Radiomics for lung adenocarcinoma manifesting as pure ground-glass nodules: invasive prediction

A multiomics dataset of paired CT image and plasma cell-free DNA end motif for patients with pulmonary nodules

Diagnosing lung cancer at a curable stage offers the opportunity for a favorable prognosis. The emerging epigenomics analysis on plasma cell-free DNA (cfDNA), including 5-methylcytosine (5mC) and 5-hydroxymethylcytosine (5hmC) modifications, has acted as a promising approach facilitating the identification of lung cancer. And, integrating 5mC biomarker with chest computed tomography (CT) image features could optimize the diagnosis of lung cancer, exceeding the performance of models built on single feature. However, the clinical applicability of integrated markers might be limited by the potential risk of overfitting due to small sample size. Hence, we prospectively collected peripheral blood sample and the paired chest CT images of 2032 patients with indeterminate pulmonary nodules across 5 centers, and constructed a large-scale, multi-institutional, multiomics database that encompass CT imaging data and plasma cfDNA fragmentomic in 5mC-, 5hmC-enriched regions. To our best knowledge, this dataset is the first radio-epigenomic dataset with the largest sample size, and provides multi-dimensional insights for early diagnosis of lung cancer, facilitating the individuated management for lung cancer.

Construction and validation of a risk stratification model based on Lung-RADS® v2022 and CT features for predicting the invasive pure ground-glass pulmonary nodules in China

OBJECTIVES

A novel risk stratification model based on Lung-RADS® v2022 and CT features was constructed and validated for predicting invasive pure ground-glass nodules (pGGNs) in China.

METHODS

Five hundred and twenty-six patients with 572 pulmonary GGNs were prospectively enrolled and divided into training (n = 169) and validation (n = 403) sets. Utilising the Lung-RADS® v2022 framework and the types of GGN-vessel relationships (GVR), a complementary Lung-RADS® v2022 was established, and the pGGNs were reclassified from categories 2, 3 and 4x of Lung-RADS® v2022 into 2, 3, 4a, 4b, and 4x of cLung-RADS® v2022. The cutoff value of invasive pGGNs was defined as the cLung-RADS® v2022 4a-4x. Evaluation metrics like recall rate, precision, F1 score, accuracy, Matthews correlation coefficient (MCC), and the area under the receiver operating characteristic curve (AUC) were employed to assess the utility of the cLung-RADS® v2022.

RESULTS

In the training set, compared with the Lung-RADS 1.0, the AUC of Lung-RADS® v2022 were decreased from 0.543 to 0.511 (p-value = 0.002), and compared to Lung-RADS 1.0 and Lung-RADS® v2022, the cLung-RADS® v2022 model exhibited the highest recall rate (94.9% vs 6.5%, 2.2%), MCC value (60.2% vs 5.4%, 6.3%), F1 score (92.5% vs 12.1%, 4.3%), accuracy (87.6% vs 23.1%, 19.5%), and AUC (0.718 vs 0.543, 0.511; p-value = 0.014, 0.0016) in diagnosing the invasiveness of pGGNs, and the similar performance was observed in the validation set.

CONCLUSION

The cLung-RADS® v2022 can effectively predict the invasiveness of pGGNs in real-world scenarios.

CRITICAL RELEVANCE STATEMENT

A complementary Lung-RADS® v2022 based on the Lung-RADS® v2022 and CT features can effectively predict the invasiveness of pulmonary pure ground-glass nodules and is applicable in clinical practice.

TRIAL REGISTRATION

Establishment and application of a multi-scale low-dose CT Lung cancer screening model based on modified lung-RADS1.1 and deep learning technology, 2022-KY-0137. Registered 24 January 2022. https://www.medicalresearch.org.cn/search/research/researchView?id=a97e67d8-1ee6-40fb-aab1-e6238dbd8f29 .

KEY POINTS

Lung-RADS® v2022 delayed lung cancer diagnosis for nodules appearing as pGGNs. Lung-RADS® v2022 showed lower accuracy and AUC than Lung-RADS 1.0. cLung-RADS® v2022 model effectively predicts the invasiveness of pulmonary pGGNs.

Dual-layer spectral detector computed tomography multiparameter machine learning model for prediction of invasive lung adenocarcinoma

Background

Lung adenocarcinoma (LUAD) is the leading cause of cancer-related deaths. High-resolution computed tomography (HRCT) has improved the detection of ground glass nodules (GGNs), which are early indicators of lung cancer. Accurate assessment of GGN invasiveness is crucial for determining the appropriate surgical approach. Dual-layer spectral detector computed tomography (DLCT) offers advanced imaging capabilities, including electron density and iodine density, which enhance the evaluation of GGN invasiveness. This study aims to develop a machine learning (ML) model that integrates DLCT parameters and clinical features to predict the invasiveness of GGNs in LUAD, aiding in surgical decision-making and prognosis improvement.

Methods

The retrospective study encompassed 272 patients who were diagnosed with LUAD, comprising 154 cases of invasive adenocarcinomas (IA) and 118 cases of pre-invasive minimally invasive adenocarcinoma (MIA) which were then randomly allocated into a training set and a test set. Six ML models were developed based on five DLCT parameters (conventional, iodine density, virtual noncontrast, electron density, and effective atomic number). Subsequently, a nomogram was constructed using multi-factor logistic regression, incorporating radiomic characteristics and clinicopathological risk factors.

Results

The ML model based on conventional plus electron density performed better than the models with other DLCT parameters, with the area under the curves (AUCs) of 0.945 and 0.964 in the training and test sets, respectively. The clinical model and radiomics score (Rad-score) were combined in the logistic regression to construct a joint model, of which the AUCs were 0.974 in the training sets and 0.949 in the test sets. The ML model effectively differentiated between IA and pre-invasive MIA, and further classified patients into high and medium risk categories for invasion using waterfall plots.

Conclusions

The ML model based on DLCT parameters helps predict the invasiveness of GGNs and classifies the GGNs into different risk grades.

Hybrid Approach to Classifying Histological Subtypes of Non-small Cell Lung Cancer (NSCLC): Combining Radiomics and Deep Learning Features from CT Images

This study aimed to develop a hybrid model combining radiomics and deep learning features derived from computed tomography (CT) images to classify histological subtypes of non-small cell lung cancer (NSCLC). We analyzed CT images and radiomics features from 235 patients with NSCLC, including 110 with adenocarcinoma (ADC) and 112 with squamous cell carcinoma (SCC). The dataset was split into a training set (75%) and a test set (25%). External validation was conducted using the NSCLC-Radiomics database, comprising 24 patients each with ADC and SCC. A total of 1409 radiomics and 8192 deep features underwent principal component analysis (PCA) and ℓ2,1-norm minimization for feature reduction and selection. The optimal feature sets for classification included 27 radiomics features, 20 deep features, and 55 combined features (30 deep and 25 radiomics). The average area under the receiver operating characteristic curve (AUC) for radiomics, deep, and combined features were 0.6568, 0.6689, and 0.7209, respectively, across the internal and external test sets. Corresponding average accuracies were 0.6013, 0.6376, and 0.6564. The combined model demonstrated superior performance in classifying NSCLC subtypes, achieving higher AUC and accuracy in both test datasets. These results suggest that the proposed hybrid approach could enhance the accuracy and reliability of NSCLC subtype classification.

Preoperative CT and Radiomics Nomograms for Distinguishing Bronchiolar Adenoma and Early-Stage Lung Adenocarcinoma

RATIONALE AND OBJECTIVES

Evaluating the capability of CT nomograms and CT-based radiomics nomograms to differentiate between Bronchiolar Adenoma (BA) and Early-stage Lung Adenocarcinoma (LUAD).

MATERIALS AND METHODS

In this retrospective study; we analyzed data from 226 patients who were treated at our institution and pathologically confirmed to have either BA or Early-stage LUAD. Patients were randomly divided into a training cohort (n=158) and a testing cohort (n=68). All CT images were independently analyzed and measured by two radiologists using conventional computed tomography. Clinical predictive factors were identified using logistic regression. Multivariable logistic regression analysis was used to construct differential diagnostic models for BA and early-stage LUAD, including traditional CT and radiomics models. The performance of the models was determined based on the area under the receiver operating characteristic curve, discrimination ability, and decision curve analysis (DCA).

RESULTS

Lesion shape, tumor-lung interface, and pleural retraction signs were identified as independent clinical predictors. The areas under the curve for the CT nomogram, radiomic features, and radiomics nomogram were 0.854, 0.769, and 0.901, respectively. Both the CT nomogram and the radiomics nomogram demonstrated good generalizability in distinguishing between the two entities. DCA indicated that the nomograms achieved a higher net benefit compared to the use of radiomic features alone.

CONCLUSION

The two preoperative nomograms hold significant value in differentiating between patients with BA and those with Early-stage LUAD, and they contribute to informed clinical treatment decision-making.

Significance of the Lesion-Pleura Relationship in Differentiating Peripheral Inflammatory Lesions and Lung Cancers

Purpose

To determine the significance of lesion-pleura relationship in differentiating peripheral inflammatory lesions (PILs) and peripheral lung cancers (PLCs).

Patients and Methods

From January 2017 to April 2022, a total of 743 patients with 501 PLCs and 292 PILs (≥1.5 cm) were retrospectively enrolled. The patients' clinical characteristics and CT features of lesions in these two groups were analyzed and compared, and the impact of the lesion-pleura relationship (broad or narrow basement and distance between lesion and pleura) on differentiation was specifically assessed.

Results

Lesions attached to pleura were more frequent in PILs (188, 64.4%) than in PLCs (244, 48.7%) (P < 0.001), and those with broad basement-to-pleura were also more common in PILs (133, 70.7%) than in PLCs (47, 19.3%) (P < 0.001). Among the 296 lesions with a lesion-pleura distance ≤16 mm, the optimal cutoff value of distance was ≤8.9 mm (area under curve [AUC], 0.733; sensitivity: 0.770; specificity: 0.623; P < 0.001) for predicting PLCs. Regarding the 728 lesions attached to pleura or with a lesion-pleura distance ≤16 mm, the AUC of the model based on the clinical and CT features for predicting PLCs significantly increased from 0.812 to 0.879 after including lesion-pleura relationship (narrow basement or lesion-pleura distance ≤ 8.9 mm) (P < 0.001). Additionally, the lesion-pleura relationship was one of independent indicators for differentiation (odds ratio, 9.433; P < 0.001).

Conclusion

When differentiating peripheral lesions (≥1.5 cm), it is crucial to consider the basement-to-pleura and lesion-pleura distance besides patients' clinical characteristics, laboratory parameters and morphological features.

Diameter thresholds for pure ground-glass pulmonary nodules at low-dose CT screening: Chinese experience

BACKGROUND

Limited research exists on screening thresholds for low-dose CT in detecting malignant pure ground-glass lung nodules (pGGNs) in the Chinese population.

MATERIALS AND METHODS

A retrospective analysis of the Guangzhou Lung-Care programme was conducted, retrieving average transverse diameter, location, histopathology, frequency and follow-up intervals. Diagnostic performances for 'lung cancers' were evaluated using areas under the curve (AUCs), decision curve analysis (DCA), sensitivities and specificities, with thresholds ranging from 5 mm to 10 mm. We divide malignant pGGNs into three groups: (1) minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IA), (2) atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS) and MIA and IA and (3) IA-only.

RESULTS

In 'MIA+IA', increasing the threshold from 5 mm to 8 mm improved specificity (60.97% to 88.85%, p<0.001) and positive predictive values (PPVs; 5.87% to 14.88%, p<0.001), but decreased sensitivity (94.44% to 75.56%, p<0.001). Further raising threshold from 8 mm reduced sensitivity (75.56% to 60.00%, p<0.001), while slightly increasing specificity (88.85% to 93.47%, p<0.001) and PPVs (14.88% to 19.15%, p<0.001). Increasing threshold from 5 mm to 7 mm enhanced the AUC for 'MIA+IA' (from 0.711 to 0.829), 'AAH+AIS+MIA+IA' (from 0.748 to 0.804) and 'IA-only' (from 0.783 to 0.833). At 8 mm, the AUCs for these categories were similar. However, increasing the threshold from 7 mm to 10 mm resulted in reduced AUCs for 'MIA+IA' (0.829 to 0.767), 'AAH+AIS+MIA+IA' (0.804 to 0.744) and 'IA-only' (0.833 to 0.800). DCA reveals that the 8 mm predictive model demonstrates greater clinical utility compared with models with other thresholds.

CONCLUSIONS

Increasing the diameter threshold for positive results for pGGNs, up to 8 mm could enhance diagnostic performance.

TRIAL REGISTRATION NUMBER

NCT04938804.

Differentiating Pulmonary Nodule Malignancy Using Exhaled Volatile Organic Compounds: A Prospective Observational Study

BACKGROUND

Advances in imaging technology have enhanced the detection of pulmonary nodules. However, determining malignancy often requires invasive procedures or repeated radiation exposure, underscoring the need for safer, noninvasive diagnostic alternatives. Analyzing exhaled volatile organic compounds (VOCs) shows promise, yet its effectiveness in assessing the malignancy of pulmonary nodules remains underexplored.

METHODS

Employing a prospective study design from June 2023 to January 2024 at the Affiliated Hospital of Yangzhou University, we assessed the malignancy of pulmonary nodules using the Mayo Clinic model and collected exhaled breath samples alongside lifestyle and health examination data. We applied five machine learning (ML) algorithms to develop predictive models which were evaluated using area under the curve (AUC), sensitivity, specificity, and other relevant metrics.

RESULTS

A total of 267 participants were enrolled, including 210 with low-risk and 57 with moderate-risk pulmonary nodules. Univariate analysis identified 11 exhaled VOCs associated with nodule malignancy, alongside two lifestyle factors (smoke index and sites of tobacco smoke inhalation) and one clinical metric (nodule diameter) as independent predictors for moderate-risk nodules. The logistic regression model integrating lifestyle and health data achieved an AUC of 0.91 (95% CI: 0.8611-0.9658), while the random forest model incorporating exhaled VOCs achieved an AUC of 0.99 (95% CI: 0.974-1.00). Calibration curves indicated strong concordance between predicted and observed risks. Decision curve analysis confirmed the net benefit of these models over traditional methods. A nomogram was developed to aid clinicians in assessing nodule malignancy based on VOCs, lifestyle, and health data.

CONCLUSIONS

The integration of ML algorithms with exhaled biomarkers and clinical data provides a robust framework for noninvasive assessment of pulmonary nodules. These models offer a safer alternative to traditional methods and may enhance early detection and management of pulmonary nodules. Further validation through larger, multicenter studies is necessary to establish their generalizability.

TRIAL REGISTRATION

Number ChiCTR2400081283.

Multimodal integration to identify the invasion status of lung adenocarcinoma intraoperatively

Evaluating the invasiveness of lung adenocarcinoma is crucial for determining the appropriate surgical strategy, impacting postoperative outcomes. This study developed a multimodality model combining radiomics, intraoperative frozen section (FS) pathology, and clinical indicators to predict invasion status. The study enrolled 1,424 patients from two hospitals, divided into multimodal training, radiology testing, and pathology testing cohorts. A prospective validation cohort of 114 patients was selected between March and May 2023. The radiomics + pathology + clinical indicators multimodality model (multi-RPC model) achieved an area under the curve (AUC) of 0.921 (95% confidence interval [CI] 0.899-0.939) in the multimodal training cohort and 0.939 (95% CI 0.878-0.975) in the validation cohort, outperforming single- and dual-modality models. The multi-RPC model's predictive accuracy of 0.860 (95% CI 0.782-0.918) suggests that it could significantly reduce inappropriate surgical procedures, enhancing precision oncology by integrating multimodal information to guide surgical decisions.

Lung adenocarcinoma: characteristic radiological presentations

Radiology, mainly computed tomography, has a fundamental role in diagnosis, staging and follow-up of lung adenocarcinoma, the most common type of pulmonary cancer. Within its broad spectrum of presentation, the pathological, clinical and morphological characteristics of this neoplasm allow, in an appropriate clinical context, to suggest certain histological subtypes among which are mucinous adenocarcinoma, lepidic growth adenocarcinoma or associated with cystic lung lesions. The objective of this review is to describe the pathologic, clinical and radiological features of those characteristic forms of lung carcinoma that can be diagnosed radiologically with fair accuracy.

Predicting the invasiveness of ground-glass opacity predominant lung adenocarcinoma with clinical stage Ia: a CT-based semantic and radiomics analysis

Background

Limited surgery is deemed advantageous due to its potential to minimize damage and preserve a greater extent of functional lung tissue, contingent upon the invasiveness of lung adenocarcinoma (ADC). The aim of this study was to non-invasively predict the invasiveness of ground-glass opacity (GGO) predominant nodules presented on preoperative computed tomography (CT) of ADC patients with clinical stage Ia.

Methods

We constructed a primary cohort comprising 437 clinical stage Ia ADC patients from the Tianjin Medical University Cancer Institute and Hospital and utilized data from 135 patients from the Tianjin Medical University General Hospital for validation. Radiomics features were extracted by the PyRadiomics software and screened by spearman correlation analysis, minimum redundancy maximum relevance and the least absolute shrinkage and selection operator (LASSO) regression analysis. The radiomics score (Rad-score) formula was then created by linearly combining the selected features, using their regression coefficients as weights. Univariate analysis followed by multivariable logistic regression were performed to estimate the independent predictors. An initial univariate analysis was followed by a multivariable logistic regression to estimate independent predictors. Area under the curve (AUC) was calculated after the model established through visual nomogram and external validation.

Results

Three hundred and seventy-four patients were pathologically confirmed as invasive ADC (65.4%), and three independent predictors were identified: maximum consolidation diameter (P=0.02), texture (P=0.042) and Rad-score (P<0.001). The combined model showed good calibration with an AUC of 0.911 [95% confidence interval (CI): 0.872, 0.951], compared with 0.883 (95% CI: 0.849, 0.932; DeLong's test P=0.16) and 0.842 (95% CI: 0.801, 0.896; DeLong's test P<0.001) when radiomics or CT semantic features were used alone. Combined prediction model accuracy for validation group was 0.865 (95% CI: 0.816, 0.908), which is reasonable.

Conclusions

Our study has provided a non-invasive prediction tool based on radiomics and CT semantic characteristics that can accurately assess the quantitative risk associated with the invasiveness of GGO predominant ADC in clinical stage Ia.

Development of a nomogram-based model incorporating radiomic features from follow-up longitudinal lung CT images to distinguish invasive adenocarcinoma from benign lesions: a retrospective study

PURPOSE

To develop and validate a radiomic model for differentiating pulmonary invasive adenocarcinomas from benign lesions based on follow-up longitudinal CT images.

METHODS

This is a retrospective study including 336 patients (161 with invasive adenocarcinomas and 175 with benign lesions) who underwent baseline (T0) and follow-up (T1) CT scans from January 2016 to June 2022. The patients were randomized in a 7:3 ratio into training and test sets. Radiomic features were extracted from lesion volumes of interest on longitudinal CT images at T0 and T1. Differences in radiomic features between T1 and T0 were defined as delta-radiomic features. Logistic regression was used to build models based on clinicoradiological (CR), T0, T1, and delta radiomic features and compute signatures. Finally, a nomogram based on the CR, T0, T1 and delta signatures was constructed. Model performance was evaluated for calibration, discrimination, and clinical utility.

RESULTS

The T1 radiomic model was superior to the other independent models. In the training set, it had an area under the curve (AUC) of 0.858), superior to the CR model (AUC 0.694), the T0 radiomic model (AUC 0.825), and the delta radiomic model (AUC 0.734). In the test set, it had an AUC of 0.817, again outperforming the CR model (AUC 0.578), the T0 radiomic model (AUC 0.789), and the delta radiomic model (AUC 0.647). The nomogram incorporating the CR, T0, T1 and delta signatures showed the best predictive performance in both the training (AUC: 0.906) and test sets (AUC: 0.856), and it exhibited excellent fit with calibration curves. Decision curve analysis provided additional validation of the clinical utility of the nomogram.

CONCLUSION

A nomogram utilizing radiomic features extracted from longitudinal CT images can enhance the discriminative capability between pulmonary invasive adenocarcinomas and benign lesions.

Differential diagnosis of benign and lung adenocarcinoma presenting as larger solid nodules and masses based on multiscale CT radiomics

PURPOSE

To develop a better radiomic model for the differential diagnosis of benign and lung adenocarcinoma lesions presenting as larger solid nodules and masses based on multiscale computed tomography (CT) radiomics.

MATERIALS AND METHODS

This retrospective study enrolled 205 patients with solid nodules and masses from Center 1 between January 2010 and February 2022 and Center 2 between January 2019 and February 2022. After applying the inclusion and exclusion criteria, we retrospectively enrolled 165 patients from two centers and assigned them to the training dataset (n = 115) or the test dataset (n = 50). Radiomics features were extracted from volumes of interest on CT images. A gradient boosting decision tree (GBDT) was used for data dimensionality reduction to perform the final feature selection. Four models were developed using clinical data, conventional imaging features and radiomics features, namely, the clinical and image model (CIM), the plain CT radiomics model (PRM), the enhanced CT radiomics model (ERM) and the combined model (CM). Model performance was evaluated to determine the best model for identifying benign and lung adenocarcinoma presenting as larger solid nodules and masses.

RESULTS

In the training dataset, the areas under the curve (AUCs) for the CIM, PRM, ERM, and CM were 0.718, 0.806, 0.819, and 0.917, respectively. The differential diagnostic capability of the ERM was better than that of the PRM and the CIM. The CM was optimal. Intermediate and junior radiologists and respiratory physicians achieved improved obviously diagnostic results with the radiomics model. The senior radiologists showed slight improved diagnostic results after using the radiomics model.

CONCLUSION

Radiomics may have the potential to be used as a noninvasive tool for the differential diagnosis of benign and lung adenocarcinoma lesions presenting as larger solid nodules and masses.

Habitat Imaging With Tumoral and Peritumoral Radiomics for Prediction of Lung Adenocarcinoma Invasiveness on Preoperative Chest CT: A Multicenter Study

BACKGROUND. Tumor growth processes result in spatial heterogeneity, with the development of tumor subregions (i.e., habitats) having unique biologic characteristics. OBJECTIVE. The purpose of our study was to develop and validate a habitat model combining tumor and peritumoral radiomic features on chest CT for predicting invasiveness of lung adenocarcinoma. METHODS. This retrospective study included 1156 patients (mean age, 57.5 years; 464 men, 692 women), from three centers and a public dataset, who underwent chest CT before lung adenocarcinoma resection (variable date ranges across datasets). Patients from one center formed training (n = 500) and validation (n = 215) sets; patients from the other sources formed three external test sets (n = 249, 113, 79). For each patient, a single nodule was manually segmented on chest CT. The nodule segmentation was combined with an automatically generated 4-mm peritumoral region into a whole-volume volume of interest (VOI). A gaussian mixture model (GMM) identified voxel clusters with similar first-order energy across patients. GMM results were used to divide each patient's whole-volume VOI into multiple habitats, which were defined consistently across patients. Radiomic features were extracted from each habitat. After feature selection, a habitat model was developed for predicting invasiveness, with the use of pathologic assessment as a reference. An integrated model was constructed, combining features extracted from habitats and whole-volume VOIs. Model performance was evaluated, including in subgroups based on nodule density (pure ground-glass, part-solid, and solid). The code for habitat imaging and model construction is publicly available (https://github.com/Shangyoulan/Habitat/). RESULTS. Invasive cancer was diagnosed in 626 of 1156 patients. GMM identified four as the optimal number of voxel clusters and thus of per-patient tumor habitats. The habitat model had an AUC of 0.932 in the validation set and 0.881, 0.880, and 0.764 in the three external test sets. The integrated model had an AUC of 0.947 in the validation set and 0.936, 0.908, and 0.800 in the three external test sets. In the three external test sets combined, across nodule densities, AUCs for the habitat model were 0.836-0.869 and for the integrated model were 0.846-0.917. CONCLUSION. Habitat imaging combining tumoral and peritumoral radiomic features could help predict lung adenocarcinoma invasiveness. Prediction is improved when combining information on tumor subregions and the tumor overall. CLINICAL IMPACT. The findings may aid personalized preoperative assessments to guide clinical decision-making in lung adenocarcinoma.

Radiomics nomogram: distinguishing benign and malignant pure ground-glass nodules based on dual-layer spectral detector CT

AIM

To investigate the value of the combined model based on spectral quantitative parameters, radiomics features, imaging and clinical features to distinguish the benign and malignant pure ground-glass nodules (pGGNs).

MATERIALS AND METHODS

A retrospective analysis of 113 patients with single pGGNs who underwent non-contrast enhancement examination of the chest on dual-layer spectral detector CT (SDCT) with two weeks before surgery was performed in our hospital. These patients were randomized into training and testing cohorts. Regions of interest based on the conventional 120 kVp poly energetic image of SDCT were outlined. Then the optimal features were extracted and selected to construct radiomic model. A combined model combining vacuole sign, electron density (ED) value and the rad score of radiomics model was built by logistic regression analysis. A nomogram was built in a training cohort and the performance of the models was evaluated in the training and testing cohorts by receiver operating characteristic curves, calibration curves and decision curve analysis.

RESULTS

ED value [Odds Ratio (OR):1.100; 95% confidence interval (CI):1.027-1.166)] and vacuole sign (OR:3.343; 95% CI:0.881-12.680) were independent risk factors for the malignant pGGNs in the training cohort. A combined model was constructed using radiomics features, ED value and vacuole sign. And the AUC was 0.910 (95% CI, 0.825-0.997) and 0.850 (95% CI, 0.714-0.981) in the training and testing cohorts, respectively.

CONCLUSION

The combined model based on SDCT has high specificity and sensitivity for distinguishing the benign and malignant pGGNs, suggesting the model can further improve diagnostic performance, and using a nomogram is helpful for individualized predictions.

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.

Evaluation of the invasiveness of pure ground-glass nodules based on dual-head ResNet technique

OBJECTIVE

To intelligently evaluate the invasiveness of pure ground-glass nodules with multiple classifications using deep learning.

METHODS

pGGNs in 1136 patients were pathologically confirmed as lung precursor lesions [atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS)], minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC). Four different models [EfficientNet-b0 2D, dual-head ResNet_3D, a 3D model combining three features (3D_3F), and a 3D model combining 19 features (3D_19F)] were constructed to evaluate the invasiveness of pGGNs using the EfficientNet and ResNet networks. The Obuchowski index was used to evaluate the differences in diagnostic efficiency among the four models.

RESULTS

The patients with pGGNs (360 men, 776 women; mean age, 54.63 ± 12.36 years) included 235 cases of AAH + AIS, 332 cases of MIA, and 569 cases of IAC. In the validation group, the areas under the curve in detecting the invasiveness of pGGNs as a three-category classification (AAH + AIS, MIA, IAC) were 0.8008, 0.8090, 0.8165, and 0.8158 for EfficientNet-b0 2D, dual-head ResNet_3D, 3D_3F, and 3D_19F, respectively, whereas the accuracies were 0.6422, 0.6158, 0.651, and 0.6364, respectively. The Obuchowski index revealed no significant differences in the diagnostic performance of the four models.

CONCLUSIONS

The dual-head ResNet_3D_3F model had the highest diagnostic efficiency for evaluating the invasiveness of pGGNs in the four models.

Artificial intelligence-measured nodule mass for determining the invasiveness of neoplastic ground glass nodules

Background

The nodule mass is an important indicator for evaluating the invasiveness of neoplastic ground-glass nodules (GGNs); however, the efficacy of nodule mass acquired by artificial intelligence (AI) has not been validated. This study thus aimed to determine the efficacy of nodule mass measured by AI in predicting the invasiveness of neoplastic GGNs.

Methods

From May 2019 to September 2023, a retrospective study was conducted on 755 consecutive patients comprising 788 pathologically confirmed neoplastic GGNs, among which 259 were adenocarcinoma in situ (AIS), 282 minimally invasive adenocarcinoma (MIA), and 247 invasive adenocarcinoma (IAC). Nodule mass was quantified using AI software, and other computed tomography (CT) features were concurrently evaluated. Clinical data and CT features were compared using the Kruskal-Wallis test or Pearson chi-square test. The predictive efficacy of mass and CT features for evaluating invasive lesions (ILs) (MIAs and IACs) and IACs was analyzed and compared via receiver operating characteristic (ROC) analysis and the Delong test.

Results

ROC curve analysis revealed that the optimal cutoff value of mass for distinguishing ILs and AISs was 225.25 mg [area under the curve (AUC) 0.821; 95% confidence interval 0.792-0.847; sensitivity 64.27%; specificity 89.19%; P<0.001], and for differentiating IACs from AISs and MIAs, it was 390.4 mg (AUC 0.883; 95% confidence interval 0.858-0.904; sensitivity 80.57%; specificity 86.32%; P<0.001). The efficacy of nodule mass in distinguishing ILs and AISs was comparable to that of size (P=0.2162) and significantly superior to other CT features (each P value <0.001). Additionally, the ability of nodule mass to differentiate IACs from AISs and MIAs was significantly better than that of CT features (each P value <0.001).

Conclusions

AI-based nodule mass analysis is an effective indicator for determining the invasiveness of neoplastic GGNs.

Peritumoral radiomics increases the efficiency of classification of pure ground-glass lung nodules: a multicenter study

PURPOSE

We aimed to evaluate the efficiency of computed tomography (CT) radiomic features extracted from gross tumor volume (GTV) and peritumoral volumes (PTV) of 5, 10, and 15 mm to identify the tumor grades corresponding to the new histological grading system proposed in 2020 by the Pathology Committee of the International Association for the Study of Lung Cancer (IASLC).

METHODS

A total of 151 lung adenocarcinomas manifesting as pure ground-glass lung nodules (pGGNs) were included in this randomized multicenter retrospective study. Four radiomic models were constructed from GTV and GTV + 5/10/15-mm PTV, respectively, and compared. The diagnostic performance of the different models was evaluated using receiver operating characteristic curve analysis RESULTS: The pGGNs were classified into grade 1 (117), 2 (34), and 3 (0), according to the IASLC grading system. In all four radiomic models, pGGNs of grade 2 had significantly higher radiomic scores than those of grade 1 (P < 0.05). The AUC of the GTV and GTV + 5/10/15-mm PTV were 0.869, 0.910, 0.951, and 0.872 in the training cohort and 0.700, 0.715, 0.745, and 0.724 in the validation cohort, respectively.

CONCLUSIONS

The radiomic features we extracted from the GTV and PTV of pGGNs could effectively be used to differentiate grade-1 and grade-2 tumors. In particular, the radiomic features from the PTV increased the efficiency of the diagnostic model, with GTV + 10 mm PTV exhibiting the highest efficacy.

Imaging diagnostics of pulmonary ground-glass nodules: a narrative review with current status and future directions

Background and Objective

The incidence rate of lung cancer, which also has the highest mortality rates for both men and women worldwide, is increasing globally. Due to advancements in imaging technology and the growing inclination of individuals to undergo screening, the detection rate of ground-glass nodules (GGNs) has surged rapidly. Currently, artificial intelligence (AI) methods for data analysis and interpretation, image processing, illness diagnosis, and lesion prediction offer a novel perspective on the diagnosis of GGNs. This article aimed to examine how to detect malignant lesions as early as possible and improve clinical diagnostic and treatment decisions by identifying benign and malignant lesions using imaging data. It also aimed to describe the use of computed tomography (CT)-guided biopsies and highlight developments in AI techniques in this area.

Methods

We used PubMed, Elsevier ScienceDirect, Springer Database, and Google Scholar to search for information relevant to the article's topic. We gathered, examined, and interpreted relevant imaging resources from the Second Affiliated Hospital of Nanchang University's Imaging Center. Additionally, we used Adobe Illustrator 2020 to process all the figures.

Key Content and Findings

We examined the common signs of GGNs, elucidated the relationship between these signs and the identification of benign and malignant lesions, and then described the application of AI in image segmentation, automatic classification, and the invasiveness prediction of GGNs over the last three years, including its limitations and outlook. We also discussed the necessity of conducting biopsies of persistent pure GGNs.

Conclusions

A variety of imaging features can be combined to improve the diagnosis of benign and malignant GGNs. The use of CT-guided puncture biopsy to clarify the nature of lesions should be considered with caution. The development of new AI tools brings new possibilities and hope to improving the ability of imaging physicians to analyze GGN images and achieving accurate diagnosis.

Differentiating the Invasiveness of Lung Adenocarcinoma Manifesting as Ground Glass Nodules: Combination of Dual-energy CT Parameters and Quantitative-semantic Features

RATIONALE AND OBJECTIVES

To evaluate the diagnostic performance of dual-energy CT (DECT) parameters and quantitative-semantic features for differentiating the invasiveness of lung adenocarcinoma manifesting as ground glass nodules (GGNs).

MATERIALS AND METHODS

Between June 2022 and September 2023, 69 patients with 74 surgically resected GGNs who underwent DECT examinations were included. CT numbers on virtual monochromatic images were calculated at 40-130 keV generated from DECT. Quantitative morphological measurements and semantic features were evaluated on unenhanced CT images and compared between pathologically confirmed adenocarcinoma in situ (AIS)-minimally invasive adenocarcinoma (MIA) and invasive lung adenocarcinoma (IAC). Multivariable logistic regression analysis was used to identify independent predictors. The diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC) and compared using DeLong's test.

RESULTS

Monochromatic CT numbers at 40-130 keV were significantly higher in IAC than in AIS-MIA (all P < 0.05). Multivariate logistic analysis revealed that CT number of 130 keV (odds ratio [OR] = 1.02, P = 0.013), maximum cross-sectional long diameter (OR =1.40, P = 0.014), deep or moderate lobulation sign (OR =19.88, P = 0.005), and abnormal intranodular vessel morphology (OR = 25.57, P = 0.017) were independent predictors of IAC. The combined prediction model showed a favorable differentiation performance with an AUC of 0.966 (95.2% sensitivity, 94.3% specificity, 94.8% accuracy), which was significantly higher than that for each risk factor (AUC = 0.791-0.822, all P < 0.05).

CONCLUSION

A multi-parameter combined prediction model integrating monochromatic CT numbers from DECT and quantitative-semantic features is promising for the preoperative discrimination of IAC and AIS-MIA in GGN-predominant lung adenocarcinoma.

Construction and validation of a risk score system for diagnosing invasive adenocarcinoma presenting as pulmonary pure ground-glass nodules: a multi-center cohort study in China

Background

Anxiety-driven clinical interventions have been queried due to the nondeterminacy of pure ground-glass nodules (pGGNs). Although radiomics and radiogenomics aid diagnosis, standardization and reproducibility challenges persist. We aimed to assess a risk score system for invasive adenocarcinoma in pGGNs.

Methods

In a retrospective, multi-center study, 772 pGGNs from 707 individuals in The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital were grouped into training (509 patients with 558 observations) and validation (198 patients with 214 observations) sets consecutively from January 2017 to November 2021. An additional test set of 143 observations in Hainan Cancer Hospital was analyzed in the same period. Computed tomography (CT) signs and clinical features were manually collected, and the quantitative parameters were achieved by artificial intelligence (AI). The positive cutoff score was ≥3. Risk scores system 3 combined carcinoma history, chronic obstructive pulmonary disease (COPD), maximum diameters, nodule volume, mean CT values, type II or III vascular supply signs, and other radiographic characteristics. The evaluation included the area under the curves (AUCs), accuracy, sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV) for both the risk score systems 1, 2, 3 and the AI model.

Results

The risk score system 3 [AUC, 0.840; 95% confidence interval (CI): 0.789-0.890] outperformed the AI model (AUC, 0.553; 95% CI: 0.487-0.619), risk score system 1 (AUC, 0.802; 95% CI: 0.754-0.851), and risk score system 2 (AUC, 0.816; 95% CI: 0.766-0.867), with 88.0% (0.850-0.904) accuracy, 95.6% (0.932-0.972) PPV, 0.620 (0.535-0.702) NPV, 89.6% (0.864-0.920) sensitivity, and 80.6% (0.717-0.872) specificity in the training sets. In the validation and test sets, risk score system 3 performed best with AUCs of 0.769 (0.678-0.860) and 0.801 (0.669-0.933).

Conclusions

An AI-based risk scoring system using quantitative image parameters, clinical features, and radiographic characteristics effectively predicts invasive adenocarcinoma in pulmonary pGGNs.

Construction of a predictive model of 2-3 cm ground-glass nodules developing into invasive lung adenocarcinoma using high-resolution CT

Background

The purpose of this study was to analyze the imaging risk factors for the development of 2-3 cm ground-glass nodules (GGN) for invasive lung adenocarcinoma and to establish a nomogram prediction model to provide a reference for the pathological prediction of 2-3 cm GGN and the selection of surgical procedures.

Methods

We reviewed the demographic, imaging, and pathological information of 596 adult patients who underwent 2-3 cm GGN resection, between 2018 and 2022, in the Department of Thoracic Surgery, Second Affiliated Hospital of the Air Force Medical University. Based on single factor analysis, the regression method was used to analyze multiple factors, and a nomogram prediction model for 2-3 cm GGN was established.

Results

(1) The risk factors for the development of 2-3 cm GGN during the invasion stage of the lung adenocarcinoma were pleural depression sign (OR = 1.687, 95%CI: 1.010-2.820), vacuole (OR = 2.334, 95%CI: 1.222-4.460), burr sign (OR = 2.617, 95%CI: 1.008-6.795), lobulated sign (OR = 3.006, 95%CI: 1.098-8.227), bronchial sign (OR = 3.134, 95%CI: 1.556-6.310), diameter of GGN (OR = 3.118, 95%CI: 1.151-8.445), and CTR (OR = 172.517, 95%CI: 48.023-619.745). (2) The 2-3 cm GGN risk prediction model was developed based on the risk factors with an AUC of 0.839; the calibration curve Y was close to the X-line, and the decision curve was drawn in the range of 0.0-1.0.

Conclusion

We analyzed the risk factors for the development of 2-3  cm GGN during the invasion stage of the lung adenocarcinoma. The predictive model developed based on the above factors had some clinical significance.

Study on Predicting Clinical Stage of Patients with Bronchial Asthma Based on CT Radiomics

Objective

To explore the value of a new model based on CT radiomics in predicting the staging of patients with bronchial asthma (BA).

Methods

Patients with BA from 2018 to 2021 were retrospectively analyzed and underwent plain chest CT before treatment. According to the guidelines for the prevention and treatment of BA (2016 edition), they were divided into two groups: acute attack and non-acute attack. The images were processed as follows: using Lung Kit software for image standardization and segmentation, using AK software for image feature extraction, and using R language for data analysis and model construction (training set: test set = 7: 3). The efficacy and clinical effects of the constructed model were evaluated with ROC curve, sensitivity, specificity, calibration curve and decision curve.

Results

A total of 112 patients with BA were enrolled, including 80 patients with acute attack (range: 2-86 years old, mean: 53.89±17.306 years old, males of 33) and 32 patients with non-acute attack (range: 4-79 years old, mean: 57.38±19.223 years old, males of 18). A total of 10 imaging features are finally retained and used to construct model using multi-factor logical regression method. In the training group, the AUC, sensitivity and specificity of the model was 0.881 (95% CI:0.808-0.955), 0.804 and 0.818, separately; while in the test group, it was 0.792 (95% CI:0.608-0.976), 0.792 and 0.80, respectively.

Conclusion

The model constructed based on radiomics has a good effect on predicting the staging of patients with BA, which provides a new method for clinical diagnosis of staging in BA patients.

Detection of the DNA methylation of seven genes contribute to the early diagnosis of lung cancer

BACKGROUND

Low-dose Computed Tomography (CT) is used for the detection of pulmonary nodules, but the ambiguous risk evaluation causes overdiagnosis. Here, we explored the significance of the DNA methylation of 7 genes including TAC1, CDO1, HOXA9, ZFP42, SOX17, RASSF1A and SHOX2 in the blood cfDNA samples in distinguishing lung cancer from benign nodules and healthy individuals.

METHOD

A total of 149 lung cancer patients [72 mass and 77 ground-glass nodules (GGNs)], 5 benign and 48 healthy individuals were tested and analyzed in this study. The lasso-logistic regression model was built for distinguishing cancer and control/healthy individuals or IA lung cancer and non-IA lung cancer cases.

RESULTS

The positive rates of methylation of 7 genes were higher in the cancer group as compared with the healthy group. We constructed a model using age, sex and the ΔCt value of 7 gene methylation to distinguish lung cancer from benign and healthy individuals. The sensitivity, specificity and AUC (area under the curve) were 86.7%, 81.4% and 0.891, respectively. Also, we assessed the significance of 7 gene methylation together with patients' age and sex in distinguishing of GGNs type from the mass type. The sensitivity, specificity and AUC were 77.1%, 65.8% and 0.753, respectively. Furthermore, the methylation positive rates of CDO1 and SHOX2 were different between I-IV stages of lung cancer. Specifically, the positive rate of CDO1 methylation was higher in the non-IA group as compared with the IA group.

CONCLUSION

Collectively, this study reveals that the methylation of 7 genes has a big significance in the diagnosis of lung cancer with high sensitivity and specificity. Also, the 7 genes present with certain significance in distinguishing the GGN type lung cancer, as well as different stages.

Machine learning-based radiomics to distinguish pulmonary nodules between lung adenocarcinoma and tuberculosis

BACKGROUND

Radiomics is increasingly utilized to distinguish pulmonary nodules between lung adenocarcinoma (LUAD) and tuberculosis (TB). However, it remains unclear whether different segmentation criteria, such as the inclusion or exclusion of the cavity region within nodules, affect the results.

METHODS

A total of 525 patients from two medical centers were retrospectively enrolled. The radiomics features were extracted according to two regions of interest (ROI) segmentation criteria. Multiple logistic regression models were trained to predict the pathology: (1) The clinical model relied on clinical-radiological semantic features; (2) The radiomics models (radiomics+ and radiomics-) utilized radiomics features from different ROIs (including or excluding cavities); (3) the composite models (composite+ and composite-) incorporated both above.

RESULTS

In the testing set, the radiomics+/- models and the composite+/- models still possessed efficient prediction performance (AUC ≥ 0.94), while the AUC of the clinical model was 0.881. In the validation set, the AUC of the clinical model was only 0.717, while that of the radiomics+/- models and the composite+/- models ranged from 0.801 to 0.825. The prediction performance of all the radiomics+/- and composite+/- models were significantly superior to that of the clinical model (p < 0.05). Whether the ROI segmentation included or excluded the cavity had no significant effect on these models (radiomics+ vs. radiomics-, composite+ model vs. composite-) (p > 0.05).

CONCLUSIONS

The present study established a machine learning-based radiomics strategy for differentiating LUAD from TB lesions. The ROI segmentation including or excluding the cavity region may exert no significant effect on the predictive ability.

The Value of Topological Radiomics Analysis in Predicting Malignant Risk of Pulmonary Ground-Glass Nodules: A Multi-Center Study

BACKGROUND

Early detection and accurate differentiation of malignant ground-glass nodules (GGNs) in lung CT scans are crucial for the effective treatment of lung adenocarcinoma. However, existing imaging diagnostic methods often struggle to distinguish between benign and malignant GGNs in the early stages. This study aims to predict the malignancy risk of GGNs observed in lung CT scans by applying two radiomics methods: topological data analysis and texture analysis.

METHODS

A retrospective analysis was conducted on 3223 patients from two centers between January 2018 and June2023. The dataset was divided into training, testing, and validation sets to ensure robust model development and validation. We developed topological features applied to GGNs using radiomics analysis based on homology. This innovative approach emphasizes the integration of topological information, capturing complex geometric and spatial relationships within GGNs. By combining machine learning and deep learning algorithms, we established a predictive model that integrates clinical parameters, previous radiomics features, and topological radiomics features.

RESULTS

Incorporating topological radiomics into our model significantly enhanced the ability to distinguish between benign and malignant GGNs. The topological radiomics model achieved areas under the curve (AUC) of 0.85 and 0.862 in two independent validation sets, outperforming previous radiomics models. Furthermore, this model demonstrated higher sensitivity compared to models based solely on clinical parameters, with sensitivities of 80.7% in validation set 1 and 82.3% in validation set 2. The most comprehensive model, which combined clinical parameters, previous radiomics features, and topological radiomics features, achieved the highest AUC value of 0.879 across all datasets.

CONCLUSION

This study validates the potential of topological radiomics in improving the predictive performance for distinguishing between benign and malignant GGNs. By integrating topological features with previous radiomics and clinical parameters, our comprehensive model provides a more accurate and reliable basis for developing treatment strategies for patients with GGNs.

Lung-PNet: An Automated Deep Learning Model for the Diagnosis of Invasive Adenocarcinoma in Pure Ground-Glass Nodules on Chest CT

BACKGROUND. Pure ground-glass nodules (pGGNs) on chest CT representing invasive adenocarcinoma (IAC) warrant lobectomy with lymph node resection. For pGGNs representing other entities, close follow-up or sublobar resection without node dissection may be appropriate. OBJECTIVE. The purpose of this study was to develop and validate an automated deep learning model for differentiation of pGGNs on chest CT representing IAC from those representing atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), and minimally invasive adenocarcinoma (MIA). METHODS. This retrospective study included 402 patients (283 women, 119 men; mean age, 53.2 years) with a total of 448 pGGNs on noncontrast chest CT that were resected from January 2019 to June 2022 and were histologically diagnosed as AAH (n = 29), AIS (n = 83), MIA (n = 235), or IAC (n = 101). Lung-PNet, a 3D deep learning model, was developed for automatic segmentation and classification (probability of IAC vs other entities) of pGGNs on CT. Nodules resected from January 2019 to December 2021 were randomly allocated to training (n = 327) and internal test (n = 82) sets. Nodules resected from January 2022 to June 2022 formed a holdout test set (n = 39). Segmentation performance was assessed with Dice coefficients with radiologists' manual segmentations as reference. Classification performance was assessed by ROC AUC and precision-recall AUC (PR AUC) and compared with that of four readers (three radiologists, one surgeon). The code used is publicly available (https://github.com/XiaodongZhang-PKUFH/Lung-PNet.git). RESULTS. In the holdout test set, Dice coefficients for segmentation of IACs and of other lesions were 0.860 and 0.838, and ROC AUC and PR AUC for classification as IAC were 0.911 and 0.842. At threshold probability of 50.0% or greater for prediction of IAC, Lung-PNet had sensitivity, specificity, accuracy, and F1 score of 50.0%, 92.0%, 76.9%, and 60.9% in the holdout test set. In the holdout test set, accuracy and F1 score (p values vs Lung-PNet) for individual readers were as follows: reader 1, 51.3% (p = .02) and 48.6% (p = .008); reader 2, 79.5% (p = .75) and 75.0% (p = .10); reader 3, 66.7% (p = .35) and 68.3% (p < .001); reader 4, 71.8% (p = .48) and 42.1% (p = .18). CONCLUSION. Lung-PNet had robust performance for segmenting and classifying (IAC vs other entities) pGGNs on chest CT. CLINICAL IMPACT. This automated deep learning tool may help guide selection of surgical strategies for pGGN management.

Predicting visceral pleural invasion in lung adenocarcinoma presenting as part-solid density utilizing a nomogram model combined with radiomics and clinical features

BACKGROUND

To develop and validate a preoperative nomogram model combining the radiomics signature and clinical features for preoperative prediction of visceral pleural invasion (VPI) in lung nodules presenting as part-solid density.

METHODS

We retrospectively reviewed 156 patients with pathologically confirmed invasive lung adenocarcinomas after surgery from January 2016 to August 2019. The patients were split into training and validation sets by a ratio of 7:3. The radiomic features were extracted with the aid of FeAture Explorer Pro (FAE). A CT-based radiomics model was constructed to predict the presence of VPI and internally validated. Multivariable regression analysis was conducted to construct a nomogram model, and the performance of the models were evaluated with the area under the receiver operating characteristic curve (AUC) and compared with each other.

RESULTS

The enrolled patients were split into training (n = 109) and validation sets (n = 47). A total of 806 features were extracted and the selected 10 optimal features were used in the construction of the radiomics model among the 707 stable features. The AUC of the nomogram model was 0.888 (95% CI: 0.762-0.961), which was superior to the clinical model (0.787, 95% CI: 0.643-0.893; p = 0.049) and comparable to the radiomics model (0.879, 95% CI: 0.751-0.965; p > 0.05). The nomogram model achieved a sensitivity of 90.5% and a specificity of 76.9% in the validation dataset.

CONCLUSIONS

The nomogram model could be considered as a noninvasive method to predict VPI with either highly sensitive or highly specific diagnoses depending on clinical needs.

Using clinical and radiomic feature-based machine learning models to predict pathological complete response in patients with esophageal squamous cell carcinoma receiving neoadjuvant chemoradiation

OBJECTIVE

This study aimed to build radiomic feature-based machine learning models to predict pathological clinical response (pCR) of neoadjuvant chemoradiation therapy (nCRT) for esophageal squamous cell carcinoma (ESCC) patients.

METHODS

A total of 112 ESCC patients who underwent nCRT followed by surgical treatment from January 2008 to December 2018 were recruited. According to pCR status (no visible cancer cells in primary cancer lesion), patients were categorized into primary cancer lesion pCR (ppCR) group (N = 65) and non-ppCR group (N = 47). Patients were also categorized into total pCR (tpCR) group (N = 48) and non-tpCR group (N = 64) according to tpCR status (no visible cancer cells in primary cancer lesion or lymph nodes). Radiomic features of pretreatment CT images were extracted, feature selection was performed, machine learning models were trained to predict ppCR and tpCR, respectively.

RESULTS

A total of 620 radiomic features were extracted. For ppCR prediction models, radiomic model had an area under the curve (AUC) of 0.817 (95% CI: 0.732-0.896) in the testing set; and the combination model that included rad-score and clinical features had a great predicting performance, with an AUC of 0.891 (95% CI: 0.823-0.950) in the testing set. For tpCR prediction models, radiomic model had an AUC of 0.713 (95% CI: 0.613-0.808) in the testing set; and the combination model also had a great predicting performance, with an AUC of 0.814 (95% CI: 0.728-0.881) in the testing set.

CONCLUSION

This study built machine learning models for predicting ppCR and tpCR of ESCC patients with favorable predicting performance respectively, which aided treatment plan optimization.

CLINICAL RELEVANCE STATEMENT

This study significantly improved the predictive value of machine learning models based on radiomic features to accurately predict response to therapy of esophageal squamous cell carcinoma patients after neoadjuvant chemoradiation therapy, providing guidance for further treatment.

KEY POINTS

• Combination model that included rad-score and clinical features had a great predicting performance. • Primary tumor pCR predicting models exhibit better predicting performance compared to corresponding total pCR predicting models.

Prediction of subsolid pulmonary nodule growth rate using radiomics

BACKGROUND

Pulmonary nodule growth rate assessment is critical in the management of subsolid pulmonary nodules (SSNs) during clinical follow-up. The present study aimed to develop a model to predict the growth rate of SSNs.

METHODS

A total of 273 growing SSNs with clinical information and 857 computed tomography (CT) scans were retrospectively analyzed. The images were randomly divided into training and validation sets. All images were categorized into fast-growth (volume doubling time (VDT) ≤ 400 days) and slow-growth (VDT > 400 days) groups. Models for predicting the growth rate of SSNs were developed using radiomics and clinical features. The models' performance was evaluated using the area under the curve (AUC) values for the receiver operating characteristic curve.

RESULTS

The fast- and slow-growth groups included 108 and 749 scans, respectively, and 10 radiomics features and three radiographic features (nodule density, presence of spiculation, and presence of vascular changes) were selected to predict the growth rate of SSNs. The nomogram integrating radiomics and radiographic features (AUC = 0.928 and AUC = 0.905, respectively) performed better than the radiographic (AUC = 0.668 and AUC = 0.689, respectively) and radiomics (AUC = 0.888 and AUC = 0.816, respectively) models alone in both the training and validation sets.

CONCLUSION

The nomogram model developed by combining radiomics with radiographic features can predict the growth rate of SSNs more accurately than traditional radiographic models. It can also optimize clinical treatment decisions for patients with SSNs and improve their long-term management.

Invasiveness identification in pure ground-glass nodules: exploring the generalizability of radiomics based on external validation and stress testing

PURPOSE

This study aimed to apply external validation and stress tests to evaluate the generalizability of radiomics models built using various machine-learning methods for identifying the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs).

METHODS

This retrospective study enrolled 495 patients (514 pGGNs) confirmed as lung adenocarcinomas by postoperative pathology from three centers. All nodules were included in the primary cohort (randomly divided into training and test cohorts), two external validation cohorts, and two stress test cohorts. Six machine-learning radiomics models were constructed in the training cohort using the optimal features. Performance of radiomics models and clinical models were compared in primary cohort and external validation cohorts. The stress tests included stratified performance evaluation and shifted performance evaluation and contrastive evaluation under three single-condition modification settings. The predictive performance was validated by area under curve (AUC) of receiver operating characteristic (ROC).

RESULTS

Of the six radiomics models, the best logistic regression (LR) model was able to maintain high differential diagnostic capability (AUC: 0.849 ± 0.049) and good stability (relative standard deviation, 5.719%), but it showed poorer performance (AUC = 0.835) than the clinical model (AUC = 0.862) in the external validation cohort E1. The stress tests suggested LR model had no significant difference in performance between subgroups after stratification and had good consistency in the predictions before and after the three transformations (Kappa = 0.960, 0.840, and 0.933, respectively; p < 0.05, all).

CONCLUSION

The rigorous testing procedure facilitates the selection of high-performance radiomics models with good clinical generalizability.

Body Composition and Radiomics From 18 F-FDG PET/CT Together Help Predict Prognosis for Patients With Stage IV Non-Small Cell Lung Cancer

PURPOSE

To determine whether integration of data on body composition and radiomic features obtained using baseline 18 F-FDG positron emission tomography/computed tomography (PET/CT) images can be used to predict the prognosis of patients with stage IV non-small cell lung cancer (NSCLC).

METHODS

A total of 107 patients with stage IV NSCLC were retrospectively enrolled in this study. We used the 3D Slicer (The National Institutes of Health, Bethesda, Maryland) software to extract the features of PET and CT images. Body composition measurements were taken at the L3 level using the Fiji (Curtis Rueden, Laboratory for Optical and Computational Instrumentation, University of Wisconsin, Madison) software. Independent prognostic factors were defined by performing univariate and multivariate analyses for clinical factors, body composition features, and metabolic parameters. Data on body composition and radiomic features were used to build body composition, radiomics, and integrated (combination of body composition and radiomic features) nomograms. The models were evaluated to determine their prognostic prediction capabilities, calibration, discriminatory abilities, and clinical applicability.

RESULTS

Eight radiomic features relevant to progression-free survival (PFS) were selected. Multivariate analysis showed that the visceral fat area/subcutaneous fat area ratio independently predicted PFS ( P = 0.040). Using the data for body composition, radiomic features, and integrated features, nomograms were established for the training (areas under the curve = 0.647, 0.736, and 0.803, respectively) and the validation sets (areas under the receiver operating characteristic = 0.625, 0.723, and 0.866, respectively); the integrated model showed better prediction ability than that of the other 2 models. The calibration curves revealed that the integrated nomogram exhibited a better agreement between the estimation and the actual observation in terms of prediction of the probability of PFS than that of the other 2 models. Decision curve analysis revealed that the integrated nomogram was superior to the body composition and radiomics nomograms for predicting clinical benefit.

CONCLUSION

Integration of data on body composition and PET/CT radiomic features can help in prediction of outcomes in patients with stage IV NSCLC.

Artificial Intelligence and Lung Cancer: Impact on Improving Patient Outcomes

Lung cancer remains one of the leading causes of cancer-related deaths worldwide, emphasizing the need for improved diagnostic and treatment approaches. In recent years, the emergence of artificial intelligence (AI) has sparked considerable interest in its potential role in lung cancer. This review aims to provide an overview of the current state of AI applications in lung cancer screening, diagnosis, and treatment. AI algorithms like machine learning, deep learning, and radiomics have shown remarkable capabilities in the detection and characterization of lung nodules, thereby aiding in accurate lung cancer screening and diagnosis. These systems can analyze various imaging modalities, such as low-dose CT scans, PET-CT imaging, and even chest radiographs, accurately identifying suspicious nodules and facilitating timely intervention. AI models have exhibited promise in utilizing biomarkers and tumor markers as supplementary screening tools, effectively enhancing the specificity and accuracy of early detection. These models can accurately distinguish between benign and malignant lung nodules, assisting radiologists in making more accurate and informed diagnostic decisions. Additionally, AI algorithms hold the potential to integrate multiple imaging modalities and clinical data, providing a more comprehensive diagnostic assessment. By utilizing high-quality data, including patient demographics, clinical history, and genetic profiles, AI models can predict treatment responses and guide the selection of optimal therapies. Notably, these models have shown considerable success in predicting the likelihood of response and recurrence following targeted therapies and optimizing radiation therapy for lung cancer patients. Implementing these AI tools in clinical practice can aid in the early diagnosis and timely management of lung cancer and potentially improve outcomes, including the mortality and morbidity of the patients.

Effective Invasiveness Recognition of Imbalanced Data by Semi-Automated Segmentations of Lung Nodules

Over the past few decades, recognition of early lung cancers was researched for effective treatments. In early lung cancers, the invasiveness is an important factor for expected survival rates. Hence, how to effectively identify the invasiveness by computed tomography (CT) images became a hot topic in the field of biomedical science. Although a number of previous works were shown to be effective on this topic, there remain some problems unsettled still. First, it needs a large amount of marked data for a better prediction, but the manual cost is high. Second, the accuracy is always limited in imbalance data. To alleviate these problems, in this paper, we propose an effective CT invasiveness recognizer by semi-automated segmentation. In terms of semi-automated segmentation, it is easy for doctors to mark the nodules. Just based on one clicked pixel, a nodule object in a CT image can be marked by fusing two proposed segmentation methods, including thresholding-based morphology and deep learning-based mask region-based convolutional neural network (Mask-RCNN). For thresholding-based morphology, an initial segmentation is derived by adaptive pixel connections. Then, a mathematical morphology is performed to achieve a better segmentation. For deep learning-based mask-RCNN, the anchor is fixed by the clicked pixel to reduce the computational complexity. To incorporate advantages of both, the segmentation is switched between these two sub-methods. After segmenting the nodules, a boosting ensemble classification model with feature selection is executed to identify the invasiveness by equalized down-sampling. The extensive experimental results on a real dataset reveal that the proposed segmentation method performs better than the traditional segmentation ones, which can reach an average dice improvement of 392.3%. Additionally, the proposed ensemble classification model infers better performances than the compared method, which can reach an area under curve (AUC) improvement of 5.3% and a specificity improvement of 14.3%. Moreover, in comparison with the models with imbalance data, the improvements of AUC and specificity can reach 10.4% and 33.3%, respectively.

KD_ConvNeXt: knowledge distillation-based image classification of lung tumor surgical specimen sections

Introduction: Lung cancer is currently among the most prevalent and lethal cancers in the world in terms of incidence and fatality rates. In clinical practice, identifying the specific subtypes of lung cancer is essential in diagnosing and treating lung lesions. Methods: This paper aims to collect histopathological section images of lung tumor surgical specimens to construct a clinical dataset for researching and addressing the classification problem of specific subtypes of lung tumors. Our method proposes a teacher-student network architecture based on a knowledge distillation mechanism for the specific subtype classification of lung tumor histopathological section images to assist clinical applications, namely KD_ConvNeXt. The proposed approach enables the student network (ConvNeXt) to extract knowledge from the intermediate feature layers of the teacher network (Swin Transformer), improving the feature extraction and fitting capabilities of ConvNeXt. Meanwhile, Swin Transformer provides soft labels containing information about the distribution of images in various categories, making the model focused more on the information carried by types with smaller sample sizes while training. Results: This work has designed many experiments on a clinical lung tumor image dataset, and the KD_ConvNeXt achieved a superior classification accuracy of 85.64% and an F1-score of 0.7717 compared with other advanced image classification methods.

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.

The predictive value of a computed tomography-based radiomics model for the surgical separability of thymic epithelial tumors from the superior vena cava and the left innominate vein

Background

The aim of this study was to develop a radiomics machine learning model based on computed tomography (CT) that can predict whether thymic epithelial tumors (TETs) can be separated from veins during surgery and to compare the accuracy of the radiomics model to that of radiologists.

Methods

Patients who underwent thymectomy at our hospital from 2009 to 2017 were included in the screening process. After the selection of patients according to the inclusion and exclusion criteria, the cohort was randomly divided into training and testing groups, and CT images of these patients were collected. Subsequently, two-dimensional (2D) and three-dimensional (3D) regions of interest were labelled using ITK-SNAP 3.8.0 software, and Radiomics features were extracted using Python software (Python Software Foundation) and selected through the least absolute shrinkage and selection operator (LASSO) regression model. To construct the classifier, a support vector machine (SVM) was employed, and a nomogram was created using logistic regression to predict vascular inseparable TETs based on the radiomics score (radscore) and image features. To assess the accuracy of these models, area under receiver operating characteristic (ROC) curves of these models were calculated, and differences among the models were identified using the Delong test.

Results

In this retrospective study, 204 patients with TETs were included, among whom 21 were diagnosed with surgical vascularly inseparable TETs. The area under ROC curve (AUC) of the 2D model, 3D model, 2D + 3D model, and radiologist diagnoses were 0.94, 0.92, 0.95, and 0.87 in the training cohort and 0.95, 0.92, 0.98, and 0.78 in testing cohort, respectively. The Delong test revealed a significant improvement in the performance of the radiomics models compared to radiologists' diagnoses. The logistic regression selected 3 image features, namely maximum diameter of the tumor, degree of abutment of vessel circumference >50%, and absence of the mediastinal fat layer or space between the tumor and surrounding structures. These features, along with the radscore, were included to develop a nomogram. The AUCs of this nomogram were 0.99 in both the training set and testing set, and the Delong test did not find a significant difference between ROC plots of the nomogram and radiomics models.

Conclusions

The proposed radiomics model could accurately predict surgical vascularly inseparable TETs preoperatively and was shown to have a higher predictive value than the radiologists.

Dual-energy CT-based radiomics for predicting invasiveness of lung adenocarcinoma appearing as ground-glass nodules

Objectives

To explore the value of radiomics based on Dual-energy CT (DECT) for discriminating preinvasive or MIA from IA appearing as GGNs before surgery.

Methods

The retrospective study included 92 patients with lung adenocarcinoma comprising 30 IA and 62 preinvasive-MIA, which were further divided into a training (n=64) and a test set (n=28). Clinical and radiographic features along with quantitative parameters were recorded. Radiomics features were derived from virtual monoenergetic images (VMI), including 50kev and 150kev images. Intraclass correlation coefficients (ICCs), Pearson's correlation analysis and least absolute shrinkage and selection operator (LASSO) penalized logistic regression were conducted to eliminate unstable and redundant features. The performance of the models was evaluated by area under the curve (AUC) and the clinical utility was assessed using decision curve analysis (DCA).

Results

The DECT-based radiomics model performed well with an AUC of 0.957 and 0.865 in the training and test set. The clinical-DECT model, comprising sex, age, tumor size, density, smoking, alcohol, effective atomic number, and normalized iodine concentration, had an AUC of 0.929 in the training and 0.719 in the test set. In addition, the radiomics model revealed a higher AUC value and a greater net benefit to patients than the clinical-DECT model.

Conclusion

DECT-based radiomics features were valuable in predicting the invasiveness of GGNs, yielding a better predictive performance than the clinical-DECT model.

CT-based radiomics models may predict the early efficacy of microwave ablation in malignant lung tumors

PURPOSE

To establish and validate radiomics models for predicting the early efficacy (less than 3 months) of microwave ablation (MWA) in malignant lung tumors.

METHODS

The study enrolled 130 malignant lung tumor patients (72 in the training cohort, 32 in the testing cohort, and 26 in the validation cohort) treated with MWA. Post-operation CT images were analyzed. To evaluate the therapeutic effect of ablation, three models were constructed by least absolute shrinkage and selection operator and logistic regression: the tumoral radiomics (T-RO), peritumoral radiomics (P-RO), and tumoral-peritumoral radiomics (TP-RO) models. Univariate and multivariate analyses were performed to identify clinical variables and radiomics features associated with early efficacy, which were incorporated into the combined radiomics (C-RO) model. The performance of the C-RO model was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve, and decision curve analysis (DCA). The C-RO model was used to derive the best cutoff value of ROC and to distinguish the high-risk group (Nomo-score of C-RO model below than cutoff value) from the low-risk group (Nomo-score of C-RO model higher than cutoff value) for survival analysis of patients.

RESULTS

Four radiomics features were selected from the region of interest of tumoral and peritumoral CT images, which showed good performance for evaluating prognosis and early efficacy in three cohorts. The C-RO model had the highest AUC value in all models, and the C-RO model was better than the P-RO model (AUC in training, 0.896 vs. 0.740; p = 0.036). The DCA confirmed the clinical benefit of the C-RO model. Survival analysis revealed that in the C-RO model, the low-risk group defined by best cutoff value had significantly better progression-free survival than the high-risk group (p<0.05).

CONCLUSIONS

CT-based radiomics models in malignant lung tumor patients after MWA could be useful for individualized risk classification and treatment.

Value of contrast-enhanced magnetic resonance imaging-T2WI-based radiomic features in distinguishing lung adenocarcinoma from lung squamous cell carcinoma with solid components >8 mm

Background

Radiomics is one of the research frontiers in the field of imaging and has excellent diagnostic performance. However, there is a lack of magnetic resonance imaging (MRI)-based omics studies on identifying pathological subtypes of lung cancer. Here we explored the value of the contrast-enhanced MRI-T2-weighted imaging (T2WI)-based radiomic analysis in distinguishing adenocarcinoma (Ade) from squamous cell carcinoma (Squ) with solid components >8 mm.

Methods

A retrospective analysis was performed of a total of 71 lung cancer patients who undergoing contrast-enhanced MRI and computed tomography (CT) before treatment, and the nodules had solid components ≥8 mm in our center from January 2020 to September 2021. All enrolled patients were divided into Squ and Ade groups according to the pathological results. In addition, the two groups were randomly divided into training set and validation set in a ratio of about 7:3. Radiomics software was used to extract the relevant radiomic features. The least absolute shrinkage and selection operator (Lasso) was used to screen radiomic features that were most relevant to lung cancer subtypes, thus calculating the radiomic scores (Rad-score) and constructing the radiomic models. Multivariate logistic regression was used to combine relevant clinical features with Rad-score to form combined model nomograms. The receiver operating characteristic (ROC) curves. the area under the ROC curve (AUC), the decision curve analysis (DCA) and the DeLong's test were used to evaluate the clinical application potentials.

Results

The sensitivity and specificity of the clinical model based on smoking was 75.0% and 93.8%. The AUC of the constructed magnetic resonance (MR)-Rad model for differentiating the pathological subtypes of lung cancer was 0.8651 in the validation sets. The AUC of the CT-Rad model in the validation set were 0.9286. The combined model constructed by combining clinical features and Rad-score had AUC of 0.8016, for identifying the 2 pathological subtypes of lung cancer in the validation set. There was no significant difference in diagnostic performance between MR-Rad model and CT-Rad model (P>0.05).

Conclusions

The MR-Rad model has a diagnostic performance similar to that of CT-Rad model, while the diagnostic performance of the combined mode was better than the single MR model.

Diagnosis of Acute Aortic Syndromes on Non-Contrast CT Images with Radiomics-Based Machine Learning

We aimed to detect acute aortic syndromes (AAS) on non-contrast computed tomography (NCCT) images using a radiomics-based machine learning model. A total of 325 patients who underwent aortic CT angiography (CTA) were enrolled retrospectively from 2 medical centers in China to form the internal cohort (230 patients, 60 patients with AAS) and the external testing cohort (95 patients with AAS). The internal cohort was divided into the training cohort (n = 135), validation cohort (n = 49), and internal testing cohort (n = 46). The aortic mask was manually delineated on NCCT by a radiologist. Least Absolute Shrinkage and Selection Operator regression (LASSO) was used to filter out nine feature parameters; the Support Vector Machine (SVM) model showed the best performance. In the training and validation cohorts, the SVM model had an area under the curve (AUC) of 0.993 (95% CI, 0.965–1); accuracy (ACC), 0.946 (95% CI, 0.877–1); sensitivity, 0.9 (95% CI, 0.696–1); and specificity, 0.964 (95% CI, 0.903–1). In the internal testing cohort, the SVM model had an AUC of 0.997 (95% CI, 0.992–1); ACC, 0.957 (95% CI, 0.945–0.988); sensitivity, 0.889 (95% CI, 0.888–0.889); and specificity, 0.973 (95% CI, 0.959–1). In the external testing cohort, the ACC was 0.991 (95% CI, 0.937–1). This model can detect AAS on NCCT, reducing misdiagnosis and improving examinations and prognosis.

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.

An integrated nomogram combined semantic-radiomic features to predict invasive pulmonary adenocarcinomas in subjects with persistent subsolid nodules

Background

Patients with persistent pulmonary subsolid nodules have a relatively high incidence of lung adenocarcinoma. Preoperative early diagnosis of invasive pulmonary adenocarcinoma spectrum lesions could help avoid extensive advanced cancer management and overdiagnosis in lung cancer screening programs.

Methods

In total, 260 consecutive patients with persistent subsolid nodules ≤30 mm (n=260) confirmed by surgical pathology were retrospectively investigated from February 2016 to August 2020 at the Kaohsiung Veterans General Hospital. All patients underwent surgical resection within 3 months of the chest CT exam. The study subjects were divided into a training cohort (N=195) and a validation cohort (N=65) at a ratio of 3:1. The purpose of our study was to develop and validate a least absolute shrinkage and selection operator-derived nomogram integrating semantic-radiomic features in differentiating preinvasive and invasive pulmonary adenocarcinoma lesions, and compare its predictive value with clinical-semantic, semantic, and radiologist's performance.

Results

In the training cohort of 195 subsolid nodules, 106 invasive lesions and 89 preinvasive lesions were identified. We developed a least absolute shrinkage and selection operator-derived combined nomogram prediction model based on six predictors (nodular size, CTR, roundness, GLCM_Entropy_log10, HISTO_Entropy_log10, and CONVENTIONAL_Humean) to predict the invasive pulmonary adenocarcinoma lesions. Compared with other predictive models, the least absolute shrinkage and selection operator-derived model showed better diagnostic performance with an area under the curve of 0.957 (95% CI: 0.918 to 0.981) for detecting invasive pulmonary adenocarcinoma lesions with balanced sensitivity (92.45%) and specificity (88.64%). The results of Hosmer-Lemeshow test showed P values of 0.394 and 0.787 in the training and validation cohorts, respectively, indicating good calibration power.

Conclusions

We developed a least absolute shrinkage and selection operator-derived model integrating semantic-radiomic features with good calibration. This nomogram may help physicians to identify invasive pulmonary adenocarcinoma lesions for guidance in personalized medicine and make more informed decisions on managing subsolid nodules.

Computed Tomography Findings for Predicting Invasiveness of Lung Adenocarcinomas Manifesting as Pure Ground-Glass Nodules

Purpose: To comprehensively evaluate qualitative and quantitative features for predicting invasiveness of pure ground-glass nodules (pGGNs) using multiplanar computed tomography. Methods: Ninety-three resected pGGNs (16 atypical adenomatous hyperplasia [AAH], 18 adenocarcinoma in situ [AIS], 31 minimally invasive adenocarcinoma [MIA], and 28 invasive adenocarcinoma [IA]) were retrospectively included. Two radiologists analyzed qualitative and quantitative features on three standard planes. Univariable and multivariable logistic regression analyses were performed to identify features to distinguish the pre-invasive (AAH/AIS) from the invasive (MIA/IA) group. Results: Tumor size showed high area under the curve (AUC) for predicting invasiveness (.860, .863, .874, and .893, for axial long diameter [AXLD], multiplanar long diameter, mean diameter, and volume, respectively). The AUC for AXLD (cutoff, 11 mm) was comparable to that of the volume (P = .202). The invasive group had a significantly higher number of qualitative features than the pre-invasive group, regardless of tumor size. Six out of 59 invasive nodules (10.2%) were smaller than 11 mm, and all had at least one qualitative feature. pGGNs smaller than 11 mm without any qualitative features (n = 16) were all pre-invasive. In multivariable analysis, AXLD, vessel change, and the presence or number of qualitative features were independent predictors for invasiveness. The model with AXLD and the number of qualitative features achieved the highest AUC (.902, 95% confidence interval .833-.971). Conclusion: In adenocarcinomas manifesting as pGGNs on computed tomography, AXLD and the number of qualitative features are independent risk factors for invasiveness; small pGGNs (<11 mm) without qualitative features have low probability of invasiveness.

Quantitative evaluation of density variability in the lesion-lung boundary zone to differentiate pulmonary subsolid nodules

Background

Transition of the CT values from nodule to peripheral normal lung is related to pathological changes and may be a potential indicator for differential diagnosis. This study investigated the significance of the standard deviation (SD) values in the lesion-lung boundary zone when differentiating between benign and neoplastic subsolid nodules (SSNs).

Methods

From January 2012 to July 2021, a total of 229 neoplastic and 84 benign SSNs confirmed by pathological examination were retrospectively and nonconsecutively enrolled in this study. The diagnostic study was not registered with a clinical trial platform, and the study protocol was not published. Computed tomography (CT) values of the ground-glass component (CT1), adjacent normal lung tissue (CT2), and lesion-lung boundary zone (CT3) were measured consecutively. The SD of CT3 was recorded to assess density variability. The CT1, CT2, CT3, and SD values were compared between benign and neoplastic SSNs.

Results

No significant differences in CT1 and CT2 were observed between benign and neoplastic SSNs (each P value >0.05). CT3 (-736.1±51.0 vs. -792.6±73.9; P<0.001) and its SD (135.6±29.6 vs. 83.6±20.6; P<0.001) in neoplastic SSNs were significantly higher than those in benign SSNs. Moreover, the SD increased with the invasiveness degree of neoplastic SSNs (r=0.657; P<0.001). The receiver operating characteristic (ROC) curve revealed that the area under the curve was 0.927 (95% CI: 0.896-0.959) when using the SD (cutoff value =106.98) as a factor to distinguish SSNs, which increased to 0.966 (95% CI: 0.934-0.985) when including nodules with a CT1 of ≥-715 Hounsfield units (HU) only (cutoff of SD 109.9, sensitivity 0.930, and specificity 0.914).

Conclusions

The SD as an objective index is valuable for differentiating SSNs, especially for those with a CT1 of ≥-715 HU, which have a higher possibility of neoplasm if the SD is >109.9.

Deep learning based dental implant failure prediction from periapical and panoramic films

Background

Dental implant failure is a critical condition that can seriously compromise therapeutic efficacy. Insufficient bone volume, unfavorable bone quality, periodontal bone loss, and systemic conditions, including osteopenia/osteoporosis and diabetes mellitus, have been associated with implant failure. Early indicators of potential implant failure could help mitigate the risk of severe complications. This study aimed to develop an effective implant outcome prediction model using dental periapical and panoramic films.

Methods

A total of 248 patients (89 with failed implants and 159 with successful implants) were examined. A total of 529 periapical images and 551 panoramic images were collected from the patients for a deep learning-based model. Based on radiographic peri-implant alveolar bone pattern, implant outcome was divided into three categories: implant failure with marginal bone loss, implant failure without marginal bone loss, and implant success. We extracted features using a deep convolutional neural network (CNN) and built a hybrid model to combine periapical and panoramic images. A comparison among three categories of receiver operating characteristic (ROC) curves was performed. The diagnostic accuracy, precision, recall and F1-score of the dataset were assessed.

Results

Our model achieved an AUC (area under the ROC curve) of 0.972 for failure with marginal bone loss, 0.947 for failure without marginal bone loss and 0.975 for success. In all conditions, for periapical images alone, the diagnostic accuracy was 78.6%; the precision was 0.84, recall was 0.73, and F1-score was 0.75. For panoramic images alone, the diagnostic accuracy was 78.7%; the precision was 0.87, recall was 0.63, and F1-score was 0.66. Both periapical and panoramic images were used in our novel method, and the prediction accuracy was 87%. The precision was 0.85, recall was 0.88, and F1-score was 0.85.

Conclusions

The deep learning model used features from periapical and panoramic images to effectively predict the occurrence of implant failure and might facilitate early clinical intervention for potential dental implant failures.

Artificial intelligence-based radiomics for the prediction of nodal metastasis in early-stage lung cancer

We aimed to investigate the value of computed tomography (CT)-based radiomics with artificial intelligence (AI) in predicting pathological lymph node metastasis (pN) in patients with clinical stage 0-IA non-small cell lung cancer (c-stage 0-IA NSCLC). This study enrolled 720 patients who underwent complete surgical resection for c-stage 0-IA NSCLC, and were assigned to the derivation and validation cohorts. Using the AI software Beta Version (Fujifilm Corporation, Japan), 39 AI imaging factors, including 17 factors from the AI ground-glass nodule analysis and 22 radiomics features from nodule characterization analysis, were extracted to identify factors associated with pN. Multivariate analysis showed that clinical stage IA3 (p = 0.028), solid-part size (p < 0.001), and average solid CT value (p = 0.033) were independently associated with pN. The receiver operating characteristic analysis showed that the area under the curve and optimal cut-off values of the average solid CT value relevant to pN were 0.761 and -103 Hounsfield units, and the threshold provided sensitivity, specificity, and negative predictive values of 69%, 65%, and 94% in the entire cohort, respectively. Measuring the average solid-CT value of tumors for pN may have broad applications such as guiding individualized surgical approaches and postoperative treatment.

Computed tomography-based radiomics machine learning models for prediction of histological invasiveness with sub-centimeter subsolid pulmonary nodules: a retrospective study

To improve the accuracy of preoperative diagnoses and avoid over- or undertreatment, we aimed to develop and compare computed tomography-based radiomics machine learning models for the prediction of histological invasiveness using sub-centimeter subsolid pulmonary nodules. Three predictive models based on radiomics were built using three machine learning classifiers to discriminate the invasiveness of the sub-centimeter subsolid pulmonary nodules. A total of 203 sub-centimeter nodules from 177 patients were collected and assigned randomly to the training set (n = 143) or test set (n = 60). The areas under the curve of the predictive models were 0.743 (95% confidence interval CI [0.661-0.824]) for the logistic regression, 0.828 (95% CI [0.76-0.896]) for the support vector machine, and 0.917 (95% CI [0.869-0.965]) for the XGBoost classifier models in the training set, and 0.803 (95% CI [0.694-0.913]), 0.726 (95% CI [0.598-0.854]), and 0.874 (95% CI [0.776-0.972]) in the test set, respectively. In addition, the decision curve showed that the XGBoost model added more net benefit within the range of 0.06 to 0.93.