Search

Purpose This study aimed to explore the predictive ability of deep learning (DL) for the common epidermal growth factor receptor (EGFR) mutation subtypes in patients with lung adenocarcinoma. Methods A total of 665 patients with lung adenocarcinoma (528/137) were recruited from two different institutions. In the training set, an 18-layer convolutional neural network (CNN) and 5-fold cross-validation strategy were used to establish a CNN model. Subsequently, an independent external validation cohort from the other institution was used to evaluate the predictive efficacy of the CNN model. Grad-weighted class activation mapping (Grad-CAM) technology was used for the visual interpretation of the CNN model. In addition, this study also compared the prediction abilities of the radiomics and CNN models. Receiver operating characteristic (ROC) curves, accuracy and precision values, and recall and F1-score were used to evaluate the effectiveness of the CNN model and compare its performance with that of the radiomics model. Results In the validation set, the micro- and macro-average values of the area under the ROC curve of the CNN model to identify the three EGFR subtypes were 0.78 and 0.79, respectively. All evaluation indicators of the CNN model were better than those of the radiomics model. Conclusions Our study confirmed the potential of DL for predicting the EGFR mutation status in lung adenocarcinoma. The imaging phenotypes of the three mutation subtypes were found to be different, which can provide a basis for choosing more accurate and personalized treatment in patients with lung adenocarcinoma. This article is protected by copyright. All rights reserved.

Purpose High-dimensional image features that underlie COVID-19 pneumonia remain opaque. We aim to compare feature engineering and deep learning methods to gain insights into the image features that drive CT-based for COVID-19 pneumonia prediction, and uncover CT image features significant for COVID-19 pneumonia from deep learning and radiomics framework. Methods A total of 266 patients with COVID-19 and other viral pneumonia with clinical symptoms and CT signs similar to that of COVID-19 during the outbreak were retrospectively collected from three hospitals in China and the USA. All the pneumonia lesions on CT images were manually delineated by four radiologists. One hundred eighty-four patients (n = 93 COVID-19 positive; n = 91 COVID-19 negative; 24,216 pneumonia lesions from 12,001 CT image slices) from two hospitals from China served as discovery cohort for model development. Thirty-two patients (17 COVID-19 positive, 15 COVID-19 negative; 7883 pneumonia lesions from 3799 CT image slices) from a US hospital served as external validation cohort. A bi-directional adversarial network-based framework and PyRadiomics package were used to extract deep learning and radiomics features, respectively. Linear and Lasso classifiers were used to develop models predictive of COVID-19 versus non-COVID-19 viral pneumonia. Results 120-dimensional deep learning image features and 120-dimensional radiomics features were extracted. Linear and Lasso classifiers identified 32 high-dimensional deep learning image features and 4 radiomics features associated with COVID-19 pneumonia diagnosis (P 73% and specificity > 75% on external validation cohort with slight superior performance for radiomics Lasso classifier. Human expert diagnostic performance improved (increase by 16.5% and 11.6% in sensitivity and specificity, respectively) when using a combined deep learning-radiomics model. Conclusions We uncover specific deep learning and radiomics features to add insight into interpretability of machine learning algorithms and compare deep learning and radiomics models for COVID-19 pneumonia that might serve to augment human diagnostic performance.

Purpose In the absence of a virus nucleic acid real-time reverse transcriptase-polymerase chain reaction (RT-PCR) test and experienced radiologists, clinical diagnosis is challenging for viral pneumonia with clinical symptoms and CT signs similar to that of coronavirus disease 2019 (COVID-19). We developed an end-to-end automatic differentiation method based on CT images to identify COVID-19 pneumonia patients in real time. Methods From January 18 to February 23, 2020, we conducted a retrospective study and enrolled 201 patients from two hospitals in China who underwent chest CT and RT-PCR tests, of which 98 patients tested positive for COVID-19 (118 males and 83 females, with an average age of 42 years). Patient CT images from one hospital were divided among training, validation and test datasets with an 80%:10%:10% ratio. An end-to-end representation learning method using a large-scale bi-directional generative adversarial network (BigBiGAN) architecture was designed to extract semantic features from the CT images. The semantic feature matrix was input for linear classifier construction. Patients from the other hospital were used for external validation. Differentiation accuracy was evaluated using a receiver operating characteristic curve. Results Based on the 120-dimensional semantic features extracted by BigBiGAN from each image, the linear classifier results indicated that the area under the curve (AUC) in the training, validation and test datasets were 0.979, 0.968 and 0.972, respectively, with an average sensitivity of 92% and specificity of 91%. The AUC for external validation was 0.850, with a sensitivity of 80% and specificity of 75%. Publicly available architecture and computing resources were used throughout the study to ensure reproducibility. Conclusion This study provides an efficient recognition method for coronavirus disease 2019 pneumonia, using an end-to-end design to implement targeted and effective isolation for the containment of this communicable disease.

This cohort study examines the latest expansion of the lung cancer screening eligibility criteria for adults in the US., Key Points Question Is the updated US Preventive Services Task Force (USPSTF) recommendations for lung cancer screening associated with a clinically meaningful change in the distribution of the characteristics of individuals who are eligible for screening? Findings In this cohort study using data derived from 5 health care systems, the updated 2021 USPSTF recommendations were associated with an increased overall proportion of women, racial and ethnic minority groups, and individuals with lower socioeconomic status who are eligible for lung cancer screening. Meaning The 2021 USPSTF recommendations for lung cancer screening eligibility are expected to enhance opportunities for community-based programs to reduce barriers to lung cancer screening access for individuals who are at highest risk for lung cancer., Importance The US Preventive Services Task Force (USPSTF) released updated lung cancer screening recommendations in 2021, lowering the screening age from 55 to 50 years and smoking history from 30 to 20 pack-years. These changes are expected to expand screening access to women and racial and ethnic minority groups. Objective To estimate the population-level changes associated with the 2021 USPSTF expansion of lung cancer screening eligibility by sex, race and ethnicity, sociodemographic factors, and comorbidities in 5 community-based health care systems. Design, Setting, and Participants This cohort study analyzed data of patients who received care from any of 5 community-based health care systems (which are members of the Population-based Research to Optimize the Screening Process Lung Consortium, a collaboration that conducts research to better understand how to improve the cancer screening processes in community health care settings) from January 1, 2010, through September 30, 2019. Individuals who had complete smoking history and were engaged with the health care system for 12 or more continuous months were included. Those who had never smoked or who had unknown smoking history were excluded. Exposures Electronic health record–derived age, sex, race and ethnicity, socioeconomic status (SES), comorbidities, and smoking history. Main Outcomes and Measures Differences in the proportion of the newly eligible population by age, sex, race and ethnicity, Charlson Comorbidity Index, chronic obstructive pulmonary disease diagnosis, and SES as well as lung cancer diagnoses under the 2013 recommendations vs the expected cases under the 2021 recommendations were evaluated using χ2 tests. Results As of September 2019, there were 341 163 individuals aged 50 to 80 years who currently or previously smoked. Among these, 34 528 had electronic health record data that captured pack-year and quit-date information and were eligible for lung cancer screening according to the 2013 USPSTF recommendations. The 2021 USPSTF recommendations expanded screening eligibility to 18 533 individuals, representing a 53.7% increase. Compared with the 2013 cohort, the newly eligible 2021 population included 5833 individuals (31.5%) aged 50 to 54 years, a larger proportion of women (52.0% [n = 9631]), and more racial or ethnic minority groups. The relative increases in the proportion of newly eligible individuals were 60.6% for Asian, Native Hawaiian, or Pacific Islander; 67.4% for Hispanic; 69.7% for non-Hispanic Black; and 49.0% for non-Hispanic White groups. The relative increase for women was 13.8% higher than for men (61.2% vs 47.4%), and those with a lower comorbidity burden and lower SES had higher relative increases (eg, 68.7% for a Charlson Comorbidity Index score of 0; 61.1% for lowest SES). The 2021 recommendations were associated with an estimated 30% increase in incident lung cancer diagnoses compared with the 2013 recommendations. Conclusions and Relevance This cohort study suggests that, in diverse health care systems, adopting the 2021 USPSTF recommendations will increase the number of women, racial and ethnic minority groups, and individuals with lower SES who are eligible for lung cancer screening, thus helping to minimize the barriers to screening access for individuals with high risk for lung cancer.

The heterogeneity and complexity of non-small cell lung cancer (NSCLC) tumors mean that NSCLC patients at the same stage can have different chemotherapy prognoses. Accurate predictive models could recognize NSCLC patients likely to respond to chemotherapy so that they can be given personalized and effective treatment. We propose to identify predictive imaging biomarkers from pre-treatment CT images and construct a radiomic model that can predict the chemotherapy response in NSCLC. This single-center cohort study included 280 NSCLC patients who received first-line chemotherapy treatment. Non-contrast CT images were taken before and after the chemotherapy, and clinical information were collected. Based on the Response Evaluation Criteria in Solid Tumors and clinical criteria, the responses were classified into two categories: response (n = 145) and progression (n = 135), then all data were divided into two cohorts: training cohort (224 patients) and independent test cohort (56 patients). In total, 1629 features characterizing the tumor phenotype were extracted from a cube containing the tumor lesion cropped from the pre-chemotherapy CT images. After dimensionality reduction, predictive models of the chemotherapy response of NSCLC with different feature selection methods and different machine-learning classifiers (support vector machine, random forest, and logistic regression) were constructed. For the independent test cohort, the predictive model based on a random-forest classifier with 20 radiomic features achieved the best performance, with an accuracy of 85.7% and an area under the receiver operating characteristic curve of 0.941 (95% confidence interval, 0.898–0.982). Of the 20 selected features, four were first-order statistics of image intensity and the others were texture features. For nine features, there were significant differences between the response and progression groups (p < 0.001). In the response group, three features, indicating heterogeneity, were overrepresented and one feature indicating homogeneity was underrepresented. The proposed radiomic model with pre-chemotherapy CT features can predict the chemotherapy response of patients with non-small cell lung cancer. This radiomic model can help to stratify patients with NSCLC, thereby offering the prospect of better treatment.

BackgroundCurrent intra-tumoral heterogeneous feature extraction in radiology is limited to the use of a single slice or the region of interest within a few context-associated slices, and the decoding of intra-tumoral spatial heterogeneity using whole tumor samples is rare. We aim to propose a mathematical model of space-filling curve-based spatial correspondence mapping to interpret intra-tumoral spatial locality and heterogeneity.MethodsA Hilbert curve-based approach was employed to decode and visualize intra-tumoral spatial heterogeneity by expanding the tumor volume to a two-dimensional (2D) matrix in voxels while preserving the spatial locality of the neighboring voxels. The proposed method was validated using three-dimensional (3D) volumes constructed from lung nodules from the LIDC-IDRI dataset, regular axial plane images, and 3D blocks.ResultsDimensionality reduction of the Hilbert volume with a single regular axial plane image showed a sparse and scattered pixel distribution on the corresponding 2D matrix. However, for 3D blocks and lung tumor inside the volume, the dimensionality reduction to the 2D matrix indicated regular and concentrated squares and rectangles. For classification into benign and malignant masses using lung nodules from the LIDC-IDRI dataset, the Inception-V4 indicated that the Hilbert matrix images improved accuracy (85.54% vs. 73.22%,p ConclusionsOur study indicates that Hilbert curve-based spatial correspondence mapping is promising for decoding intra-tumoral spatial heterogeneity of partial or whole tumor samples on radiological images. This spatial-locality-preserving approach for voxel expansion enables existing radiomics and convolution neural networks to filter structured and spatially correlated high-dimensional intra-tumoral heterogeneity.

Purpose This retrospective study was designed to investigate the ability of radiomics to predict the mutation status of epidermal growth factor receptor (EGFR) subtypes (19Del and L858R) in patients with non-small cell lung cancer (NSCLC). Methods In total, 312 patients with NSCLC were included, and 580 radiomic features were extracted from the computed tomography images of each patient. In the training set, univariate analysis was performed on the clinical and radiomic features; logistic regression models were established using a 5-fold cross validation strategy for the prediction of EGFR subtypes 19Del and L858R. Subsequently, the predictive ability of the joint models was evaluated using the test set. Results The results revealed that the radiomic features specific for EGFR 19Del and L858R were Gabor's MTRVariance, Gabor's PTREntropy, and sphericity. Additionally, the respective areas under the receiver operating characteristic curves of the EGFR 19Del and L858R joint models were 0.7925 and 0.7750 for the test set. Conclusions Our study demonstrated the potential for radiomics to predict EGFR 19Del and L858R. Epidermal growth factor receptor 19Del and L858R exhibited distinct imaging phenotypes, which may help to guide the selection of more accurate and personalized treatment programs for patients with NSCLC.

Highlights • Radiomics-based classifier agreed with radiologists for the classification of COVID-19. • Radiomics enables to quantify the CT variation with SARS-CoV-2 positivity & SARS-CoV-2 negativity. • The features identified by multi-classifier can interpret and generalise the CT signs of COVID-19., Purpose To investigate the efficacy of radiomics in diagnosing patients with coronavirus disease (COVID-19) and other types of viral pneumonia with clinical symptoms and CT signs similar to those of COVID-19. Methods Between 18 January 2020 and 20 May 2020, 110 SARS-CoV-2 positive and 108 SARS-CoV-2 negative patients were retrospectively recruited from three hospitals based on the inclusion criteria. Manual segmentation of pneumonia lesions on CT scans was performed by four radiologists. The latest version of Pyradiomics was used for feature extraction. Four classifiers (linear classifier, k-nearest neighbour, least absolute shrinkage and selection operator [LASSO], and random forest) were used to differentiate SARS-CoV-2 positive and SARS-CoV-2 negative patients. Comparison of the performance of the classifiers and radiologists was evaluated by ROC curve and Kappa score. Results We manually segmented 16,053 CT slices, comprising 32,625 pneumonia lesions, from the CT scans of all patients. Using Pyradiomics, 120 radiomic features were extracted from each image. The key radiomic features screened by different classifiers varied and lead to significant differences in classification accuracy. The LASSO achieved the best performance (sensitivity: 72.2%, specificity: 75.1%, and AUC: 0.81) on the external validation dataset and attained excellent agreement (Kappa score: 0.89) with radiologists (average sensitivity: 75.6%, specificity: 78.2%, and AUC: 0.81). All classifiers indicated that "Original_Firstorder_RootMeanSquared" and "Original_Firstorder_Uniformity" were significant features for this task. Conclusions We identified radiomic features that were significantly associated with the classification of COVID-19 pneumonia using multiple classifiers. The quantifiable interpretation of the differences in features between the two groups extends our understanding of CT imaging characteristics of COVID-19 pneumonia.

Purpose To evaluate the general rules and future trajectories of deep learning (DL) networks in medical image analysis through bibliometric and hot spot analysis of original articles published between 2012 and 2020. Methods Original articles related to DL and medical imaging were retrieved from the PubMed database. For the analysis, data regarding radiological subspecialties; imaging techniques; DL networks; sample size; study purposes, setting, origins and design; statistical analysis; funding sources; authors; and first authors’ affiliation was manually extracted from each article. The Bibliographic Item Co-Occurrence Matrix Builder and VOSviewer were used to identify the research topics of the included articles and illustrate the future trajectories of studies. Results The study included 2,685 original articles. The number of publications on DL and medical imaging has increased substantially since 2017, accounting for 97.2% of all included articles. We evaluated the rules of the application of 47 DL networks to eight radiological tasks on 11 human organ sites. Neuroradiology, thorax, and abdomen were frequent research subjects, while thyroid was under-represented. Segmentation and classification tasks were the primary purposes. U-Net, ResNet, and VGG were the most frequently used Convolutional neural network-derived networks. GAN-derived networks were widely developed and applied in 2020, and transfer learning was highlighted in the COVID-19 studies. Brain, prostate, and diabetic retinopathy-related studies were mature research topics in the field. Breast- and lung-related studies were in a stage of rapid development. Conclusions This study evaluates the general rules and future trajectories of DL network application in medical image analyses and provides guidance for future studies.

Purpose: We established a CT-derived approach to achieve accurate progression-free survival (PFS) prediction to EGFR tyrosine kinase inhibitors (TKI) therapy in multicenter, stage IV EGFR-mutated non–small cell lung cancer (NSCLC) patients. Experimental Design: A total of 1,032 CT-based phenotypic characteristics were extracted according to the intensity, shape, and texture of NSCLC pretherapy images. On the basis of these CT features extracted from 117 stage IV EGFR-mutant NSCLC patients, a CT-based phenotypic signature was proposed using a Cox regression model with LASSO penalty for the survival risk stratification of EGFR-TKI therapy. The signature was validated using two independent cohorts (101 and 96 patients, respectively). The benefit of EGFR-TKIs in stratified patients was then compared with another stage-IV EGFR-mutant NSCLC cohort only treated with standard chemotherapy (56 patients). Furthermore, an individualized prediction model incorporating the phenotypic signature and clinicopathologic risk characteristics was proposed for PFS prediction, and also validated by multicenter cohorts. Results: The signature consisted of 12 CT features demonstrated good accuracy for discriminating patients with rapid and slow progression to EGFR-TKI therapy in three cohorts (HR: 3.61, 3.77, and 3.67, respectively). Rapid progression patients received EGFR TKIs did not show significant difference with patients underwent chemotherapy for progression-free survival benefit (P = 0.682). Decision curve analysis revealed that the proposed model significantly improved the clinical benefit compared with the clinicopathologic-based characteristics model (P < 0.0001). Conclusions: The proposed CT-based predictive strategy can achieve individualized prediction of PFS probability to EGFR-TKI therapy in NSCLCs, which holds promise of improving the pretherapy personalized management of TKIs. Clin Cancer Res; 24(15); 3583–92. ©2018 AACR.

OBJECTIVE: To compare 2D and 3D radiomics features prognostic performance differences in CT images of non-small cell lung cancer (NSCLC). METHOD: We enrolled 588 NSCLC patients from three independent cohorts. Two sets of 463 patients from two different institutes were used as the training cohort. The remaining cohort with 125 patients was set as the validation cohort. A total of 1014 radiomics features (507 2D features and 507 3D features correspondingly) were assessed. Based on the dichotomized survival data, 2D and 3D radiomics indicators were calculated for each patient by trained classifiers. We used the area under the receiver operating characteristic curve (AUC) to assess the prediction performance of trained classifiers (the support vector machine and logistic regression). Kaplan–Meier and Cox hazard survival analyses were also employed. Harrell's concordance index (C-Index) and Akaike's information criteria (AIC) were applied to assess the trained models. RESULTS: Radiomics indicators were built and compared by AUCs. In the training cohort, 2D_AUC = 0.653, 3D_AUC = 0.671. In the validation cohort, 2D_AUC = 0.755, 3D_AUC = 0.663. Both 2D and 3D trained indicators achieved significant results (P

To determine the characteristics of and trends in research in the emerging field of radiomics through bibliometric and hotspot analyses of relevant original articles published between 2013 and 2018.We evaluated 553 original articles concerning radiomics, published in a total of 61 peer-reviewed journals between 2013 and 2018. The following information was retrieved for each article: radiological subspecialty, imaging technique(s), machine learning technique(s), sample size, study setting and design, statistical result(s), study purpose, software used for feature calculation, funding declarations, author number, first author's affiliation, study origin, and journal name. Qualitative and quantitative analyses were performed for the manually extracted data for identification and visualization of the trends in radiomics research.The annual growth rate in the number of published papers was 177.82% (p0.001). The characteristics and trends of research hotspots in the field of radiomics were clarified and visualized in this study. It was found that the field of radiomics is at a more mature stage for lung, breast, and prostate cancers than for other sites. Radiomics studies primarily focused on radiological characterization (215) and monitoring (182). Logistic regression and LASSO were the two most commonly used techniques for feature selection. Non-clinical researchers without a medical background dominated radiomics studies (70.52%), the vast majority of which only highlighted positive results (97.80%) while downplaying negative findings.The reporting of quantifiable knowledge about the characteristics and trajectories of radiomics can inform researchers about the gaps in the field of radiomics and guide its future direction.

Objectives Models should be developed to assist choice between liver resection (LR) and transarterial chemoembolization (TACE) for hepatocellular carcinoma. Methods After separating 520 cases from 5 hospitals into training (n = 302) and validation (n = 218) data sets, we weighted the cases to control baseline difference and ensured the causal effect between treatments (LR and TACE) and estimated progression-free survival (PFS) difference. A noninvasive PFS model was constructed with clinical factors, radiological characteristics, and radiomic features. We compared our model with other 4 state-of-the-art models. Finally, patients were classified into subgroups with and without significant PFS difference between treatments. Results Our model included treatments, age, sex, modified Barcelona Clinic Liver Cancer stage, fusion lesions, hepatocellular carcinoma capsule, and 3 radiomic features, with good discrimination and calibrations (area under the curve for 3-year PFS was 0.80 in the training data set and 0.75 in the validation data set; similar results were achieved in 1- and 2-year PFS). The model had better accuracy than the other 4 models. A nomogram was built, with different scores assigned for LR and TACE. Separated by the threshold of score difference between treatments, for some patients, LR provided longer PFS and might be the better option (training: hazard ratio [HR] = 0.50, P = 0.014; validation: HR = 0.52, P = 0.026); in the others, LR provided similar PFS with TACE (training: HR = 0.84, P = 0.388; validation: HR = 1.14, P = 0.614). TACE may be better because it was less invasive. Discussion We propose an individualized model predicting PFS difference between LR and TACE to assist in the optimal treatment choice.

An end-to-end efficacy evaluation approach for identifying progression risk after epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitor (TKI) therapy in patients with stage IV EGFR variant-positive non-small cell lung cancer (NSCLC) is lacking.To propose a clinically applicable large-scale bidirectional generative adversarial network for predicting the efficacy of EGFR-TKI therapy in patients with NSCLC.This diagnostic/prognostic study enrolled 465 patients from January 1, 2010, to August 1, 2017, with follow-up from February 1, 2010, to June 1, 2020. A deep learning (DL) semantic signature to predict progression-free survival (PFS) was constructed in the training cohort, validated in 2 external validation and 2 control cohorts, and compared with the radiomics signature.An end-to-end bidirectional generative adversarial network framework was designed to predict the progression risk in patients with NSCLC.The primary end point was PFS, considering the time from the initiation of therapy to the date of recurrence, confirmed disease progression, or death.A total of 342 patients with stage IV EGFR variant-positive NSCLC receiving EGFR-TKI therapy met the inclusion criteria. Of these, 145 patients from 2 of the hospitals (n = 117 and 28) formed a training cohort (mean [SD] age, 61 [11] years; 87 [60.0%] female), and the patients from 2 other hospitals comprised 2 external validation cohorts (validation cohort 1: n = 101; mean [SD] age, 57 [12] years; 60 [59.4%] female; and validation cohort 2: n = 96, mean [SD] age, 58 [9] years; 55 [57.3%] female). Fifty-six patients with advanced-stage EGFR variant-positive NSCLC (mean [SD] age, 52 [11] years; 26 [46.4%] female) and 67 patients with advanced-stage EGFR wild-type NSCLC (mean [SD] age, 54 [10] years; 10 [15.0%] female) who received first-line chemotherapy were included. A total of 90 (26%) receiving EGFR-TKI therapy with a high risk of rapid disease progression were identified (median [range] PFS, 7.3 [1.4-32.0] months in the training cohort, 5.0 [0.6-34.6] months in validation cohort 1, and 6.4 [1.8-20.1] months, in validation cohort 2) using the DL semantic signature.The PFS decreased by 36% (hazard ratio, 2.13; 95% CI, 1.30-3.49; P .001) compared with that in other patients (median [range] PFS, 11.5 [1.5-64.2] months in the training cohort, 10.9 [1.1-50.5] in validation cohort 1, and 8.9 [0.8-40.6] months in validation cohort 2. No significant differences were observed when comparing the PFS of high-risk patients receiving EGFR-TKI therapy with the chemotherapy cohorts (median PFS, 6.9 vs 4.4 months; P = .08). In terms of predicting the tumor progression risk after EGFR-TKI therapy, clinical decisions based on the DL semantic signature led to better survival outcomes than those based on radiomics signature across all risk probabilities by the decision curve analysis.This diagnostic/prognostic study provides a clinically applicable approach for identifying patients with stage IV EGFR variant-positive NSCLC who are not likely to benefit from EGFR-TKI therapy. The end-to-end DL-derived semantic features eliminated all manual interventions required while using previous radiomics methods and have a better prognostic performance.

Purpose To summarize the data of previously reported medical imaging features on human malignancies to provide a scientific basis for more credible imaging feature selection for future studies. Materials and Methods A search was performed in PubMed from database inception through March 23, 2018, for studies clearly stating the decoding of medical imaging features for malignancy-related objectives and/or hypotheses. The Newcastle-Ottawa scale was used for quality assessment of the included studies. Unsupervised hierarchical clustering was performed on the manually extracted features from each included study to identify the application rules of medical imaging features across human malignancies. CT images of 1000 retrospective patients with non–small cell lung cancer were used to reveal a pattern for the value distribution of complex texture features. Results A total of 5026 imaging features of malignancies affecting 20 parts of the human body from 930 original articles were collated and assessed in this study. A meta-feature construct was proposed to facilitate the investigation of details of any high-dimensional complex imaging features of malignancy. A correlation atlas was constructed to clarify the general rules of applying medical imaging features to the analysis of human malignancy. Assessment of this data revealed a pattern of value distributions of the most commonly reported texture features across human malignancies. Furthermore, the significant expression of the gene mutational signature 1B across human cancer was highly consistent with the presence of the run length imaging feature across different human malignancy types. Conclusion The results of this study may facilitate more credible imaging feature selection in all oncology tasks across a wide spectrum of human malignancies and help to reduce bias and redundancies in future medical imaging studies. Keywords: Computer Aided Diagnosis (CAD), Computer Applications-General (Informatics), Evidence Based Medicine, Informatics, Research Design, Statistics, Technology Assessment Supplemental material is available for this article. Published under a CC BY 4.0 license.

Objectives To establish a pre-therapy prognostic index model (PIM) of the first-line chemotherapy aiming to achieve accurate prediction of time to progression (TTP) and overall survival among the patients diagnosed with locally advanced (stage III) or distant metastasis (stage IV) lung squamous cell carcinoma (LSCC). Methods Ninety-six LSCC patients treated with first-line chemotherapy were retrospectively enrolled to build the model. Fourteen epidermal growth factor receptor (EGFR)-mutant LSCC patients treated with first-line EGFR-tyrosine kinase inhibitor (TKI) therapy were enrolled for validation dataset. From CT images, 56,000 phenotype features were initially computed. PIM was constructed by integrating a CT phenotype signature selected by the least absolute shrinkage and selection operator and the significant blood-based biomarkers selected by multivariate Cox regression. PIM was then compared with other four prognostic models constructed by the CT phenotype signature, clinical factors, post-therapy tumor response, and Glasgow Prognostic Score. Results The signature includes eight optimal features extracted from co-occurrence, run length, and Gabor features. By using PIM, chemotherapy efficacy of patients categorized in the low-risk, intermediate-risk, and high-risk progression subgroups (median TTP = 7.2 months, 3.4 months, and 1.8 months, respectively) was significantly different (p

To distinguish squamous cell carcinoma (SCC) from lung adenocarcinoma (ADC) based on a radiomic signature This study involved 129 patients with non-small cell lung cancer (NSCLC) (81 in the training cohort and 48 in the independent validation cohort). Approximately 485 features were extracted from a manually outlined tumor region. The LASSO logistic regression model selected the key features of a radiomic signature. Receiver operating characteristic curve and area under the curve (AUC) were used to evaluate the performance of the radiomic signature in the training and validation cohorts. Five features were selected to construct the radiomic signature for histologic subtype classification. The performance of the radiomic signature to distinguish between lung ADC and SCC in both training and validation cohorts was good, with an AUC of 0.905 (95% confidence interval [CI]: 0.838 to 0.971), sensitivity of 0.830, and specificity of 0.929. In the validation cohort, the radiomic signature showed an AUC of 0.893 (95% CI: 0.789 to 0.996), sensitivity of 0.828, and specificity of 0.900. A unique radiomic signature was constructed for use as a diagnostic factor for discriminating lung ADC from SCC. Patients with NSCLC will benefit from the proposed radiomic signature. • Machine learning can be used for auxiliary distinguish in lung cancer. • Radiomic signature can discriminate lung ADC from SCC. • Radiomics can help to achieve precision medical treatment.

Accurately predict the risk of disease progression and benefit of tyrosine kinase inhibitors (TKIs) therapy for stage IV non-small cell lung cancer (NSCLC) patients with activing epidermal growth factor receptor (EGFR) mutations by current staging methods are challenge. We postulated that integrating a classifier consisted of multiple computed tomography (CT) phenotypic features, and other clinicopathological risk factors into a single model could improve risk stratification and prediction of progression-free survival (PFS) of EGFR TKIs for these patients. Patients confirmed as stage IV EGFR-mutant NSCLC received EGFR TKIs with no resection; pretreatment contrast enhanced CT performed at approximately 2 weeks before the treatment was enrolled. A six-CT-phenotypic-feature-based classifier constructed by the LASSO Cox regression model, and three clinicopathological factors: pathologic N category, performance status (PS) score, and intrapulmonary metastasis status were used to construct a nomogram in a training set of 115 patients. The prognostic and predictive accuracy of this nomogram was then subjected to an external independent validation of 107 patients. PFS between the training and independent validation set is no statistical difference by Mann-Whitney U test (P = 0.2670). PFS of the patients could be predicted with good consistency compared with the actual survival. C-index of the proposed individualized nomogram in the training set (0·707, 95%CI: 0·643, 0·771) and the independent validation set (0·715, 95%CI: 0·650, 0·780) showed the potential of clinical prognosis to predict PFS of stage IV EGFR-mutant NSCLC from EGFR TKIs. The individualized nomogram might facilitate patient counselling and individualise management of patients with this disease.

This was a retrospective study to investigate the predictive and prognostic ability of quantitative computed tomography phenotypic features in patients with non-small cell lung cancer (NSCLC). 661 patients with pathological confirmed as NSCLC were enrolled between 2007 and 2014. 592 phenotypic descriptors was automatically extracted on the pre-therapy CT images. Firstly, support vector machine (SVM) was used to evaluate the predictive value of each feature for pathology and TNM clinical stage. Secondly, Cox proportional hazards model was used to evaluate the prognostic value of these imaging signatures selected by SVM which subjected to a primary cohort of 138 patients, and an external independent validation of 61 patients. The results indicated that predictive accuracy for histopathology, N staging, and overall clinical stage was 75.16%, 79.40% and 80.33%, respectively. Besides, Cox models indicated the signatures selected by SVM: “correlation of co-occurrence after wavelet transform” was significantly associated with overall survival in the two datasets (hazard ratio [HR]: 1.65, 95% confidence interval [CI]: 1.41–2.75, p = 0.010; and HR: 2.74, 95%CI: 1.10–6.85, p = 0.027, respectively). Our study indicates that the phenotypic features might provide some insight in metastatic potential or aggressiveness for NSCLC, which potentially offer clinical value in directing personalized therapeutic regimen selection for NSCLC.

For non-small cell lung cancer (NSCLC) patients with epidermal growth factor receptor (EGFR) mutations, current staging methods do not accurately predict the risk of disease recurrence after tyrosine kinase inhibitors (TKI) therapy. Developing a noninvasive method to predict whether individual could benefit from TKI therapy has great clinical significance. In this research, a radiomics approach was proposed to determine whether the tumor heterogeneity of NSCLC, which was measured by the texture on computed tomography (CT), could make an independent prediction of progression-free survival (PFS). A primary dataset contained 80 patients (median PFS, 9.5 months) with positive EGFR mutations and a validation dataset contained 72 NSCLC (median PFS, 10.2 months) patients were used for prognosis trial. The experiment results indicated that the features: "Cluster Prominence of Gray Level Co-occurrence" (hazard ratio [HR]: 2.13, 95% confidence interval [CI]: (1.33, 3.40), P = 0.010) and "Short Run High Gray Level Emphasis of Run Length" (HR: 2.43, 95%CI: (1.46, 4.05), P = 0.005) were significantly associated with PFS in the primary dataset, and these two texture features also make a consistent performance on the validation cohort. Our study further supported that the quantitative measurement of tumor heterogeneity can be associated with prognosis of NSCLC patients with EGFR mutation.

In this paper, a radiomics approach was proposed to determine whether the tumor heterogeneity of non-small cell lung cancer (NSCLC), which was measured by the texture on computed tomography (CT), could make an independent prediction of overall survival. A primary dataset contained 72 patients (mean survival, 15.9 months) with pathologic diagnosis of NSCLC and a validation dataset contained 67 NSCLC (mean survival, 18.1 months) patients which were used for prognosis trial. The experiment results indicated that the features: "energy of run-length (ERL)" (hazard ratio [HR]: 0.55, 95% confidence interval [CI]: (0.34, 0.89), P = 0.014) and "long-run high gray level emphasis of run-length (LRHGLERL)" (HR: 0.50, 95%CI: (0.32, 0.80), P = 0.005) were significantly associated with overall survival in the primary dataset, and these two texture features also make an consistent performance on the validation cohort. Our study further supported that the quantitative measurement of tumor heterogeneity can be associated with prognosis of NSCLC.

The accurate segmentation of lung lesions from computed tomography (CT) scans is important for lung cancer research and can offer valuable information for clinical diagnosis and treatment. However, it is challenging to achieve a fully automatic lesion detection and segmentation with acceptable accuracy due to the heterogeneity of lung lesions. Here, we propose a novel toboggan based growing automatic segmentation approach (TBGA) with a three-step framework, which are automatic initial seed point selection, multi-constraints 3D lesion extraction and the final lesion refinement. The new approach does not require any human interaction or training dataset for lesion detection, yet it can provide a high lesion detection sensitivity (96.35%) and a comparable segmentation accuracy with manual segmentation $({\rm P}>0.05)$ , which was proved by a series assessments using the LIDC-IDRI dataset (850 lesions) and in-house clinical dataset (121 lesions). We also compared TBGA with commonly used level set and skeleton graph cut methods, respectively. The results indicated a significant improvement of segmentation accuracy $({\rm P} . Furthermore, the average time consumption for one lesion segmentation was under 8 s using our new method. In conclusion, we believe that the novel TBGA can achieve robust, efficient and accurate lung lesion segmentation in CT images automatically.

Lung cancer is the leading cause of cancer mortality around the world, the early diagnosis of lung cancer plays a very important role in therapeutic regimen selection. However, lung cancers are spatially and temporally heterogeneous; this limits the use of invasive biopsy. But radiomics which refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features has the ability to capture intra-tumoural heterogeneity in a non-invasive way. Here we carry out a radiomic analysis of 150 features quantifying lung tumour image intensity, shape and texture. These features are extracted from 593 patients computed tomography (CT) data on Lung Image Database Consortium Image Database Resource Initiative (LIDC-IDRI) dataset. By using support vector machine, we find that a large number of quantitative radiomic features have diagnosis power. The accuracy of prediction of malignant of lung tumor is 86% in training set and 76.1% in testing set. As CT imaging of lung tumor is widely used in routine clinical practice, our radiomic classifier will be a valuable tool which can help clinical doctor diagnose the lung cancer.