Radiomics model for distinguishing tuberculosis and lung cancer on computed tomography scans

Construction and validation of a clinical differentiation model between peripheral lung cancer and solitary pulmonary tuberculosis

OBJECTIVE

To establish and validate a clinical model for differentiating peripheral lung cancer (PLC) from solitary pulmonary tuberculosis (SP-TB) based on clinical and imaging features.

MATERIALS AND METHODS

Retrospectively, 183 patients (100 PLC, 83 SP-TB) in our hospital were randomly divided into a training group and an internal validation group (ratio 7:3), and 100 patients (50 PLC, 50 SP-TB) in Sichuan Provincial People's Hospital were identified as an external validation group. The collected qualitative and quantitative variables were used to determine the independent feature variables for distinguishing between PLC and SP-TB through univariate logistic regression, multivariate logistic regression. Then, traditional logistic regression models and machine learning algorithm models (decision tree, random forest, xgboost, support vector machine, k-nearest neighbors, light gradient boosting machine) were established using the independent feature variables. The model with the highest AUC value in the internal validation group was used for subsequent analysis. The receiver operating characteristic curve (ROC), calibration curve, and decision curves analysis (DCA) were used to assess the model's discrimination, calibration, and clinical usefulness.

RESULT

Age, smoking history, maximum diameter of lesion, lobulation, spiculation, calcification, and vascular convergence sign were independent characteristic variables to differentiate PLC from SP-TB. The logistic regression model had the highest AUC value of 0.878 for the internal validation group, based on which a quantitative visualization nomogram was constructed to discriminate the two diseases. The area under the ROC curve (AUC) of the model in the training, internal validation, and external validation groups were 0.915 (95 % CI: 0.866-0.965), 0.878 (95 % CI: 0.784-0.971), and 0.912 (95 % CI: 0.855-0.969), respectively, and the calibration curves fitted well. Decision curves analysis (DCA) confirmed the good clinical benefit of the model.

CONCLUSION

The model constructed based on clinical and imaging features can accurately differentiate between PLC and SP-TB, providing potential value for developing reasonable clinical plans.

A nomogram to predict lung cancer in pulmonary lesions for tuberculosis infection patients

Similar clinical features make the differential diagnosis difficult, particularly between lung cancer and pulmonary tuberculosis (TB), without pathological evidence for patients with concomitant TB infection. Our study aimed to build a nomogram to predict malignant pulmonary lesions applicable to clinical practice. We retrospectively analyzed clinical characteristics, imaging features, and laboratory indicators of TB infection patients diagnosed with lung cancer or active pulmonary TB at Xiangya Hospital of Central South University. A total of 158 cases from January 1, 2018 to May 30, 2019 were included in the training cohort. Predictive factors for lung cancer were screened by a multiple-stepwise logistic regression analysis. A nomogram model was established, and the discrimination, stability, and prediction performance of the model were analyzed. A total of 79 cases from June 1, 2019, to December 30, 2019, were used as the validation cohort to verify the predictive value of the model. Eight predictor variables, including age, pleural effusion, mediastinal lymph node, the number of positive tumor markers, the T cell spot test for TB, pulmonary lesion morphology, location, and distribution, were selected to construct the model. The corrected C-statistics and the Brier scores were 0.854 and 0.130 in the training cohort, and 0.823 and 0.163 in the validation cohort. Calibration plots showed good performance, and decision curve analysis indicated a high net benefit. In conclusion, the nomogram model provides an effective method to calculate the probability of lung cancer in TB infection patients, and it has excellent discrimination, stability, and prediction performance in detecting a malignant diagnosis of undiagnosed pulmonary lesions.

Deep learning and radiomics of longitudinal CT scans for early prediction of tuberculosis treatment outcomes

BACKGROUND

To predict tuberculosis (TB) treatment outcomes at an early stage, prevent poor outcomes ofdrug-resistant tuberculosis(DR-TB) and interrupt transmission.

METHODS

An internal cohort for model development consists of 204 bacteriologically-confirmed TB patients who completed anti-tuberculosis treatment, with one pretreatment and two follow-up CT images (612 scans). Three radiomics feature-based models (RM) with multiple classifiers of Bagging, Random forest and Gradient boosting and two deep-learning-based models (i.e., supervised deep-learning model, SDLM; weakly supervised deep-learning model, WSDLM) are developed independently. Prediction scores of RM and deep-learning models with respectively highest performance are fused to create new fusion models under different fusion strategies. An additional independent validation was conducted on the external cohort comprising 80 patients (160 scans).

RESULTS

For RM scheme, 16 optimal radiomics features are finally selected using longitudinal scans. The AUCs of RM for Bagging, Random forest and Gradient boosting were 0.789, 0.773 and 0.764 in the internal cohort and 0.840, 0.834 and 0.816 in the external cohort, respectively. For deep learning-based scheme, AUCs of SDLM and WSDLM were 0.767 and 0.661 in the internal cohort, and 0.823 and 0.651 in the external. The fusion model yields AUCs from 0.767 to 0.802 in the internal cohort, and from 0.831 to 0.857 in the external cohort.

CONCLUSIONS

Fusion of radiomics features and deep-learning model may have the potential to predict early failure outcome of DR-TB, which may be combined to help prevent poor TB treatment outcomes.

Serum Metabolomic Profiles for Distinguishing Lung Cancer From Pulmonary Tuberculosis: Identification of Rapid and Noninvasive Biomarker

BACKGROUND

Pulmonary tuberculosis (PTB) and lung cancer (LC) have similar clinical symptoms and atypical imaging findings, which are easily misdiagnosed. There is an urgent need for a noninvasive and accurate biomarker to distinguish LC from PTB.

METHODS

A total of 694 subjects were enrolled and divided into discovery set (n = 122), identification set (n = 214), and validation set (n = 358). Metabolites were identified by multivariate and univariate analyses. Receiver operating characteristic curve were used to evaluate the diagnostic efficacy of biomarkers.

RESULTS

Seven metabolites were identified and validated. Phenylalanylphenylalanine for distinguishing LC from PTB yielded an area under the curve of 0.89, sensitivity of 71%, and specificity of 92%. It also showed good diagnostic abilities in discovery set and identification set. Compared with that in healthy volunteers (median [interquartile range], 1.57 [1.01, 2.34] μg/mL), it was elevated in LC (4.76 [2.74, 7.08] μg/mL; ratio of median, [ROM] = 3.03, P < .01) and reduced in PTB (1.06 [0.51, 2.09] μg/mL; ROM = 0.68, P < .05).

CONCLUSIONS

The metabolomic profile of LC and PTB was described and a key biomarker identified. We produced a rapid and noninvasive method to supplement existing clinical diagnostic examinations for distinguishing LC from PTB.

Introducing a secondary segmentation to construct a radiomics model for pulmonary tuberculosis cavities

PURPOSE

Accurate segmentation (separating diseased portions of the lung from normal appearing lung) is a challenge in radiomic studies of non-neoplastic diseases, such as pulmonary tuberculosis (PTB). In this study, we developed a segmentation method, applicable to chest X-rays (CXR), that can eliminate the need for precise disease delineation, and that is effective for constructing radiomic models for automatic PTB cavity classification.

METHODS

This retrospective study used a dataset of 266 posteroanterior CXR of patients diagnosed with laboratory confirmed PTB. The lungs were segmented using a U-net-based in-house automatic segmentation model. A secondary segmentation was developed using a sliding window, superimposed on the primary lung segmentation. Pyradiomics was used for feature extraction from every window which increased the dimensionality of the data, but this allowed us to accurately capture the spread of the features across the lung. Two separate measures (standard-deviation and variance) were used to consolidate the features. Pearson's correlation analysis (with a 0.8 cut-off value) was then applied for dimensionality reduction followed by the construction of Random Forest radiomic models.

RESULTS

Two almost identical radiomic signatures consisting of 10 texture features each (9 were the same plus 1 other feature) were identified using the two separate consolidation measures. Two well performing random forest models were constructed from these signatures. The standard-deviation model (AUC = 0.9444 (95% CI, 0.8762; 0.9814)) performed marginally better than the variance model (AUC = 0.9288 (95% CI, 0.9046; 0.9843)).

CONCLUSION

The introduction of the secondary sliding window segmentation on CXR could eliminate the need for disease delineation in pulmonary radiomic studies, and it could improve the accuracy of CXR reporting currently regaining prominence as a high-volume screening tool as the developed radiomic models correctly classify cavities from normal CXR.

Construction and Validation of a Diagnostic Scoring System for Predicting Active Pulmonary Tuberculosis in Patients with Positive T-SPOT Based on Indicators Associated with Coagulation and Inflammation: A Retrospective Cross-Sectional Study

Introduction

Tuberculosis (TB) is a life-threatening single infectious disease, which remains a major global public health concern. This study was to establish and validate a clinically practical diagnostic scoring system for predicting active pulmonary tuberculosis (APTB) in patients with positive tuberculosis T cell spot test [T-SPOT] using indicators associated with coagulation and inflammation.

Methods

A single-center retrospective cross-sectional study was performed to include patients with positive T-SOPT registered and hospitalized at Wuhan Jinyintan Hospital between January 2017 and December 2019. All patients were separated into the active pulmonary tuberculosis (APTB) group and the inactive pulmonary tuberculosis (IPTB) group, according to the diagnostic criteria from China's Expert Consensus for APTB and IPTB. Subsequently, the patients were randomized into a training set and a validation set at a ratio of 2:1. Indicators associated with coagulation and inflammation, including prothrombin time activity (PTA), activated partial thromboplastin time (APTT), thrombin time (TT), fibrinogen concentration (Fbg-C), C-reactive protein/albumin ratio (CAR), C-reactive protein/prealbumin ratio (CPR), neutrophils count/lymphocyte count ratio (NLR), platelet count/lymphocyte count ratio (PLR), monocyte count/lymphocyte count ratio (MLR), and erythrocyte sedimentation rate (ESR) were obtained from electronic medical record system (EMRS). Stepwise logistic regression was performed in the training set to build a diagnostic model for predicting APTB, which was transformed into an easily applicable scoring system via nomogram. Receiver operating characteristic (ROC) analysis, calibration curve (CC), and decision curve analysis (DCA) were conducted to evaluate the predictive performance of the established diagnostic scoring system.

Results

A total of 508 patients [training set (211 cases of APTB and 116 cases of IPTB) and validation set (103 cases of APTB and 78 cases of IPTB)] with positive T-SPOT were recruited in the study. Stepwise logistic regression showed that CPR, MLR, ESR, APTT and Fbg-C were independent predictors for APTB. The scoring system was subsequently formulated based on the abovementioned predictors, which correspond to scores of 10, 6, 7, 5, and 5, respectively. In addition, patients are more likely to be diagnosed as APTB when the cut-off score was ≥16 scores, while patients with <16 scores are more likely to be diagnosed as IPTB. The scoring system showed good predictive efficacy in both the training set [area under the curve (AUC): 0.887] and the validation set (AUC: 0.898). Furthermore, both CC and DCA confirmed the clinical utility of the scoring system.

Conclusion

The data suggest that the combination of indicators associated with coagulation and inflammation could serve as biomarkers to identify APTB in patients with positive T-SPOT. In addition, patients with positive T-SPOT were more prone to be diagnosed with APTB when having a combined total of scores ≥16 in the scoring system.

Feature selection methods and predictive models in CT lung cancer radiomics

Radiomics is a technique that extracts quantitative features from medical images using data-characterization algorithms. Radiomic features can be used to identify tissue characteristics and radiologic phenotyping that is not observable by clinicians. A typical workflow for a radiomics study includes cohort selection, radiomic feature extraction, feature and predictive model selection, and model training and validation. While there has been increasing attention given to radiomic feature extraction, standardization, and reproducibility, currently, there is a lack of rigorous evaluation of feature selection methods and predictive models. Herein, we review the published radiomics investigations in CT lung cancer and provide an overview of the commonly used radiomic feature selection methods and predictive models. We also compare limitations of various methods in clinical applications and present sources of uncertainty associated with those methods. This review is expected to help raise awareness of the impact of radiomic feature and model selection methods on the integrity of radiomics studies.

Nomogram model based on radiomics signatures and age to assist in the diagnosis of knee osteoarthritis

BACKGROUND

Knee osteoarthritis (KOA) is a common disease in the elderly. An effective method for accurate diagnosis could affect the management and prognosis of patients.

OBJECTIVES

To develop a nomogram model based on X-ray imaging data and age, and to evaluate its effectiveness in the diagnosis of KOA.

METHODS

A total of 4403 knee X-rays from 1174 patients (July 2017 to November 2018) were retrospectively analyzed. Radiomics features were extracted and selected from the X-ray image data to quantify the phenotypic characteristics of the lesion region. Feature selection was performed in three steps to enable the derivation of robust and effective radiomics signatures. Then, logistic regression (LR), support vector machine (SVM) AdaBoost, gradient boosting decision tree (GBDT), and multi-layer perceptron (MLP) was adopted to verify the performance of radiomics signatures. In addition, a nomogram model combining age with radiomics signatures was constructed. At last, receiver operating characteristic (ROC) curve, calibration and decision curves were used to evaluate the discriminative performance.

RESULTS

The LR model has the best classification performance among the four radiomics models in testing cohort (LR AUC vs. SVM AUC: 0.843 vs. 0.818, DeLong test P = 0.0024; LR AUC vs. GBDT AUC: 0.843 vs. 0.821, P = 0.0028; LR AUC vs. MLP AUC: 0.843 vs. 0.822, P = 0.0019). The nomogram model achieved better predictive efficacy than the radiomics model in testing cohort compared to radiomics models although the statistical difference was not significant (Nomogram AUC vs. Radiomics AUC: 0.847 vs. 0.843, P = 0.06). The decision curve analysis revealed that the constructed nomogram had clinical usefulness.

CONCLUSION

The nomogram model combining radiomics signatures with age has good performance for the accurate diagnosis of KOA and may help to improve clinical decision-making.

Deep learning based CT images automatic analysis model for active/non-active pulmonary tuberculosis differential diagnosis

Active pulmonary tuberculosis (ATB), which is more infectious and has a higher mortality rate compared with non-active pulmonary tuberculosis (non-ATB), needs to be diagnosed accurately and timely to prevent the tuberculosis from spreading and causing deaths. However, traditional differential diagnosis methods of active pulmonary tuberculosis involve bacteriological testing, sputum culturing and radiological images reading, which is time consuming and labour intensive. Therefore, an artificial intelligence model for ATB differential diagnosis would offer great assistance in clinical practice. In this study, computer tomography (CT) scans images and corresponding clinical information of 1160 ATB patients and 1131 patients with non-ATB were collected and divided into training, validation, and testing sets. A 3-dimension (3D) Nested UNet model was utilized to delineate lung field regions in the CT images, and three different pre-trained deep learning models including 3D VGG-16, 3D EfficientNet and 3D ResNet-50 were used for classification and differential diagnosis task. We also collected an external testing set with 100 ATB cases and 100 Non-ATB cases for further validation of the model. In the internal and external testing set, the 3D ResNet-50 model outperformed other models, reaching an AUC of 0.961 and 0.946, respectively. The 3D ResNet-50 model reached even higher levels of diagnostic accuracy than experienced radiologists, while the CT images reading and diagnosing speed was 10 times faster than human experts. The model was also capable of visualizing clinician interpretable lung lesion regions important for differential diagnosis, making it a powerful tool assisting ATB diagnosis. In conclusion, we developed an auxiliary tool to differentiate active and non-active pulmonary tuberculosis, which would have broad prospects in the bedside.

Radiomics combined with clinical features in distinguishing non-calcifying tuberculosis granuloma and lung adenocarcinoma in small pulmonary nodules

Aim

To evaluate the performance of radiomics models with the combination of clinical features in distinguishing non-calcified tuberculosis granuloma (TBG) and lung adenocarcinoma (LAC) in small pulmonary nodules.

Methodology

We conducted a retrospective analysis of 280 patients with pulmonary nodules confirmed by surgical biopsy from January 2017 to December 2020. Samples were divided into LAC group (n = 143) and TBG group (n = 137). We assigned them to a training dataset (n = 196) and a testing dataset (n = 84). Clinical features including gender, age, smoking, CT appearance (size, location, spiculated sign, lobulated shape, vessel convergence, and pleural indentation) were extracted and included in the radiomics models. 3D slicer and FAE software were used to delineate the Region of Interest (ROI) and extract clinical features. The performance of the model was evaluated by the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC).

Results

Based on the model selection, clinical features gender, and age in the LAC group and TBG group showed a significant difference in both datasets (P < 0.05). CT appearance lobulated shape was also significantly different in the LAC group and TBG group (Training dataset, P = 0.034; Testing dataset, P = 0.030). AUC were 0.8344 (95% CI [0.7712-0.8872]) and 0.751 (95% CI [0.6382-0.8531]) in training and testing dataset, respectively.

Conclusion

With the capacity to detect differences between TBG and LAC based on their clinical features, radiomics models with a combined of clinical features may function as the potential non-invasive tool for distinguishing TBG and LAC in small pulmonary nodules.

A CT-based radiomics nomogram for the differentiation of pulmonary cystic echinococcosis from pulmonary abscess

The purpose of this study was to establish a clinical prediction model for the differential diagnosis of pulmonary cystic echinococcosis (CE) and pulmonary abscess according to computed tomography (CT)-based radiomics signatures and clinical indicators. This is a retrospective single-centre study. A total of 117 patients, including 53 with pulmonary CE and 64 with pulmonary abscess, were included in our study and were randomly divided into a training set (n = 95) and validation set (n = 22). Radiomics features were extracted from CT images, a radiomics signature was constructed, and clinical indicators were evaluated to establish a clinical prediction model. Finally, a model combining imaging radiomics features and clinical indicators was constructed. The performance of the nomogram, radiomics signature and clinical prediction model was evaluated and validated with the training and test datasets, and then the three models were compared. The radiomics signature of this study was established by 25 features, and the radiomics nomogram was constructed by using clinical factors and the radiomics signature. Finally, the areas under the receiver operating characteristic curve (AUCs) for the training set and test set were 0.970 and 0.983, respectively. Decision curve analysis showed that the radiologic nomogram was better than the clinical prediction model and individual radiologic characteristic model in differentiating pulmonary CE from pulmonary abscess. The radiological nomogram and models based on clinical factors and individual radiomics features can distinguish pulmonary CE from pulmonary abscess and will be of great help to clinical diagnoses in the future.

A scoring system developed from a nomogram to differentiate active pulmonary tuberculosis from inactive pulmonary tuberculosis

Purpose

This study aimed to develop and validate a scoring system based on a nomogram of common clinical metrics to discriminate between active pulmonary tuberculosis (APTB) and inactive pulmonary tuberculosis (IPTB).

Patients and methods

A total of 1096 patients with pulmonary tuberculosis (PTB) admitted to Wuhan Jinyintan Hospital between January 2017 and December 2019 were included in this study. Of these patients with PTB, 744 were included in the training cohort (70%; 458 patients with APTB, and 286 patients with IPTB), and 352 were included in the validation cohort (30%; 220 patients with APTB, and 132 patients with IPTB). Data from 744 patients from the training cohort were used to establish the diagnostic model. Routine blood examination indices and biochemical indicators were collected to construct a diagnostic model using the nomogram, which was then transformed into a scoring system. Furthermore, data from 352 patients from the validation cohort were used to validate the scoring system.

Results

Six variables were selected to construct the prediction model. In the scoring system, the mean corpuscular volume, erythrocyte sedimentation rate, albumin level, adenosine deaminase level, monocyte-to-high-density lipoprotein ratio, and high-sensitivity C-reactive protein-to-lymphocyte ratio were 6, 4, 7, 5, 5, and 10, respectively. When the cut-off value was 15.5, the scoring system for recognizing APTB and IPTB exhibited excellent diagnostic performance. The area under the curve, specificity, and sensitivity of the training cohort were 0.919, 84.06%, and 86.36%, respectively, whereas those of the validation cohort were 0.900, 82.73, and 86.36%, respectively.

Conclusion

This study successfully constructed a scoring system for distinguishing APTB from IPTB that performed well.

The Novel Predictive Biomarkers for Type 2 Diabetes Mellitus in Active Pulmonary Tuberculosis Patients

Purpose

This study was to explore the predictive value of monocyte to high-density lipoprotein cholesterol ratio (MHR), neutrophils to high-density lipoprotein cholesterol ratio (NHR), C-reactive protein-to-lymphocyte ratio (CLR), and C-reactive protein-to-albumin ratio (CAR) for type 2 diabetes mellitus (T2DM) in patients with active pulmonary tuberculosis (APTB).

Patients and Methods

A total of 991 active pulmonary tuberculosis (APTB) patients (201 with T2DM) were hospitalized in the Department of Tuberculosis, Wuhan Jinyintan Hospital, Tongji Medical College, Huazhong University of Science and Technology were included. The routine blood examination indicators and biochemical parameters were collected to calculate MHR, NHR, CLR, and CAR. The Pearson correlation analysis, Univariate Logistic regression analysis, and receiver operating characteristic (ROC) curve analysis were performed to assess the predictive value of MHR, NHR, CLR, and CAR for APTB-T2DM patients.

Results

The levels of MHR, NHR, CLR, and CAR in the APTB-T2DM patients were significantly higher than in the APTB-no T2DM patients (P < 0.05). Additionally, the MHR, NHR, CLR, and CAR have a positive correlation with fasting blood glucose in the whole study population. However, in the APTB-T2DM patients, MHR, NHR, and CAR were not correlated with fasting blood glucose, and only CLR was positively correlated with fasting blood glucose. The area under curve (AUC) predicting APTB-T2DM patients of the MHR, NHR, CLR, and CAR was 0.632, 0.72, 0.715, and 0.713, respectively. Further, univariate logistic regression analyses showed that the higher MHR, NHR, CLR, and CAR were independent risk factors for APTB-T2DM (P < 0.01). The MHR, NHR, CLR, and CAR quartiles were used to divide the APTB patients into four groups for further analysis. The prevalence of T2DM was significantly higher in APTB individuals as MHR, NHR, CLR, and CAR values increased (P < 0.05).

Conclusion

MHR, NHR, CLR, and CAR are simple and practicable inflammatory parameters that could be used for assessing T2DM in APTB. APTB patients have a greater possibility to be diagnosed with T2DM with the higher MHR, NHR CLR, and CAR values. Therefore, more attention should be given to the indicator in the examination of APTB.

Radiomics based on enhanced CT for differentiating between pulmonary tuberculosis and pulmonary adenocarcinoma presenting as solid nodules or masses

PURPOSE

To investigate the incremental value of enhanced CT-based radiomics in discriminating between pulmonary tuberculosis (PTB) and pulmonary adenocarcinoma (PAC) presenting as solid nodules or masses and to develop an optimal radiomics model.

METHODS

A total of 128 lesions (from 123 patients) from three hospitals were retrospectively analyzed and were randomly divided into training and test datasets at a ratio of 7:3. Independent predictors in subjective image features were used to develop the subjective image model (SIM). The plain CT-based and enhanced CT-based radiomics features were screened by the correlation coefficient method, univariate analysis, and the least absolute shrinkage and selection operator, then used to build the plain CT radiomics model (PRM) and enhanced CT radiomics model (ERM), respectively. Finally, the combined model (CM) combining PRM and ERM was established. In addition, the performance of three radiologists and one respiratory physician was evaluated. The areas under the receiver operating characteristic curve (AUCs) were used to assess the performance of each model.

RESULTS

The differential diagnostic capability of the ERM (training: AUC = 0.933; test: AUC = 0.881) was better than that of the PRM (training: AUC = 0.861; test: AUC = 0.756) and the SIM (training: AUC = 0.760; test: AUC = 0.611). The CM was optimal (training: AUC = 0.948; test: AUC = 0.917) and outperformed the respiratory physician and most radiologists.

CONCLUSIONS

The ERM was more helpful than the PRM for identifying PTB and PAC that present as solid nodules or masses, and the CM was the best.

The Role of Chest CT Radiomics in Diagnosis of Lung Cancer or Tuberculosis: A Pilot Study

In many low-income countries, the poor availability of lung biopsy leads to delayed diagnosis of lung cancer (LC), which can appear radiologically similar to tuberculosis (TB). To assess the ability of CT Radiomics in differentiating between TB and LC, and to evaluate the potential predictive role of clinical parameters, from March 2020 to September 2021, patients with histological diagnosis of TB or LC underwent chest CT evaluation and were retrospectively enrolled. Exclusion criteria were: availability of only enhanced CT scans, previous lung surgery and significant CT motion artefacts. After manual 3D segmentation of enhanced CT, two radiologists, in consensus, extracted and compared radiomics features (T-test or Mann−Whitney), and they tested their performance, in differentiating LC from TB, via Receiver operating characteristic (ROC) curves. Forty patients (28 LC and 12 TB) were finally enrolled, and 31 were male, with a mean age of 59 ± 13 years. Significant differences were found in normal WBC count (p < 0.019) and age (p < 0.001), in favor of the LC group (89% vs. 58%) and with an older population in LC group, respectively. Significant differences were found in 16/107 radiomic features (all p < 0.05). LargeDependenceEmphasis and LargeAreaLowGrayLevelEmphasis showed the best performance in discriminating LC from TB, (AUC: 0.92, sensitivity: 85.7%, specificity: 91.7%, p < 0.0001; AUC: 0.92, sensitivity: 75%, specificity: 100%, p < 0.0001, respectively). Radiomics may be a non-invasive imaging tool in many poor nations, for differentiating LC from TB, with a pivotal role in improving oncological patients’ management; however, future prospective studies will be necessary to validate these initial findings.

Comparison of the Detection Rates of Different Diagnostic Methods for Primary Peripheral Lung Cancer

Objective

The present study aims to compare the detection rates of different diagnostic methods for primary peripheral lung cancer (PPLC).

Methods

The detection rate and patient information were collected from a total of 359 cases of PPLC or a suspected diagnosis of lung cancer; among these, 186 cases were simultaneously treated with fibreoptic bronchoscopy, brush inspection and flush inspection, and 173 cases underwent a computed tomography (CT)-guided percutaneous lung biopsy (PNB). The positive detection rates of the different methods were compared.

Results

In the detection of peripheral lesions (diameter of <5 cm), the CT-PNB had the significantly highest detection rate, followed by the combined basic method (fibreoptic bronchoscopy + brushing + flushing). The independent use of the three basic sampling methods showed a significantly lower detection rate compared with the combined use.

Conclusion

In the diagnosis of peripheral lung cancer, the CT-PNB had the best detection rate; hence, it could be used in clinical practice for the diagnosis of such lesions.

Development and validation a radiomics nomogram for diagnosing occult brain metastases in patients with stage IV lung adenocarcinoma

Background

To develop and validate a radiomics model using computed tomography (CT) images acquired from the first diagnosis to estimate the status of occult brain metastases (BM) in patients with stage IV lung adenocarcinoma (LADC).

Methods

One hundred and ninety-three patients who were first diagnosed with stage IV LADC were enrolled and divided into a training cohort (n=135) and a validation cohort (n=58). Then, 725 radiomic features were extracted from contoured primary tumor volumes of LADCs. Intra- and interobserver reliabilities were calculated, and the least absolute shrinkage and selection operator (LASSO) was applied for feature selection. Subsequently, a radiomics signature (Rad-Score) was built. To improve performance, a nomogram incorporating a radiomics signature and an independent clinical predictor was developed. Finally, the established signature and nomogram were assessed using receiver operating characteristic (ROC) curves and precision-recall curves (PRC). Both empirical and α-binomial model-based ROCs and PRCs were plotted, and the area under the curve (AUC) and average precision (AP) of ROCs and PRCs were calculated and compared.

Results

A radiomics signature and Rad-Score were constructed using eight radiomic features, and these had significant correlations with occult BM status. A nomogram was developed by incorporating a Rad-Score and the primary tumor location. The nomogram yielded an optimal AUC of 0.911 [95% confidence interval (CI): 0.903–0.919] and an AP of 0.885 (95% CI: 0.876–0.894) in the training cohort, and an AUC of 0.873 (95% CI: 0.866–0.80) and an AP of 0.827 (95% CI: 0.820–0.834) in the validation cohort using α-binomial model-based method. The calibration curve demonstrated that the nomogram showed high agreement between the actual occult BM probability and predicted by the nomogram (P=0.427).

Conclusions

The nomogram incorporating a radiomics signature and a clinical risk factor achieved optimal performance after holistic assessment using unbiased indexes for diagnosing occult BM of patients who were first diagnosed with stage IV LADC.

Content-based image retrieval with a Convolutional Siamese Neural Network: Distinguishing lung cancer and tuberculosis in CT images

BACKGROUND

CT findings of lung cancer and tuberculosis are sometimes similar, potentially leading to misdiagnosis. This study aims to combine deep learning and content-based image retrieval (CBIR) to distinguish lung cancer (LC) from nodular/mass atypical tuberculosis (NMTB) in CT images.

METHODS

This study proposes CBIR with a convolutional Siamese neural network (CBIR-CSNN). First, the lesion patches are cropped out to compose LC and NMTB datasets and the pairs of two arbitrary patches form a patch-pair dataset. Second, this patch-pair dataset is utilized to train a CSNN. Third, a test patch is treated as a query. The distance between this query and 20 patches in both datasets is calculated using the trained CSNN. The patches closest to the query are used to give the final prediction by majority voting. One dataset of 719 patients is used to train and test the CBIR-CSNN. Another external dataset with 30 patients is employed to verify CBIR-CSNN.

RESULTS

The CBIR-CSNN achieves excellent performance at the patch level with an mAP (Mean Average Precision) of 0.953, an accuracy of 0.947, and an area under the curve (AUC) of 0.970. At the patient level, the CBIR-CSNN correctly predicted all labels. In the external dataset, the CBIR-CSNN has an accuracy of 0.802 and AUC of 0.858 at the patch level, and 0.833 and 0.902 at the patient level.

CONCLUSIONS

This CBIR-CSNN can accurately and automatically distinguish LC from NMTB using CT images. CBIR-CSNN has excellent representation capability, compatibility with few-shot learning, and visual explainability.

Pulmonary tuberculosis diagnosis, differentiation and disease management: A review of radiomics applications

Pulmonary tuberculosis is a worldwide epidemic that can only be fought effectively with early and accurate diagnosis and proper disease management. The means of diagnosis and disease management should be easily accessible, cost effective and be readily available in the high tuberculosis burdened countries where it is most needed. Fortunately, the fast development of computer science in recent years has ensured that medical images can accurately be quantified. Radiomics is one such tool that can be used to quantify medical images. This review article focuses on the literature currently available on the application of radiomics explicitly for the purpose of diagnosis, differentiation from other pulmonary diseases and disease management of pulmonary tuberculosis. Despite using a formal search strategy, only five articles could be found on the application of radiomics to pulmonary tuberculosis. In all five articles reviewed, radiomic feature extraction was successfully used to quantify digital medical images for the purpose of comparing, or differentiating, pulmonary tuberculosis from other pulmonary diseases. This demonstrates that the use of radiomics for the purpose of tuberculosis disease management and diagnosis remains a valuable data mining opportunity not yet realised.

Clinical characteristics and chest computed tomography findings related to the infectivity of pulmonary tuberculosis

AIM

This study mainly evaluates the clinical characteristics and chest chest computed tomography (CT) findings of AFB-positive and AFB-negative pulmonary tuberculosis (PTB) patients to explore the relationship between AFB-positive and clinico-radiological findings.

METHODS

A retrospective analysis of 224 hospitalized tuberculosis patients from 2018 to 2020 was undertaken. According to the AFB smear results, they were divided into AFB-positive pulmonary tuberculosis (positive by Ziehl-Neelsen staining) and AFB-negative pulmonary tuberculosis and patients' CT results and laboratory test results were analyzed.

RESULTS

A total of 224 PTB patients were enrolled. AFB-positive (n = 94, 42%) and AFB-negative (n = 130, 58%). AFB-positive patients had more consolidation (77.7% vs. 53.8%, p < 0.01), cavity (55.3% vs. 34.6%, p < 0.01), calcification (38.3% vs. 20%, p < 0.01), bronchiectasis (7.5% vs. 1.5%, p < 0.05), bronchiarctia (6.4% vs. 0.8%, p < 0.05), and right upper lobe involvement (57.5% vs. 33.1%, p < 0.01), left upper lobe involvement (46.8% vs. 33.1%, p < 0.05) and lymphadenopathy (58.5% vs. 37.7%, p < 0.01).

CONCLUSION

The study found that when pulmonary tuberculosis patients have consolidation, cavity, upper lobe involvement and lymphadenopathy on chest CT images, they may have a higher risk of AFB-positive tuberculosis.

Cancer or Tuberculosis: A Comprehensive Review of the Clinical and Imaging Features in Diagnosis of the Confusing Mass

Confusing masses constitute a challenging clinical problem for differentiating between cancer and tuberculosis diagnoses. This review summarizes the major theories designed to identify factors associated with misdiagnosis, such as imaging features, laboratory tests, and clinical characteristics. Then, the clinical experiences regarding the misdiagnosis of cancer and tuberculosis are summarized. Finally, the main diagnostic points and differential diagnostic criteria are explored, and the characteristics of multimodal imaging and radiomics are summarized.