Lung cancer screening: how do we make it better?

Effect of Deep Learning Image Reconstruction Algorithms on Radiomic Features of Pulmonary Nodules in Ultra-Low-Dose CT

OBJECTIVE

The purpose of this study is to explore the impact of deep learning image reconstruction (DLIR) algorithm on the quantification of radiomic features in ultra-low-dose computed tomography (ULD-CT) compared with adaptive statistical iterative reconstruction-Veo (ASIR-V).

METHODS

One hundred eighty-three patients with pulmonary nodules underwent standard-dose computed tomography (SDCT) (4.30 ± 0.36 mSv) and ULD-CT (UL-A, 0.57 ± 0.09 mSv or UL-B, 0.33 ± 0.04 mSv). SDCT was the reference standard using (ASIR-V) at 50% strength (50%ASIR-V). ULD-CT was reconstructed with 50%ASIR-V, DLIR at medium and high strength (DLIR-M, DLIR-H). Radiomics analysis extracted 102 features, and the intraclass correlation coefficient (ICC) quantified reproducibility between ULD-CT and SDCT reconstructed by 50%ASIR-V, DLIR-M, and DLIR-H for each feature.

RESULTS

Among 102 radiomic features, the percentages of reproducibility of 50%ASIR-V, DLIR-M, and DLIR-H were 48.04% (49/102), 49.02% (50/102), and 52.94% (54/102), respectively. Shape and first order features demonstrated high reproducibility across different reconstruction algorithms and radiation doses, with mean ICC values exceeding 0.75. In texture features, DLIR-M and DLIR-H showed improved mean ICC values for pure ground glass nodules (pGGNs) from 0.69 ± 0.23 to 0.75 ± 0.18 and 0.81 ± 0.12, respectively, compared with 50%ASIR-V. Similarly, the mean ICC values for solid nodules (SNs) increased from 0.60 ± 0.19 to 0.66 ± 0.14 and 0.69 ± 0.13, respectively. Additionally, the mean ICC values of texture features for pGGNs and SNs in both ULD-CT groups decreased with reduced radiation dose.

CONCLUSIONS

DLIR can improve the reproducibility of radiomic features at ultra-low doses compared with ASIR-V. In addition, pGGNs showed better reproducibility at ultra-low doses than SNs.

Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals

As one of the most reliable and significant indicators, Chronic Obstructive Pulmonary Disease (COPD) becomes a robust predictor of lung cancer early detection, the world's leading cause of cancer death. One of the methods is to analyze the Volatile Organic Compounds (VOCs) in exhaled breath using electronic noses (E-noses), which have become emerging tools for analyzing breath because of their potential and promising technology for diagnosing. However, the signal processing of the E-Nose sensor becomes vital in exposing information about the subject condition, which most researchers strive to accomplish. We proposed a Convolutional Neural Network (CNN) architecture to classify COPD in smokers and non-smokers, healthy subjects, and smokers from E-Nose signals to contribute to this field. Two models were constructed following E-Nose signal processing state-of-the-arts. One was by combined feature extraction and classifier, and the second was by CNN, which directly processed the raw signal. In addition, various feature extraction and classifier (Machine Learning and CNN) used in prior research were investigated. Using 3K and 5K Fold cross-validation results demonstrated that our proposed models outperformed in Kernel Principal Component Analysis (KPCA) with Fx-ConvNet and Pure-ConvNet. They all reached maximum F1-Score with zero standard deviation values indicating a consistent result. Further experiments also showed that KPCA contributed to the increasing performance of some classifiers with average F1-Score 0.933 and 0.068 as standard deviation values.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Establishment and verification of a prediction model based on clinical characteristics and positron emission tomography/computed tomography (PET/CT) parameters for distinguishing malignant from benign ground-glass nodules

Background

To develop and verify a prediction model for distinguishing malignant from benign ground-glass nodules (GGNs) combined with clinical characteristics and ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography-computed tomography (PET/CT) parameters.

Methods

We retrospectively analyzed 170 patients (56 males and 114 females) with GGNs who underwent PET/CT and high-resolution CT examination in our hospital from November 2011 to December 2019. The clinical and imaging data of all patients were collected, and the nodules were randomly divided into a derivation set and a validation set. For the derivation set, we used multivariate logistic regression to develop a prediction model for distinguishing benign from malignant GGNs. A receiver operating characteristic (ROC) curve was used to evaluate the diagnostic efficacy of the model, and the data in the validation set were used to verify the prediction model.

Results

Among the 170 patients, 197 GGNs were confirmed via postoperative pathological examination or clinical follow-up. There were 21 patients with 27 GGNs in the benign group and 149 patients with 170 GGNs in the adenocarcinoma group. A total of five parameters, including the patient's sex, nodule location, margin, pleural indentation, and standardized uptake value (SUV) index (the ratio of nodule SUVmax to liver SUVmean), were selected to develop a prediction model for distinguishing benign from malignant GGNs. The area under the curve (AUC) of the model was 0.875 in the derivation set, with a sensitivity of 0.702 and a specificity of 0.923. The positive likelihood ratio was 9.131, and the negative likelihood ratio was 0.322. In the validation set, the AUC of the model was 0.874, which was not significantly different from the derivation set (P=0.989).

Conclusions

This study developed and validated a prediction model based on ¹⁸F-FDG PET/CT imaging and clinical characteristics for distinguishing malignant from benign GGNs. The model showed good diagnostic efficacy and high specificity, which can improve the preoperative diagnosis of high-risk GGNs.