Prediction of future imagery of lung nodule as growth modeling with follow-up computed tomography scans using deep learning: a retrospective cohort study

Lung cancer detection based on computed tomography image using convolutional neural networks

BACKGROUND

Lung cancer is the most common type of cancer, accounting for 12.8% of cancer cases worldwide. As initially non-specific symptoms occur, it is difficult to diagnose in the early stages.

OBJECTIVE

Image processing techniques developed using machine learning methods have played a crucial role in the development of decision support systems. This study aimed to classify benign and malignant lung lesions with a deep learning approach and convolutional neural networks (CNNs).

METHODS

The image dataset includes 4459 Computed tomography (CT) scans (benign, 2242; malignant, 2217). The research type was retrospective; the case-control analysis. A method based on GoogLeNet architecture, which is one of the deep learning approaches, was used to make maximum inference on images and minimize manual control.

RESULTS

The dataset used to develop the CNNs model is included in the training (3567) and testing (892) datasets. The model's highest accuracy rate in the training phase was estimated as 0.98. According to accuracy, sensitivity, specificity, positive predictive value, and negative predictive values of testing data, the highest classification performance ratio was positive predictive value with 0.984.

CONCLUSION

The deep learning methods are beneficial in the diagnosis and classification of lung cancer through computed tomography images.

Parameterized Gompertz-Guided Morphological AutoEncoder for Predicting Pulmonary Nodule Growth

The growth rate of pulmonary nodules is a critical clue to the cancerous diagnosis. It is essential to monitor their dynamic progressions during pulmonary nodule management. To facilitate the prosperity of research on nodule growth prediction, we organized and published a temporal dataset called NLSTt with consecutive computed tomography (CT) scans. Based on the self-built dataset, we develop a visual learner to predict the growth for the following CT scan qualitatively and further propose a model to predict the growth rate of pulmonary nodules quantitatively, so that better diagnosis can be achieved with the help of our predicted results. To this end, in this work, we propose a parameterized Gempertz-guided morphological autoencoder (GM-AE) to generate any future-time-span high-quality visual appearances of pulmonary nodules from the baseline CT scan. Specifically, we parameterize a popular mathematical model for tumor growth kinetics, Gompertz, to predict future masses and volumes of pulmonary nodules. Then, we exploit the expected growth rate on the mass and volume to guide decoders generating future shape and texture of pulmonary nodules. We introduce two branches in an autoencoder to encourage shape-aware and textural-aware representation learning and integrate the generated shape into the textural-aware branch to simulate the future morphology of pulmonary nodules. We conduct extensive experiments on the self-built NLSTt dataset to demonstrate the superiority of our GM-AE to its competitive counterparts. Experiment results also reveal the learnable Gompertz function enjoys promising descriptive power in accounting for inter-subject variability of the growth rate for pulmonary nodules. Besides, we evaluate our GM-AE model on an in-house dataset to validate its generalizability and practicality. We make its code publicly available along with the published NLSTt dataset.

Radiomics-based Machine Learning Methods for Volume Doubling Time Prediction of Pulmonary Ground-glass Nodules With Baseline Chest Computed Tomography

PURPOSE

Reliable prediction of volume doubling time (VDT) is essential for the personalized management of pulmonary ground-glass nodules (GGNs). We aimed to determine the optimal VDT prediction method by comparing different machine learning methods only based on the baseline chest computed tomography (CT) images.

MATERIALS AND METHODS

Seven classical machine learning methods were evaluated in terms of their stability and performance for VDT prediction. The VDT, calculated by the preoperative and baseline CT, was divided into 2 groups with a cutoff value of 400 days. A total of 90 GGNs from 3 hospitals constituted the training set, and 86 GGNs from the fourth hospital served as the external validation set. The training set was used for feature selection and model training, and the validation set was used to evaluate the predictive performance of the model independently.

RESULTS

The eXtreme Gradient Boosting showed the highest predictive performance (accuracy: 0.890±0.128 and area under the ROC curve (AUC): 0.896±0.134), followed by the neural network (NNet) (accuracy: 0.865±0.103 and AUC: 0.886±0.097). While regarding stability, the NNet showed the highest robustness against data perturbation (relative SDs [%] of mean AUC: 10.9%). Therefore, the NNet was chosen as the final model, achieving high accuracy of 0.756 in the external validation set.

CONCLUSION

The NNet is a promising machine learning method to predict the VDT of GGNs, which would assist in the personalized follow-up and treatment strategies for GGNs reducing unnecessary follow-up and radiation dose.

Establishment and visualization of a model based on high-resolution CT qualitative and quantitative features for prediction of micropapillary or solid components in invasive lung adenocarcinoma

OBJECTIVE

To predict the existence of micropapillary or solid components in invasive adenocarcinoma, a model was constructed using qualitative and quantitative features in high-resolution computed tomography (HRCT).

METHODS

Through pathological examinations, 176 lesions were divided into two groups depending on the presence or absence of micropapillary and/or solid components (MP/S): MP/S- group (n = 128) and MP/S + group (n = 48). Multivariate logistic regression analyses were used to identify independent predictors of the MP/S. Artificial intelligence (AI)-assisted diagnostic software was used to automatically identify the lesions and extract corresponding quantitative parameters on CT images. The qualitative, quantitative, and combined models were constructed according to the results of multivariate logistic regression analysis. The receiver operating characteristic (ROC) analysis was conducted to evaluate the discrimination capacity of the models with the area under the curve (AUC), sensitivity, and specificity calculated. The calibration and clinical utility of the three models were determined using the calibration curve and decision curve analysis (DCA), respectively. The combined model was visualized in a nomogram.

RESULTS

The multivariate logistic regression analysis using both qualitative and quantitative features indicated that tumor shape (P =  0.029 OR =  4.89; 95% CI 1.175-20.379), pleural indentation (P = 0.039 OR =  1.91; 95% CI 0.791-4.631), and consolidation tumor ratios (CTR) (P < 0.001; OR = 1.05; 95% CI 1.036-1.070) were independent predictors for MP/S + . The areas under the curve (AUC) of the qualitative, quantitative, and combined models in predicting MP/S + were 0.844 (95% CI 0.778-0.909), 0.863 (95% CI 0.803-0.923), and 0.880 (95% CI 0.824-0.937). The combined model of AUC was the most superior and statistically better than qualitative model.

CONCLUSION

The combined model could assist doctors to evaluate patient's prognoses and devise personalized diagnostic and treatment protocols for patients.

Growth assessment of pure ground-glass nodules on CT: comparison of density and size measurement methods

PURPOSE

To investigate the differences of size and density measurements in assessing pure ground-glass nodules (pGGNs) growth, and compare the growth rates and growth proportions of the two methods during follow-up period.

METHODS

Ninety patients with at least 3 consecutive thin-section chest CTs and confirmed 103 pGGNs on baseline CT were enrolled retrospectively. Using the two definitions of size and density to evaluate pGGNs growth with semi-automated segmentation. Then, the two methods were compared to assess differences in pGGNs growth.

RESULTS

For the size and density methods to assess nodule growth, 50.5% and 26.2% showed interval growth at the last CT (p < 0.001). Among the 19 nodules that grew in both size and density, the volume doubling time (VDT) of solid component (mean, 317.1; standard deviation, 224.8 days) was shorter than total VDT (median, 942.8; range, 400.1-2315.9 days) (p < 0.001). Of the 27 growth pGGNs assessed by the density method, the growth rates at years 1 and 2 were 25.9% and 63.0%, while the growth rates of 52 growing nodules assessed by size method were 11.5% and 48.1%, respectively. Twenty of 103 (19.4%) nodules were classified into category 4A lesions, and 7 (6.8%) were 4B lesions.

CONCLUSION

Compared to size measurements, observed density increases have a higher proportion of early growth and faster growth rates in growing nodules. Clinicians need to pay close attention to the nodules of new solid components and make timely decision management.

The natural growth history of persistent pulmonary subsolid nodules: Radiology, genetics, and clinical management

The high detection rate of pulmonary subsolid nodules (SSN) is an increasingly crucial clinical issue due to the increased number of screening tests and the growing popularity of low-dose computed tomography (LDCT). The persistence of SSN strongly suggests the possibility of malignancy. Guidelines have been published over the past few years and guide the optimal management of SSNs, but many remain controversial and confusing for clinicians. Therefore, in-depth research on the natural growth history of persistent pulmonary SSN can help provide evidence-based medical recommendations for nodule management. In this review, we briefly describe the differential diagnosis, growth patterns and rates, genetic characteristics, and factors that influence the growth of persistent SSN. With the advancement of radiomics and artificial intelligence (AI) technology, individualized evaluation of SSN becomes possible. These technologies together with liquid biopsy, will promote the transformation of current diagnosis and follow-up strategies and provide significant progress in the precise management of subsolid nodules in the early stage of lung cancer.

Deep learning-based growth prediction for sub-solid pulmonary nodules on CT images

Background

Estimating the growth of pulmonary sub-solid nodules (SSNs) is crucial to the successful management of them during follow-up periods. The purpose of this study is to (1) investigate the measurement sensitivity of diameter, volume, and mass of SSNs for identifying growth and (2) seek to establish a deep learning-based model to predict the growth of SSNs.

Methods

A total of 2,523 patients underwent at least 2-year examination records retrospectively collected with sub-solid nodules. A total of 2,358 patients with 3,120 SSNs from the NLST dataset were randomly divided into training and validation sets. Patients from the Yibicom Health Management Center and Guangdong Provincial People’s Hospital were collected as an external test set (165 patients with 213 SSN). Trained models based on LUNA16 and Lndb19 datasets were employed to automatically obtain the diameter, volume, and mass of SSNs. Then, the increase rate in measurements between cancer and non-cancer groups was studied to evaluate the most appropriate way to identify growth-associated lung cancer. Further, according to the selected measurement, all SSNs were classified into two groups: growth and non-growth. Based on the data, the deep learning-based model (SiamModel) and radiomics model were developed and verified.

Results

The double time of diameter, volume, and mass were 711 vs. 963 days (P = 0.20), 552 vs. 621 days (P = 0.04) and 488 vs. 623 days (P< 0.001) in the cancer and non-cancer groups, respectively. Our proposed SiamModel performed better than the radiomics model in both the NLST validation set and external test set, with an AUC of 0.858 (95% CI 0.786–0.921) and 0.760 (95% CI 0.646–0.857) in the validation set and 0.862 (95% CI 0.789–0.927) and 0.681 (95% CI 0.506–0.841) in the external test set, respectively. Furthermore, our SiamModel could use the data from first-time CT to predict the growth of SSNs, with an AUC of 0.855 (95% CI 0.793–0.908) in the NLST validation set and 0.821 (95% CI 0.725–0.904) in the external test set.

Conclusion

Mass increase rate can reflect more sensitively the growth of SSNs associated with lung cancer than diameter and volume increase rates. A deep learning-based model has a great potential to predict the growth of SSNs.

Correlation Analysis of Computed Tomography Features and Pathological Types of Multifocal Ground-Glass Nodular Lung Adenocarcinoma

To investigate the correlation between computed tomography (CT) image characteristics of multiple lung ground-glass nodules (GGNs) and pathological classification, the CT image data of multiple lung GGN patients confirmed by pathology (n = 132) in our hospital were collected. The imaging features of GGNs were analyzed by qualified physicians, including lesion size (diameter, volume, and mass), location, CT values (mean and relative CT values), lesion morphology (round and irregular), marginal structure (pagination and burr), internal structure (bronchial inflation sign), and adjacent structure (pleural depression). CT imaging analysis was performed for the subtype of infiltrating adenocarcinoma (IAC). In CT findings, GGNs were greatly different from adenomatous hyperplasia (AAH), pure GGN adenocarcinoma in situ (AIS), and microinvasive adenocarcinoma (MIA) in terms of marginal structure, lesion morphology, internal structure, adjacent structure, and size (P < 0.05). The mean and relative CT values of mural adenocarcinoma, acinar adenocarcinoma, and papillary adenocarcinoma of IAC subtypes were greatly different from those of AAH/AIS/MIA (P < 0.05). In summary, the CT images of GGNs can be used as the basis for the differentiation of AAH, AIS, and MIA early noninvasive types and IAC invasive types, and the CT value of the IAC subtype can be used as the basis for the classification and differentiation of IAC pathological subtypes.