Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas

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

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

Low-Dose CT Screening of Persistent Subsolid Lung Nodules: First-Order Features in Radiomics

BACKGROUND

 Nondisappearing subsolid nodules requiring follow-up are often detected during lung cancer screening, but changes in their invasiveness can be overlooked owing to slow growth. We aimed to develop a method for automatic identification of invasive tumors among subsolid nodules during multiple health checkups using radiomics technology based on low-dose computed tomography (LD-CT) and examine its effectiveness.

METHODS

 We examined patients who underwent LD-CT screening from 2014 to 2019 and had lung adenocarcinomas resected after 5-year follow-ups. They were categorized into the invasive or less-invasive group; the annual growth/change rate (Δ) of the nodule voxel histogram using three-dimensional CT (e.g., tumor volume, solid volume percentage, mean CT value, variance, kurtosis, skewness, and entropy) was assessed. A discriminant model was designed through multivariate regression analysis with internal validation to compare its efficacy with that of a volume doubling time of < 400 days.

RESULTS

 The study included 47 tumors (23 invasive, 24 less invasive), with no significant difference in the initial tumor volumes. Δskewness was identified as an independent predictor of invasiveness (adjusted odds ratio, 0.021; p = 0.043), and when combined with Δvariance, it yielded high accuracy in detecting invasive lesions (88% true-positive, 80% false-positive). The detection model indicated surgery 2 years earlier than the volume doubling time, maintaining accuracy (median 3 years vs.1 year before actual surgery, p = 0.011).

CONCLUSION

 LD-CT radiomics showed promising potential in ensuring timely detection and monitoring of subsolid nodules that warrant follow-up over time.

Predicting invasion in early-stage ground-glass opacity pulmonary adenocarcinoma: a radiomics-based machine learning approach

BACKGROUND

To design a pulmonary ground-glass nodules (GGN) classification method based on computed tomography (CT) radiomics and machine learning for prediction of invasion in early-stage ground-glass opacity (GGO) pulmonary adenocarcinoma.

METHODS

This retrospective study included pulmonary GGN patients who were histologically confirmed to have adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma cancer (IAC) from 2020 to 2023. CT images of all patients were automatically segmented and 107 radiomic features were obtained for each patient. Classification models were developed using random forest (RF) and cross-validation, including three one-versus-others models and one three-class model. For each model, features were ranked by normalized Gini importance, and a minimal subset was selected with a cumulative importance exceeding 0.9. These selected features were then used to train the final models. The models' performance metrics, including area under the curve (AUC), accuracy, sensitivity, and specificity, were computed. AUC and accuracy were compared to determine the final optimal method.

RESULTS

The study comprised 193 patients (mean age 54 ± 11 years, 65 men), including 65 AIS, 54 MIA, and 74 IAC, divided into one training cohort (N = 154) and one test cohort (N = 39). The final three-class RF model outperformed three individual one-versus-others models in distinguishing each class from the other two. For the multiclass classification model, the AUC, accuracy, sensitivity, and specificity were 0.87, 0.79, 0.62, and 0.88 for AIS; 0.90, 0.79, 0.54, and 0.89 for MIA; and 0.87, 0.69, 0.73, and 0.67 for IAC, respectively.

CONCLUSIONS

A radiomics-based multiclass RF model could effectively differentiate three types of pulmonary GGN, which enabled early diagnosis of GGO pulmonary adenocarcinoma.

Radiomics predict the WHO/ISUP nuclear grade and survival in clear cell renal cell carcinoma

OBJECTIVES

This study aimed to assess the predictive value of radiomics derived from intratumoral and peritumoral regions and to develop a radiomics nomogram to predict preoperative nuclear grade and overall survival (OS) in patients with clear cell renal cell carcinoma (ccRCC).

METHODS

The study included 395 patients with ccRCC from our institution. The patients in Center A (anonymous) institution were randomly divided into a training cohort (n = 284) and an internal validation cohort (n = 71). An external validation cohort comprising 40 patients from Center B also was included. Computed tomography (CT) radiomics features were extracted from the internal area of the tumor (IAT) and IAT combined peritumoral areas of the tumor at 3 mm (PAT 3 mm) and 5 mm (PAT 5 mm). Independent predictors from both clinical and radiomics scores (Radscore) were used to construct a radiomics nomogram. Kaplan-Meier analysis with a log-rank test was performed to evaluate the correlation between factors and OS.

RESULTS

The PAT 5-mm radiomics model (RM) exhibited exceptional predictive capability for grading, achieving an area under the curves of 0.80, 0.80, and 0.90 in the training, internal validation, and external validation cohorts. The nomogram and RM gained from the PAT 5-mm region were more clinically useful than the clinical model. The association between OS and predicted nuclear grade derived from the PAT 5-mm Radscore and the nomogram-predicted score was statistically significant (p < 0.05).

CONCLUSION

The CT-based radiomics and nomograms showed valuable predictive capabilities for the World Health Organization/International Society of Urological Pathology grade and OS in patients with ccRCC.

CRITICAL RELEVANCE STATEMENT

The intratumoral and peritumoral radiomics are feasible and promising to predict nuclear grade and overall survival in patients with clear cell renal cell carcinoma, which can contribute to the development of personalized preoperative treatment strategies.

KEY POINTS

The multi-regional radiomics features are associated with clear cell renal cell carcinoma (ccRCC) grading and prognosis. The combination of intratumoral and peritumoral 5 mm regional features demonstrated superior predictive performance for grading. The nomogram and radiomics models have a broad range of clinical applications.

A Radiological-Radiomics model for differentiation between minimally invasive adenocarcinoma and invasive adenocarcinoma less than or equal to 3 cm: A two-center retrospective study

OBJECTIVE

To develop a Radiological-Radiomics (R-R) combined model for differentiation between minimal invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IA) of lung adenocarcinoma (LUAD) and evaluate its predictive performance.

METHODS

The clinical, pathological, and imaging data of a total of 509 patients (522 lesions) with LUAD diagnosed by surgical pathology from 2 medical centres were retrospectively collected, with 392 patients (402 lesions) from center 1 trained and validated using a five-fold cross-validation method, and 117 patients (120 lesions) from center 2 serving as an independent external test set. The least absolute shrinkage and selection operator (LASSO) method was utilized to filter features. Logistic regression was used to construct three models for predicting IA, namely, Radiological model, Radiomics model, and R-R model. Also, receiver operating curve curves (ROCs) were plotted, generating corresponding area under the curve (AUC), sensitivity, specificity, and accuracy.

RESULTS

The R-R model for IA prediction achieved an AUC of 0.918 (95 % CI: 0.889-0.947), a sensitivity of 80.3 %, a specificity of 88.2 %, and an accuracy of 82.1 % in the training set. In the validation set, this model exhibited an AUC of 0.906 (95 % CI: 0.842-0.970), a sensitivity of 79.9 %, a specificity of 88.1 %, and an accuracy of 81.8 %. In the external test set, the AUC was 0.894 (95 % CI: 0.824-0.964), a sensitivity of 84.8 %, a specificity of 78.6 %, and an accuracy of 83.3 %.

CONCLUSION

The R-R model showed excellent diagnostic performance in differentiating MIA and IA, which can provide a certain reference for clinical diagnosis and surgical treatment plans.

Subsolid Nodules: Significance and Current Understanding

Subsolid nodules are heterogeneously appearing and behaving entities, commonly encountered incidentally and in high-risk populations. Accurate characterization of subsolid nodules, and application of evolving surveillance guidelines, facilitates evidence-based and multidisciplinary patient-centered management.

Radiomics-Based Machine Learning Model for Diagnosis of Acute Pancreatitis Using Computed Tomography

In the early diagnostic workup of acute pancreatitis (AP), the role of contrast-enhanced CT is to establish the diagnosis in uncertain cases, assess severity, and detect potential complications like necrosis, fluid collections, bleeding or portal vein thrombosis. The value of texture analysis/radiomics of medical images has rapidly increased during the past decade, and the main focus has been on oncological imaging and tumor classification. Previous studies assessed the value of radiomics for differentiating between malignancies and inflammatory diseases of the pancreas as well as for prediction of AP severity. The aim of our study was to evaluate an automatic machine learning model for AP detection using radiomics analysis. Patients with abdominal pain and contrast-enhanced CT of the abdomen in an emergency setting were retrospectively included in this single-center study. The pancreas was automatically segmented using TotalSegmentator and radiomics features were extracted using PyRadiomics. We performed unsupervised hierarchical clustering and applied the random-forest based Boruta model to select the most important radiomics features. Important features and lipase levels were included in a logistic regression model with AP as the dependent variable. The model was established in a training cohort using fivefold cross-validation and applied to the test cohort (80/20 split). From a total of 1012 patients, 137 patients with AP and 138 patients without AP were included in the final study cohort. Feature selection confirmed 28 important features (mainly shape and first-order features) for the differentiation between AP and controls. The logistic regression model showed excellent diagnostic accuracy of radiomics features for the detection of AP, with an area under the curve (AUC) of 0.932. Using lipase levels only, an AUC of 0.946 was observed. Using both radiomics features and lipase levels, we showed an excellent AUC of 0.933 for the detection of AP. Automated segmentation of the pancreas and consecutive radiomics analysis almost achieved the high diagnostic accuracy of lipase levels, a well-established predictor of AP, and might be considered an additional diagnostic tool in unclear cases. This study provides scientific evidence that automated image analysis of the pancreas achieves comparable diagnostic accuracy to lipase levels and might therefore be used in the future in the rapidly growing era of AI-based image analysis.

CT‑based radiomics analysis of consolidation characteristics in differentiating pulmonary disease of non‑tuberculous mycobacterium from pulmonary tuberculosis

Global incidence rate of non-tuberculous mycobacteria (NTM) pulmonary disease has been increasing rapidly. In some countries and regions, its incidence rate is higher than that of tuberculosis. It is easily confused with tuberculosis. The topic of this study is to identify two diseases using CT radioomics. The aim in the present study was to investigate the value of CT-based radiomics to analyze consolidation features in differentiation of non-tuberculous mycobacteria (NTM) from pulmonary tuberculosis (TB). A total of 156 patients (75 with NTM pulmonary disease and 81 with TB) exhibiting consolidation characteristics in Shandong Public Health Clinical Center were retrospectively analyzed. Subsequently, 305 regions of interest of CT consolidation were outlined. Using a random number generated via a computer, 70 and 30% of consolidations were allocated to the training and the validation cohort, respectively. By means of variance threshold, when investigating the effective radiomics features, SelectKBest and the least absolute shrinkage and selection operator regression method were employed for feature selection and combined to calculate the radiomics score. K-nearest neighbor (KNN), support vector machine (SVM) and logistic regression (LR) were used to analyze effective radiomics features. A total of 18 patients with NTM pulmonary disease and 18 with TB possessing consolidation characteristics in Jinan Infectious Disease Hospital were collected for external validation of the model. A total of three methods was used in the selection of 52 optimal features. For KNN, the area under the curve (AUC; sensitivity, specificity) for the training and validation cohorts were 0.98 (0.93, 0.94) and 0.90 (0.88, 083), respectively; for SVM, AUC was 0.99 (0.96, 0.96) and 0.92 (0.86, 0.85) and for LR, AUC was 0.99 (0.97, 0.97) and 0.89 (0.88, 0.85). In the external validation cohort, AUC values of models were all >0.84 and LR classifier exhibited the most significant precision, recall and F1 score (0.87, 0.94 and 0.88, respectively). LR classifier possessed the best performance in differentiating diseases. Therefore, CT-based radiomics analysis of consolidation features may distinguish NTM pulmonary disease from TB.

Preoperative 18F-FDG PET/CT and CT radiomics for identifying aggressive histopathological subtypes in early stage lung adenocarcinoma

Lung adenocarcinoma (ADC) is the most common non-small cell lung cancer. Surgical resection is the primary treatment for early-stage lung ADC while lung-sparing surgery is an alternative for non-aggressive cases. Identifying histopathologic subtypes before surgery helps determine the optimal surgical approach. Predominantly solid or micropapillary (MIP) subtypes are aggressive and associated with a higher likelihood of recurrence and metastasis and lower survival rates. This study aims to non-invasively identify these aggressive subtypes using preoperative 18F-FDG PET/CT and diagnostic CT radiomics analysis. We retrospectively studied 119 patients with stage I lung ADC and tumors ≤ 2 cm, where 23 had aggressive subtypes (18 solid and 5 MIPs). Out of 214 radiomic features from the PET/CT and CT scans and 14 clinical parameters, 78 significant features (3 CT and 75 PET features) were identified through univariate analysis and hierarchical clustering with minimized feature collinearity. A combination of Support Vector Machine classifier and Least Absolute Shrinkage and Selection Operator built predictive models. Ten iterations of 10-fold cross-validation (10 ×10-fold CV) evaluated the model. A pair of texture feature (PET GLCM Correlation) and shape feature (CT Sphericity) emerged as the best predictor. The radiomics model significantly outperformed the conventional predictor SUVmax (accuracy: 83.5% vs. 74.7%, p = 9e-9) and identified aggressive subtypes by evaluating FDG uptake in the tumor and tumor shape. It also demonstrated a high negative predictive value of 95.6% compared to SUVmax (88.2%, p = 2e-10). The proposed radiomics approach could reduce unnecessary extensive surgeries for non-aggressive subtype patients, improving surgical decision-making for early-stage lung ADC patients.

Preoperative predicting invasiveness of lung adenocarcinoma manifesting as ground-glass nodules based on multimodal images of dual-layer spectral detector CT radiomics models

OBJECTIVE

To construct and validate conventional and radiomics models based on dual-layer spectral CT radiomics for preoperative prediction of lung ground glass nodules (GGNs) invasiveness.

MATERIALS AND METHODS

A retrospective study was conducted on 176 GGNs patients who underwent chest non-contrast enhancement scan on dual-layer spectral detector CT at our hospital within 2 weeks before surgery. Patients were randomized into the training cohort and testing cohort. Clinical features, imaging features and spectral quantitative parameters were collected to establish a conventional model. Radiomics models were established by extracting 1781 radiomics features form regions of interest of each spectral image [120 kVp poly energetic images (PI), 60 keV images and electron density maps], respectively. After selecting the optimal radiomic features and integrating multiple machine learning models, the conventional model, PI model, 60 keV model, electron density (ED) model and combined model based on multimodal spectral images were finally established. The performance of these models was assessed through the evaluation of discrimination, calibration, and clinical application.

RESULTS

In the conventional model, age, vacuole sign, 60 keV and ED were independent risk factors of invasiveness. The combined model using logistic regression-least absolute shrinkage and selection operator classifiers was the optimal model with a higher area under the curve of the training (0.961, 95% confidence interval, CI: 0.932-0.991) and testing set (0.944, 0.890-0.999).

CONCLUSION

The combined models are helpful to predict the invasiveness of GGNs before surgery and guide the individualized treatment of patients.

Spatial downregulation of CD74 signatures may drive invasive component development in part-solid lung adenocarcinoma

Pulmonary nodules with part-solid imaging features manifest during the progression from preinvasive to invasive lung adenocarcinoma. To define the spatial composition and evolutionary trajectories of early-stage lung adenocarcinoma, we combined spatial transcriptomics (ST) and pathological annotations from 20 part-solid nodules (PSNs), four of which were matched with single-cell RNA sequencing. Two malignant cell populations (MC1 and MC2) were identified, and a linear evolutionary relationship was observed. Compared to MC2, the pre-existing malignant MC1 exhibited a lower metastatic signature, corresponding to the preinvasive component (lepidic) on pathology and the ground glass component on PSN imaging. Higher immune infiltration was observed among MC1 regions in ST profiles, and further analysis revealed that macrophages may be involved in this process through the CD74 axis. This work provides deeper insights into the evolutionary process and spatial immune cell composition behind PSNs and highlights the mechanisms of immune escape behind this adenocarcinoma trajectory.

Differentiation Between Heterogeneous GGN and Part-Solid Nodule Using 2 D Grayscale Histogram Analysis of Thin-Section CT Image

INTRODUCTION/BACKGROUND

To evaluate cases of surgically resected pulmonary adenocarcinoma (Ad) with heterogenous ground-glass nodules (HGGNs) or part-solid nodules (PSNs) and to clarify the differences between them, and between invasive adenocarcinoma (IVA) and minimally invasive adenocarcinoma (MIA) + adenocarcinoma in situ (AIS) using grayscale histogram analysis of thin-section computed tomography (TSCT).

MATERIALS AND METHODS

241 patients with pulmonary Ad were retrospectively classified into HGGNs and PSNs on TSCT by three thoracic radiologists. Sixty HGGNs were classified into 17 IVAs, 26 MIAs, and 17 AISs. 181 PSNs were classified into 114 IVAs, 55 MIAs, and 12 AISs.

RESULTS

We found significant differences in area (P = 0.0024), relative size of solid component (P <0.0001), circumference (P <0.0001), mean CT value (P <0.0001), standard deviation of the CT value (P <0.0001), maximum CT value (P <0.0001), skewness (P <0.0001), kurtosis (P <0.0001), and entropy (P <0.0001) between HGGNs and PSNs. In HGGNs, we found significant differences in relative size of solid component (P <0.0001), mean CT value (P = 0.0005), standard deviation of CT value (P = 0.0071), maximum CT value (P = 0.0237), and skewness (P = 0.0027) between IVAs and MIA+AIS lesions. In PSNs, we found significant differences in area (P = 0.0029), relative size of solid component (P = 0.0003), circumference (P = 0.0004), mean CT value (P = 0.0011), skewness (P = 0.0009), and entropy (P = 0.0002) between IVAs and the MIA+AIS lesions.

CONCLUSION

Quantitative evaluations using grayscale histogram analysis can clearly distinguish between HGGNs and PSNs, and may be useful for estimating the pathology of such lesions.

Discrimination of ground-glass nodular lung adenocarcinoma pathological subtypes via transfer learning: A multicenter study

BACKGROUND

The surgical approach and prognosis for invasive adenocarcinoma (IAC) and minimally invasive adenocarcinoma (MIA) of the lung differ. However, they both manifest as identical ground-glass nodules (GGNs) in computed tomography images, and no effective method exists to discriminate them.

METHODS

We developed and validated a three-dimensional (3D) deep transfer learning model to discriminate IAC from MIA based on CT images of GGNs. This model uses a 3D medical image pre-training model (MedicalNet) and a fusion model to build a classification network. Transfer learning was utilized for end-to-end predictive modeling of the cohort data of the first center, and the cohort data of the other two centers were used as independent external validation data. This study included 999 lung GGN images of 921 patients pathologically diagnosed with IAC or MIA at three cohort centers.

RESULTS

The predictive performance of the model was assessed using the area under the receiver operating characteristic curve (AUC). The model had high diagnostic efficacy for the training and validation groups (accuracy: 89%, sensitivity: 95%, specificity: 84%, and AUC: 95% in the training group; accuracy: 88%, sensitivity: 84%, specificity: 93%, and AUC: 92% in the internal validation group; accuracy: 83%, sensitivity: 83%, specificity: 83%, and AUC: 89% in one external validation group; accuracy: 78%, sensitivity: 80%, specificity: 77%, and AUC: 82% in the other external validation group).

CONCLUSIONS

Our 3D deep transfer learning model provides a noninvasive, low-cost, rapid, and reproducible method for preoperative prediction of IAC and MIA in lung cancer patients with GGNs. It can help clinicians to choose the optimal surgical strategy and improve the prognosis of patients.

Artificial Intelligence in Lung Cancer Screening: The Future Is Now

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

Three dimensional computed tomography texture analysis of pulmonary lesions: Does radiomics allow differentiation between carcinoma, neuroendocrine tumor and organizing pneumonia?

PURPOSE

To investigate whether CT texture analysis allows differentiation between adenocarcinomas, squamous cell carcinomas, carcinoids, small cell lung cancers and organizing pneumonia and between carcinomas and neuroendocrine tumors.

METHOD

This retrospective study included patients 133 patients (30 patients with organizing pneumonia, 30 patients with adenocarcinoma, 30 patients with squamous cell carcinoma, 23 patients with small cell lung cancer, 20 patients with carcinoid), who underwent CT-guided biopsy of the lung and had a corresponding histopathologic diagnosis. Pulmonary lesions were segmented in consensus by two radiologists with and without a threshold of -50HU in three dimensions. Groupwise comparisons were performed to assess for differences between all five above-listed entities and between carcinomas and neuroendocrine tumors.

RESULTS

Pairwise comparisons of the five entities revealed 53 statistically significant texture features when using no HU-threshold and 6 statistically significant features with a threshold of -50HU. The largest AUC (0.818 [95%CI 0.706-0.930]) was found for the feature wavelet-HHH_glszm_SmallAreaEmphasis for discrimination of carcinoid from the other entities when using no HU-threshold. In differentiating neuroendocrine tumors from carcinomas, 173 parameters proved statistically significant when using no HU threshold versus 52 parameters when using a -50HU-threshold. The largest AUC (0.810 [95%CI 0.728-0,893]) was found for the parameter original_glcm_Correlation for discrimination of neuroendocrine tumors from carcinomas when using no HU-threshold.

CONCLUSIONS

CT texture analysis revealed features that differed significantly between malignant pulmonary lesions and organizing pneumonia and between carcinomas and neuroendocrine tumors of the lung. Applying a HU-threshold for segmentation substantially influenced the results of texture analysis.

CT texture analysis reliability in pulmonary lesions: the influence of 3D vs. 2D lesion segmentation and volume definition by a Hounsfield-unit threshold

OBJECTIVE

Reproducibility problems are a known limitation of radiomics. The segmentation of the target lesion plays a critical role in texture analysis variability. This study's aim was to compare the interobserver reliability of manual 2D vs. 3D lung lesion segmentation with and without pre-definition of the volume using a threshold of - 50 HU.

METHODS

Seventy-five patients with histopathologically proven lung lesions (15 patients each with adenocarcinoma, squamous cell carcinoma, small cell lung cancer, carcinoid, and organizing pneumonia) who underwent an unenhanced CT scan of the chest were included. Three radiologists independently segmented each lesion manually in 3D and 2D with and without pre-segmentation volume definition by a HU threshold, and shape parameters and original, Laplacian of Gaussian-filtered, and wavelet-based texture features were derived. To assess interobserver reliability and identify the most robust texture features, intraclass correlation coefficients (ICCs) for different segmentation settings were calculated.

RESULTS

Shape parameters had high reliability (64-79% had excellent and good ICCs). Texture features had weak reliability levels, with the highest ICCs (38% excellent or good) found for original features in 3D segmentation without the use of a HU threshold. A small proportion (4.3-11.5%) of texture features had excellent or good ICC values at all segmentation settings.

CONCLUSION

Interobserver reliability of texture features from CT scans of a heterogeneous collection of manually segmented lung lesions was low with a small proportion of features demonstrating high reliability independent of the segmentation settings. These results indicate a limited applicability of texture analysis and the need to define robust texture features in patients with lung lesions.

KEY POINTS

• Our study showed a low reproducibility of texture features when 3 radiologists independently segmented lung lesions in CT images, which highlights a serious limitation of texture analysis. • Interobserver reliability of texture features was low regardless of whether the lesion was segmented in 2D and 3D with or without a HU threshold. • In contrast to texture features, shape parameters showed a high interobserver reliability when lesions were segmented in 2D vs. 3D with and without a HU threshold of - 50.

Radiomics-based analysis of CT imaging for the preoperative prediction of invasiveness in pure ground-glass nodule lung adenocarcinomas

OBJECTIVE

The purpose of the study is to investigate the performance of radiomics-based analysis in prediction of pure ground-glass nodule (pGGN) lung adenocarcinomas invasiveness using thin-section computed tomography images.

METHODS

A total of 382 patients surgically resected single pGGN and pathologically confirmed were enrolled in the retrospective study. The pGGN cases were divided into two groups: the noninvasive group and the invasive adenocarcinoma (IAC) group. 330 patients were randomly assigned to the training and testing cohorts with a ratio of 7:3 (245 noninvasive lesions, 85 IAC lesions), while 52 patients (30 noninvasive lesions, 22 IAC lesions) were assigned to the external validation cohort. A model, radiomics model, and combined clinical-radiographic-radiomic model were built using the LASSO and multivariate backward stepwise regression analysis on the basis of the selected and radiomics features. The area under the curve (AUC) and decision curve analysis (DCA) were used to evaluate and compare the model performance for invasiveness discrimination among the three cohorts.

RESULTS

Three clinical-radiographic features (including age, gender and the mean CT value) and three radiomics features were selected for model building. The combined model and radiomics model performed better than the clinical-radiographic model. The AUCs of the combined model in the training, testing, and validation cohorts were 0.856, 0.859, and 0.765, respectively. The DCA demonstrated the radiomics signatures incorporating clinical-radiographic feature was clinically useful in predicting pGGN invasiveness.

CONCLUSIONS

The proposed radiomics-based analysis incorporating the clinical-radiographic feature could accurately predict pGGN invasiveness, providing a noninvasive biomarker for the individualized and precise medical treatment of patients.

Artificial-intelligence-based computed tomography histogram analysis predicting tumor invasiveness of lung adenocarcinomas manifesting as radiological part-solid nodules

Background

Tumor invasiveness plays a key role in determining surgical strategy and patient prognosis in clinical practice. The study aimed to explore artificial-intelligence-based computed tomography (CT) histogram indicators significantly related to the invasion status of lung adenocarcinoma appearing as part-solid nodules (PSNs), and to construct radiomics models for prediction of tumor invasiveness.

Methods

We identified surgically resected lung adenocarcinomas manifesting as PSNs in Peking University People's Hospital from January 2014 to October 2019. Tumors were categorized as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) by comprehensive pathological assessment. The whole cohort was randomly assigned into a training (70%, n=832) and a validation cohort (30%, n=356) to establish and validate the prediction model. An artificial-intelligence-based algorithm (InferRead CT Lung) was applied to extract CT histogram parameters for each pulmonary nodule. For feature selection, multivariate regression models were built to identify factors associated with tumor invasiveness. Logistic regression classifier was used for radiomics model building. The predictive performance of the model was then evaluated by ROC and calibration curves.

Results

In total, 299 AIS/MIAs and 889 IACs were included. In the training cohort, multivariate logistic regression analysis demonstrated that age [odds ratio (OR), 1.020; 95% CI, 1.004-1.037; p=0.017], smoking history (OR, 1.846; 95% CI, 1.058-3.221; p=0.031), solid mean density (OR, 1.014; 95% CI, 1.004-1.024; p=0.008], solid volume (OR, 5.858; 95% CI, 1.259-27.247; p = 0.037), pleural retraction sign (OR, 3.179; 95% CI, 1.057-9.559; p = 0.039), variance (OR, 0.570; 95% CI, 0.399-0.813; p=0.002), and entropy (OR, 4.606; 95% CI, 2.750-7.717; p<0.001) were independent predictors for IAC. The areas under the curve (AUCs) in the training and validation cohorts indicated a better discriminative ability of the histogram model (AUC=0.892) compared with the clinical model (AUC=0.852) and integrated model (AUC=0.886).

Conclusion

We developed an AI-based histogram model, which could reliably predict tumor invasiveness in lung adenocarcinoma manifesting as PSNs. This finding would provide promising value in guiding the precision management of PSNs in the daily practice.

Refining the definition of HER2-low class in invasive breast cancer

BACKGROUND

Emerging evidence indicates that breast cancer (BC) patients whose tumours express HER2 protein without HER2 gene amplification (HER2-low), can benefit from antibody-drug conjugates (ADC). However, the current definition of HER2-low BC remains incomplete with low rates of concordance. This study aims to refine HER2-low definition with emphasis on distinguishing HER2 score 0 from score 1+ to identify patients who are eligible for ADC.

METHODS

A BC cohort (n = 363) with HER2 IHC scores 0, 1+ and 2+ (without HER2 gene amplification) and available HER2 mRNA was included. HER2 staining intensity, pattern and subcellular localisation were reassessed. Artificial neural network analysis was applied to cluster the cohort and to distinguish HER2 score 0 from 1+. Reproducibility and reliability of the refined criteria were tested.

RESULTS

HER2 IHC score 1+ was refined as membranous staining in invasive cells as either: (1) faint intensity in ≥ 20% of cells regardless the circumferential completeness, (2) weak complete staining in ≤ 10%, (3) weak incomplete staining in > 10% and (4) moderate incomplete staining in ≤ 10%. Based on this, 63% of the HER2-negative cases were reclassified as positive (HER2-low). The refined score showed perfect observer agreement compared to the moderate agreement in the original clinical scores. Similar results were generated when the refined score was applied on the independent BC cohorts. A proposal to refine the definition of other HER2 classes is presented.

CONCLUSION

This study refined the definition of HER2-low BC based on correlation with HER2 mRNA and distinguished between HER2 IHC score 1+ and score 0 tumours.

Clinical and radiomic factors for predicting invasiveness in pulmonary ground‑glass opacity

Patients with preinvasive or invasive pulmonary ground-glass opacity (GGO) often face different clinical treatments and prognoses. The present study aimed to identify the invasiveness of pulmonary GGO by analysing clinical and radiomic features. Patients with pulmonary GGOs who were treated between January 2014 and February 2019 were included. Clinical features were collected, while radiomic features were extracted from computed tomography records using the three-dimensional Slicer software. Predictors of GGO invasiveness were selected by least absolute shrinkage and selection operator logistic regression analysis, and receiver operating characteristic (ROC) curves were drawn for each prediction model. A total of 194 patients with pulmonary GGOs were included in the present study. The maximum diameter of the solid component, waveletHLL_ngtdm_Coarseness (P=0.03), waveletLHH_firstorder_Maximum (P<0.01) and waveletLLH_glrlm_LongRunEmphasis (P<0.01) were significant predictors of invasive lung GGOs. The area under the ROC curve (AUC) for the prediction models of clinical features and radiomic features was 0.755 and 0.719, respectively, whereas the AUC for the combined prediction model was 0.864 (95% CI, 0.802-0.926). Finally, a nomogram was established for individualized prediction of invasiveness. The combination of radiomic and clinical features can enable the differentiation between preinvasive and invasive GGOs. The present results can provide some basis for the best choice of treatment in patients with lung GGOs.

Texture analysis of contrast-enhanced magnetic resonance imaging predicts microvascular invasion in hepatocellular carcinoma

BACKGROUND

Microvascular invasion is one of the important risk factors of postoperative recurrence of hepatocellular carcinoma. Texture analysis uses mathematical methods to analyze the gray's quantitative value and distribution of images, for quantifying the heterogeneity of tissues.

PURPOSE

To investigate the feasibility of predicting MVI in HCC by analyzing the texture features of hepatic MR-enhanced images.

METHODS

110 patients with HCC who underwent MR-enhanced examinations were included in this study, were divided into MVI-positive group (n = 52) and MVI-negative group (n = 58) according to postoperative pathology. Clinical, pathological data and MR imaging features were collected. 11 texture parameters were selected from the gray histogram and gray level co-occurrence matrix (GLCM). Texture parameters of MR-enhanced images were calculated for statistical analysis.

RESULTS

There were statistically significant differences in tumor size, location, degree of differentiation, AFP level, signal, pseudocapsule, margin, peritumoral enhancement and intratumoral artery between MVI-positive group and MVI-negative group (P < 0.05). The AUC value of combining MR image features in prediction of MVI was 0.693(sensitivity and specificity: 53.8 %, 82.8 %, respectively). There were statistically significant differences in the texture parameters of GLCM between two groups (P < 0.05). The AUC value of combining texture parameters in prediction of MVI was 0.797 (sensitivity and specificity: 88.2 %, 62.7 %, respectively).

CONCLUSION

MR image features and texture analysis have certain predictive effect on MVI, which are mutually verified and complementary. The texture parameters of GLCM could reflect tumor heterogeneity, which have great potential to help with preoperative decision. The combination of MR image features and texture analysis may improve the efficiency in prediction of MVI.

Applying a CT texture analysis model trained with deep-learning reconstruction images to iterative reconstruction images in pulmonary nodule diagnosis

OBJECTIVE

To investigate the feasibility and accuracy of applying a computed tomography (CT) texture analysis model trained with deep-learning reconstruction images to iterative reconstruction images for classifying pulmonary nodules.

MATERIALS AND METHODS

CT images of 102 patients, with a total of 118 pulmonary nodules (52 benign, 66 malignant) were retrospectively reconstructed with a deep-learning reconstruction (artificial intelligence iterative reconstruction [AIIR]) and a hybrid iterative reconstruction (HIR) technique. The AIIR data were divided into a training (n = 96) and a validation set (n = 22), and the HIR data were set as the test set (n = 118). Extracted texture features were compared using the Mann-Whitney U test and t-test. The diagnostic performance of the classification model was analyzed with the receiver operating characteristic curve (ROC), the area under ROC (AUC), sensitivity, specificity, and accuracy.

RESULTS

Among the obtained 68 texture features, 51 (75.0%) were not influenced by the change of reconstruction algorithm (p > 0.05). Forty-four features were significantly different between benign and malignant nodules (p < 0.05) for the AIIR dataset, which were selected to build the classification model. The accuracy and AUC of the classification model were 92.3% and 0.91 (95% confidence interval [CI], 0.74-0.90) with the validation set, which were 80.0% and 0.80 (95% CI, 0.68-0.86) with the test set.

CONCLUSION

With the CT texture analysis model trained with deep-learning reconstruction (AIIR) images showing favorable diagnostic accuracy in discriminating benign and malignant pulmonary nodules, it also has certain applicability to the iterative reconstruction (HIR) images.

A radiomics nomogram for invasiveness prediction in lung adenocarcinoma manifesting as part-solid nodules with solid components smaller than 6 mm

Objective

To investigate whether radiomics can help radiologists and thoracic surgeons accurately predict invasive adenocarcinoma (IAC) manifesting as part-solid nodules (PSNs) with solid components <6 mm and provide a basis for rational clinical decision-making.

Materials and Methods

In total, 1,210 patients (mean age ± standard deviation: 54.28 ± 11.38 years, 374 men and 836 women) from our hospital and another hospital with 1,248 PSNs pathologically diagnosed with adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or IAC were enrolled in this study. Among them, 1,050 cases from our hospital were randomly divided into a derivation set (n = 735) and an internal validation set (n = 315), 198 cases from another hospital were used for external validation. Each labeled nodule was segmented, and 105 radiomics features were extracted. Least absolute shrinkage and selection operator (LASSO) was used to calculate Rad-score and build the radiomics model. Multivariable logistic regression was conducted to identify the clinicoradiological predictors and establish the clinical-radiographic model. The combined model and predictive nomogram were developed based on identified clinicoradiological independent predictors and Rad-score using multivariable logistic regression analysis. The predictive performances of the three models were compared via receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) was performed on both the internal and external validation sets to evaluate the clinical utility of the nomogram.

Results

The radiomics model showed superior predictive performance than the clinical-radiographic model in both internal and external validation sets (Az values, 0.884 vs. 0.810, p = 0.001; 0.924 vs. 0.855, p < 0.001, respectively). The combined model showed comparable predictive performance to the radiomics model (Az values, 0.887 vs. 0.884, p = 0.398; 0.917 vs. 0.924, p = 0.271, respectively). The clinical application value of the nomogram developed based on the Rad-score, maximum diameter, and lesion shape was confirmed, and DCA demonstrated that application of the Rad-score would be beneficial for radiologists predicting invasive lesions.

Conclusions

Radiomics has the potential as an independent diagnostic tool to predict the invasiveness of PSNs with solid components <6 mm.

Fusion of CT images and clinical variables based on deep learning for predicting invasiveness risk of stage I lung adenocarcinoma

PURPOSE

To develop a novel multimodal data fusion model by incorporating computed tomography (CT) images and clinical variables based on deep learning for predicting the invasiveness risk of stage I lung adenocarcinoma that manifests as ground-glass nodules (GGNs), and compare the diagnostic performance of it with that of radiologists.

METHODS

A total of 1946 patients with solitary and histopathologically confirmed GGNs with maximum diameter less than 3 cm were retrospectively enrolled. The training dataset containing 1704 GGNs was augmented by resampling, scaling, random cropping, etc., to generate new training data. A multimodal data fusion model based on residual learning architecture and two multilayer perceptron with attention mechanism combining CT images with patient general data and serum tumor markers was built. The distance-based confidence scores (DCS) were calculated and compared among multimodal data models with different combinations. An observer study was conducted and the prediction performance of the fusion algorithms was compared with that of the two radiologists by an independent testing dataset with 242 GGNs.

RESULTS

Among the whole GGNs, 606 GGNs are confirmed as invasive adenocarcinoma (IA) and 1340 are non-IA. The proposed novel multimodal data fusion model combining CT images, patient general data and serum tumor markers achieved the highest accuracy (88.5%), Area under a ROC curve (AUC) (0.957), F1 (81.5%), F1_weighted (81.9%) and Matthews correlation coefficient (MCC) (73.2%) for classifying between IA and non-IA GGNs, which was even better than the senior radiologist's performance (accuracy, 86.1%). In addition, the DCSs for multimodal data suggested that CT image had a stronger influence (0.9540) quantitatively than general data (0.6726) or tumor marker (0.6971).

CONCLUSION

This study demonstrated that the feasibility of integrating different types of data including CT images and clinical variables, and the multimodal data fusion model yielded higher performance for distinguishing IA from non-IA GGNs. This article is protected by copyright. All rights reserved.

Computerized Texture Analysis of Optical Coherence Tomography Angiography of Choriocapillaris in Normal Eyes of Young and Healthy Subjects

Computerized texture analysis uses higher-order mathematics to identify patterns beyond what the naked eye can recognize. We tested its feasibility in optical coherence tomography angiography imaging of choriocapillaris. Our objective was to determine sets of parameters that provide coherent and consistent output when applied to a homogeneous, healthy group of patients. This observational cross-sectional study involved 19 eyes of 10 young and healthy Caucasian subjects. En-face macular optical coherence tomography angiography of superficial choriocapillaris was obtained by the RTVue-XR Avanti system. Various algorithms were used to extract texture features. The mean and standard deviation were used to assess the distribution and dispersion of data points in each metric among eyes, which included: average gray level, gray level yielding 70% threshold and 30% threshold, balance, skewness, energy, entropy, contrast, edge mean gradient, root-mean-square variation, and first moment of power spectrum, which was compared between images, showing a highly concordant homology between all eyes of participants. We conclude that computerized texture analysis for en-face optical coherence tomography angiography images of choriocapillaris is feasible and provides values that are coherent and tightly distributed around the mean in a homogenous, healthy group of patients. Homology of blob size among subjects may represent a “repeat pattern” in signal density and thus a perfusion in the superficial choriocapillaris of healthy young individuals of the same ethnic background.

The value of radiomics based on dual-energy CT for differentiating benign from malignant solitary pulmonary nodules

OBJECTIVE

To investigate the value of monochromatic dual-energy CT (DECT) images based on radiomics in differentiating benign from malignant solitary pulmonary nodules.

MATERIALS AND METHODS

This retrospective study was approved by the institutional review board, and informed consent was waived. Pathologically confirmed lung nodules smaller than 3 cm with integrated arterial phase and venous phase (AP and VP) gemstone spectral imaging were retrospectively identified. After extracting the radiomic features of each case, principal component analysis (PCA) was used for feature selection, and after training with the logistic regression method, three classification models (Model_AP, Model_VP and Model_Combination) were constructed. The performance was assessed by the area under the receiver operating curve (AUC), and the efficacy of the models was validated using an independent cohort.

RESULTS

A total of 153 patients were included and divided into a training cohort (n = 107) and a validation cohort (n = 46). A total of 1130 radiomic features were extracted from each case. The PCA method selected 22, 25 and 35 principal components to construct the three models. The diagnostic accuracy of Model_AP, Model_VP and Model_Combination was 0.8043, 0.6739, and 0.7826 in the validation set, with AUCs of 0.8148 (95% CI 0.682-0.948), 0.7485 (95% CI 0.602-0.895), and 0.8772 (95% CI 0.780-0.974), respectively. The DeLong test showed that there were significant differences in the AUCs between Model_AP and Model_Combination (P = 0.0396) and between Model_VP and Model_Combination (P = 0.0465). However, the difference in AUCs between Model_AP and Model_VP was not significant (P = 0.5061). These results demonstrate that Model_Combination shows a better performance than the other models. Decision curve analysis proved the clinical utility of this model.

CONCLUSIONS

We developed a radiomics model based on monochromatic DECT images to identify solitary pulmonary nodules. This model could serve as an effective tool for discriminating benign from malignant pulmonary nodules in patients. The combination of arterial phase and venous phase imaging could significantly improve the model performance.

Computed Tomography-Based Radiomics for Differentiation of Thymic Epithelial Tumors and Lymphomas in Anterior Mediastinum

Objective

To investigate the differential diagnostic performance of computed tomography (CT)-based radiomics in thymic epithelial tumors (TETs) and lymphomas in anterior mediastinum.

Methods

There were 149 patients with TETs and 93 patients with lymphomas enrolled. These patients were assigned to a training set (n = 171) and an external validation set (n = 71). Dedicated radiomics prototype software was used to segment lesions on preoperative chest enhanced CT images and extract features. The multivariable logistic regression algorithm was used to construct three models according to clinico-radiologic features, radiomics features, and combined features, respectively. Performance of the three models was compared by using the area under the receiver operating characteristic curves (AUCs). Decision curve analysis was used to evaluate clinical utility of the three models.

Results

For clinico-radiologic model, radiomics signature model, and combined model, the AUCs were 0.860, 0.965, 0.975 and 0.843, 0.961, 0.955 in the training cohort and the test cohort, respectively (all P<0.05). The accuracies of each model were 0.836, 0.895, 0.918 and 0.845, 0.901, 0.859 in the two cohorts, respectively (all P<0.05). Compared with the clinico-radiologic model, better diagnostic performances were found in the radiomics signature model and the combined model.

Conclusions

Radiomics signature model and combined model exhibit outstanding and comparable differential diagnostic performances between TETs and lymphomas. The CT-based radiomics analysis might serve as an effective tool for accurately differentiating TETs from lymphomas before treatment.

Predictive Efficacy of a Radiomics Random Forest Model for Identifying Pathological Subtypes of Lung Adenocarcinoma Presenting as Ground-Glass Nodules

Purpose

To establish and verify the ability of a radiomics prediction model to distinguish invasive adenocarcinoma (IAC) and minimal invasive adenocarcinoma (MIA) presenting as ground-glass nodules (GGNs).

Methods

We retrospectively analyzed 118 lung GGN images and clinical data from 106 patients in our hospital from March 2016 to April 2019. All pathological classifications of lung GGN were confirmed as IAC or MIA by two pathologists. R language software (version 3.5.1) was used for the statistical analysis of the general clinical data. ITK-SNAP (version 3.6) and A.K. software (Analysis Kit, American GE Company) were used to manually outline the regions of interest of lung GGNs and collect three-dimensional radiomics features. Patients were randomly divided into training and verification groups (ratio, 7:3). Random forest combined with hyperparameter tuning was used for feature selection and prediction modeling. The receiver operating characteristic curve and the area under the curve (AUC) were used to evaluate model prediction efficacy. The calibration curve was used to evaluate the calibration effect.

Results

There was no significant difference between IAC and MIA in terms of age, gender, smoking history, tumor history, and lung GGN location in both the training and verification groups (P>0.05). For each lung GGN, the collected data included 396 three-dimensional radiomics features in six categories. Based on the training cohort, nine optimal radiomics features in three categories were finally screened out, and a prediction model was established. We found that the training group had a high diagnostic efficacy [accuracy, sensitivity, specificity, and AUC of the training group were 0.89 (95%CI, 0.73 - 0.99), 0.98 (95%CI, 0.78 - 1.00), 0.81 (95%CI, 0.59 - 1.00), and 0.97 (95%CI, 0.92-1.00), respectively; those of the validation group were 0.80 (95%CI, 0.58 - 0.93), 0.82 (95%CI, 0.55 - 1.00), 0.78 (95%CI, 0.57 - 1.00), and 0.92 (95%CI, 0.83 - 1.00), respectively]. The model calibration curve showed good consistency between the predicted and actual probabilities.

Conclusions

The radiomics prediction model established by combining random forest with hyperparameter tuning effectively distinguished IAC from MIA presenting as GGNs and represents a noninvasive, low-cost, rapid, and reproducible preoperative prediction method for clinical application.

Different CT slice thickness and contrast-enhancement phase in radiomics models on the differential performance of lung adenocarcinoma

Background

To investigate the effects of computed tomography (CT) reconstruction slice thickness and contrast‐enhancement phase on the differential diagnosis performance of radiomic signature in lung adenocarcinoma.

Methods

A total of 187 patients who had been pathologically confirmed with lung adenocarcinoma and nonadenocarcinoma were divided into a training cohort (n = 149) and validation cohort (n = 38). All the patients underwent contrast‐enhanced CT and the images were reconstructed with different slice thickness. The radiomic features were extracted from different slice thickness and scan phase. The logistic regression (LR) algorithm was used to build a machine learning model for each group. The area under the curve (AUC) obtained from the receiver operating characteristic (ROC) curve and DeLong test was used to evaluate its discriminating performance.

Results

Finally, 34 image features and five semantic features were selected to establish a radiomics model. Based on the three contrast‐enhanced CT phases and four reconstruction slice thickness, 12 groups of radiomics models showed good discrimination ability with the AUCs range from 0.9287 to 0.9631, sensitivity range from 0.8349 to 0.9083, specificity range from 0.825 to 0.925 in the training group. Similar results were observed in the validation group. However, there was no statistical significance between the different CT scan phase groups and different slice thickness (p > 0.05).

Conclusions

The radiomic analysis of contrast‐enhanced CT can be used for the differential diagnosis of lung adenocarcinoma. Moreover, different slice thickness and contrast‐enhanced scan phase did not affect the discriminating ability in the radiomics models.

CT-guided Percutaneous Cryoablation in Patients with Lung Nodules Mainly Composed of Ground-Glass Opacities

PURPOSE

To assess the safety and efficacy of cryoablation in patients with lung nodules mainly composed of ground-glass opacities (GGOs).

MATERIALS AND METHODS

In this retrospective study, 50 patients (mean age, 65.0 ± 12.3; 28 women) diagnosed with lung GGO nodules who underwent cryoablation were included (from June 2016-June 2021). The local recurrence rate, the incidence of regional metastases to lymph nodes, the incidence of distant metastases, adverse events, and the lung function condition were analyzed.

RESULTS

Follow-up computed tomography (CT) was performed an average of 33 months (range, 3-60 months) after the cryoablation procedure. Outcomes were only evaluated in 30 patients. A total of 20 patients were excluded: 10 patients had no cancer detected at histopathological analysis and were diagnosed with CT scan or positron emission tomography-CT (PET/CT), and the other 10 patients had nodules with a diameter of less than 10 mm and a consolidation-to-tumor ratio (CTR) of more than 0.25, and thus histopathological analysis was not performed due to small nodule size and patients were diagnosed with CT or PET/CT. The local recurrence rate was 0% (0 of 30). Evidence of regional metastases of the lymph nodes was not found in any patients (0%; 0 of 30), and the incidence of distant metastases was 0% (0 of 30). No major complications were noted. Lung function recovered to normal within one month after cryoablation in all patients.

CONCLUSION

Cryoablation may serve as a safe and feasible option for the treatment of lung nodules mainly composed of GGOs.

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.

Reproducibility of radiomic features of pulmonary nodules between low-dose CT and conventional-dose CT

BACKGROUND

The reproducibility of radiomic features is essential to lung cancer detection. This study aimed to investigate the reproducibility of radiomic features of pulmonary nodules between low-dose computed tomography (LDCT) and conventional-dose computed tomography (CDCT).

METHODS

A total of 105 patients with 119 pulmonary nodules [39 ground-glass nodules (GGNs) and 80 solid nodules] who underwent LDCT and CDCT were retrospectively studied between September 2019 and November 2020. Pulmonary nodules were manually segmented and 1,125 radiomic features (shape, first-order intensity, texture, wavelet, and Laplacian of the Gaussian features) were extracted from both LDCT and CDCT images. The concordance correlation coefficient (CCC) was used to evaluate the reproducibility of these radiomic features.

RESULTS

Of the 1,125 radiomic features considered, 35.5% (399 of 1,125) and 41.5% (467 of 1,125) were reproducible (CCC ≥0.85) for GGNs and solid nodules, respectively. The intensity, texture, and wavelet features of solid nodules were more reproducible than those of GGNs. The mean CCC values for intensity and texture features of solid nodules were of 0.85 and above, whereas the mean values for those of GGNs were of less than 0.85. After Gaussian kernel (σ =2) preprocessing, the CCC of intensity and texture features of GGNs improved from 0.77 to 0.90, and 84.9% (79 of 93) of the radiomic features were reproducible (mean CCC increase from 0.84±0.13 to 0.92±0.08 for intensity features, and from 0.75±0.15 to 0.89±0.11 for texture features). Wavelet features had the lowest CCCs for both GGNs and solid nodules.

CONCLUSIONS

The majority of the radiomic feature classes of solid pulmonary nodules have a high level of reproducibility between LDCT and CDCT. However, LDCT should not be used as an alternative to CDCT in the radiomic study of GGNs.

Preoperative Changes of Lung Nodule on Computed Tomography and Their Relationship With Pathological Outcomes

Background

Whether changes of lung nodules on computed tomography could bring us helpful information related to their pathological outcomes remained unclear.

Materials and Methods

This retrospective study was carried out among 1,185 cases of lung nodules in Shanghai Chest Hospital from January 2015 to April 2017, which did not shrink or disappear after preoperative follow-up over three months. Their imaging features, changes, and clinical characteristics were collected. A separate analysis was performed in nodules with or without growth in long-axis diameter after follow-up, searching significant changes related to nodule malignancy and the median interval of follow-up for reference. Further study was performed similarly in malignant nodules for discrimination of malignant grading.

Results

Most nodules were stable (n = 885, 75%), whereas others grew (n = 300, 25%). For predicting nodule malignancy, increase in density (&gt;10 Hounsfield units, median follow-up of 549 days) played an important role in growing group whereas it failed in stable group, and the increase in size was less significant in growing group. For discrimination of malignant grading, increase in density (&gt;70 Hounsfield units, median follow-up of 366 days) showed its significance in stable group, and so did increase in size in growing group (maximum diameter growth &gt;3.3 mm, median follow-up of 549 days, or average diameter growth &gt;3.1 mm, median follow-up of 625 days).

Conclusions

There were significant changes of lung nodules by follow-up on computed tomography, related to their pathological outcomes. The predictive power of increase in density or size varied in different situations, whereas all referred to a long-time preoperative follow-up.

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

OBJECTIVES

To develop and validate a preoperative CT-based nomogram combined with radiomic and clinical-radiological signatures to distinguish preinvasive lesions from pulmonary invasive lesions.

METHODS

This was a retrospective, diagnostic study conducted from August 1, 2018, to May 1, 2020, at three centers. Patients with a solitary pulmonary nodule were enrolled in the GDPH center and were divided into two groups (7:3) randomly: development (n = 149) and internal validation (n = 54). The SYSMH center and the ZSLC Center formed an external validation cohort of 170 patients. The least absolute shrinkage and selection operator (LASSO) algorithm and logistic regression analysis were used to feature signatures and transform them into models.

RESULTS

The study comprised 373 individuals from three independent centers (female: 225/373, 60.3%; median [IQR] age, 57.0 [48.0-65.0] years). The AUCs for the combined radiomic signature selected from the nodular area and the perinodular area were 0.93, 0.91, and 0.90 in the three cohorts. The nomogram combining the clinical and combined radiomic signatures could accurately predict interstitial invasion in patients with a solitary pulmonary nodule (AUC, 0.94, 0.90, 0.92) in the three cohorts, respectively. The radiomic nomogram outperformed any clinical or radiomic signature in terms of clinical predictive abilities, according to a decision curve analysis and the Akaike information criteria.

CONCLUSIONS

This study demonstrated that a nomogram constructed by identified clinical-radiological signatures and combined radiomic signatures has the potential to precisely predict pathology invasiveness.

KEY POINTS

• The radiomic signature from the perinodular area has the potential to predict pathology invasiveness of the solitary pulmonary nodule. • The new radiomic nomogram was useful in clinical decision-making associated with personalized surgical intervention and therapeutic regimen selection in patients with early-stage non-small-cell lung cancer.

Inter-Reader Variability of Volumetric Subsolid Pulmonary Nodule Radiomic Features

OBJECTIVE

To evaluate the inter-observer consistency for subsolid pulmonary nodule radiomic features.

MATERIALS AND METHODS

Subsolid nodules were selected by reviewing radiology reports of CT examinations performed December 1, 2015 to April 1, 2016. Patients with CTs at two time points were included in this study. There were 55 patients with subsolid nodules, of whom 14 had two nodules. Of 69 subsolid nodules, 66 were persistent at the second time point, yielding 135 lesions for segmentation. Two thoracic radiologists and an imaging fellow segmented the lesions using a semi-automated volumetry algorithm (Syngo.via Vb20, Siemens). Coefficient of variation (CV) was used to assess consistency of 91 quantitative measures extracted from the subsolid nodule segmentations, including first and higher order texture features. The accuracy of segmentation was visually graded by an experienced thoracic radiologist. Influencing factors on radiomic feature consistency and segmentation accuracy were assessed using generalized estimating equation analyses and the Exact Mann-Whitney test.

RESULTS

Mean patient age was 71 (38-93 years), with 39 women and 16 men. Mean nodule volume was 1.39mL, range .03-48.2mL, for 135 nodules. Several radiomic features showed high inter-reader consistency (CV<5%), including entropy, uniformity, sphericity, and spherical disproportion. Descriptors such as surface area and energy had low consistency across inter-reader segmentations (CV>10%). Nodule percent solid component and attenuation influenced inter-reader variability of some radiomic features. The presence of contrast did not significantly affect the consistency of subsolid nodule radiomic features. Near perfect segmentation, within 5% of actual nodule size, was achieved in 68% of segmentations, and very good segmentation, within 25% of actual nodule size, in 94%. Morphologic features including nodule margin and shape (each p <0.01), and presence of air bronchograms (p = 0.004), bubble lucencies (p = 0.02) and broad pleural contact (p < 0.01) significantly affected the probability of near perfect segmentation. Stroke angle (p = 0.001) and length (p < 0.001) also significantly influenced probability of near perfect segmentation.

CONCLUSIONS

The inter-observer consistency of radiomic features for subsolid pulmonary nodules varies, with high consistency for several features, including sphericity, spherical disproportion, and first and higher order entropy, and normalized non-uniformity. Nodule morphology influences the consistency of subsolid nodule radiomic features, and the accuracy of subsolid nodule segmentation.

Using texture analysis in the development of a potential radiomic signature for early identification of hepatic metastasis in colorectal cancer

Background

Aim

Methods

Results

Conclusion

Convolutional Neural Network-Based Diagnostic Model for a Solid, Indeterminate Solitary Pulmonary Nodule or Mass on Computed Tomography

PURPOSE

To establish a non-invasive diagnostic model based on convolutional neural networks (CNNs) to distinguish benign from malignant lesions manifesting as a solid, indeterminate solitary pulmonary nodule (SPN) or mass (SPM) on computed tomography (CT).

METHOD

A total of 459 patients with solid indeterminate SPNs/SPMs on CT were ultimately included in this retrospective study and assigned to the train (n=366), validation (n=46), and test (n=47) sets. Histopathologic analysis was available for each patient. An end-to-end CNN model was proposed to predict the natural history of solid indeterminate SPN/SPMs on CT. Receiver operating characteristic curves were plotted to evaluate the predictive performance of the proposed CNN model. The accuracy, sensitivity, and specificity of diagnoses by radiologists alone were compared with those of diagnoses by radiologists by using the CNN model to assess its clinical utility.

RESULTS

For the CNN model, the AUC was 91% (95% confidence interval [CI]: 0.83-0.99) in the test set. The diagnostic accuracy of radiologists with the CNN model was significantly higher than that without the model (89 vs. 66%, P<0.01; 87 vs. 61%, P<0.01; 85 vs. 66%, P=0.03, in the train, validation, and test sets, respectively). In addition, while there was a slight increase in sensitivity, the specificity improved significantly by an average of 42% (the corresponding improvements in the three sets ranged from 43, 33, and 42% to 82, 78, and 84%, respectively; P<0.01 for all).

CONCLUSION

The CNN model could be a valuable tool in non-invasively differentiating benign from malignant lesions manifesting as solid, indeterminate SPNs/SPMs on CT.

Texture analysis imaging "what a clinical radiologist needs to know"

Texture analysis has arisen as a tool to explore the amount of data contained in images that cannot be explored by humans visually. Radiomics is a method that extracts a large number of features from radiographic medical images using data-characterisation algorithms. These features, termed radiomic features, have the potential to uncover disease characteristics. The goal of both radiomics and texture analysis is to go beyond size or human-eye based semantic descriptors, to enable the non-invasive extraction of quantitative radiological data to correlate them with clinical outcomes or pathological characteristics. In the latest years there has been a flourishing sub-field of radiology where texture analysis and radiomics have been used in many settings. It is difficult for the clinical radiologist to cope with such amount of data in all the different radiological sub-fields and to identify the most significant papers. The aim of this review is to provide a tool to better understand the basic principles underlining texture analysis and radiological data mining and a summary of the most significant papers of the latest years.

Quantification of Cancer-Developing Idiopathic Pulmonary Fibrosis Using Whole-Lung Texture Analysis of HRCT Images

Simple Summary

Idiopathic pulmonary fibrosis (IPF) patients have a significantly higher risk of developing lung cancer. Traditional risk factors including age, male gender, smoking status, and emphysema have been reported. However, there are only limited data on radiomics features from HRCT images useful for risk stratification of IPF patients for lung cancer. In this study, we found that texture-based radiomics features can be differentiated between IPF patients with and without cancer development, and their diagnostic accuracy is not inferior to that of traditional risk factors. By combining radiomics features and traditional risk factors, the diagnostic accuracy can be improved.

Abstract

Idiopathic pulmonary fibrosis (IPF) patients have a significantly higher risk of developing lung cancer (LC). There is only limited evidence of the use of texture-based radiomics features from high-resolution computed tomography (HRCT) images for risk stratification of IPF patients for LC. We retrospectively enrolled subjects who suffered from IPF in this study. Clinical data including age, gender, smoking status, and pulmonary function were recorded. Non-contrast chest CT for fibrotic score calculation and determination of three dimensional measures of whole-lung texture and emphysema were performed using a promising deep learning imaging platform. The results revealed that among 116 subjects with IPF (90 non-cancer and 26 lung cancer cases), the radiomics features showed significant differences between non-cancer and cancer patients. In the training cohort, the diagnostic accuracy using selected radiomics features with AUC of 0.66–0.73 (sensitivity of 80.0–85.0% and specificity of 54.2–59.7%) was not inferior to that obtained using traditional risk factors, such as gender, smoking status, and emphysema (%). In the validation cohort, the combination of radiomics features and traditional risk factors produced a diagnostic accuracy of 0.87 AUC and an accuracy of 75.0%. In this study, we found that whole-lung CT texture analysis is a promising tool for LC risk stratification of IPF patients.

T1 invasive lung adenocarcinoma: Thin-section CT solid score and histological periostin expression predict tumor recurrence

Adenocarcinoma is the most common histological type of non-small cell lung cancer (NSCLC), and various biomarkers for predicting its prognosis after surgical resection have been suggested, particularly in early-stage lung adenocarcinoma. Periostin (also referred to as POSTN, PN or osteoblast-specific factor) is an extracellular matrix protein, the expression of which is associated with tumor invasiveness in patients with NSCLC. In the present study, the novel approach, in which the thin-section CT findings prior to surgical resection and periostin expression of resected specimens were analyzed in combination, was undertaken to assess whether the findings could be a biomarker for predicting the outcomes following resection of T1 invasive lung adenocarcinoma. A total of 73 patients who underwent surgical resection between January 2000 and December 2009 were enrolled. A total of seven parameters were assessed in the thin-section CT scans: i) Contour; ii) part-solid ground-glass nodule or solid nodule; iii) percentage of solid component (the CT solid score); iv) presence of air-bronchogram and/or bubble-like lucencies; v) number of involved vessels; vi) shape linear strands between the nodule and the visceral pleura; and vii) number of linear strands between the nodule and the visceral pleura. Two chest radiologists independently assessed the parameters. Periostin expression was evaluated on the basis of the strength and extent of staining. Univariate and multivariate analyses were subsequently performed using the Cox proportional hazards model. There was a substantial to almost perfect agreement between the two observers with regard to classification of the seven thin-section CT parameters (κ=0.64-0.85). In the univariate analysis, a CT solid score >80%, pathological lymphatic invasion, tumor and lymph node status and high periostin expression were significantly associated with recurrence (all P<0.05). Multivariate analysis demonstrated that a CT solid score >80% and high periostin expression were risk factors for recurrence (P=0.002 and P=0.011, respectively). The cumulative recurrence rates among the three groups (both negative, CT solid score >80% or high periostin expression, or both positive) were significantly different (log-rank test, P<0.001). Although the solid component is already known to be a major predictor of outcome in lung adenocarcinomas according to previous studies, the combined analysis of CT solid score and periostin expression might predict the likelihood of tumor recurrence more precisely.

Noninvasive evaluation of hypoxia in rabbit VX2 lung transplant tumors using spectral CT parameters and texture analysis

AIM

Noninvasive evaluation of hypoxia in rabbit VX2 lung transplant tumors using spectral CT parameters and texture analysis.

MATERIALS AND METHODS

Twenty-five VX2 lung transplant tumors of twenty-two rabbits were included in the study. Contrast-enhanced spectral CT scanning in the arterial phase (AP) and venous phase (VP) was performed. Tumors were divided into strong and weak hypoxic groups by hypoxic probe staining results. Spectral CT image-related parameters [70 keV CT value, normalized iodine concentration (NIC), slope of spectral HU curve (λ_HU)] were measured and the texture analysis on the monochromatic images was performed. Imaging parameters and texture features between tumors with different hypoxic degrees were compared and their diagnostic efficacies for predicting hypoxia in lung cancers were analyzed using receiver operating characteristic (ROC) curve.

RESULTS

NIC in VP and λ_HU in VP of the strong hypoxic group were significantly higher than those in the weak hypoxic group (p < 0.05). For the texture features, entropy in VP and kurtosis in AP were significantly different between the two hypoxic groups. According to ROC analysis, λ_HU in VP had a better diagnostic ability for predicting hypoxia in tumors [Area Under Curve (AUC): 0.883, sensitivity: 85.7%, specificity: 100%]. The combination of four features improved AUC to 0.955.

CONCLUSION

NIC in VP, λ_HU in VP, entropy in VP and kurtosis in AP have certain values in predicting tumor hypoxia and a combination of image parameters and texture features improves diagnostic efficiency.

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

RATIONALE AND OBJECTIVES

To identify whether the radiomics features of computed tomography (CT) allowed for the preoperative discrimination of the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs) and further to develop and compare different predictive models.

MATERIALS AND METHODS

We retrospectively included 187 lung adenocarcinomas presenting as pGGNs (66 preinvasive lesions and 121 invasive lesions), which were randomly divided into the training and test sets (8:2). Radiomics features were extracted from non-enhanced CT images. Clinical features, including patient's demographic characteristics, smoking status, and conventional CT features that reflect tumor's morphology and surrounding information were also collected. Intraclass correlation coefficient and ℓ_2.1-norm minimization were used to identify influential feature subset which was then used to build three predictive models (clinical, radiomics, and clinical-radiomics models) with the gradient boosting regression tree classifier. The performances of the predictive models were evaluated using the area under the curve (AUC).

RESULTS

Of the 1409 radiomics features and 27 clinical feature subtypes, 102 features were selected to construct the hybrid clinical-radiomics model, which achieved the best discriminative power (AUC = 0.934 and 0.929 in training and test set). The radiomics model showed comparable predictive performance (AUC = 0.911 and 0.901 in training and test set) compared to the clinical model (AUC = 0.911 and 0.894 in training and test set).

CONCLUSION

The radiomics model showed good predictive performance in discriminating invasive lesions from preinvasive lesions for lung adenocarcinomas presenting as pGGNs. Its performance can be further improved by adding clinical features.

Application of Radiomics and Artificial Intelligence for Lung Cancer Precision Medicine

Medical imaging is the standard-of-care for early detection, diagnosis, treatment planning, monitoring, and image-guided interventions of lung cancer patients. Most medical images are stored digitally in a standardized Digital Imaging and Communications in Medicine format that can be readily accessed and used for qualitative and quantitative analysis. Over the several last decades, medical images have been shown to contain complementary and interchangeable data orthogonal to other sources such as pathology, hematology, genomics, and/or proteomics. As such, "radiomics" has emerged as a field of research that involves the process of converting standard-of-care images into quantitative image-based data that can be merged with other data sources and subsequently analyzed using conventional biostatistics or artificial intelligence (AI) methods. As radiomic features capture biological and pathophysiological information, these quantitative radiomic features have shown to provide rapid and accurate noninvasive biomarkers for lung cancer risk prediction, diagnostics, prognosis, treatment response monitoring, and tumor biology. In this review, radiomics and emerging AI methods in lung cancer research are highlighted and discussed including advantages, challenges, and pitfalls.

Differentiation of adenocarcinoma in situ with alveolar collapse from minimally invasive adenocarcinoma or invasive adenocarcinoma appearing as part-solid ground-glass nodules (≤ 2 cm) using computed tomography

PURPOSE

To investigate the differentiating computed tomographic (CT) features between adenocarcinoma in situ (AIS) with alveolar collapse and minimally invasive adenocarcinoma (MIA) or invasive adenocarcinoma (IA) appearing as part-solid nodules.

METHODS

A total of 147 consecutive patients with 157 pathology-confirmed part-solid ground-glass nodules (GGNs) ≤ 20 mm without other pathological condition such as inflammation and fibrosis who underwent chest CT were included.

RESULTS

The 157 part-solid GGNs included 33 (21.02%) pathologically confirmed AISs with alveolar collapse. Multivariate analysis revealed that smaller lesion size (odds ratio [OR] 0.671), and well-defined border (OR 5.544), concentrated distribution (OR 7.994), and homogeneity of the solid portion (OR 4.365) were significant independent predictors for differentiating AIS with alveolar collapse from MIA (P < 0.05) with excellent accuracy (area under receiver operating characteristic [ROC] curve, 0.902). Multivariate analysis revealed that smaller lesion size (OR 0.782), and size (OR 0.821), well-defined border (OR 5.752), and homogeneity of solid portion (OR 6.182) were significant independent predictors differentiating AIS with alveolar collapse from IA (P < 0.05) with excellent accuracy (area under ROC curve 0.910).

CONCLUSION

Among part-solid GGNs, AIS with alveolar collapse can be accurately differentiated from MIA on the basis of smaller lesion size, well-defined border, concentrated distribution, and homogeneity of solid portion, and from IA according to smaller lesion size, and smaller size, well-defined border, and homogeneity of solid portion.

Deep Learning-Based Stage-Wise Risk Stratification for Early Lung Adenocarcinoma in CT Images: A Multi-Center Study

Simple Summary

Prediction of the malignancy and invasiveness of ground glass nodules (GGNs) from computed tomography images is a crucial task for radiologists in risk stratification of early-stage lung adenocarcinoma. In order to solve this challenge, a two-stage deep neural network (DNN) was developed based on the images collected from four centers. A multi-reader multi-case observer study was conducted to evaluate the model capability. The performance of our model was comparable or even more accurate than that of senior radiologists, with average area under the curve values of 0.76 and 0.95 for two tasks, respectively. Findings suggest (1) a positive trend between the diagnostic performance and radiologist’s experience, (2) DNN yielded equivalent or even higher performance in comparison with senior radiologists, and (3) low image resolution reduced the model performance in predicting the risks of GGNs.

Abstract

This study aims to develop a deep neural network (DNN)-based two-stage risk stratification model for early lung adenocarcinomas in CT images, and investigate the performance compared with practicing radiologists. A total of 2393 GGNs were retrospectively collected from 2105 patients in four centers. All the pathologic results of GGNs were obtained from surgically resected specimens. A two-stage deep neural network was developed based on the 3D residual network and atrous convolution module to diagnose benign and malignant GGNs (Task1) and classify between invasive adenocarcinoma (IA) and non-IA for these malignant GGNs (Task2). A multi-reader multi-case observer study with six board-certified radiologists’ (average experience 11 years, range 2–28 years) participation was conducted to evaluate the model capability. DNN yielded area under the receiver operating characteristic curve (AUC) values of 0.76 ± 0.03 (95% confidence interval (CI): (0.69, 0.82)) and 0.96 ± 0.02 (95% CI: (0.92, 0.98)) for Task1 and Task2, which were equivalent to or higher than radiologists in the senior group with average AUC values of 0.76 and 0.95, respectively (p > 0.05). With the CT image slice thickness increasing from 1.15 mm ± 0.36 to 1.73 mm ± 0.64, DNN performance decreased 0.08 and 0.22 for the two tasks. The results demonstrated (1) a positive trend between the diagnostic performance and radiologist’s experience, (2) the DNN yielded equivalent or even higher performance in comparison with senior radiologists, and (3) low image resolution decreased model performance in predicting the risks of GGNs. Once tested prospectively in clinical practice, the DNN could have the potential to assist doctors in precision diagnosis and treatment of early lung adenocarcinoma.

The value of various peritumoral radiomic features in differentiating the invasiveness of adenocarcinoma manifesting as ground-glass nodules

OBJECTIVES

To evaluate the ability of CT radiomic features extracted from peritumoral parenchyma of 2 mm and 5 mm distinguishing invasive adenocarcinoma (IAC) from adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA).

METHODS

For this retrospective study, 121 lung adenocarcinomas appearing as ground-glass nodules on thin-section CT were evaluated. Quantitative radiomic features were extracted from the peritumoral parenchymal region of 2 mm and 5 mm on CT imaging, and the radiomic models of External2 and External5 were constructed. The ROC curves were used to evaluate the performance of different models. Differences between the AUCs were evaluated using DeLong's method.

RESULTS

The radiomic scores of IAC were statistically higher than those of MIA/AIS in both the External2 and External5 models. The AUCs of the External2 and External5 models were 0.882, 0.778 in the training cohort and 0.888, 0.804 in the validation cohort, respectively. The AUC of the External2 model was not statistically different from the External5 model both in the training cohort (p = 0.116) and validation cohort (p = 0.423).

CONCLUSIONS

The radiomic features extracted from the peritumoral region of 2 mm and 5 mm at thin-section CT showed good predictive values to differentiate the IAC from AIS/MIA. The radiomic features from the peritumoral region of 5 mm provide no additional benefit in distinguishing IAC from MIA/AIS than that of the 2 mm region.

KEY POINTS

• The radiomic models from various peritumoral lung parenchyma were developed and validated to predict invasiveness of adenocarcinoma. • The peritumoral parenchyma of lung adenocarcinoma may contain useful information. • Radiomics from peritumoral lung parenchyma of 5 mm provides no added efficiency of the prediction for invasiveness of lung adenocarcinoma.

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.

Semi-Quantitative Analysis for Determining the Optimal Threshold Value on CT to Measure the Solid Portion of Pulmonary Subsolid Nodules

PURPOSE

This study aimed to investigate the optimal threshold value in Hounsfield units (HU) on CT to detect the solid components of pulmonary subsolid nodules using pathologic invasive foci as reference.

MATERIALS AND METHODS

Thin-section non-enhanced chest CT scans of 25 patients with pathologically confirmed minimally invasive adenocarcinoma were retrospectively reviewed. On CT images, the solid portion was defined as the area with higher attenuation than various HU thresholds ranging from -600 to -100 HU in 50-HU intervals. The solid portion was measured as the largest diameter on axial images and as the maximum diameter on multiplanar reconstruction images. A linear mixed model was used to evaluate bias in each threshold by using the pathological size of invasive foci as reference.

RESULTS

At a threshold of -400 HU, the biases were lowest between the largest/maximum diameter of the solid portion of subsolid nodule and the size of invasive foci of the pathological specimen, with 0.388 and -0.0176, respectively. They showed insignificant difference (p = 0.2682, p = 0.963, respectively) at a threshold of -400 HU.

CONCLUSION

For quantitative analysis, -400 HU may be the optimal threshold to define the solid portion of subsolid nodules as a surrogate marker of invasive foci.

Value of contrast-enhanced CT texture analysis in predicting IDH mutation status of intrahepatic cholangiocarcinoma

To explore the value of contrast-enhanced CT texture analysis in predicting isocitrate dehydrogenase (IDH) mutation status of intrahepatic cholangiocarcinomas (ICCs). Institutional review board approved this study. Contrast-enhanced CT images of 138 ICC patients (21 with IDH mutation and 117 without IDH mutation) were retrospectively reviewed. Texture analysis was performed for each lesion and compared between ICCs with and without IDH mutation. All textural features in each phase and combinations of textural features (p < 0.05) by Mann–Whitney U tests were separately used to train multiple support vector machine (SVM) classifiers. The classification generalizability and performance were evaluated using a tenfold cross-validation scheme. Among plain, arterial phase (AP), portal venous phase (VP), equilibrium phase (EP) and Sig classifiers, VP classifier showed the highest accuracy of 0.863 (sensitivity, 0.727; specificity, 0.885), with a mean area under the receiver operating characteristic curve of 0.813 in predicting IDH mutation in validation cohort. Texture features of CT images in portal venous phase could predict IDH mutation status of ICCs with SVM classifier preoperatively.