Hybrid Clinical-Radiomics Model for Precisely Predicting the Invasiveness of Lung Adenocarcinoma Manifesting as Pure Ground-Glass Nodule

Pituitary MRI Radiomics Improves Diagnostic Performance of Growth Hormone Deficiency in Children Short Stature: A Multicenter Radiomics Study

RATIONALE AND OBJECTIVES

To develop an efficient machine-learning model using pituitary MRI radiomics and clinical data to differentiate growth hormone deficiency (GHD) from idiopathic short stature (ISS), making the diagnostic process more acceptable to patients and their families.

MATERIALS AND METHODS

A retrospective cohort of 297 GHD and 300 ISS children (4-12 years) were enrolled as training and validation cohorts (8:2 ratio). An external cohort from another institution (49 GHD and 51 ISS) was employed as the testing cohort. Radiomics features extracted from the anterior pituitary gland on sagittal T1-weighted image (1.5 T or 3.0 T) were used to develop a radiomics model after feature selection. Hematological biomarkers were selected to create a clinical model and combine with the optimal radiomics features to create a clinical-radiomics model. The area under the receive operating characteristic curve (AUC) and Delong test compared the diagnostic performance of the previously mentioned three models across different validation and testing cohorts.

RESULTS

17 radiomics features were selected for the radiomics model, and total protein, total cholesterol, free triiodothyronine, and triglyceride were utilized for the clinical model. In the training and validation cohorts, the diagnostic performance of the clinical-radiomics model (AUC=0.820 and 0.801) was comparable to the radiomics model (AUC=0.812 and 0.779, both P >0.05), both outperforming the clinical model (AUC=0.575 and 0.593, P <0.001). In the testing cohort, the clinical-radiomics model exhibited the highest AUC of 0.762 than the clinical and radiomics model (AUC=0.604 and 0.741, respectively, P <0.05). In addition, the clinical and radiomics models demonstrated similar diagnostic performance in the testing cohort (P >0.05).

CONCLUSION

Integrating radiomics features from conventional pituitary MRI with clinical indicators offers a minimally invasive approach for identifying GHD and shows robustness in a multicenter setting.

Predicting Invasiveness of Lung Adenocarcinoma at Chest CT with Deep Learning Ternary Classification Models

Background Preoperative discrimination of preinvasive, minimally invasive, and invasive adenocarcinoma at CT informs clinical management decisions but may be challenging for classifying pure ground-glass nodules (pGGNs). Deep learning (DL) may improve ternary classification. Purpose To determine whether a strategy that includes an adjudication approach can enhance the performance of DL ternary classification models in predicting the invasiveness of adenocarcinoma at chest CT and maintain performance in classifying pGGNs. Materials and Methods In this retrospective study, six ternary models for classifying preinvasive, minimally invasive, and invasive adenocarcinoma were developed using a multicenter data set of lung nodules. The DL-based models were progressively modified through framework optimization, joint learning, and an adjudication strategy (simulating a multireader approach to resolving discordant nodule classifications), integrating two binary classification models with a ternary classification model to resolve discordant classifications sequentially. The six ternary models were then tested on an external data set of pGGNs imaged between December 2019 and January 2021. Diagnostic performance including accuracy, specificity, and sensitivity was assessed. The χ2 test was used to compare model performance in different subgroups stratified by clinical confounders. Results A total of 4929 nodules from 4483 patients (mean age, 50.1 years ± 9.5 [SD]; 2806 female) were divided into training (n = 3384), validation (n = 579), and internal (n = 966) test sets. A total of 361 pGGNs from 281 patients (mean age, 55.2 years ± 11.1 [SD]; 186 female) formed the external test set. The proposed strategy improved DL model performance in external testing (P < .001). For classifying minimally invasive adenocarcinoma, the accuracy was 85% and 79%, sensitivity was 75% and 63%, and specificity was 89% and 85% for the model with adjudication (model 6) and the model without (model 3), respectively. Model 6 showed a relatively narrow range (maximum minus minimum) across diagnostic indexes (accuracy, 1.7%; sensitivity, 7.3%; specificity, 0.9%) compared with the other models (accuracy, 0.6%-10.8%; sensitivity, 14%-39.1%; specificity, 5.5%-17.9%). Conclusion Combining framework optimization, joint learning, and an adjudication approach improved DL classification of adenocarcinoma invasiveness at chest CT. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Sohn and Fields in this issue.

A multi-classification model for non-small cell lung cancer subtypes based on independent subtask learning

PURPOSE

The non-small cell lung cancer (NSCLC) can be divided into adenocarcinoma (ADC), squamous cell carcinoma (SCC), large cell carcinoma (LCC), and not otherwise specified (NOS), which is crucial for clinical decision-making. However, current related researches are rare for the complex multi-classification of NSCLC, mainly due to the serious data imbalance, the difficulty to unify the feature space, and the complicated decision boundary among multiple subtypes. The machine learning method of traditional "one-vs-one" (OVO) is difficult to solve these problems and achieve good results.

METHODS

To this end, we propose a novel independent subtask learning (ISTL) method to better carry out the multi-classification task. Specifically, it includes four pertinent strategies: (1) independent data expansion; (2) independent feature selection (IFS); (3) independent model construction; and (4) a novel voting strategy: majority voting combined with Bayesian prior. We performed experiments using 1036 CT scans (ADC:SCC:LCC:NOS = 600:268:105:63) collected from eight international databases, and the data acquisition was highly complex and diverse.

RESULTS

The experimental results showed that the ISTL method obtained an accuracy of 0.812 on the independent test cohort, which significantly improved the performance of multi-classification compared with the traditional OVO-support vector machine (0.691) and OVO-random forest (0.710) models. After the IFS, six selected feature sets of six binary tasks are obviously different, indicating that the ISTL method has better interpretability to distinguish the multiple NSCLC subtypes. The results of a further auxiliary contrast experiment showed that four pertinent strategies were all effective.

CONCLUSION

Our work indicates that the ISTL method can effectively perform multi-classification of NSCLC subtypes with better interpretability for clinical computer-aided detection and has the potential to be applied in a wide range of multi-classification studies.

A Nomogram Incorporating Tumor-Related Vessels for Differentiating Adenocarcinoma In Situ from Minimally Invasive and Invasive Adenocarcinoma Appearing as Subsolid Nodules

OBJECTIVES

To develop a nomogram incorporating the quantity of tumor-related vessels (TRVs) and conventional CT features (CCTFs) for the preoperative differentiation of adenocarcinoma in situ (AIS) from minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) appearing as subsolid nodules.

METHODS

High-resolution CT target scans of 274 subsolid nodules from 268 patients were included in this study and randomly assigned to the training and validation groups at a ratio of 7:3. A nomogram incorporating CCTFs with the category of TRVs (CTRVs, using TRVs as categorical variables) and a final nomogram combining the number of TRVs (QTRVs) and CCTFs were constructed using multivariable logistic regression analysis. The performance levels of the two nomograms were evaluated and validated on the training and validation datasets and then compared.

RESULTS

The CCTF-QTRV nomogram incorporating abnormal air bronchogram, density, number of dilated and distorted vessels and number of adherent vessels showed more favorable predictive efficacy than the CCTF-CTRV nomogram (training cohort: area under the curve (AUC) = 0.893 vs. 0.844, validation cohort: AUC = 0.871 vs. 0.807). The net reclassification index (training cohort: 0.188, validation cohort: 0.326) and the integrated discrimination improvement values (training cohort: 0.091, validation cohort: 0.125) indicated that the CCTF-QTRV nomogram performed significantly better discriminative ability than the CCTF-CTRV nomogram (all p-value < 0.05).

CONCLUSIONS

The nomogram incorporating the QTRVs and CCTFs showed favorable predictive efficacy for differentiating AIS from MIA-IAC appearing as subsolid nodules and may serve as a potential tool to provide individual care for these patients.

Prediction of invasive adenocarcinomas manifesting as pure ground-glass nodules based on radiomic signature of low-dose CT in lung cancer screening

OBJECTIVE

To develop a radiomic model based on low-dose CT (LDCT) to distinguish invasive adenocarcinomas (IAs) from adenocarcinoma in situ/minimally invasive adenocarcinomas (AIS/MIAs) manifesting as pure ground-glass nodules (pGGNs) and compare its performance with conventional quantitative and semantic features of LDCT, radiomic model of standard-dose CT, and intraoperative frozen section (FS).

METHODS

A total of 147 consecutive pathologically confirmed pGGNs were divided into primary cohort (43 IAs and 60 AIS/MIAs) and validation cohort (19 IAs and 25 AIS/MIAs). Logistic regression models were built using conventional quantitative and semantic features, selected radiomic features of LDCT and standard-dose CT, and intraoperative FS diagnosis, respectively. The diagnostic performance was assessed by area under curve (AUC) of receiver operating characteristic curve, sensitivity, and specificity.

RESULTS

The AUCs of quantitative-semantic model, radiomic model of LDCT, radiomic model of standard-dose CT, and FS model were 0.879 (95% CI, 0.801-0.935), 0.929 (95% CI, 0.862-0.971), 0.941 (95% CI, 0.876-0.978), and 0.884 (95% CI, 0.805-0.938) in the primary cohort and 0.897 (95% CI, 0.768-0.968), 0.933 (95% CI, 0.815-0.986), 0.901 (95% CI, 0.773-0.970), and 0.828 (95% CI, 0.685-0.925) in the validation cohort. No significant difference of the AUCs was found among these models in both the primary and validation cohorts (all p > 0.05).

CONCLUSION

The LDCT-based quantitative-semantic score and radiomic signature, with good predictive performance, can be pre-operative and non-invasive biomarkers for assessing the invasive risk of pGGNs in lung cancer screening.

ADVANCES IN KNOWLEDGE

The LDCT-based quantitative-semantic score and radiomic signature, with the equivalent performance to the radiomic model of standard-dose CT, can be pre-operative predictors for assessing the invasiveness of pGGNs in lung cancer screening and reducing excess examination and treatment.

A Multi-Classification Model for Predicting the Invasiveness of Lung Adenocarcinoma Presenting as Pure Ground-Glass Nodules

Objectives

To establish a multi-classification model for precisely predicting the invasiveness (pre-invasive adenocarcinoma, PIA; minimally invasive adenocarcinoma, MIA; invasive adenocarcinoma, IAC) of lung adenocarcinoma manifesting as pure ground-glass nodules (pGGNs).

Methods

By the inclusion and exclusion criteria, this retrospective study enrolled 346 patients (female, 297, and male, 49; age, 55.79 ± 10.53 (24-83)) presenting as pGGNs from 1292 consecutive patients with pathologically confirmed lung adenocarcinoma. A total of 27 clinical were collected and 1409 radiomics features were extracted by PyRadiomics package on python. After feature selection with L2,1-norm minimization, logistic regression (LR), extra w(ET) and gradient boosting decision tree (GBDT) were used to construct the three-classification model. Then, an ensemble model of the three algorithms based on model ensemble strategy was established to further improve the classification performance.

Results

After feature selection, a hybrid of 166 features consisting of 1 clinical (short-axis diameter, ranked 27th) and 165 radiomics (4 shape, 71 intensity and 90 texture) features were selected. The three most important features are wavelet-HLL_firstorder_Minimum, wavelet-HLL_ngtdm_Busyness and square_firstorder_Kurtosis. The hybrid-ensemble model based on hybrid clinical-radiomics features and the ensemble strategy showed more accurate predictive performance than other models (hybrid-LR, hybrid-ET, hybrid-GBDT, clinical-ensemble and radiomics-ensemble). On the training set and test set, the model can obtain the accuracy values of 0.918 ± 0.022 and 0.841, and its F1-scores respectively were 0.917 ± 0.024 and 0.824.

Conclusion

The multi-classification of invasive pGGNs can be precisely predicted by our proposed hybrid-ensemble model to assist patients in the early diagnosis of lung adenocarcinoma and prognosis.

Radiomics in Early Lung Cancer Diagnosis: From Diagnosis to Clinical Decision Support and Education

Lung cancer is the most frequent cause of cancer-related death around the world. With the recent introduction of low-dose lung computed tomography for lung cancer screening, there has been an increasing number of smoking- and non-smoking-related lung cancer cases worldwide that are manifesting with subsolid nodules, especially in Asian populations. However, the pros and cons of lung cancer screening also follow the implementation of lung cancer screening programs. Here, we review the literature related to radiomics for early lung cancer diagnosis. There are four main radiomics applications: the classification of lung nodules as being malignant/benign; determining the degree of invasiveness of the lung adenocarcinoma; histopathologic subtyping; and prognostication in lung cancer prediction models. In conclusion, radiomics offers great potential to improve diagnosis and personalized risk stratification in early lung cancer diagnosis through patient–doctor cooperation and shared decision making.

Radiomics Nomogram for Predicting Locoregional Failure in Locally Advanced Non-small Cell Lung Cancer Treated with Definitive Chemoradiotherapy

RATIONALE AND OBJECTIVES

To develop and validate a computed tomography (CT)-based radiomics nomogram for predicting locoregional failure (LRF) in patients with locally advanced non-small cell lung cancer (NSCLC) treated with definitive chemoradiotherapy (CRT).

MATERIALS AND METHODS

A total of 141 patients with locally advanced NSCLC treated with definitive CRT from January 2014 to December 2017 were included and divided into testing cohort (n = 100) and validation (n = 41) cohort. Radiomics features were extracted from pretreatment contrast enhanced CT. The least absolute shrinkage and selection operator logistic regression was processed to select predictive features from the testing cohort and constructed a radiomics signature. Clinical characteristics and the radiomics signature were analyzed using univariable and multivariate Cox regression. The radiomics nomogram was established with the radiomics signature and independent clinical factors. Harrell's C-index, calibration curves and decision curves were used to assess the performance of the radiomics nomogram.

RESULTS

The radiomics signature, which consisted of eight selected features, was an independent factor of LRF. The clinical predictors of LRF were the histologic type and clinical stage. The radiomics nomogram combined with the radiomics signature and clinical prognostic factors showed good performance with C-indexes of 0.796 (95% confidence interval [CI]: 0.709-0.883) and 0.756 (95% CI: 0.674-0.838) in the testing and validation cohorts respectively. Additionally, the combined nomogram resulted in better performance (p < 0.001) for the estimation of LRF than the nomograms with the radiomics signature (C-index: 0.776; 95% CI: 0.686-0.866) or clinical predictors (C-index: 0.641; 95% CI: 0.542-0.740) alone.

CONCLUSION

The radiomics nomogram provided the best performance for LRF prediction in patients with locally advanced NSCLC, which may help optimize individual treatments.

Predicting lung adenocarcinoma invasiveness by measurement of pure ground-glass nodule roundness by using multiplanar reformation: a retrospective analysis

AIM

To explore the value of roundness measurement based on thin-section axial, coronal, and sagittal section computed tomography (CT) images for predicting pure ground-glass nodule (pGGN) invasiveness.

MATERIALS AND METHODS

A total of 168 pGGNs in 155 patients (44 male, 111 females; mean age, 55.74 ± 10.57 years), and confirmed by surgery and histopathology, were analysed retrospectively and divided into pre-invasive (n=72) and invasive (n=96) groups. Photoshop (CS6) software was used to measure pGGN roundness based on conventional axial section, as well as coronal and sagittal sections generated by multiplanar reformation, from thin-section (1-mm-thick) CT lung images.

RESULTS

pGGN roundness values, measured in axial, coronal, and sagittal thin-section CT sections from the pre-invasive group were 0.8 ± 0.049, 0.816 ± 0.05, and 0.818 ± 0.043, respectively, while those in the invasive group were 0.745 ± 0.077, 0.684 ± 0.106, and 0.678 ± 0.106; differences between the two groups were significant (all p<0.001). Binary logistic regression analysis showed that roundness values based on coronal and sagittal sections (p<0.001) were better than those from axial sections (p>0.05) in predicting pGGN invasiveness, with odds ratio (OR) values of 14.858 and 23.315, respectively. ROC analysis showed that evaluation of roundness measured in sagittal sections was better at predicting pGGN invasiveness than when coronal sections were used (AUC 0.870 versus 0.832).

CONCLUSION

Roundness is useful for predicting pGGN invasiveness, with measurements from coronal and sagittal sections better than those from conventional axial sections, with sagittal section images having the best predictive value.

Use of CT radiomics to differentiate minimally invasive adenocarcinomas and invasive adenocarcinomas presenting as pure ground-glass nodules larger than 10 mm

PURPOSE

This study aimed to develop a model based on radiomics features extracted from computed tomography (CT) images to effectively differentiate between minimally invasive adenocarcinomas (MIAs) and invasive adenocarcinomas (IAs) manifesting as pure ground-glass nodules (pGGNs) larger than 10 mm.

METHOD

This retrospective study included patients who underwent surgical resection for persistent pGGN between November 2012 and June 2018 and diagnosed with MIAs or IAs. The patients were randomly assigned to the training and test cohorts. The correlation coefficient method and the least absolute shrinkage and selection operator (LASSO) method were applied to select radiomics features useful for constructing a model whose performance was assessed by the area under the receiver operating characteristic curve (AUC-ROC). The radiomics model was compared to a standard CT model (shape, volume and mean CT value of the largest cross-section) and the combined radiomics-standard CT model using univariate and multivariate logistic regression analysis.

RESULTS

The radiomics model showed better discriminative ability (training AUC, 0.879; test AUC, 0.877) than the standard CT model (training AUC, 0.820; test AUC, 0.828). The combined model (training AUC, 0.879; test AUC, 0.870) did not demonstrate improved performance compared with the radiomics model. Radiomics_score was an independent predictor of invasiveness following multivariate logistic analysis.

CONCLUSIONS

For pGGNs larger than 10 mm, the radiomics model demonstrated superior diagnostic performance in differentiating between IAs and MIAs, which may be useful to clinicians for diagnosis and treatment selection.

Radiomic signature based on CT imaging to distinguish invasive adenocarcinoma from minimally invasive adenocarcinoma in pure ground-glass nodules with pleural contact

Background

Pure ground-glass nodules (pGGNs) with pleural contact (P-pGGNs) comprise not only invasive adenocarcinoma (IAC), but also minimally invasive adenocarcinoma (MIA). Radiomics recognizes complex patterns in imaging data by extracting high-throughput features of intra-tumor heterogeneity in a non-invasive manner. In this study, we sought to develop and validate a radiomics signature to identify IAC and MIA presented as P-pGGNs.

Methods

In total, 100 patients with P-pGGNs (69 training samples and 31 testing samples) were retrospectively enrolled from December 2012 to May 2018. Imaging and clinical findings were also analyzed. In total, 106 radiomics features were extracted from the 3D region of interest (ROI) using computed tomography (CT) imaging. Univariate analyses were used to identify independent risk factors for IAC. The least absolute shrinkage and selection operator (LASSO) method with 10-fold cross-validation was used to generate predictive features to build a radiomics signature. Receiver-operator characteristic (ROC) curves and calibration curves were used to evaluate the predictive accuracy of the radiomics signature. Decision curve analyses (DCA) were also conducted to evaluate whether the radiomics signature was sufficiently robust for clinical practice.

Results

Univariate analysis showed significant differences between MIA (N = 47) and IAC (N = 53) groups in terms of patient age, lobulation signs, spiculate margins, tumor size, CT values and relative CT values (all P < 0.05). ROC curve analysis showed, when MIA was identified from IAC, that the critical value of tumor length diameter (TLD) was1.39 cm and the area under the ROC curve (AUC) was 0.724 (sensitivity = 0.792, specificity = 0.553). The critical CT value on the largest axial plane (CT-LAP) was − 597.45 HU, and the AUC was 0.666 (sensitivity = 0.698, specificity= 0.638). The radiomics signature consisted of seven features and exhibited a good discriminative performance between IAC and MIA, with an AUC of 0.892 (sensitivity = 0.811, specificity 0.719), and 0.862 (sensitivity = 0.625, specificity = 0.800) in training and testing samples, respectively.

Conclusions

Our radiomics signature exhibited good discriminative performance in differentiating IAC from MIA in P-pGGNs, and may offer a crucial reference point for follow-up and selective surgical management.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-020-00376-1.