Search

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.

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.

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: 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.

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

Radiomics, as a newly emerging technology, converts medical images into high-dimensional data via high-throughput extraction of quantitative features, followed by subsequent data analysis for decision support. It identifies general diagnostic or prognostic phenotypes with target clinical need, providing an unprecedented opportunity to improve individualized treatment in cancer at low cost. In this chapter, we will introduce radiomics from its development to its clinical applications. We divide the clinical applications into three sections based on three most common medical modality, including computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography (PET), to give a comprehensive introduction of how radiomics works with the example of a typical cancer type. The workflow and detailed technology skills are well described in each section.

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.