Advances in intelligent diagnosis methods for pulmonary ground-glass opacity nodules

CT imaging indications correlate with the degree of lung adenocarcinoma infiltration

Background

Ground glass nodules (GGN) of the lung may be a precursor of lung cancer and have received increasing attention in recent years with the popularity of low-dose high-resolution computed tomography (CT). Many studies have discussed imaging features that suggest the benignity or malignancy of GGN, but the extent of its postoperative pathological infiltration is poorly understood. In this study, we identified CT imaging features that indicate the extent of GGN pathological infiltration.

Methods

A retrospective analysis of 189 patients with pulmonary GGN from January 2020 to December 2021 at Shanxi Cancer Hospital was performed. Patients were classified according to their pathological type into non-invasive adenocarcinoma [atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS) in a total of 34 cases], micro-invasive adenocarcinoma (MIA) in 80 cases, and invasive adenocarcinoma (IAC) in a total of 75 cases. The general demographic data, nodule size, nodule area, solid component, CT indications and pathological findings of the three groups of patients were analyzed to predict the correlation between GGN and the degree of lung adenocarcinoma infiltration.

Results

No statistically significant differences were found among the three groups in general information, vascular signs, and vacuolar signs (P > 0.05). Statistically significant differences among the three groups were found in nodule size, nodule area, lobar signs, pleural traction, burr signs, bronchial signs, and solid components (P < 0.05). Logistic regression equation tests based on the statistically significant indicators showed that nodal area, lobar sign, pleural pull, burr sign, bronchial sign, and solid component were independent predictors of lung adenocarcinoma infiltration. The subject operating characteristic (ROC) curve analysis showed that nodal area is valuable in predicting GGN infiltration.

Conclusion

CT-based imaging indications are useful predictors of infiltrative adenocarcinoma manifested as pulmonary ground glass nodules.

Computer-aided diagnosis of primary membranous nephropathy using expert system

BACKGROUND

The diagnosis of primary membranous nephropathy (PMN) often depends on invasive renal biopsy, and the diagnosis based on clinical manifestations and target antigens may not be completely reliable as it could be affected by uncertain factors. Moreover, different experts could even have different diagnosis results due to their different experiences, which could further impact the reliability of the diagnosis. Therefore, how to properly integrate the knowledge of different experts to provide more reliable and comprehensive PMN diagnosis has become an urgent issue.

METHODS

This paper develops a belief rule-based system for PMN diagnosis. The belief rule base is constructed based on the knowledge of the experts, with 9 biochemical indicators selected as the input variables. The belief rule-based system is developed of three layers: (1) input layer; (2) belief rule base layer; and (3) output layer, where 9 biochemical indicators are selected as the input variables and the diagnosis result is provided as the conclusion. The belief rule base layer is constructed based on the knowledge of the experts. The final validation was held with gold pattern clinical cases, i.e., with known and clinically confirmed diagnoses.

RESULTS

134 patients are used in this study, and the proposed method is defined by its sensitivity, specificity, accuracy and area under curve (AUC), which are 98.0%, 96.9%, 97.8% and 0.93, respectively. The results of this study present a novel and effective way for PMN diagnosis without the requirement of renal biopsy.

CONCLUSIONS

Through analysis of the diagnosis results and comparisons with other methods, it can be concluded that the developed system could help diagnose PMN based on biochemical indicators with relatively high accuracy.

Evaluation of the dual vascular supply patterns in ground-glass nodules with a dynamic volume computed tomography

BACKGROUND

In recent years, the detection rate of ground-glass nodules (GGNs) has been improved dramatically due to the popularization of low-dose computed tomography (CT) screening with high-resolution CT technique. This presents challenges for the characterization and management of the GGNs, which depends on a thorough investigation and sufficient diagnostic knowledge of the GGNs. In most diagnostic studies of the GGNs, morphological manifestations are used to differentiate benignancy and malignancy. In contrast, few studies are dedicated to the assessment of the hemodynamics, i.e., perfusion parameters of the GGNs.

AIM

To assess the dual vascular supply patterns of GGNs on different histopathology and opacities.

METHODS

Forty-seven GGNs from 47 patients were prospectively included and underwent the dynamic volume CT. Histopathologic diagnoses were obtained within two weeks after the CT examination. Blood flow from the bronchial artery [bronchial flow (BF)] and pulmonary artery [pulmonary flow (PF)] as well as the perfusion index (PI) = [PF/(PF + BF)] were obtained using first-pass dual-input CT perfusion analysis and compared respectively between different histopathology and lesion types (pure or mixed GGNs) and correlated with the attenuation values of the lesions using one-way ANOVA, student’s t test and Pearson correlation analysis.

RESULTS

Of the 47 GGNs (mean diameter, 8.17 mm; range, 5.3-12.7 mm), 30 (64%) were carcinoma, 6 (13%) were atypical adenomatous hyperplasia and 11 (23%) were organizing pneumonia. All perfusion parameters (BF, PF and PI) demonstrated no significant difference among the three conditions (all P > 0.05). The PFs were higher than the BFs in all the three conditions (all P < 0.001). Of the 30 GGN carcinomas, 14 showed mixed GGNs and 16 pure GGNs with a higher PI in the latter (P < 0.01). Of the 17 benign GGNs, 4 showed mixed GGNs and 13 pure GGNs with no significant difference of the PI between the GGN types (P = 0.21). A negative correlation (r = -0.76, P < 0.001) was demonstrated between the CT attenuation values and the PIs in the 30 GGN carcinomas.

CONCLUSION

The GGNs are perfused dominantly by the PF regardless of its histopathology while the weight of the BF in the GGN carcinomas increases gradually during the progress of its opacification.

Pulmonary Nodule Clinical Trial Data Collection and Intelligent Differential Diagnosis for Medical Internet of Things

In this paper, the medical Internet of things (IoT) is used to pool data from clinical trials of pulmonary nodules, and on this basis, intelligent differential diagnosis techniques are investigated. A filtered orthogonal frequency division multiplexing model based on polarisation coding is proposed, where the input data are fed to a modulator after polarisation cascade coding, and the system performance is analysed under a medical Internet of things modulated additive Gaussian white noise channel. The above polarisation-coded filtered orthogonal frequency division multiplexing system components are applied to electroencephalogram (EEG) signal transmission, to which a threshold compression module and a vector reconstruction module are added to address the system power burden associated with the acquisition and transmission of large amounts of real-time EEG data in the medical IoT. In the threshold compression module, the inherent characteristics of EEG signals are analysed, and the generated EEG data are decomposed into multiple symbolic streams and compressed by applying different thresholds to improve the compression ratio while ensuring the quality of service of the application. A deep neural network-based approach is proposed for the detection and diagnosis of lung nodules. Automatic identification and measurement of simulated lung nodules and the corresponding volumes of nodules in images under different conditions are applied. The sensitivity of each AIADS in identifying lung nodules under different convolution kernel conditions, false positives (FP), false negatives (FN), relative volume errors (RVE), the miss detection rate (MDR) for different types of lung nodules, and the performance of each system in predicting the four types of nodules are calculated. In this paper, an interpretable multibranch feature convolutional neural network model is proposed for the diagnosis of benign and malignant lung nodules. It is demonstrated that the proposed model not only yields interpretable lung nodule classification results but also achieves better lung nodule classification performance with an accuracy rate of 97.8%.

Invasive Prediction of Ground Glass Nodule Based on Clinical Characteristics and Radiomics Feature

Objective: To explore the diagnostic value of CT radiographic images and radiomics features for invasive classification of lung adenocarcinoma manifesting as ground-glass nodules (GGNs) in computer tomography (CT).

Methods: A total of 312 GGNs were enrolled in this retrospective study. All GGNs were randomly divided into training set (n = 219) and test set (n = 93). Univariate and multivariate logistic regressions were used to establish a clinical model, while the minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) algorithm were used to select the radiomics features and construct the radiomics model. A combined model was finally built by combining these two models. The performance of these models was assessed in both training and test set. A combined nomogram was developed based on the combined model and evaluated with its calibration curves and C-index.

Results: Diameter [odds ratio (OR), 1.159; p ＜ 0.001], lobulation (OR, 2.953; p = 0.002), and vascular changes (OR, 3.431; p ＜ 0.001) were retained as independent predictors of the invasive adenocarcinoma (IAC) group. Eleven radiomics features were selected by mRMR and LASSO method to established radiomics model. The clinical model and radiomics mode showed good predictive ability in both training set and test set. When two models were combined, the diagnostic area under the curve (AUC) value was higher than the single clinical or radiomics model (training set: 0.86 vs. 0.83 vs. 0.82; test set: 0.80 vs. 0.78 vs. 0.79). The constructed combined nomogram could effectively quantify the risk degree of 3 image features and Rad score with a C-index of 0.855 (95%: 0.805∼0.905).

Conclusion: Radiographic and radiomics features show high accuracy in the invasive diagnosis of GGNs, and their combined analysis can improve the diagnostic efficacy of IAC manifesting as GGNs. The nomogram, serving as a noninvasive and accurate predictive tool, can help judge the invasiveness of GGNs prior to surgery and assist clinicians in creating personalized treatment strategies.

Predicting Malignancy and Invasiveness of Pulmonary Subsolid Nodules on CT Images Using Deep Learning

Background

To develop and validate a deep learning-based model on CT images for the malignancy and invasiveness prediction of pulmonary subsolid nodules (SSNs).

Materials and Methods

This study retrospectively collected patients with pulmonary SSNs treated by surgery in our hospital from 2012 to 2018. Postoperative pathology was used as the diagnostic reference standard. Three-dimensional convolutional neural network (3D CNN) models were constructed using preoperative CT images to predict the malignancy and invasiveness of SSNs. Then, an observer reader study conducted by two thoracic radiologists was used to compare with the CNN model. The diagnostic power of the models was evaluated with receiver operating characteristic curve (ROC) analysis.

Results

A total of 2,614 patients were finally included and randomly divided for training (60.9%), validation (19.1%), and testing (20%). For the benign and malignant classification, the best 3D CNN model achieved a satisfactory AUC of 0.913 (95% CI: 0.885-0.940), sensitivity of 86.1%, and specificity of 83.8% at the optimal decision point, which outperformed all observer readers' performance (AUC: 0.846±0.031). For pre-invasive and invasive classification of malignant SSNs, the 3D CNN also achieved satisfactory AUC of 0.908 (95% CI: 0.877-0.939), sensitivity of 87.4%, and specificity of 80.8%.

Conclusion

The deep-learning model showed its potential to accurately identify the malignancy and invasiveness of SSNs and thus can help surgeons make treatment decisions.

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.

Comprehensive Perspective for Lung Cancer Characterisation Based on AI Solutions Using CT Images

Lung cancer is still the leading cause of cancer death in the world. For this reason, novel approaches for early and more accurate diagnosis are needed. Computer-aided decision (CAD) can be an interesting option for a noninvasive tumour characterisation based on thoracic computed tomography (CT) image analysis. Until now, radiomics have been focused on tumour features analysis, and have not considered the information on other lung structures that can have relevant features for tumour genotype classification, especially for epidermal growth factor receptor (EGFR), which is the mutation with the most successful targeted therapies. With this perspective paper, we aim to explore a comprehensive analysis of the need to combine the information from tumours with other lung structures for the next generation of CADs, which could create a high impact on targeted therapies and personalised medicine. The forthcoming artificial intelligence (AI)-based approaches for lung cancer assessment should be able to make a holistic analysis, capturing information from pathological processes involved in cancer development. The powerful and interpretable AI models allow us to identify novel biomarkers of cancer development, contributing to new insights about the pathological processes, and making a more accurate diagnosis to help in the treatment plan selection.

Predicting the invasiveness of lung adenocarcinomas appearing as ground-glass nodule on CT scan using multi-task learning and deep radiomics

Background

Due to different treatment method and prognosis of different subtypes of lung adenocarcinomas appearing as ground-glass nodules (GGNs) on computed tomography (CT) scan, it is important to classify invasive adenocarcinomas from non-invasive adenocarcinomas. The purpose of this paper is to build and evaluate the performance of deep learning networks on the differentiation the invasiveness of lung adenocarcinoma appearing as GGNs.

Methods

This retrospective study included 886 GGNs from 794 pathological confirmed patients with lung adenocarcinoma for training and testing the proposed networks. Three deep learning networks, namely XimaNet (deep learning-based classification model), XimaSharp (classification and nodule segmentation model), and Deep-RadNet (deep learning and radiomics combined classification model, i.e., deep radiomics) were built. Three classification tasks, namely task 1: classification of AAH/AIS and MIA, task 2: classification of MIA and IAC, and task 3: classification of non-invasive adenocarcinomas and invasive adenocarcinomas (AAH/AIS&MIA and IAC) were conducted to evaluate the model performance. The Z-test was used to compare the model performance.

Results

The AUC for classification of AAH/AIS with MIA were 0.891, 0.841 and 0.779 for Deep-RadNet, XimaNet and XimaSharp respectively. The AUC for classification of MIA with IAC were 0.889, 0.785 and 0.778 for three networks and AUC for classification of AAH/AIS&MIA with IAC were 0.941, 0.892 and 0.827 respectively. The performance of deep_RadNet was better than the other two models with the Z-test (P<0.05).

Conclusions

Deep-RadNet with the visual heat map could evaluate the invasiveness of GGNs accurately and intuitively, providing a theoretical basis for individualized and accurate medical treatment of patients with GGNs.

CT features and quantitative analysis of subsolid nodule lung adenocarcinoma for pathological classification prediction

Background

The value of the CT features and quantitative analysis of lung subsolid nodules (SSNs) in the prediction of the pathological grading of lung adenocarcinoma is discussed.

Methods

Clinical data and CT images of 207 cases (216 lesions) with CT manifestations of an SSNs lung adenocarcinoma confirmed by surgery pathology were retrospectively analysed. The pathological results were divided into three groups, including atypical adenomatous hyperplasia (AAH)/adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC). Then, the quantitative and qualitative data of these nodules were compared and analysed.

Results

The mean size, maximum diameter, mean CT value and maximum CT value of the nodules were significantly different among the three groups of AAH/AIS, MIA and IAC and were different between the paired groups (AAH/AIS and MIA or MIA and IAC) (P < 0.05). The critical values of the above indicators between AAH/AIS and MIA were 10.05 mm, 11.16 mm, − 548.00 HU and − 419.74 HU. The critical values of the above indicators between MIA and IAC were 14.42 mm, 16.48 mm, − 364.59 HU and − 16.98 HU. The binary logistic regression analysis of the features with the statistical significance showed that the regression model between AAH/AIS and MIA is logit(p) = − 0.93 + 0.216X¹ + 0.004X⁴. The regression model between MIA and IAC is logit(p) = − 1.242–1.428X⁵(1) − 1.458X⁶(1) + 1.146X⁷(1) + 0.272X² + 0.005X³. The areas under the curve (AUC) obtained by plotting the receiver operating characteristic curve (ROC) using the regression probabilities of regression models I and II were 0.815 and 0.931.

Conclusions

Preoperative prediction of pathological classification of CT image features has important guiding value for clinical management. Correct diagnosis results can effectively improve the patient survival rate. Through comprehensive analysis of the CT features and qualitative data of SSNs, the diagnostic accuracy of SSNs can be effectively improved. The logistic regression model established in this study can better predict the pathological classification of SSNs lung adenocarcinoma on CT, and the predictive value is significantly higher than the independent use of each quantitative factor.