective validations and standardizations is emerging. In this narrative review, we summarize current evidence regarding radiomic applications in high-incidence cancers (breast and lung) for screening, diagnosis, staging, treatment choice, response, and clinical outcome evaluation. We also discuss pro and cons of the radiomic approach, suggesting possible solutions to critical issues which might invalidate radiomics studies and propose future perspectives.

A comprehensive predictive model for postoperative joint function in robot-assisted total hip arthroplasty patients: combining radiomics and clinical indicators

Total hip arthroplasty (THA) effectively treats various end-stage hip conditions, offering pain relief and improved joint function. However, surgical outcomes are influenced by multifaceted factors. This research aims to create a predictive model, incorporating radiomic and clinical information, to forecast post-surgery joint function in robot-assisted THA (RA-THA) patients. The study set comprised 136 patients who underwent unilateral RA-THA, which were subsequently partitioned into a training set (n = 95) and a test set (n = 41) for analysis. Preoperative CT imaging was employed to derive 851 radiomic characteristics, selecting those with an intra-class correlation coefficient > 0.75 for analysis. Least absolute shrinkage and selection operator regression reduced redundancy to six significant radiomic features. Clinical data including preoperative Visual Analog Scale (VAS), Harris Hip Score (HHS), and Western Ontario and McMaster University Osteoarthritis Index (WOMAC) score were collected. Logistic regression identified significant predictors, and three models were developed. Receiver operating characteristic and decision curves evaluated the models. Preoperative VAS, HHS, WOMAC score, and radiomics feature scores were significant predictors. In the training set, the AUCs were 0.835 (clinical model), 0.757 (radiomic model), and 0.891 (combined model). In the test set, the AUCs were 0.777 (clinical model), 0.824 (radiomic model), and 0.881 (combined model). The constructed nomogram prediction model combines radiological features with relevant clinical data to accurately predict functional outcomes 3 years after RA-THA. This model has significant prediction accuracy and broad clinical application prospects and can provide a valuable reference for formulating personalized treatment plans and optimizing patient management strategies.

The scoring system combined with radiomics and imaging features in predicting the malignant potential of incidental indeterminate small (<20 mm) solid pulmonary nodules

OBJECTIVE

Develop a practical scoring system based on radiomics and imaging features, for predicting the malignant potential of incidental indeterminate small solid pulmonary nodules (IISSPNs) smaller than 20 mm.

METHODS

A total of 360 patients with malignant IISSPNs (n = 213) and benign IISSPNs (n = 147) confirmed after surgery were retrospectively analyzed. The whole cohort was randomly divided into training and validation groups at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) algorithm was used to debase the dimensions of radiomics features. Multivariate logistic analysis was performed to establish models. The receiver operating characteristic (ROC) curve, area under the curve (AUC), 95% confidence interval (CI), sensitivity and specificity of each model were recorded. Scoring system based on odds ratio was developed.

RESULTS

Three radiomics features were selected for further model establishment. After multivariate logistic analysis, the combined model including Mean, age, emphysema, lobulated and size, reached highest AUC of 0.877 (95%CI: 0.830-0.915), accuracy rate of 83.3%, sensitivity of 85.3% and specificity of 80.2% in the training group, followed by radiomics model (AUC: 0.804) and imaging model (AUC: 0.773). A scoring system with a cutoff value greater than 4 points was developed. If the score was larger than 8 points, the possibility of diagnosing malignant IISSPNs could reach at least 92.7%.

CONCLUSION

The combined model demonstrated good diagnostic performance in predicting the malignant potential of IISSPNs. A perfect accuracy rate of 100% can be achieved with a score exceeding 12 points in the user-friendly scoring system.

A metric for quantitative evaluation of glioma margin changes in magnetic resonance imaging

BACKGROUND

Gliomas differ from meningiomas in their margins, most of which are not separated from the surrounding tissue by a distinct interface.

PURPOSE

To characterize the margins of gliomas quantitatively based on the margin sharpness coefficient (MSC) is significant for clinical judgment and invasive analysis of gliomas.

MATERIAL AND METHODS

The data for this study used magnetic resonance image (MRI) data from 67 local patients and 15 open patients to quantify the intensity of changes in the glioma margins of the brain using MSC. The accuracy of MSC was assessed by consistency analysis and Bland-Altman test analysis, as well as invasive correlations using receiver operating characteristic (ROC) and Spearman correlation coefficients for subjects.

RESULTS

In grading the tumors, the mean MSC values were significantly lower for high-grade gliomas (HGG) than for low-grade gliomas (LGG). The concordance correlation between the measured gradient and the actual gradient was high (HGG: 0.981; LGG: 0.993), and the Bland-Altman mean difference at the 95% confidence interval (HGG: -0.576; LGG: 0.254) and the limits of concordance (HGG: 5.580; LGG: 5.436) indicated no statistical difference. The correlation between MSC and invasion based on the margins of gliomas showed an AUC of 0.903 and 0.911 for HGG and LGG, respectively. The mean Spearman correlation coefficient of the MSC versus the actual distance of invasion was -0.631 in gliomas.

CONCLUSION

The relatively low MSC on the blurred margins and irregular shape of gliomas may help in benign-malignant differentiation and invasion prediction of gliomas and has potential application for clinical judgment.

Nomogram using intratumoral and peritumoral radiomics for the preoperative prediction of visceral pleural invasion in clinical stage IA lung adenocarcinoma

BACKGROUND

Accurate prediction of visceral pleural invasion (VPI) in lung adenocarcinoma before operation can provide guidance and help for surgical operation and postoperative treatment. We investigate the value of intratumoral and peritumoral radiomics nomograms for preoperatively predicting the status of VPI in patients diagnosed with clinical stage IA lung adenocarcinoma.

METHODS

A total of 404 patients from our hospital were randomly assigned to a training set (n = 283) and an internal validation set (n = 121) using a 7:3 ratio, while 81 patients from two other hospitals constituted the external validation set. We extracted 1218 CT-based radiomics features from the gross tumor volume (GTV) as well as the gross peritumoral tumor volume (GPTV5, 10, 15), respectively, and constructed radiomic models. Additionally, we developed a nomogram based on relevant CT features and the radscore derived from the optimal radiomics model.

RESULTS

The GPTV10 radiomics model exhibited superior predictive performance compared to GTV, GPTV5, and GPTV15, with area under the curve (AUC) values of 0.855, 0.842, and 0.842 in the three respective sets. In the clinical model, the solid component size, pleural indentation, solid attachment, and vascular convergence sign were identified as independent risk factors among the CT features. The predictive performance of the nomogram, which incorporated relevant CT features and the GPTV10-radscore, outperformed both the radiomics model and clinical model alone, with AUC values of 0.894, 0.828, and 0.876 in the three respective sets.

CONCLUSIONS

The nomogram, integrating radiomics features and CT morphological features, exhibits good performance in predicting VPI status in lung adenocarcinoma.

NGEF is a potential prognostic biomarker and could serve as an indicator for immunotherapy and chemotherapy in lung adenocarcinoma

BACKGROUND

Neuronal guanine nucleotide exchange factor (NGEF) plays a key role in several cancers; however, its role in lung adenocarcinoma (LUAD) remains unclear. The aim of this study was to evaluate the efficacy of NGEF as a prognostic biomarker and potential therapeutic target for LUAD.

METHODS

NGEF expression data for multiple cancers and LUAD were downloaded from multiple databases. The high- and low-NGEF expression groups were constructed based on median NGEF expression in LUAD samples, and then performed Kaplan-Meier survival analysis. Differentially expressed genes (DEGs) from the two NGEF expression groups were screened and applied to construct a protein-protein interaction network. The primary pathways were obtained using gene set enrichment analysis. The associations between NGEF expression and clinical characteristics, immune infiltration, immune checkpoint inhibitors (ICIs), sensitivity to chemotherapy, and tumor mutation burden (TMB) were investigated using R. Levels of NGEF expression in the lung tissue was validated using single-cell RNA sequencing, quantitative polymerase chain reaction (qPCR), immunohistochemical staining, and western blot analysis.

RESULTS

The expression of NGEF mRNA was upregulated in multiple cancers. mRNA and protein expression levels of NGEF were higher in patients with LUAD than in controls, as validated using qPCR and western blot. High NGEF expression was an independent prognostic factor for LUAD and was associated with advanced tumor stage, large tumor size, more lymph node metastasis, and worse overall survival (OS). A total of 182 overlapping DEGs were screened between The Cancer Genome Atlas and GSE31210, among which the top 20 hub genes were identified. NGEF expression was mainly enriched in the pathways of apoptosis, cell cycle, and DNA replication. Moreover, elevated NGEF expression were associated with a high fraction of activated memory CD4+ T cells and M0 macrophages; elevated expression levels of the ICIs: programmed cell death 1 and programmed cell death 1 ligand 1 expression; higher TMB; and better sensitivity to bortezomib, docetaxel, paclitaxel, and parthenolide, but less sensitivity to axitinib and metformin.

CONCLUSION

NGEF expression is upregulated in LUAD and is significantly associated with tumor stages, OS probability, immune infiltration, immunotherapy response, and chemotherapy response. NGEF may be a potential diagnostic and prognostic biomarker and therapeutic target in LUAD.

CT imaging features of lung ground-glass nodule patients with upgraded intraoperative frozen pathology

PURPOSE

Intraoperative frozen section pathology (FS) is widely used to guide surgical strategies while the accuracy is relatively low. Underestimating the pathological condition may result in inadequate surgical margins. This study aims to identify CT imaging features related to upgraded FS and develop a predictive model.

METHODS

Collected data from 860 patients who underwent lung surgery from January to December 2019. We analyzed the consistency rate of FS and categorized the patients into three groups: Group 1 (n = 360) had both FS and Formalin-fixed Paraffin-embedded section (FP) as non-invasive adenocarcinoma (IAC); Group 2 (n = 128) had FS as non-IAC but FP as IAC; Group 3 (n = 372) had both FS and FP as IAC. Clinical baseline characteristics were compared and propensity score adjustment was used to mitigate the effects of these characteristics. Univariate analyses identified imaging features with inter-group differences. A multivariate analysis was conducted to screen independent risk factors for FS upgrade, after which a logistic regression prediction model was established and a receiver operating characteristic (ROC) curve was plotted.

RESULTS

The consistency rate of FS with FP was 84.19%. 26.67% of the patients with non-IAC FS diagnosis were upgraded to IAC. The predictive model's Area Under Curve (AUC) is 0.785. Consolidation tumor ratio (CTR) ≤ 0.5 and smaller nodule diameter are associated with the underestimation of IAC in FS.

CONCLUSION

CT imaging has the capacity to effectively detect patients at risk of upstaging during FS.

A nomogram based on CT intratumoral and peritumoral radiomics features preoperatively predicts poorly differentiated invasive pulmonary adenocarcinoma manifesting as subsolid or solid lesions: a double-center study

Background

The novel International Association for the Study of Lung Cancer (IASLC) grading system suggests that poorly differentiated invasive pulmonary adenocarcinoma (IPA) has a worse prognosis. Therefore, prediction of poorly differentiated IPA before treatment can provide an essential reference for therapeutic modality and personalized follow-up strategy. This study intended to train a nomogram based on CT intratumoral and peritumoral radiomics features combined with clinical semantic features, which predicted poorly differentiated IPA and was tested in independent data cohorts regarding models' generalization ability.

Methods

We retrospectively recruited 480 patients with IPA appearing as subsolid or solid lesions, confirmed by surgical pathology from two medical centers and collected their CT images and clinical information. Patients from the first center (n =363) were randomly assigned to the development cohort (n = 254) and internal testing cohort (n = 109) in a 7:3 ratio; patients (n = 117) from the second center served as the external testing cohort. Feature selection was performed by univariate analysis, multivariate analysis, Spearman correlation analysis, minimum redundancy maximum relevance, and least absolute shrinkage and selection operator. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the model performance.

Results

The AUCs of the combined model based on intratumoral and peritumoral radiomics signatures in internal testing cohort and external testing cohort were 0.906 and 0.886, respectively. The AUCs of the nomogram that integrated clinical semantic features and combined radiomics signatures in internal testing cohort and external testing cohort were 0.921 and 0.887, respectively. The Delong test showed that the AUCs of the nomogram were significantly higher than that of the clinical semantic model in both the internal testing cohort(0.921 vs 0.789, p< 0.05) and external testing cohort(0.887 vs 0.829, p< 0.05).

Conclusion

The nomogram based on CT intratumoral and peritumoral radiomics signatures with clinical semantic features has the potential to predict poorly differentiated IPA manifesting as subsolid or solid lesions preoperatively.

Interpretable CT radiomics model for invasiveness prediction in patients with ground-glass nodules

AIM

To evaluate the performance of an interpretable computed tomography (CT) radiomic model in predicting the invasiveness of ground-glass nodules (GGNs).

MATERIALS AND METHODS

The study was conducted retrospectively from 1 August 2017 to 1 August 2022, at three different centres. Two hundred and thirty patients with GGNs were enrolled at centre I as a training cohort. Centres II (n=157) and III (n=156) formed two external validation cohorts. Radiomics features extracted based on CT were reduced by a coarse-fine feature screening strategy. A radiomic model was developed through the use of the LASSO (least absolute shrinkage and selection operator) and XGBoost algorithms. Then, a radiological model was established through multivariate logistic regression analysis. Finally, the interpretability of the model was explored using SHapley Additive exPlanations (SHAP).

RESULTS

The radiomic XGBoost model outperformed the radiomic logistic model and radiological model in assessing the invasiveness of GGNs. The area under the curve (AUC) values for the radiomic XGBoost model were 0.885 (95% confidence interval [CI] 0.836-0.923), 0.853 (95% CI 0.790-0.906), and 0.838 (95% CI 0.773-0.902) in the training and the two external validation cohorts, respectively. The SHAP method allowed for both a quantitative and visual representation of how decisions were made using a given model for each individual patient. This can provide a deeper understanding of the decision-making mechanisms within the model and the factors that contribute to its prediction effectiveness.

CONCLUSIONS

The present interpretable CT radiomics model has the potential to preoperatively evaluate the invasiveness of GGNs. Furthermore, it can provide personalised, image-based clinical-decision support.

Radiomics and Artificial Intelligence in Renal Lesion Assessment

Radiomics, the extraction and analysis of quantitative features from medical images, has emerged as a promising field in radiology with the potential to revolutionize the diagnosis and management of renal lesions. This comprehensive review explores the radiomics workflow, including image acquisition, feature extraction, selection, and classification, and highlights its application in differentiating between benign and malignant renal lesions. The integration of radiomics with artificial intelligence (AI) techniques, such as machine learning and deep learning, can help patients' management and allow the planning of the appropriate treatments. AI models have shown remarkable accuracy in predicting tumor aggressiveness, treatment response, and patient outcomes. This review provides insights into the current state of radiomics and AI in renal lesion assessment and outlines future directions for research in this rapidly evolving field.

Predicting the pathological invasiveness in patients with a solitary pulmonary nodule via Shapley additive explanations interpretation of a tree-based machine learning radiomics model: a multicenter study

Background

Radiomics models could help assess the benign and malignant invasiveness and prognosis of pulmonary nodules. However, the lack of interpretability limits application of these models. We thus aimed to construct and validate an interpretable and generalized computed tomography (CT) radiomics model to evaluate the pathological invasiveness in patients with a solitary pulmonary nodule in order to improve the management of these patients.

Methods

We retrospectively enrolled 248 patients with CT-diagnosed solitary pulmonary nodules. Radiomic features were extracted from nodular region and perinodular regions of 3 and 5 mm. After coarse-to-fine feature selection, the radiomics score (radscore) was calculated using the least absolute shrinkage and selection operator logistic method. Univariate and multivariate logistic regression analyses were performed to determine the invasiveness-related clinicoradiological factors. The clinical-radiomics model was then constructed using the logistic and extreme gradient boosting (XGBoost) algorithms. The Shapley additive explanations (SHAP) method was then used to explain the contributions of the features. After removing batch effects with the ComBat algorithm, we assessed the generalization of the explainable clinical-radiomics model in two independent external validation cohorts (n=147 and n=149).

Results

The clinical-radiomic XGBoost model integrating the radscore, CT value, nodule length, and crescent sign demonstrated better predictive performance than did the clinical-radiomics logistic model in assessing pulmonary nodule invasiveness, with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.889 [95% confidence interval (CI), 0.848-0.927] in the training cohort. The SHAP algorithm illustrates the contribution of each feature in the final model. The specific model decision process was visualized using a tree-based decision heatmap. Satisfactory generalization performance was shown with AUCs of 0.889 (95% CI, 0.823-0.942) and 0.915 (95% CI, 0.851-0.963) in the two external validation cohorts.

Conclusions

An interpretable and generalized clinical-radiomics model for predicting pulmonary nodule invasibility was constructed to help clinicians determine the invasiveness of pulmonary nodules and devise assessment strategies in an easily understandable manner.

Multi-Layer Perceptron Classifier with the Proposed Combined Feature Vector of 3D CNN Features and Lung Radiomics Features for COPD Stage Classification

Computed tomography (CT) has been regarded as the most effective modality for characterizing and quantifying chronic obstructive pulmonary disease (COPD). Therefore, chest CT images should provide more information for COPD diagnosis, such as COPD stage classification. This paper proposes a features combination strategy by concatenating three-dimension (3D) CNN features and lung radiomics features for COPD stage classification based on the multi-layer perceptron (MLP) classifier. First, 465 sets of chest HRCT images are automatically segmented by a trained ResU-Net, obtaining the lung images with the Hounsfield unit. Second, the 3D CNN features are extracted from the lung region images based on a truncated transfer learning strategy. Then, the lung radiomics features are extracted from the lung region images by PyRadiomics. Third, the MLP classifier with the best classification performance is determined by the 3D CNN features and the lung radiomics features. Finally, the proposed combined feature vector is used to improve the MLP classifier's performance. The results show that compared with CNN models and other ML classifiers, the MLP classifier with the best classification performance is determined. The MLP classifier with the proposed combined feature vector has achieved accuracy, mean precision, mean recall, mean F1-score, and AUC of 0.879, 0.879, 0.879, 0.875, and 0.971, respectively. Compared to the MLP classifier with the 3D CNN features selected by Lasso, our method based on the MLP classifier has improved the classification performance by 5.8% (accuracy), 5.3% (mean precision), 5.8% (mean recall), 5.4% (mean F1-score), and 2.5% (AUC). Compared to the MLP classifier with lung radiomics features selected by Lasso, our method based on the MLP classifier has improved the classification performance by 5.0% (accuracy), 5.1% (mean precision), 5.0% (mean recall), 5.1% (mean F1-score), and 2.1% (AUC). Therefore, it is concluded that our method is effective in improving the classification performance for COPD stage classification.

Invasiveness identification in pure ground-glass nodules: exploring the generalizability of radiomics based on external validation and stress testing

PURPOSE

This study aimed to apply external validation and stress tests to evaluate the generalizability of radiomics models built using various machine-learning methods for identifying the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs).

METHODS

This retrospective study enrolled 495 patients (514 pGGNs) confirmed as lung adenocarcinomas by postoperative pathology from three centers. All nodules were included in the primary cohort (randomly divided into training and test cohorts), two external validation cohorts, and two stress test cohorts. Six machine-learning radiomics models were constructed in the training cohort using the optimal features. Performance of radiomics models and clinical models were compared in primary cohort and external validation cohorts. The stress tests included stratified performance evaluation and shifted performance evaluation and contrastive evaluation under three single-condition modification settings. The predictive performance was validated by area under curve (AUC) of receiver operating characteristic (ROC).

RESULTS

Of the six radiomics models, the best logistic regression (LR) model was able to maintain high differential diagnostic capability (AUC: 0.849 ± 0.049) and good stability (relative standard deviation, 5.719%), but it showed poorer performance (AUC = 0.835) than the clinical model (AUC = 0.862) in the external validation cohort E1. The stress tests suggested LR model had no significant difference in performance between subgroups after stratification and had good consistency in the predictions before and after the three transformations (Kappa = 0.960, 0.840, and 0.933, respectively; p < 0.05, all).

CONCLUSION

The rigorous testing procedure facilitates the selection of high-performance radiomics models with good clinical generalizability.

Pretreatment radiomic biomarker for immunotherapy responder prediction in stage IB-IV NSCLC (LCDigital-IO Study): a multicenter retrospective study

BACKGROUND

The predictive efficacy of current biomarker of immune checkpoint inhibitors (ICIs) is not sufficient. This study investigated the causality between radiomic biomarkers and immunotherapy response status in patients with stage IB-IV non-small cell lung cancer (NSCLC), including its biological context for ICIs treatment response prediction.

METHODS

CT images from 319 patients with pretreatment NSCLC receiving immunotherapy between January 2015 and November 2021 were retrospectively collected and composed a discovery (n=214), independent validation (n=54), and external test cohort (n=51). A set of 851 features was extracted from tumorous and peritumoral volumes of interest (VOIs). The reference standard is the durable clinical benefit (DCB, sustained disease control for more than 6 months assessed via radiological evaluation). The predictive value of combined radiomic signature (CRS) for pathological response was subsequently assessed in another cohort of 98 patients with resectable NSCLC receiving ICIs preoperatively. The association between radiomic features and tumor immune landscape on the online data set (n=60) was also examined. A model combining clinical predictor and radiomic signatures was constructed to improve performance further.

RESULTS

CRS discriminated DCB and non-DCB patients well in the training and validation cohorts with an area under the curve (AUC) of 0.82, 95% CI: 0.75 to 0.88, and 0.75, 95% CI: 0.64 to 0.87, respectively. In this study, the predictive value of CRS was better than programmed cell death ligand-1 (PD-L1) expression (AUC of PD-L1 subset: 0.59, 95% CI: 0.50 to 0.69) or clinical model (AUC: 0.66, 95% CI: 0.51 to 0.81). After combining the clinical signature with CRS, the predictive performance improved further with an AUC of 0.837, 0.790 and 0.781 in training, validation and D2 cohorts, respectively. When predicting pathological response, CRS divided patients into a major pathological response (MPR) and non-MPR group (AUC: 0.76, 95% CI: 0.67 to 0.81). Moreover, CRS showed a promising stratification ability on overall survival (HR: 0.49, 95% CI: 0.27 to 0.89; p=0.020) and progression-free survival (HR: 0.43, 95% CI: 0.26 to 0.74; p=0.002).

CONCLUSION

By analyzing both tumorous and peritumoral regions of CT images in a radiomic strategy, we developed a non-invasive biomarker for distinguishing responders of ICIs therapy and stratifying their survival outcome efficiently, which may support the clinical decisions on the use of ICIs in advanced as well as patients with resectable NSCLC.

Artificial Intelligence in Lung Cancer Screening: The Future Is Now

Lung cancer has one of the worst morbidity and fatality rates of any malignant tumour. Most lung cancers are discovered in the middle and late stages of the disease, when treatment choices are limited, and patients' survival rate is low. The aim of lung cancer screening is the identification of lung malignancies in the early stage of the disease, when more options for effective treatments are available, to improve the patients' outcomes. The desire to improve the efficacy and efficiency of clinical care continues to drive multiple innovations into practice for better patient management, and in this context, artificial intelligence (AI) plays a key role. AI may have a role in each process of the lung cancer screening workflow. First, in the acquisition of low-dose computed tomography for screening programs, AI-based reconstruction allows a further dose reduction, while still maintaining an optimal image quality. AI can help the personalization of screening programs through risk stratification based on the collection and analysis of a huge amount of imaging and clinical data. A computer-aided detection (CAD) system provides automatic detection of potential lung nodules with high sensitivity, working as a concurrent or second reader and reducing the time needed for image interpretation. Once a nodule has been detected, it should be characterized as benign or malignant. Two AI-based approaches are available to perform this task: the first one is represented by automatic segmentation with a consequent assessment of the lesion size, volume, and densitometric features; the second consists of segmentation first, followed by radiomic features extraction to characterize the whole abnormalities providing the so-called "virtual biopsy". This narrative review aims to provide an overview of all possible AI applications in lung cancer screening.

Radiomics applications in cardiac imaging: a comprehensive review

Radiomics is a new emerging field that includes extraction of metrics and quantification of so-called radiomic features from medical images. The growing importance of radiomics applied to oncology in improving diagnosis, cancer staging and grading, and improved personalized treatment, has been well established; yet, this new analysis technique has still few applications in cardiovascular imaging. Several studies have shown promising results describing how radiomics principles could improve the diagnostic accuracy of coronary computed tomography angiography (CCTA) and magnetic resonance imaging (MRI) in diagnosis, risk stratification, and follow-up of patients with coronary heart disease (CAD), ischemic heart disease (IHD), hypertrophic cardiomyopathy (HCM), hypertensive heart disease (HHD), and many other cardiovascular diseases. Such quantitative approach could be useful to overcome the main limitations of CCTA and MRI in the evaluation of cardiovascular diseases, such as readers' subjectiveness and lack of repeatability. Moreover, this new discipline could potentially overcome some technical problems, namely the need of contrast administration or invasive examinations. Despite such advantages, radiomics is still not applied in clinical routine, due to lack of standardized parameters acquisition, inconsistent radiomic methods, lack of external validation, and different knowledge and experience among the readers. The purpose of this manuscript is to provide a recent update on the status of radiomics clinical applications in cardiovascular imaging.

Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives

Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.

Qualitative and Semiquantitative Parameters of 18F-FDG-PET/CT as Predictors of Malignancy in Patients with Solitary Pulmonary Nodule

This study aims to evaluate the reliability of qualitative and semiquantitative parameters of ¹⁸F-FDG PET-CT, and eventually a correlation between them, in predicting the risk of malignancy in patients with solitary pulmonary nodules (SPNs) before the diagnosis of lung cancer. A total of 146 patients were retrospectively studied according to their pre-test probability of malignancy (all patients were intermediate risk), based on radiological features and risk factors, and qualitative and semiquantitative parameters, such as SUVmax, SUVmean, TLG, and MTV, which were obtained from the FDG PET-CT scan of such patients before diagnosis. It has been observed that visual analysis correlates well with the risk of malignancy in patients with SPN; indeed, only 20% of SPNs in which FDG uptake was low or absent were found to be malignant at the cytopathological examination, while 45.45% of SPNs in which FDG uptake was moderate and 90.24% in which FDG uptake was intense were found to be malignant. The same trend was observed evaluating semiquantitative parameters, since increasing values of SUVmax, SUVmean, TLG, and MTV were observed in patients whose cytopathological examination of SPN showed the presence of lung cancer. In particular, in patients whose SPN was neoplastic, we observed a median (MAD) SUVmax of 7.89 (±2.24), median (MAD) SUVmean of 3.76 (±2.59), median (MAD) TLG of 16.36 (±15.87), and a median (MAD) MTV of 3.39 (±2.86). In contrast, in patients whose SPN was non-neoplastic, the SUVmax was 2.24 (±1.73), SUVmean 1.67 (±1.15), TLG 1.63 (±2.33), and MTV 1.20 (±1.20). Optimal cut-offs were drawn for semiquantitative parameters considered predictors of malignancy. Nodule size correlated significantly with FDG uptake intensity and with SUVmax. Finally, age and nodule size proved significant predictors of malignancy. In conclusion, considering the pre-test probability of malignancy, qualitative and semiquantitative parameters can be considered reliable tools in patients with SPN, since cut-offs for SUVmax, SUVmean, TLG, and MTV showed good sensitivity and specificity in predicting malignancy.

Radiomics and Artificial Intelligence Can Predict Malignancy of Solitary Pulmonary Nodules in the Elderly

Solitary pulmonary nodules (SPNs) are a diagnostic and therapeutic challenge for thoracic surgeons. Although such lesions are usually benign, the risk of malignancy remains significant, particularly in elderly patients, who represent a large segment of the affected population. Surgical treatment in this subset, which usually presents several comorbidities, requires careful evaluation, especially when pre-operative biopsy is not feasible and comorbidities may jeopardize the outcome. Radiomics and artificial intelligence (AI) are progressively being applied in predicting malignancy in suspicious nodules and assisting the decision-making process. In this study, we analyzed features of the radiomic images of 71 patients with SPN aged more than 75 years (median 79, IQR 76-81) who had undergone upfront pulmonary resection based on CT and PET-CT findings. Three different machine learning algorithms were applied-functional tree, Rep Tree and J48. Histology was malignant in 64.8% of nodules and the best predictive value was achieved by the J48 model (AUC 0.9). The use of AI analysis of radiomic features may be applied to the decision-making process in elderly frail patients with suspicious SPNs to minimize the false positive rate and reduce the incidence of unnecessary surgery.

Nomogram prediction model of postoperative pneumonia in patients with lung cancer: A retrospective cohort study

Background

The prediction model of postoperative pneumonia (POP) after lung cancer surgery is still scarce.

Methods

Retrospective analysis of patients with lung cancer who underwent surgery at The Fourth Hospital of Hebei Medical University from September 2019 to March 2020 was performed. All patients were randomly divided into two groups, training cohort and validation cohort at the ratio of 7:3. The nomogram was formulated based on the results of multivariable logistic regression analysis and clinically important factors associated with POP. Concordance index (C-index), receiver operating characteristic (ROC) curve, calibration curve, Hosmer-Lemeshow goodness-of-fit test and decision curve analysis (DCA) were used to evaluate the predictive performance of the nomogram.

Results

A total of 1252 patients with lung cancer was enrolled, including 877 cases in the training cohort and 375 cases in the validation cohort. POP was found in 201 of 877 patients (22.9%) and 89 of 375 patients (23.7%) in the training and validation cohorts, respectively. The model consisted of six variables, including smoking, diabetes mellitus, history of preoperative chemotherapy, thoracotomy, ASA grade and surgery time. The C-index from AUC was 0.717 (95%CI:0.677-0.758) in the training cohort and 0.726 (95%CI:0.661-0.790) in the validation cohort. The calibration curves showed the model had good agreement. The result of DCA showed that the model had good clinical benefits.

Conclusion

This proposed nomogram could predict the risk of POP in patients with lung cancer surgery in advance, which can help clinician make reasonable preventive and treatment measures.

Multi-modal data combination strategy based on chest HRCT images and PFT parameters for intelligent dyspnea identification in COPD

Introduction

Because of persistent airflow limitation in chronic obstructive pulmonary disease (COPD), patients with COPD often have complications of dyspnea. However, as a leading symptom of COPD, dyspnea in COPD deserves special consideration regarding treatment in this fragile population for pre-clinical health management in COPD. Methods: Based on the above, this paper proposes a multi-modal data combination strategy by combining the local and global features for dyspnea identification in COPD based on the multi-layer perceptron (MLP) classifier.

Methods

First, lung region images are automatically segmented from chest HRCT images for extracting the original 1,316 lung radiomics (OLR, 1,316) and 13,824 3D CNN features (O3C, 13,824). Second, the local features, including five selected pulmonary function test (PFT) parameters (SLF, 5), 28 selected lung radiomics (SLR, 28), and 22 selected 3D CNN features (S3C, 22), are respectively selected from the original 11 PFT parameters (OLF, 11), 1,316 OLR, and 13,824 O3C by the least absolute shrinkage and selection operator (Lasso) algorithm. Meantime, the global features, including two fused PFT parameters (FLF, 2), six fused lung radiomics (FLR, 6), and 34 fused 3D CNN features (F3C, 34), are respectively fused by 11 OLF, 1,316 OLR, and 13,824 O3C using the principal component analysis (PCA) algorithm. Finally, we combine all the local and global features (SLF + FLF + SLR + FLR + S3C + F3C, 5+ 2 + 28 + 6 + 22 + 34) for dyspnea identification in COPD based on the MLP classifier.

Results

Our proposed method comprehensively improves classification performance. The MLP classifier with all the local and global features achieves the best classification performance at 87.7% of accuracy, 87.7% of precision, 87.7% of recall, 87.7% of F1-scorel, and 89.3% of AUC, respectively.

Discussion

Compared with single-modal data, the proposed strategy effectively improves the classification performance for dyspnea identification in COPD, providing an objective and effective tool for COPD management.

Development and validation of a nomogram for predicting survival time and making treatment decisions for clinical stage IA NSCLC based on the SEER database

Background

The aim of this study was to establish and validate a nomogram model for accurate prediction of patients' survival with T1aN0M0 none small cell lung cancer (NSCLC).

Methods

The patients, diagnosed with the stage IA NSCLC from 2004-2015, were identified from the Surveillance, Epidemiology and End Results (SEER) database. The variables with a P-value < 0.05 in a multivariate Cox regression were selected to establish the nomogram. The discriminative ability of the model was evaluated by the concordance index (C-index). The proximity of the nomogram prediction to the actual risk was depicted by a calibration plot. The clinical usefulness was estimated by the decision curve analysis (DCA). Survival curves were made with Kaplan-Meier method and compared by Log-Rank test.

Results

Eight variables, including treatment, age, sex, race, marriage, tumor size, histology, and grade were selected to develop the nomogram model by univariate and multivariate cox regression. The C-index was 0.704 (95% CI, 0.694-0.714) in the training set and 0.713 (95% CI, 0.697-0.728) in the test set, which performed significantly better than 8th edition AJCC TNM stage system (0.550, 95% CI, 0.408-0.683, P < 0.001). The calibration curve showed that the prediction ability of 3-years and 5-years survival rate demonstrated a high degree of agreement between the nomogram model and the actual observation. The DCA curves also proved that the nomogram-assisted decisions could improve patient outcomes.

Conclusion

We established and validated a prognostic nomogram to predict 3-years and 5-years overall survival in stage IA NSCLC.

Development and validation of 68Ga-PSMA-11 PET/CT-based radiomics model to detect primary prostate cancer

Background

This study aimed to develop a novel analytic approach based on a radiomics model derived from ⁶⁸Ga-prostate-specific membrane antigen (PSMA)-11 PET/CT for predicting intraprostatic lesions in patients with prostate cancer (PCa).

Methods

This retrospective study included consecutive patients with or without PCa who underwent surgery or biopsy after ⁶⁸Ga-PSMA-11 PET/CT. A total of 944 radiomics features were extracted from the images. A radiomics model was constructed using the least absolute shrinkage and selection operator (LASSO) algorithm with tenfold cross-validation in the training set. PET/CT images for the test set were reviewed by experienced nuclear medicine radiologists. The sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) were calculated for the model and radiologists’ results. The AUCs were compared.

Results

The total of 125 patients (86 PCa, 39 benign prostate disease [BPD]) included 87 (61 PCa, 26 BPD) in the training set and 38 (61 PCa, 26 BPD) in the test set. Nine features were selected to construct the radiomics model. The model score differed between PCa and BPD in the training and test sets (both P < 0.001). In the test set, the radiomics model performed better than the radiologists’ assessment (AUC, 0.85 [95% confidence interval 0.73, 0.97] vs. 0.63 [0.47, 0.79]; P = 0.036) and showed higher sensitivity (model vs radiologists, 0.84 [0.63, 0.95] vs. 0.74 [0.53, 0.88]; P = 0.002).

Conclusion

Radiomics analysis based on ⁶⁸Ga-PSMA-11 PET may non-invasively predict intraprostatic lesions in patients with PCa.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13550-022-00936-5.

Identification of pulmonary adenocarcinoma and benign lesions in isolated solid lung nodules based on a nomogram of intranodal and perinodal CT radiomic features

To develop and validate a predictive model based on clinical radiology and radiomics to enhance the ability to distinguish between benign and malignant solitary solid pulmonary nodules. In this study, we retrospectively collected computed tomography (CT) images and clinical data of 286 patients with isolated solid pulmonary nodules diagnosed by surgical pathology, including 155 peripheral adenocarcinomas and 131 benign nodules. They were randomly divided into a training set and verification set at a 7:3 ratio, and 851 radiomic features were extracted from thin-layer enhanced venous phase CT images by outlining intranodal and perinodal regions of interest. We conducted preprocessing measures of image resampling and eigenvalue normalization. The minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (lasso) methods were used to downscale and select features. At the same time, univariate and multifactorial analyses were performed to screen clinical radiology features. Finally, we constructed a nomogram based on clinical radiology, intranodular, and perinodular radiomics features. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUC), and the clinical decision curve (DCA) was used to evaluate the clinical practicability of the models. Univariate and multivariate analyses showed that the two clinical factors of sex and age were statistically significant. Lasso screened four intranodal and four perinodal radiomic features. The nomogram based on clinical radiology, intranodular, and perinodular radiomics features showed the best predictive performance (AUC=0.95, accuracy=0.89, sensitivity=0.83, specificity=0.96), which was superior to other independent models. A nomogram based on clinical radiology, intranodular, and perinodular radiomics features is helpful to improve the ability to predict benign and malignant solitary pulmonary nodules.

Signature based on RNA-binding protein-related genes for predicting prognosis and guiding therapy in non-small cell lung cancer

Background: Studies have reported that RNA-binding proteins (RBPs) are dysregulated in multiple cancers and are correlated with the progression and prognosis of disease. However, the functions of RBPs in non-small cell lung cancer (NSCLC) remain unclear. The present study aimed to explore the function of RBPs in NSCLC and their prognostic and therapeutic value.

Methods: The mRNA expression profiles, DNA methylation data, gene mutation data, copy number variation data, and corresponding clinical information on NSCLC were downloaded from The Cancer Genome Atlas, Gene Expression Omnibus, and the University of California Santa Cruz Xena databases. The differentially expressed RBPs were identified between tumor and control tissues, and the expression and prognostic value of these RBPs were systemically investigated by bioinformatics analysis. A quantitative polymerase chain reaction (qPCR) was performed to validate the dysregulated genes in the prognostic signature.

Results: A prognostic RBP-related signature was successfully constructed based on eight RBPs represented as a risk score using least absolute shrinkage and selection operator (LASSO) regression analysis. The high-risk group had a worse overall survival (OS) probability than the low-risk group (p &lt; 0.001) with 1-, 3-, and 5-year area under the receiver operator characteristic curve values of 0.671, 0.638, and 0.637, respectively. The risk score was associated with the stage of disease (p &lt; 0.05) and was an independent prognostic factor for NSCLC when adjusted for age and UICC stage (p &lt; 0.001, hazard ratio (HR): 1.888). The constructed nomogram showed a good predictive value. The P53, focal adhesion, and NOD-like receptor signaling pathways were the primary pathways in the high-risk group (adjusted p value &lt;0.05). The high-risk group was correlated with increased immune infiltration (p &lt; 0.05), upregulated relative expression levels of programmed cell death 1 (PD1) (p = 0.015), cytotoxic T-lymphocyte-associated protein 4 (CTLA4) (p = 0.042), higher gene mutation frequency, higher tumor mutational burden (p = 0.034), and better chemotherapy response (p &lt; 0.001). The signature was successfully validated using the GSE26939, GSE31210, GSE30219, and GSE157009 datasets. Dysregulation of these genes in patients with NSCLC was confirmed using the qPCR in an independent cohort (p &lt; 0.05).

Conclusion: An RBP-related signature was successfully constructed to predict prognosis in NSCLC, functioning as a reference for individualized therapy, including immunotherapy and chemotherapy.

A Ferroptosis-Related Gene Signature for Overall Survival Prediction and Immune Infiltration in Lung Squamous Cell Carcinoma

Background: Ferroptosis is associated with cancer initiation and progression. However, the molecular mechanism and prognostic value of ferroptosis-related genes in lung squamous cell carcinoma (LUSC) are poorly understood.

Methods: The mRNA expression profiles, methylation data, and clinical information of patients with LUSC were downloaded from TCGA and GEO database. Ferroptosis-related differentially expressed genes (DEGs) were identified between cancerous and non-cancerous tissues, and their prognostic value was systemically investigated by bioinformatic analyses.

Results: A ferroptosis-related gene signature (ALOX5, TFRC, PHKG2, FADS2, NOX1) was constructed using multivariate Cox regression analysis and represented as a risk score. Overall survival (OS) probability was significantly lower in the high-risk group than in the low-risk group (P<0.001), and receiver operating characteristic curve showed a good predictive capacity (AUC = 0.739). The risk score was an independent prognostic factor for LUSC. A nomogram was constructed to predict the OS probabilities at 1, 3, and 5 years. High-risk score was associated with increased immune infiltration, lower methylation levels, higher immune checkpoint genes expression levels, and better chemotherapy response. Cell adhesion molecules, focal adhesion, and extracellular matrix receptor interaction were the main pathways in the high-risk group. The signature was validated using the TCGA test cohort, entire TCGA cohort, GSE30219, GSE157010, GSE73403, and GSE4573 datasets. The gene disorders in patients with LUSC were validated using real-time PCR and single-cell RNA sequencing analysis.

Conclusions: A ferroptosis-related gene signature was constructed to predict OS probability in LUSC. This could facilitate novel therapeutic methods and guide individualized therapy.

Early COPD Risk Decision for Adults Aged From 40 to 79 Years Based on Lung Radiomics Features

Background

Chronic obstructive pulmonary disease (COPD), a preventable lung disease, has the highest prevalence in the elderly and deserves special consideration regarding earlier warnings in this fragile population. The impact of age on COPD is well known, but the COPD risk of the aging process in the lungs remains unclear. Therefore, it is necessary to understand the COPD risk of the aging process in the lungs, providing an early COPD risk decision for adults.

Methods

COPD risk is evaluated for adults to make an early COPD risk decision from the perspective of lung radiomics features. First, the subjects are divided into four groups according to the COPD stages. Their ages are divided into eight equal age intervals in each group. Second, four survival Cox models are established based on the lung radiomics features to evaluate the risk probability from COPD stage 0 to suffering COPD and COPD stages. Finally, four risk ranks are defined by equally dividing the COPD risk probability from 0 to 1. Subsequently, the COPD risk at different stages is evaluated with varying age intervals to provide an early COPD risk decision.

Results

The evaluation metrics area under the curve (AUC)/C index of four survival Cox models are 0.87/0.94, 0.84/0.83, 0.94/0.89, and 0.97/0.86, respectively, showing the effectiveness of the models. The risk rank levels up every 5 years for the subjects who had suffered COPD after 60. For the subjects with COPD stage 0, the risk rank of suffering COPD stage I levels up every 5 years after the age of 65 years, and the risk rank of suffering COPD stages II and III &amp; IV levels up every 5 years after the age of 70 years.

Conclusion

Once the age is above 60 years, the patients with COPD need to take action to prevent the progress and deterioration of COPD. Once the age is above 65 years, the patients with COPD stage 0 need to take precautions against COPD.

Development and Validation of a Preoperative CT-Based Nomogram to Differentiate Invasive from Non-Invasive Pulmonary Adenocarcinoma in Solitary Pulmonary Nodules

Purpose

Patients and Methods

Results

Conclusion