Exploratory Study of a CT Radiomics Model for the Classification of Small Cell Lung Cancer and Non-small-Cell Lung Cancer

Using MRI radiomics to predict the efficacy of immunotherapy for brain metastasis in patients with small cell lung cancer

BACKGROUND

Brain metastases (BMs) are common in small cell lung cancer (SCLC), and the efficacy of immune checkpoint inhibitors (ICIs) in these patients is uncertain. In this study we aimed to develop and validate a radiomics nomogram based on magnetic resonance imaging (MRI) for intracranial efficacy prediction of ICIs in patients with BMs from SCLC.

METHODS

The training and validation cohorts consisted of 101 patients from two centers. The interclass correlation coefficient (ICC), logistic univariate regression analysis, and random forest were applied to select the radiomic features, generating the radiomics score (Rad-score) through the formula. Using multivariable logistic regression analysis, a nomogram was created by the combined model. The discrimination, calibration, and clinical utility were used to assess the performance of the nomogram. Kaplan-Meier curves were plotted based on the nomogram scores.

RESULTS

Ten radiomic features were selected for calculating the Rad-score as they could differentiate the intracranial efficacy in the training (area under the curve [AUC], 0.759) and the validation cohort (AUC, 0.667). A nomogram was created by combining Rad-score, treatment lines, and neutrophil-to-lymphocyte ratio (NLR). The training cohort obtained an AUC of 0.878 for the combined model, verified in the validation cohort (AUC = 0.875). Kaplan-Meier analyses showed the nomogram was associated with progression-free survival (PFS) (p = 0.0152) and intracranial progression-free survival (iPFS) (p = 0.0052) but not overall survival (OS) (p = 0.4894).

CONCLUSION

A radiomics nomogram model for predicting the intracranial efficacy of ICIs in SCLC patients with BMs can provide suggestions for exploring individual-based treatments for patients.

Effectiveness of CT radiomic features combined with clinical factors in predicting prognosis in patients with limited-stage small cell lung cancer

BACKGROUND

The prognosis of SCLC is poor and difficult to predict. The aim of this study was to explore whether a model based on radiomics and clinical features could predict the prognosis of patients with limited-stage small cell lung cancer (LS-SCLC).

METHODS

Simulated positioning CT images and clinical features were retrospectively collected from 200 patients with histological diagnosis of LS-SCLC admitted between 2013 and 2021, which were randomly divided into the training (n = 140) and testing (n = 60) groups. Radiomics features were extracted from simulated positioning CT images, and the t-test and the least absolute shrinkage and selection operator (LASSO) were used to screen radiomics features. We then constructed radiomic score (RadScore) based on the filtered radiomics features. Clinical factors were analyzed using the Kaplan-Meier method. The Cox proportional hazards model was used for further analyses of possible prognostic features and clinical factors to build three models including a radiomic model, a clinical model, and a combined model including clinical factors and RadScore. When a model has prognostic predictive value (AUC > 0.7) in both train and test groups, a nomogram will be created. The performance of three models was evaluated using area under the receiver operating characteristic curve (AUC) and Kaplan-Meier analysis.

RESULTS

A total of 1037 features were extracted from simulated positioning CT images which were contrast enhanced CT of the chest. The combined model showed the best prediction, with very poor AUC for the radiomic model and the clinical model. The combined model of OS included 4 clinical features and RadScore, with AUCs of 0.71 and 0.70 in the training and test groups. The combined model of PFS included 4 clinical features and RadScore, with AUCs of 0.72 and 0.71 in the training and test groups. T stages, ProGRP and smoke status were the independent variables for OS in the combined model, whereas T stages, ProGRP and prophylactic cranial irradiation (PCI) were the independent factors for PFS. There was a statistically significant difference between the low- and high-risk groups in the combined model of OS (training group, p < 0.0001; testing group, p = 0.0269) and PFS (training group, p < 0.0001; testing group, p < 0.0001).

CONCLUSION

Combined models involved RadScore and clinical factors can predict prognosis in LS-SCLC and show better performance than individual radiomics and clinical models.

18F-FDG PET/CT-based radiomics model for predicting the degree of pathological differentiation in non-small cell lung cancer: a multicentre study

AIM

To explore the value of 2-[18F]-fluoro-2-deoxy-d-glucose (FDG) positron-emission tomography (PET)/computed tomography (CT)-based radiomics model for predicting the degree of pathological differentiation in non-small-cell lung cancer (NSCLC).

MATERIALS AND METHODS

Clinical characteristics of 182 NSCLC patients from four centres were collected, and radiomics features were extracted from 18F-FDG PET/CT images. Three logistic regression prediction models were established: clinical model; radiomics model; and nomogram combining radiomics signatures and clinical features. The predictive ability of the models was assessed using receiver operating characteristics curve analysis.

RESULTS

Patients from centre 1 were assigned randomly to the training and internal validation cohorts (7:3 ratio); patients from centres 2-4 served as the external validation cohort. The area under the curve (AUC) values for the clinical model in the training, internal validation, and external validation cohort were 0.74 (95% confidence interval [CI] = 0.64-0.84), 0.64 (95% CI = 0.46-0.81), and 0.74 (95% CI = 0.60-0.88), respectively. In the training (AUC: 0.84 [95% CI = 0.77-0.92]), internal validation (AUC: 0.81 [95% CI = 0.67-0.95]), and external validation cohorts (AUC: 0.74 [95% CI = 0.58-0.89]), the radiomics model showed good predictive ability for differentiation. Compared to the clinical and radiomics models, the nomogram has relatively better diagnostic performance, and the AUC values for nomogram in the training, internal validation, and external validation cohort were 0.86 (95% CI = 0.78-0.93), 0.83 (95% CI = 0.70-0.96), and 0.77 (95% CI = 0.62-0.92), respectively.

CONCLUSIONS

The 18F-FDG PET/CT-based radiomics model showed good ability for predicting the degree of differentiation of NSCLC. The nomogram combining the radiomics signature and clinical features has relatively better diagnostic performance.

Development and validation of a radiomics nomogram for diagnosis of malignant pleural effusion

OBJECTIVE

We aimed to develop a radiomics nomogram based on computed tomography (CT) scan features and high-throughput radiomics features for diagnosis of malignant pleural effusion (MPE).

METHODS

In this study, 507 eligible patients with PE (207 malignant and 300 benign) were collected retrospectively. Patients were divided into training (n = 355) and validation cohorts (n = 152). Radiomics features were extracted from initial unenhanced CT images. CT scan features of PE were also collected. We used the variance threshold algorithm and least absolute shrinkage and selection operator (LASSO) to select optimal features to build a radiomics model for predicting the nature of PE. Univariate and multivariable logistic regression analyzes were used to identify significant independent factors associated with MPE, which were then included in the radiomics nomogram.

RESULTS

A total of four CT features were retained as significant independent factors, including massive PE, obstructive atelectasis or pneumonia, pleural thickening > 10 mm, and pulmonary nodules and/or masses. The radiomics nomogram constructed from 13 radiomics parameters and four CT features showed good predictive efficacy in training cohort [area under the curve (AUC) = 0.926, 95% CI 0.894, 0.951] and validation cohort (AUC = 0.916, 95% CI 0.860, 0.955). The calibration curve and decision curve analysis showed that the nomogram helped differentiate MPE from benign pleural effusion (BPE) in clinical practice.

CONCLUSION

This study presents a nomogram model incorporating CT scan features and radiomics features to help physicians differentiate MPE from BPE.

Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis

Artificial intelligence and emerging data science techniques are being leveraged to interpret medical image scans. Traditional image analysis relies on visual interpretation by a trained radiologist, which is time-consuming and can, to some degree, be subjective. The development of reliable, automated diagnostic tools is a key goal of radiomics, a fast-growing research field which combines medical imaging with personalized medicine. Radiomic studies have demonstrated potential for accurate lung cancer diagnoses and prognostications. The practice of delineating the tumor region of interest, known as segmentation, is a key bottleneck in the development of generalized classification models. In this study, the incremental multiple resolution residual network (iMRRN), a publicly available and trained deep learning segmentation model, was applied to automatically segment CT images collected from 355 lung cancer patients included in the dataset "Lung-PET-CT-Dx", obtained from The Cancer Imaging Archive (TCIA), an open-access source for radiological images. We report a failure rate of 4.35% when using the iMRRN to segment tumor lesions within plain CT images in the lung cancer CT dataset. Seven classification algorithms were trained on the extracted radiomic features and tested for their ability to classify different lung cancer subtypes. Over-sampling was used to handle unbalanced data. Chi-square tests revealed the higher order texture features to be the most predictive when classifying lung cancers by subtype. The support vector machine showed the highest accuracy, 92.7% (0.97 AUC), when classifying three histological subtypes of lung cancer: adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. The results demonstrate the potential of AI-based computer-aided diagnostic tools to automatically diagnose subtypes of lung cancer by coupling deep learning image segmentation with supervised classification. Our study demonstrated the integrated application of existing AI techniques in the non-invasive and effective diagnosis of lung cancer subtypes, and also shed light on several practical issues concerning the application of AI in biomedicine.

Benign-malignant classification of pulmonary nodules by low-dose spiral computerized tomography and clinical data with machine learning in opportunistic screening

BACKGROUND

Many people were found with pulmonary nodules during physical examinations. It is of great practical significance to discriminate benign and malignant nodules by using data mining technology.

METHODS

The subjects' demographic data, baseline examination results, and annual follow-up low-dose spiral computerized tomography (LDCT) results were recorded. The findings from annual physical examinations of positive nodules, including highly suspicious nodules and clinically tentative benign nodules, was analyzed. The extreme gradient boosting (XGBoost) model was constructed and the Grid Search CV method was used to select the super parameters. External unit data were used as an external validation set to evaluate the generalization performance of the model.

RESULTS

A total of 135,503 physical examinees were enrolled. Baseline testing found that 27,636 (20.40%) participants had clinically tentative benign nodules and 611 (0.45%) participants had highly suspicious nodules. The proportion of highly suspicious nodules in participants with negative baseline was about 0.12%-0.46%, which was lower than the baseline level except the follow-up of >5 years. In the 27,636 participants with clinically tentative benign nodules, only in the first year of LDCT re-examination was the proportion of highly suspicious nodules (1.40%) significantly greater than that of baseline screening (0.45%) (p < 0.001), and the proportion of highly suspicious nodules was not different between the baseline screening and other follow-up years (p > 0.05). Furthermore, 322 cases with benign nodules and 196 patients with malignant nodules confirmed by surgery and pathology were compared. A model and the top 15 most important clinical variables were determined by XGBoost algorithm. The area under the curve (AUC) of the model was 0.76 [95% CI: 0.67-0.84], and the accuracy was 0.75. The sensitivity and specificity of the model under this threshold were 0.78 and 0.73, respectively. In the validation of model using external data, the AUC was 0.87 and the accuracy was 0.80. The sensitivity and specificity were 0.83 and 0.77, respectively.

CONCLUSIONS

It is important that pulmonary nodules could be more accurately identified at the first LDCT examination. A model with 15 variables which are routinely measured in the clinic could be helpful to distinguish benign and malignant nodules. It could help the radiological team issue a more accurate report; and it may guide the clinical team regarding LDCT follow-up.

Feature selection methods and predictive models in CT lung cancer radiomics

Radiomics is a technique that extracts quantitative features from medical images using data-characterization algorithms. Radiomic features can be used to identify tissue characteristics and radiologic phenotyping that is not observable by clinicians. A typical workflow for a radiomics study includes cohort selection, radiomic feature extraction, feature and predictive model selection, and model training and validation. While there has been increasing attention given to radiomic feature extraction, standardization, and reproducibility, currently, there is a lack of rigorous evaluation of feature selection methods and predictive models. Herein, we review the published radiomics investigations in CT lung cancer and provide an overview of the commonly used radiomic feature selection methods and predictive models. We also compare limitations of various methods in clinical applications and present sources of uncertainty associated with those methods. This review is expected to help raise awareness of the impact of radiomic feature and model selection methods on the integrity of radiomics studies.

CT radiomics model combined with clinical and radiographic features for discriminating peripheral small cell lung cancer from peripheral lung adenocarcinoma

Purpose

Exploring a non-invasive method to accurately differentiate peripheral small cell lung cancer (PSCLC) and peripheral lung adenocarcinoma (PADC) could improve clinical decision-making and prognosis.

Methods

This retrospective study reviewed the clinicopathological and imaging data of lung cancer patients between October 2017 and March 2022. A total of 240 patients were enrolled in this study, including 80 cases diagnosed with PSCLC and 160 with PADC. All patients were randomized in a seven-to-three ratio into the training and validation datasets (170 vs. 70, respectively). The least absolute shrinkage and selection operator regression was employed to generate radiomics features and univariate analysis, followed by multivariate logistic regression to select significant clinical and radiographic factors to generate four models: clinical, radiomics, clinical-radiographic, and clinical-radiographic-radiomics (comprehensive). The Delong test was to compare areas under the receiver operating characteristic curves (AUCs) in the models.

Results

Five clinical-radiographic features and twenty-three selected radiomics features differed significantly in the identification of PSCLC and PADC. The clinical, radiomics, clinical-radiographic and comprehensive models demonstrated AUCs of 0.8960, 0.8356, 0.9396, and 0.9671 in the validation set, with the comprehensive model having better discernment than the clinical model (P=0.036), the radiomics model (P=0.006) and the clinical-radiographic model (P=0.049).

Conclusions

The proposed model combining clinical data, radiographic characteristics and radiomics features could accurately distinguish PSCLC from PADC, thus providing a potential non-invasive method to help clinicians improve treatment decisions.

A comparison study of monoexponential and fractional order calculus diffusion models and 18F-FDG PET in differentiating benign and malignant solitary pulmonary lesions and their pathological types

Objective

To evaluate the application value of monoexponential, fractional order calculus (FROC) diffusion models and PET imaging to distinguish between benign and malignant solitary pulmonary lesions (SPLs) and malignant SPLs with different pathological types and explore the correlation between each parameter and Ki67 expression.

Methods

A total of 112 patients were enrolled in this study. Prior to treatment, all patients underwent a dedicated thoracic ¹⁸F-FDG PET/MR examination. Five parameters [including apparent diffusion coefficient (ADC) derived from the monoexponential model; diffusion coefficient (D), a microstructural quantity (μ), and fractional order parameter (β) derived from the FROC model and maximum standardized uptake value (SUVmax) derived from PET] were compared between benign and malignant SPLs and different pathological types of malignant SPLs. Independent sample t test, Mann-Whitney U test, DeLong test and receiver operating characteristic (ROC) curve analysis were used for statistical evaluation. Pearson correlation analysis was used to calculate the correlations between Ki-67 and ADC, D, μ, β, and SUVmax.

Results

The ADC and D values were significantly higher and the μ and SUVmax values were significantly lower in the benign group [1.57 (1.37, 2.05) μm²/ms, 1.59 (1.52, 1.72) μm²/ms, 5.06 (3.76, 5.66) μm, 5.15 ± 2.60] than in the malignant group [1.32 (1.03, 1.51) μm²/ms, 1.43 (1.29, 1.52) μm²/ms, 7.06 (5.87, 9.45) μm, 9.85 ± 4.95]. The ADC, D and β values were significantly lower and the μ and SUVmax values were significantly higher in the squamous cell carcinoma (SCC) group [1.29 (0.66, 1.42) μm²/ms, 1.32 (1.02, 1.42) μm²/ms, 0.63 ± 0.10, 9.40 (7.76, 15.38) μm, 11.70 ± 5.98] than in the adenocarcinoma (AC) group [1.40 (1.28, 1.67) μm²/ms, 1.52 (1.44, 1.64) μm²/ms, 0.70 ± 0.10, 5.99 (4.54, 6.87) μm, 8.76 ± 4.18]. ROC curve analysis showed that for a single parameter, μ exhibited the best AUC value in discriminating between benign and malignant SPLs groups and AC and SCC groups (AUC = 0.824 and 0.911, respectively). Importantly, the combination of monoexponential, FROC models and PET imaging can further improve diagnostic performance (AUC = 0.872 and 0.922, respectively). The Pearson correlation analysis showed that Ki67 was positively correlated with μ value and negatively correlated with ADC and D values (r = 0.402, -0.346, -0.450, respectively).

Conclusion

The parameters D and μ derived from the FROC model were superior to ADC and SUVmax in distinguishing benign from malignant SPLs and adenocarcinoma from squamous cell carcinoma, in addition, the combination of multiple parameters can further improve diagnostic performance. The non-Gaussian FROC diffusion model is expected to become a noninvasive quantitative imaging technique for identifying SPLs.

Combined model of radiomics, clinical, and imaging features for differentiating focal pneumonia-like lung cancer from pulmonary inflammatory lesions: an exploratory study

Background

Only few studies have focused on differentiating focal pneumonia-like lung cancer (F-PLC) from focal pulmonary inflammatory lesion (F-PIL). This exploratory study aimed to evaluate the clinical value of a combined model incorporating computed tomography (CT)-based radiomics signatures, clinical factors, and CT morphological features for distinguishing F-PLC and F-PIL.

Methods

In total, 396 patients pathologically diagnosed with F-PLC and F-PIL from two medical institutions between January 2015 and May 2021 were retrospectively analyzed. Patients from center 1 were included in the training (n = 242) and internal validation (n = 104) cohorts. Moreover, patients from center 2 were classified under the external validation cohort (n = 50). The clinical and CT morphological characteristics of both groups were compared first. And then, a clinical model incorporating clinical and CT morphological features, a radiomics model reflecting the radiomics signature of lung lesions, and a combined model were developed and validated, respectively.

Results

Age, gender, smoking history, respiratory symptoms, air bronchogram, necrosis, and pleural attachment differed significantly between the F-PLC and F-PIL groups (all P < 0.05). For the clinical model, age, necrosis, and pleural attachment were the most effective factors to differentiate F-PIL from F-PLC, with the area under the curves (AUCs) of 0.838, 0.819, and 0.717 in the training and internal and external validation cohorts, respectively. For the radiomics model, five radiomics features were found to be significantly related to the identification of F-PLC and F-PIL (all P < 0.001), with the AUCs of 0.804, 0.877, and 0.734 in the training and internal and external validation cohorts, respectively. For the combined model, five radiomics features, age, necrosis, and pleural attachment were independent predictors for distinguishing between F-PLC and F-PIL, with the AUCs of 0.915, 0.899, and 0.805 in the training and internal and external validation cohorts, respectively. The combined model exhibited a better performance than had the clinical and radiomics models.

Conclusions

The combined model, which incorporates CT-based radiomics signatures, clinical factors, and CT morphological characteristics, is effective in differentiating F-PLC from F-PIL.

Application of Artificial Intelligence in Lung Cancer

Simple Summary

Lung cancer is the leading cause of malignancy-related mortality worldwide. AI has the potential to help to treat lung cancer from detection, diagnosis and decision making to prognosis prediction. AI could reduce the labor work of LDCT, CXR, and pathology slides reading. AI as a second reader in LDCT and CXR reading reduces the effort of radiologists and increases the accuracy of nodule detection. Introducing AI to WSI in digital pathology increases the Kappa value of the pathologist and help to predict molecular phenotypes with radiomics and H&E staining. By extracting radiomics from image data and WSI from the histopathology field, clinicians could use AI to predict tumor properties such as gene mutation and PD-L1 expression. Furthermore, AI could help clinicians in decision-making by predicting treatment response, side effects, and prognosis prediction in medical treatment, surgery, and radiotherapy. Integrating AI in the future clinical workflow would be promising.

Abstract

Lung cancer is the leading cause of malignancy-related mortality worldwide due to its heterogeneous features and diagnosis at a late stage. Artificial intelligence (AI) is good at handling a large volume of computational and repeated labor work and is suitable for assisting doctors in analyzing image-dominant diseases like lung cancer. Scientists have shown long-standing efforts to apply AI in lung cancer screening via CXR and chest CT since the 1960s. Several grand challenges were held to find the best AI model. Currently, the FDA have approved several AI programs in CXR and chest CT reading, which enables AI systems to take part in lung cancer detection. Following the success of AI application in the radiology field, AI was applied to digitalized whole slide imaging (WSI) annotation. Integrating with more information, like demographics and clinical data, the AI systems could play a role in decision-making by classifying EGFR mutations and PD-L1 expression. AI systems also help clinicians to estimate the patient’s prognosis by predicting drug response, the tumor recurrence rate after surgery, radiotherapy response, and side effects. Though there are still some obstacles, deploying AI systems in the clinical workflow is vital for the foreseeable future.

Development and validation a radiomics nomogram for diagnosing occult brain metastases in patients with stage IV lung adenocarcinoma

Background

To develop and validate a radiomics model using computed tomography (CT) images acquired from the first diagnosis to estimate the status of occult brain metastases (BM) in patients with stage IV lung adenocarcinoma (LADC).

Methods

One hundred and ninety-three patients who were first diagnosed with stage IV LADC were enrolled and divided into a training cohort (n=135) and a validation cohort (n=58). Then, 725 radiomic features were extracted from contoured primary tumor volumes of LADCs. Intra- and interobserver reliabilities were calculated, and the least absolute shrinkage and selection operator (LASSO) was applied for feature selection. Subsequently, a radiomics signature (Rad-Score) was built. To improve performance, a nomogram incorporating a radiomics signature and an independent clinical predictor was developed. Finally, the established signature and nomogram were assessed using receiver operating characteristic (ROC) curves and precision-recall curves (PRC). Both empirical and α-binomial model-based ROCs and PRCs were plotted, and the area under the curve (AUC) and average precision (AP) of ROCs and PRCs were calculated and compared.

Results

A radiomics signature and Rad-Score were constructed using eight radiomic features, and these had significant correlations with occult BM status. A nomogram was developed by incorporating a Rad-Score and the primary tumor location. The nomogram yielded an optimal AUC of 0.911 [95% confidence interval (CI): 0.903–0.919] and an AP of 0.885 (95% CI: 0.876–0.894) in the training cohort, and an AUC of 0.873 (95% CI: 0.866–0.80) and an AP of 0.827 (95% CI: 0.820–0.834) in the validation cohort using α-binomial model-based method. The calibration curve demonstrated that the nomogram showed high agreement between the actual occult BM probability and predicted by the nomogram (P=0.427).

Conclusions

The nomogram incorporating a radiomics signature and a clinical risk factor achieved optimal performance after holistic assessment using unbiased indexes for diagnosing occult BM of patients who were first diagnosed with stage IV LADC.

Radiomics Study for Discriminating Second Primary Lung Cancers From Pulmonary Metastases in Pulmonary Solid Lesions

BACKGROUND

The objective of this study was to assess the value of quantitative radiomics features in discriminating second primary lung cancers (SPLCs) from pulmonary metastases (PMs).

METHODS

This retrospective study enrolled 252 malignant pulmonary nodules with histopathologically confirmed SPLCs or PMs and randomly assigned them to a training or validation cohort. Clinical data were collected from the electronic medical records system. The imaging and radiomics features of each nodule were extracted from CT images.

RESULTS

A rad-score was generated from the training cohort using the least absolute shrinkage and selection operator regression. A clinical and radiographic model was constructed using the clinical and imaging features selected by univariate and multivariate regression. A nomogram composed of clinical-radiographic factors and a rad-score were developed to validate the discriminative ability. The rad-scores differed significantly between the SPLC and PM groups. Sixteen radiomics features and four clinical-radiographic features were selected to build the final model to differentiate between SPLCs and PMs. The comprehensive clinical radiographic-radiomics model demonstrated good discriminative capacity with an area under the curve of the receiver operating characteristic curve of 0.9421 and 0.9041 in the respective training and validation cohorts. The decision curve analysis demonstrated that the comprehensive model showed a higher clinical value than the model without the rad-score.

CONCLUSION

The proposed model based on clinical data, imaging features, and radiomics features could accurately discriminate SPLCs from PMs. The model thus has the potential to support clinicians in improving decision-making in a noninvasive manner.

Deep Radiotranscriptomics of Non-Small Cell Lung Carcinoma for Assessing Molecular and Histology Subtypes with a Data-Driven Analysis

Radiogenomic and radiotranscriptomic studies have the potential to pave the way for a holistic decision support system built on genomics, transcriptomics, radiomics, deep features and clinical parameters to assess treatment evaluation and care planning. The integration of invasive and routine imaging data into a common feature space has the potential to yield robust models for inferring the drivers of underlying biological mechanisms. In this non-small cell lung carcinoma study, a multi-omics representation comprised deep features and transcriptomics was evaluated to further explore the synergetic and complementary properties of these diverse multi-view data sources by utilizing data-driven machine learning models. The proposed deep radiotranscriptomic analysis is a feature-based fusion that significantly enhances sensitivity by up to 0.174 and AUC by up to 0.22, compared to the baseline single source models, across all experiments on the unseen testing set. Additionally, a radiomics-based fusion was also explored as an alternative methodology yielding radiomic signatures that are comparable to several previous publications in the field of radiogenomics. Furthermore, the machine learning multi-omics analysis based on deep features and transcriptomics achieved an AUC performance of up to 0.831 ± 0.09/0.925 ± 0.04 for the examined molecular and histology subtypes analysis, respectively. The clinical impact of such high-performing models can add prognostic value and lead to optimal treatment assessment by targeting specific oncogenes, namely the response of tyrosine kinase inhibitors of EGFR mutated or predicting the chemotherapy resistance of KRAS mutated tumors.

CT Radiomics Model for Predicting the Ki-67 Index of Lung Cancer： An Exploratory Study

Objective

To establish a radiomics signature and a nomogram model based on enhanced CT images to predict the Ki-67 index of lung cancer.

Methods

From January 2014 to December 2018, 282 patients with lung cancer who had undergone enhanced CT scans and Ki-67 examination within 2 weeks were retrospectively enrolled and analyzed. The clinical data of the patients were collected, such as age, sex, smoking history, maximum tumor diameter and serum tumor markers. Our primary cohort was randomly divided into a training group (n=197) and a validation group (n=85) at a 7:3 ratio. A Ki-67 index ≤ 40% indicated low expression, and a Ki-67 index > 40% indicated high expression. In total, 396 radiomics features were extracted using AK software. Feature reduction and selection were performed using the lasso regression model. Logistic regression analysis was used to establish a multivariate predictive model to identify high and low Ki-67 expression in lung cancer. A nomogram integrating the radiomics score was established based on multiple logistic regression analysis. Area under the curve (AUC) was used to evaluate the prediction efficiency of the radiomics signature and nomogram.

Results

The AUC,sensitivity, specificity and accuracy of the radiomics signature in the training and validation groups were 0.88 (95% CI: 0.82~0.93),79.2%,84.3%,81.2% and 0.86 (95% CI: 0.78~0.94),74.6%,88.1%,79.8%, respectively. A nomogram combining radiomics features and clinical risk factors (smoking history and NSE) was developed. The AUC, sensitivity, specificity and accuracy were 0.87 (95% CI: 0.80~0.95), 75.0%, 90.2% and 83.5% in the validation group, respectively.

Conclusion

The radiomics signature and nomogram based on enhanced CT images provide a way to predict the Ki-67 expression level in lung cancer.

A Propensity-Matched Analysis of Survival of Clinically Diagnosed Early-Stage Lung Cancer and Biopsy-Proven Early-Stage Non-Small Cell Lung Cancer Following Stereotactic Ablative Radiotherapy

Purpose

Stereotactic body radiotherapy (SBRT) has been increasingly regarded as a reasonable option for early-stage lung cancer patients without pretreatment pathologic results, but the efficacy and safety in a Chinese population remains unclear. The aim of this study was to compare survival outcomes and toxicities between patients with clinically diagnosed early-stage lung cancer or biopsy-proven early-stage non-small cell lung cancer and to demonstrate the rationality of this treatment.

Material and Methods

From May 2012 to December 2018, 56 patients with clinically diagnosed early-stage lung cancer and 60 patients with early-stage biopsy-proven were selected into non-pathological group and pathological group, respectively. Propensity score matching (PSM) was performed to reduce patient selection bias. Survival analysis with log-rank test was used to assess the differences of treatment outcomes, which included local control (LC), progression-free survival (PFS), and overall survival (OS).

Results

The median age was 76 (range 47–93) years, and the median follow-up time was 58.3 (range 4.3–95.1) months in the cohort without pathologic results. The median age was 74 (range 57–88) years, and the median follow-up time was 56.3 (range 2.6–94) months in the cohort with pathologic results. 45 matched-pair were analyzed. The 5-year LC, PFS, and OS rates in matched-pair patients with or without pathologic biopsy were 85.5% and 89.8%, 40.6% and 70.9%, and 63.2% and 76.1%, respectively. On Kaplan-Meier survival analysis after PSM analysis, there was no significant difference between patients with pathologic results versus patients with no pathologic results in terms of LC (P= 0.498) and OS (P=0.141). Of the matched-pair patients treated with SBRT, only 1 patient experienced grade 3 or above radiation pneumonitis.

Conclusion

For early-stage lung cancer patients with medically inoperable or not suitable for invasive diagnosis, SBRT may be a good local treatment.

Radiomics Based Bayesian Inversion Method for Prediction of Cancer and Pathological Stage

OBJECTIVE

To develop a Bayesian inversion framework on longitudinal chest CT scans which can perform efficient multi-class classification of lung cancer.

METHODS

While the unavailability of large number of training medical images impedes the performance of lung cancer classifiers, the purpose built deep networks have not performed well in multi-class classification. The presented framework employs particle filtering approach to address the non-linear behaviour of radiomic features towards benign and cancerous (stages I, II, III, IV) nodules and performs efficient multi-class classification (benign, early stage cancer, advanced stage cancer) in terms of posterior probability function. A joint likelihood function incorporating diagnostic radiomic features is formulated which can compute likelihood of cancer and its pathological stage. The proposed research study also investigates and validates diagnostic features to discriminate accurately between early stage (I, II) and advanced stage (III, IV) cancer.

RESULTS

The proposed stochastic framework achieved 86% accuracy on the benchmark database which is better than the other prominent cancer detection methods.

CONCLUSION

The presented classification framework can aid radiologists in accurate interpretation of lung CT images at an early stage and can lead to timely medical treatment of cancer patients.

A CT-Based Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Periampullary Carcinomas

Purpose

To establish and validate a radiomics nomogram for preoperatively predicting lymph node (LN) metastasis in periampullary carcinomas.

Materials and Methods

A total of 122 patients with periampullary carcinoma were assigned into a training set (n = 85) and a validation set (n = 37). The preoperative CT radiomics of all patients were retrospectively assessed and the radiomic features were extracted from portal venous-phase images. The one-way analysis of variance test and the least absolute shrinkage and selection operator regression were used for feature selection. A radiomics signature was constructed with logistic regression algorithm, and the radiomics score was calculated. Multivariate logistic regression model integrating independent risk factors was adopted to develop a radiomics nomogram. The performance of the radiomics nomogram was assessed by its calibration, discrimination, and clinical utility with independent validation.

Results

The radiomics signature, constructed by seven selected features, was closely related to LN metastasis in the training set (p < 0.001) and validation set (p = 0.017). The radiomics nomogram that incorporated radiomics signature and CT-reported LN status demonstrated favorable calibration and discrimination in the training set [area under the curve (AUC), 0.853] and validation set (AUC, 0.853). The decision curve indicated the clinical utility of our nomogram.

Conclusion

Our CT-based radiomics nomogram, incorporating radiomics signature and CT-reported LN status, could be an individualized and non-invasive tool for preoperative prediction of LN metastasis in periampullary carcinomas, which might assist clinical decision making.

Machine Learning Radiomics Model for Early Identification of Small-Cell Lung Cancer on Computed Tomography Scans

PURPOSE

Small-cell lung cancer (SCLC) is the deadliest form of lung cancer, partly because of its short doubling time. Delays in imaging identification and diagnosis of nodules create a risk for stage migration. The purpose of our study was to determine if a machine learning radiomics model can detect SCLC on computed tomography (CT) among all nodules at least 1 cm in size.

MATERIALS AND METHODS

Computed tomography scans from a single institution were selected and resampled to 1 × 1 × 1 mm. Studies were divided into SCLC and other scans comprising benign, adenocarcinoma, and squamous cell carcinoma that were segregated into group A (noncontrast scans) and group B (contrast-enhanced scans). Four machine learning classification models, support vector classifier, random forest (RF), XGBoost, and logistic regression, were used to generate radiomic models using 59 quantitative first-order and texture Imaging Biomarker Standardization Initiative compliant PyRadiomics features, which were found to be robust between two segmenters with minimum Redundancy Maximum Relevance feature selection within each leave-one-out-cross-validation to avoid overfitting. The performance was evaluated using a receiver operating characteristic curve. A final model was created using the RF classifier and aggregate minimum Redundancy Maximum Relevance to determine feature importance.

RESULTS

A total of 103 studies were included in the analysis. The area under the receiver operating characteristic curve for RF, support vector classifier, XGBoost, and logistic regression was 0.81, 0.77, 0.84, and 0.84 in group A, and 0.88, 0.87, 0.85, and 0.81 in group B, respectively. Nine radiomic features in group A and 14 radiomic features in group B were predictive of SCLC. Six radiomic features overlapped between groups A and B.

CONCLUSION

A machine learning radiomics model may help differentiate SCLC from other lung lesions.

Structural and functional radiomics for lung cancer

INTRODUCTION

Lung cancer ranks second in new cancer cases and first in cancer-related deaths worldwide. Precision medicine is working on altering treatment approaches and improving outcomes in this patient population. Radiological images are a powerful non-invasive tool in the screening and diagnosis of early-stage lung cancer, treatment strategy support, prognosis assessment, and follow-up for advanced-stage lung cancer. Recently, radiological features have evolved from solely semantic to include (handcrafted and deep) radiomic features. Radiomics entails the extraction and analysis of quantitative features from medical images using mathematical and machine learning methods to explore possible ties with biology and clinical outcomes.

METHODS

Here, we outline the latest applications of both structural and functional radiomics in detection, diagnosis, and prediction of pathology, gene mutation, treatment strategy, follow-up, treatment response evaluation, and prognosis in the field of lung cancer.

CONCLUSION

The major drawbacks of radiomics are the lack of large datasets with high-quality data, standardization of methodology, the black-box nature of deep learning, and reproducibility. The prerequisite for the clinical implementation of radiomics is that these limitations are addressed. Future directions include a safer and more efficient model-training mode, merge multi-modality images, and combined multi-discipline or multi-omics to form "Medomics."

Evaluation of the linear interpolation method in correcting the influence of slice thicknesses on radiomic feature values in solid pulmonary nodules: a prospective patient study

Background

To investigate the influence of slice thickness on radiomic feature (RF) values in solid pulmonary nodules and evaluate the effect of a linear interpolation method in correcting the influence.

Methods

Thirty pulmonary nodules from 28 patients were selected prospectively with a thick-slice of 5 mm and a thin-slice of 1.25 mm on CT. A resampling method was used to normalize the voxel size of thick and thin slices CT images to 1×1×1 mm³ by linear interpolation. Lung nodules were segmented manually. A total of 396 radiomic features (RFs) were extracted from thick-slice and thin-slice images, together with the images resampled from thick (thick-r) and thin (thin-r) slices. The differences between the RF values were evaluated using a paired t-test. A comparison between groups was made using the Chi-squared test.

Results

Among the 396 RFs, 305 RFs showed an intraclass correlation coefficient ≥0.75 after test-retest analysis (including 22 histogram features, 20 geometry features, and 263 texture features). In the non-resampled data, 239 RF values (78.4%, 239/305) showed significant differences between thick and thin slice CT images. Resampling of thick images revealed that 202 RF values (66.2%, 202/305) showed significant differences between thick-r and thin slice CT images, showing a significant decrease in the number of different RF values when compared to non-resampled data (P<0.01). For the RF subgroups, only texture features showed a significant reduction in the number of different RF values after resampling (P<0.01). When both thick and thin slice images were resampled, the number of significantly different RF values between thick-r and thin-r images was increased to 247 (81.0%, 247/305), showing no significant difference when compared to non-resampled data (P=0.421).

Conclusions

Slice thickness demonstrated a considerable influence on RF values in solid pulmonary nodules, producing false results when CT images with different slice thicknesses were used. Linear interpolation of the resampling method was limited because of the relatively small correction effect.