Artificial intelligence-driven computer aided diagnosis system provides similar diagnosis value compared with doctors' evaluation in lung cancer screening.

OBJECTIVE: To evaluate the consistency between doctors and artificial intelligence (AI) software in analysing and diagnosing pulmonary nodules, and assess whether the characteristics of pulmonary nodules derived from the two methods are consistent for the interpretation of carcinomatous nodules. MATERIALS AND METHODS: This retrospective study analysed participants aged 40-74 in the local area from 2011 to 2013. Pulmonary nodules were examined radiologically using a low-dose chest CT scan, evaluated by an expert panel of doctors in radiology, oncology, and thoracic departments, as well as a computer-aided diagnostic(CAD) system based on the three-dimensional(3D) convolutional neural network (CNN) with DenseNet architecture(InferRead CT Lung, IRCL). Consistency tests were employed to assess the uniformity of the radiological characteristics of the pulmonary nodules. The receiver operating characteristic (ROC) curve was used to evaluate the diagnostic accuracy. Logistic regression analysis is utilized to determine whether the two methods yield the same predictive factors for cancerous nodules. RESULTS: A total of 570 subjects were included in this retrospective study. The AI software demonstrated high consistency with the panel's evaluation in determining the position and diameter of the pulmonary nodules (kappa = 0.883, concordance correlation coefficient (CCC) = 0.809, p = 0.000). The comparison of the solid nodules' attenuation characteristics also showed acceptable consistency (kappa = 0.503). In patients diagnosed with lung cancer, the area under the curve (AUC) for the panel and AI were 0.873 (95%CI: 0.829-0.909) and 0.921 (95%CI: 0.884-0.949), respectively. However, there was no significant difference (p = 0.0950). The maximum diameter, solid nodules, subsolid nodules were the crucial factors for interpreting carcinomatous nodules in the analysis of expert panel and IRCL pulmonary nodule characteristics. CONCLUSION: AI software can assist doctors in diagnosing nodules and is consistent with doctors' evaluations and diagnosis of pulmonary nodules.

Diagnosis of pulmonary tuberculosis with 3D neural network based on multi-scale attention mechanism.

This paper presents a novel multi-scale attention residual network (MAResNet) for diagnosing patients with pulmonary tuberculosis (PTB) by computed tomography (CT) images. First, a three-dimensional (3D) network structure is applied in MAResNet based on the continuity and correlation of nodal features on different slices of CT images. Secondly, MAResNet incorporates the residual module and Convolutional Block Attention Module (CBAM) to reuse the shallow features of CT images and focus on key features to enhance the feature distinguishability of images. In addition, multi-scale inputs can increase the global receptive field of the network, extract the location information of PTB, and capture the local details of nodules. The expression ability of both high-level and low-level semantic information in the network can also be enhanced. The proposed MAResNet shows excellent results, with overall 94% accuracy in PTB classification. MAResNet based on 3D CT images can assist doctors make more accurate diagnosis of PTB and alleviate the burden of manual screening. In the experiment, a called Grad-CAM was employed to enhance the class activation mapping (CAM) technique for analyzing the model's output, which can identify lesions in important parts of the lungs and make transparent decisions.

Multisequence MRI-based radiomics signature as potential biomarkers for differentiating KRAS mutations in non-small cell lung cancer with brain metastases.

Background: Kirsten rat sarcoma virus (KRAS) has evolved from a genotype with predictive value to a therapeutic target recently. The study aimed to establish non-invasive radiomics models based on MRI to discriminate KRAS from epidermal growth factor receptor (EGFR) or anaplastic lymphoma kinase (ALK) mutations in lung cancer patients with brain metastases (BM), then further explore the optimal sequence for prediction. Methods: This retrospective study involved 317 patients (218 patients in training cohort and 99 patients in testing cohort) who had confirmed of KRAS, EGFR or ALK mutations. Radiomics features were separately extracted from T2WI, T2 fluid-attenuated inversion recovery (T2-FLAIR), diffusion weighted imaging (DWI) and contrast-enhanced T1-weighted imaging (T1-CE) sequences. The maximal information coefficient and recursive feature elimination method were used to select informative features. Then we built four radiomics models for differentiating KRAS from EGFR or ALK using random forest classifier. ROC curves were used to validate the capability of the models. Results: The four radiomics models for discriminating KRAS from EGFR all worked well, especially DWI and T2WI models (AUCs: 0.942, 0.942 in training cohort, 0.949, 0.954 in testing cohort). When KRAS compared to ALK, DWI and T2-FLAIR models showed excellent performance in two cohorts (AUCs: 0.947, 0.917 in training cohort, 0.850, 0.824 in testing cohort). Conclusions: Radiomics classifiers integrating MRI have potential to discriminate KRAS from EGFR or ALK, which are helpful to guide treatment and facilitate the discovery of new approaches capable of achieving this long-sought goal of cure in lung cancer patients with KRAS.

The incremental value of Mycobacterium tuberculosis trace nucleic acid detection in CT-guided percutaneous biopsy needle rinse solutions for the diagnosis of tuberculosis.

Introduction: Tuberculosis (TB) diagnosis still faces challenges with high proportion of bacteriologic test negative incidences worldwide. We assessed the diagnostic value of digital PCR (dPCR) analysis of ultramicro Mycobacterium tuberculosis (M.tb) nucleic acid in CT-guided percutaneous biopsy needle rinse solution (BNRS) for TB. Methods: BNRS specimens were consecutively collected and total DNA was purified. The concentrations of M.tb-specific IS6110 and IS1081 were quantified using droplet dPCR. The diagnostic performances of BNRS-dPCR and its sensitivity in comparison with conventional tests were analyzed. Results: A total of 106 patients were enrolled, 63 of whom were TB (48 definite and 15 clinically suspected TB) and 43 were non-TB. The sensitivity of BNRS IS6110 OR IS1081-dPCR for total, confirmed and clinically suspected TB was 66.7%, 68.8% and 60.0%, respectively, with a specificity of 97.7%. Its sensitivity was higher than that of conventional etiological tests, including smear microscopy, mycobacterial culture and Xpert using sputum and BALF samples. The positive detection rate in TB patients increased from 39.3% for biopsy AFB test alone to 73.2% when combined with BNRS-dPCR, and from 71.4% for biopsy M.tb molecular detection alone to 85.7% when combined with BNRS-dPCR. Conclusion: Our results preliminarily indicated that BNRS IS6110 OR IS1081-dPCR is a feasible etiological test, which has the potential to be used as a supplementary method to augment the diagnostic yield of biopsy and improve TB diagnosis.

A deep learning model integrating multisequence MRI to predict EGFR mutation subtype in brain metastases from non-small cell lung cancer.

BACKGROUND: To establish a predictive model based on multisequence magnetic resonance imaging (MRI) using deep learning to identify wild-type (WT) epidermal growth factor receptor (EGFR), EGFR exon 19 deletion (19Del), and EGFR exon 21-point mutation (21L858R) simultaneously. METHODS: A total of 399 patients with proven brain metastases of non-small cell lung cancer (NSCLC) were retrospectively enrolled and divided into training (n = 306) and testing (n = 93) cohorts separately based on two timepoints. All patients underwent 3.0-T brain MRI including T2-weighted, T2-weighted fluid-attenuated inversion recovery, diffusion-weighted imaging, and contrast-enhanced T1-weighted sequences. Radiomics features were extracted from each lesion based on four sequences. An algorithm combining radiomics approach with graph convolutional networks architecture (Radio-GCN) was designed for the prediction of EGFR mutation status and subtype. The area under the curve (AUC) at receiver operating characteristic analysis was used to evaluate the predication capabilities of each model. RESULTS: We extracted 1,290 radiomics features from each MRI sequence. The AUCs of the Radio-GCN model for identifying EGFR 19Del, 21L858R, and WT for the lesion-wise analysis were 0.996 ± 0.004, 0.971 ± 0.013, and 1.000 ± 0.000 on the independent testing cohort separately. It also yielded AUCs of 1.000 ± 0.000, 0.991 ± 0.009, and 1.000 ± 0.000 for predicting EGFR mutations respectively for the patient-wise analysis. The κ coefficients were 0.735 and 0.812, respectively. CONCLUSIONS: The constructed Radio-GCN model is a new potential tool to predict the EGFR mutation status and subtype in NSCLC patients with brain metastases. RELEVANCE STATEMENT: The study demonstrated that a deep learning approach based on multisequence MRI can help to predict the EGFR mutation status in NSCLC patients with brain metastases, which is beneficial to guide a personalized treatment. KEY POINTS: • This is the first study to predict the EGFR mutation subtype simultaneously. • The Radio-GCN model holds the potential to be used as a diagnostic tool. • This study provides an imaging surrogate for identifying the EGFR mutation subtype.

Chinese expert consensus on imaging diagnosis of drug-resistant pulmonary tuberculosis.

Tuberculosis (TB) remains one of the major infectious diseases in the world with a high incidence rate. Drug-resistant tuberculosis (DR-TB) is a key and difficult challenge in the prevention and treatment of TB. Early, rapid, and accurate diagnosis of DR-TB is essential for selecting appropriate and personalized treatment and is an important means of reducing disease transmission and mortality. In recent years, imaging diagnosis of DR-TB has developed rapidly, but there is a lack of consistent understanding. To this end, the Infectious Disease Imaging Group, Infectious Disease Branch, Chinese Research Hospital Association; Infectious Diseases Group of Chinese Medical Association of Radiology; Digital Health Committee of China Association for the Promotion of Science and Technology Industrialization, and other organizations, formed a group of TB experts across China. The conglomerate then considered the Chinese and international diagnosis and treatment status of DR-TB, China's clinical practice, and evidence-based medicine on the methodological requirements of guidelines and standards. After repeated discussion, the expert consensus of imaging diagnosis of DR-PB was proposed. This consensus includes clinical diagnosis and classification of DR-TB, selection of etiology and imaging examination [mainly X-ray and computed tomography (CT)], imaging manifestations, diagnosis, and differential diagnosis. This expert consensus is expected to improve the understanding of the imaging changes of DR-TB, as a starting point for timely detection of suspected DR-TB patients, and can effectively improve the efficiency of clinical diagnosis and achieve the purpose of early diagnosis and treatment of DR-TB.

Multisequence MRI-based radiomics analysis for early prediction of the risk of T790M resistance in new brain metastases.

Background: Predicting whether T790M emerges early is crucial to the adjustment of targeted drugs for non-small cell lung cancer (NSCLC) patients. This study aimed to evaluate the risk of T790M resistance in progressive new brain metastases (BMs) based on multisequence magnetic resonance imaging (MRI) radiomics. Methods: This retrospective study included 405 consecutive patients (training cohort: 294 patients; testing cohort: 111 patients) with proven NSCLC with disease progression of new BM. The radiomics features were separately extracted from T2-weighted imaging (T2WI), T2 fluid-attenuated inversion recovery (T2-FLAIR), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted imaging (T1-CE) sequence of baseline MRI. Then, we calculated radiomics scores (rad-score) of the 4 sequences respectively and established predictive models (lesion- or patient-level) to evaluate T790M resistance within up to 14 months using random forest classifier. Receiver operating characteristic (ROC) curves and F1 scores were used to validate the performance of two models in both the training and testing cohort. Results: There were significant differences in rad-scores of the four sequences between T790M-positive and negative groups whether in the training or testing cohort (P<0.05). The lesion-level model consisting of rad-scores showed excellent discrimination, with an area under the curve (AUC) and F1-score of 0.879 and 0.798 in the training cohort, and 0.834 and 0.742 in the testing cohort, respectively. The patient-level model also showed a favorable discriminatory ability with an AUC and F1 score of 0.851 and 0.837, which was confirmed with an AUC and F1 score of 0.734 and 0.716 in the testing cohort. Conclusions: The MRI-based radiomics signatures may be new markers to identify patients at high risk of developing resistance in the early period.

CT-based nomogram for early identification of T790M resistance in metastatic non-small cell lung cancer before first-line epidermal growth factor receptor-tyrosine kinase inhibitors therapy.

BACKGROUND: To evaluate the value of computed tomography (CT) radiomics in predicting the risk of developing epidermal growth factor receptor (EGFR) T790M resistance mutation for metastatic non-small lung cancer (NSCLC) patients before first-line EGFR-tyrosine kinase inhibitors (EGFR-TKIs) therapy. METHODS: A total of 162 metastatic NSCLC patients were recruited and split into training and testing cohort. Radiomics features were extracted from tumor lesions on nonenhanced CT (NECT) and contrast-enhanced CT (CECT). Radiomics score (rad-score) of two CT scans was calculated respectively. A nomogram combining two CT scans was developed to evaluate T790M resistance within up to 14 months. Patients were followed up to calculate the time of T790M occurrence. Models were evaluated by area under the curve at receiver operating characteristic analysis (ROC-AUC), calibration curve, and decision curve analysis (DCA). The association of the nomogram with the time of T790M occurrence was evaluated by Kaplan-Meier survival analysis. RESULTS: The nomogram constructed with the rad-score of NECT and CECT for predicting T790M resistance within 14 months achieved the highest ROC-AUCs of 0.828 and 0.853 in training and testing cohorts, respectively. The DCA showed that the nomogram was clinically useful. The Kaplan-Meier analysis showed that the occurrence time of T790M difference between the high- and low-risk groups distinguished by the rad-score was significant (p < 0.001). CONCLUSIONS: The CT-based radiomics signature may provide prognostic information and improve pretreatment risk stratification in EGFR NSCLC patients before EGFR-TKIs therapy. The multimodal radiomics nomogram further improved the capability. RELEVANCE STATEMENT: Radiomics based on NECT and CECT images can effectively identify and stratify the risk of T790M resistance before the first-line TKIs treatment in metastatic non-small cell lung cancer patients. KEY POINTS: • Early identification of the risk of T790M resistance before TKIs treatment is clinically relevant. • Multimodel radiomics nomogram holds potential to be a diagnostic tool. • It provided an imaging surrogate for identifying the pretreatment risk of T790M.

Utility of Machine Learning and Radiomics Based on Cavity for Predicting the Therapeutic Response of MDR-TB.

Background: Sputum culture result at the sixth month is essential for predicting therapeutic response to longer multidrug-resistant tuberculosis (MDR-TB) regimens. This study aimed to construct a predictive model using cavity-based radiomics to predict sputum status at the sixth month for MDR-TB patients treated with longer regimens. Methods: This retrospective study recruited 315 MDR-TB patients treated with longer regimens from two centers (250 patients from center 1 and 65 patients from center 2), who were divided into persistently positive and conversion to negative sputum culture groups according to sputum results. Radiomics features were extracted based on the cavity, and a radiomics model was selected and established using a random forest classifier. The clinical characteristics and primary CT signs with significant differences were integrated to build a clinical model. A combined model was generated using the radiomics and clinical model. ROC curves, F1-score and DCA curves were used to assess the predictive performance of the models. Results: Twenty-eight radiomics features were selected to build a radiomics model for predicting the sputum status. The radiomics model achieved good performance, with AUCs of 0.892 and 0.839 in the training and testing cohort, respectively, which was similar to the performance of the combined model (0.913 and 0.815) and much higher than that of the clinical model (0.688 and 0.525) in the two cohorts. Conclusion: The cavity-based radiomics model has the potential to predict sputum culture status for MDR-TB patients receiving longer regimens, which could guide follow-up treatment effectively.

Multisequence MRI-based radiomics nomogram for early prediction of osimertinib resistance in patients with non-small cell lung cancer brain metastases.

Background: Osimertinib resistance is a major problem in the course of targeted therapy for non-small cell lung cancer (NSCLC) patients. To develop and validate a multisequence MRI-based radiomics nomogram for early prediction of osimertinib resistance in NSCLC with brain metastases (BM). Methods: Pretreatment brain MRI of 251 NSCLC patients proven with BM were retrospectively enrolled from two centers (training cohort: 196 patients; testing cohort: 55 patients). According to the gene test result of osimertinib resistance, patients were labeled as resistance and non-resistance groups (training cohort: 65 versus 131 patients; testing cohort: 25 versus 30 patients). Radiomics features were extracted from T2WI, T2 fluid-attenuated inversion recovery (T2-FLAIR), diffusion weighted imaging (DWI) and contrast-enhanced T1-weighted imaging (T1-CE) sequences separately and radiomics score (rad-score) were built from the four sequences. Then a multisequence MRI-based nomogram was developed and the predictive ability was evaluated by ROC curves and calibration curves. Results: The rad-scores of the four sequences has significant differences between resistance and non-resistance groups in both training and testing cohorts. The nomogram achieved the highest predictive ability with area under the curve (AUC) of 0.989 (95 % confidence interval, 0.976-1.000) and 0.923 (95 % confidence interval, 0.851-0.995) in the training and testing cohort respectively. The calibration curves showed excellent concordance between the predicted and actual probability of osimertinib resistance using the radiomics nomogram. Conclusions: The multisequence MRI-based radiomics nomogram can be used as a noninvasive auxiliary tool to identify candidates who were resistant to osimertinib, which could guide clinical therapy for NSCLC patients with BM.

A prospective multicenter clinical research study validating the effectiveness and safety of a chest X-ray-based pulmonary tuberculosis screening software JF CXR-1 built on a convolutional neural network algorithm.

Background: Chest radiography (chest X-ray or CXR) plays an important role in the early detection of active pulmonary tuberculosis (TB). In areas with a high TB burden that require urgent screening, there is often a shortage of radiologists available to interpret the X-ray results. Computer-aided detection (CAD) software employed with artificial intelligence (AI) systems may have the potential to solve this problem. Objective: We validated the effectiveness and safety of pulmonary tuberculosis imaging screening software that is based on a convolutional neural network algorithm. Methods: We conducted prospective multicenter clinical research to validate the performance of pulmonary tuberculosis imaging screening software (JF CXR-1). Volunteers under the age of 15 years, both with or without suspicion of pulmonary tuberculosis, were recruited for CXR photography. The software reported a probability score of TB for each participant. The results were compared with those reported by radiologists. We measured sensitivity, specificity, consistency rate, and the area under the receiver operating characteristic curves (AUC) for the diagnosis of tuberculosis. Besides, adverse events (AE) and severe adverse events (SAE) were also evaluated. Results: The clinical research was conducted in six general infectious disease hospitals across China. A total of 1,165 participants were enrolled, and 1,161 were enrolled in the full analysis set (FAS). Men accounted for 60.0% (697/1,161). Compared to the results from radiologists on the board, the software showed a sensitivity of 94.2% (95% CI: 92.0-95.8%) and a specificity of 91.2% (95% CI: 88.5-93.2%). The consistency rate was 92.7% (91.1-94.1%), with a Kappa value of 0.854 (P = 0.000). The AUC was 0.98. In the safety set (SS), which consisted of 1,161 participants, 0.3% (3/1,161) had AEs that were not related to the software, and no severe AEs were observed. Conclusion: The software for tuberculosis screening based on a convolutional neural network algorithm is effective and safe. It is a potential candidate for solving tuberculosis screening problems in areas lacking radiologists with a high TB burden.

Neural network-based model for evaluating inert nodules and volume doubling time in T1 lung adenocarcinoma: a nested case-control study.

Objective: The purpose of this study is to establish model for assessing inert nodules predicting nodule volume-doubling. Methods: A total of 201 patients with T1 lung adenocarcinoma were analysed retrospectively pulmonary nodule information was predicted by an AI pulmonary nodule auxiliary diagnosis system. The nodules were classified into two groups: inert nodules (volume-doubling time (VDT)>600 days n=152) noninert nodules (VDT<600 days n=49). Then taking the clinical imaging features obtained at the first examination as predictive variables the inert nodule judgement model >(INM) volume-doubling time estimation model (VDTM) were constructed based on a deep learning-based neural network. The performance of the INM was evaluated by the area under the curve (AUC) obtained from receiver operating characteristic (ROC) analysis the performance of the VDTM was evaluated by R2(determination coefficient). Results: The accuracy of the INM in the training and testing cohorts was 81.13% and 77.50%, respectively. The AUC of the INM in the training and testing cohorts was 0.7707 (95% CI 0.6779-0.8636) and 0.7700 (95% CI 0.5988-0.9412), respectively. The INM was effective in identifying inert pulmonary nodules; additionally, the R2 of the VDTM in the training cohort was 0.8008, and that in the testing cohort was 0.6268. The VDTM showed moderate performance in estimating the VDT, which can provide some reference during a patients' first examination and consultation. Conclusion: The INM and the VDTM based on deep learning can help radiologists and clinicians distinguish among inert nodules and predict the nodule volume-doubling time to accurately treat patients with pulmonary nodules.

Radiomics analysis of lung CT for multidrug resistance prediction in active tuberculosis: a multicentre study.

OBJECTIVES: Multidrug-resistant TB (MDR-TB) is a severe burden and public health threat worldwide. This study aimed to develop a radiomics model based on the tree-in-bud (TIB) sign and nodules and validate its predictive performance for MDR-TB. METHODS: We retrospectively recruited 454 patients with proven active TB from two hospitals and classified them into three training and testing cohorts: TIB (n = 295, 102), nodules (n = 302, 97), and their combination (n = 261, 81). Radiomics features relating to TIB and nodules were separately extracted. The maximal information coefficient and recursive feature elimination were used to select informative features per the two signs. Two radiomics models were constructed to predict MDR-TB using a random forest classifier. Then, a combined model was built incorporating radiomics features based on these two signs. The capability of the models in the combined training and testing cohorts was validated with ROC curves. RESULTS: Sixteen features were extracted from TIB and 15 from nodules. The AUCs of the combined model were slightly higher than those of the TIB model in the combined training cohort (0.911 versus 0.877, p > 0.05) and testing cohort (0.820 versus 0.786, p < 0.05) and similar to the performance of the nodules model in the combined training cohort (0.911 versus 0.933, p > 0.05) and testing cohort (0.820 versus 0.855, p > 0.05). CONCLUSIONS: The CT-based radiomics models hold promise for use as a non-invasive tool in the prediction of MDR-TB. CLINICAL RELEVANCE STATEMENT: Our study revealed that complementary information regarding MDR-TB can be provided by radiomics based on the TIB sign and nodules. The proposed radiomics models may be new markers to predict MDR in active TB patients. KEY POINTS: • This is the first study to build, validate, and apply radiomics based on tree-in-bud sign and nodules for the prediction of MDR-TB. • The radiomics model showed a favorable performance for the identification of MDR-TB. • The combined model holds potential to be used as a diagnostic tool in routine clinical practice.

Regional homogeneity alterations in multifrequency bands in patients with extracranial multi-organ tuberculosis: a prospective cross-sectional study.

Background: This study aimed to clarify the spontaneous neural activity in the conventional frequency band (0.01-0.08 Hz) and 2 subfrequency bands (slow-4: 0.027-0.073 Hz; slow-5: 0.01-0.027 Hz) in patients with extracranial multi-organ tuberculosis (EMTB) through regional homogeneity (ReHo) analysis. Methods: In all, 32 patients with EMTB and 31 healthy controls (HCs) were assessed by resting-state functional magnetic resonance imaging (rs-fMRI) scans to clarify the abnormal spontaneous neural activity through ReHo analysis in the conventional frequency band and 2 subfrequency bands. Results: Compared with the HCs, the patients with EMTB exhibited decreased ReHo in the left postcentral gyrus [t=-4.79; 95% confidence interval (CI): -0.79 to -0.31] and the left superior cerebellum (t=-4.45; 95% CI: -0.54 to -0.21) in the conventional band. Conversely, increased ReHo was observed in the right middle occipital gyrus (t=3.94; 95% CI: 0.18-0.53). In the slow-4 band, patients with EMTB only exhibited decreased ReHo in the superior cerebellum (t=-4.69; 95% CI: -0.54 to -0.22); meanwhile, in the slow-5 band, these patients exhibited decreased ReHo in the right postcentral gyrus (t=-3.76; 95% CI: -0.74 to -0.21) and the left superior cerebellum (t=-5.20, 95% CI: -0.72 to -0.31). After Bonferroni correction, no significant correlation was observed between the ReHo values in clusters showing significant between-group differences and cognitive test scores. Conclusions: ReHo showed abnormal synchronous neural activity in patients with EMTB in different frequency bands, which provides a novel understanding of the pathological mechanism of EMTB.

Differentiating peritoneal tuberculosis and peritoneal carcinomatosis based on a machine learning model with CT: a multicentre study.

PURPOSE: It is still a challenge to make early differentiation of peritoneal tuberculosis (PTB) and peritoneal carcinomatosis (PC) clinically as well as on imaging and laboratory tests. We aimed to develop a model to differentiate PTB from PC based on clinical characteristics and primary CT signs. METHODS: This retrospective study included 88 PTB patients and 90 PC patients (training cohort: 68 PTB patients and 69 PC patients from Beijing Chest Hospital; testing cohort: 20 PTB patients and 21 PC patients from Beijing Shijitan Hospital). The images were analyzed for omental thickening, peritoneal thickening and enhancement, small bowel mesentery thickening, the volume and density of ascites, and enlarged lymph nodes (LN). Meaningful clinical characteristics and primary CT signs comprised the model. ROC curve was used to validate the capability of the model in the training and testing cohorts. RESULTS: There were significant differences in the following aspects between the two groups: (1) age; (2) fever; (3) night sweat; (4) cake-like thickening of the omentum and omental rim (OR) sign; (5) irregular thickening of the peritoneum, peritoneal nodules, and scalloping sign; (6) large ascites; and (7) calcified and ring enhancement of LN. The AUC and F1 score of the model were 0.971 and 0.923 in the training cohort and 0.914 and 0.867 in the testing cohort. CONCLUSION: The model has the potential to distinguish PTB from PC and thus has the potential to be a diagnostic tool.

Machine learning and radiomics for the prediction of multidrug resistance in cavitary pulmonary tuberculosis: a multicentre study.

OBJECTIVES: Multidrug-resistant tuberculosis (MDR-TB) is a major challenge to global health security. Early identification of MDR-TB patients increases the likelihood of treatment success and interrupts transmission. We aimed to develop a predictive model for MDR to cavitary pulmonary TB using CT radiomics features. METHODS: This retrospective study included 257 consecutive patients with proven active cavitary TB (training cohort: 187 patients from Beijing Chest Hospital; testing cohort: 70 patients from Infectious Disease Hospital of Heilongjiang Province). Radiomics features were extracted from the segmented cavitation. A radiomics model was constructed to predict MDR using a random forest classifier. Meaningful clinical characteristics and subjective CT findings comprised the clinical model. The radiomics and clinical models were combined to create a combined model. ROC curves were used to validate the capability of the models in the training and testing cohorts. RESULTS: Twenty-one radiomics features were selected as optimal predictors to build the model for predicting MDR-TB. The AUCs of the radiomics model were significantly higher than those of the clinical model in either the training cohort (0.844 versus 0.589, p < 0.05) or the testing cohort (0.829 versus 0.500, p < 0.05). The AUCs of the radiomics model were slightly lower than those of the combined model in the training cohort (0.844 versus 0.881, p > 0.05) and testing cohort (0.829 versus 0.834, p > 0.05), but there was no significant difference. CONCLUSIONS: The radiomics model has the potential to predict MDR in cavitary TB patients and thus has the potential to be a diagnostic tool. KEY POINTS: • This is the first study to build and validate models that distinguish MDR-TB from DS-TB with clinical and radiomics features based on cavitation. • The radiomics model demonstrated good performance and might potentially aid in prior TB characterisation treatment. • This noninvasive and convenient technique can be used as a diagnosis tool into routine clinical practice.

Predicting EGFR T790M Mutation in Brain Metastases Using Multisequence MRI-Based Radiomics Signature.

RATIONALE AND OBJECTIVES: Timely identifying T790M mutation for non-small cell lung cancer (NSCLC) patients with brain metastases (BM) is essential to adjust targeted treatment strategies. To develop and validate radiomics models based on multisequence MRI for differentiating patients with T790M resistance from no T790M mutation in BM and explore the optimal sequence for prediction. MATERIALS AND METHODS: This retrospective study enrolled 233 patients with proven of BM in NSCLC which included 95 with T790M and 138 without T790M from two hospitals as the training cohort and testing cohort separately. Radiomics features extracted from T2WI, T2 fluid-attenuated inversion recovery (T2-FLAIR), diffusion weighted imaging (DWI) and contrast-enhanced T1-weighted imaging (T1-CE) sequence respectively. The most predictable features were selected based on the maximal information coefficient and Boruta method. Then four radiomics models were built to characterize T790M mutation by random forest classifier. ROC curves, F1 score and DCA curves were constructed to validate the capability and verify the performance of four models. RESULTS: The DWI model showed best performance with AUC and F1 score of 0.886 and 0.789 in the training cohort, 0.850 and 0.743 in the testing cohort. DCA curves also showed higher overall net benefit from the DWI model than from the remaining three models in the testing cohort. Other three models also had some classification power whether in the training or testing cohort, especially T2-FLAIR model. CONCLUSION: Multisequence MRI-based radiomics has potential to predict the emergence of EGFR T790M resistance mutations especially the radiomics signature based on DWI sequence.

Differentiating malignant pleural mesothelioma and metastatic pleural disease based on a machine learning model with primary CT signs: A multicentre study.

Rationale and Objectives: It is still a challenge to make confirming diagnosis of malignant pleural mesothelioma (MPM), especially differentiating from metastatic pleural disease (MPD). The aim of this study was to develop a model to distinguish MPM with MPD based on primary CT signs. Materials and methods: We retrospectively recruited 150 MPM patients and 147 MPD patients from two centers and assigned them to training (115 MPM patients and 113 MPD patients) and testing (35 MPM patients and 34 MPD patients) cohorts. The images were analyzed for pleural thickening, hydrothorax, lymphadenopathy, thoracic volume and calcified pleural plaque (CPP). The selected clinical characteristics and primary CT signs comprised the model by multivariate logistic regression in the training cohort. Then the model was tested on the external testing cohort. ROC curve and F1 score were used to validate the capability of the model in both two cohorts. Results: There were significant differences between two groups: (1) carcinoembryonic antigen (CEA); (2) nodular and mass pleural thickening; (3) the enhancement of pleura; (4) focal, diffuse and circumferential pleural thickening; (5) the thickest pleura; (6) thickening of diaphragmatic pleura; (7) multiple nodules and effusion of interlobar pleura; (8) hilar LN and ring enhancement of LN; (9) punctate and stipe CPP. The AUC and F1 score of the model were 0.970 and 0.857 in the training cohort, 0.955 and 0.818 in the testing cohort. Conclusion: The model holds promise for use as a diagnostic tool to distinguish MPM from MPD.

Differentiating EGFR from ALK mutation status using radiomics signature based on MR sequences of brain metastasis.

PURPOSE: More and more small brain metastases (BMs) in asymptomatic patients can be detected even prior to their primary lung cancer with the development of MRI. The aim of this study was to develop a predictive radiomics model to identify epidermal growth factor receptor (EGFR) and anaplastic lymphoma kinase (ALK) mutation status in BM and explore the optimal MR sequence for predication. METHODS: This retrospective study included 186 patients with proven BM of lung cancer (training cohort: 70 patients with EGFR mutations and 65 patients with ALK rearrangements; testing cohort: 26 patients with EGFR mutations and 25 patients with ALK rearrangements). Radiomics features were separately extracted from contrast-enhanced T1-weighted imaging (T1-CE), T2 fluid-attenuated inversion recovery (T2-FLAIR) and T2WI sequences. The model for three MR sequences were constructed using a random forest classifier. ROC curves were used to validate the capability of the models in the training and testing cohorts. RESULTS: The AUCs of the T2-FLAIR model were significantly higher than those of the T1-CE model in training cohort (0.991 versus 0.954) and testing cohort (0.950 versus 0.867) and much higher than those of the T2WI model in training cohort (0.991 versus 0.880) and testing cohort (0.950 versus 0.731). Besides, the F1 scores of the T1-CE model were slightly higher than the T2-FLAIR model and much higher than the T2WI model in two cohorts. CONCLUSION: T2-FLAIR and T1-CE radiomics models that can be used as noninvasive tools for identifying EGFR and ALK mutation status are helpful to guide therapeutic strategies.

Long-Read Sequencing Annotation of the Transcriptome in DNA-PK Inactivated Cells.

The DNA-dependent protein kinase catalytic subunit (DNA-PKcs) with a Ku70/Ku80 heterodimer constitutes the intact DNA-PK kinase, which is an upstream component of the DNA repair machinery that signals the DNA damage, orchestrates the DNA repair, and serves to maintain genome integrity. Beyond its role in DNA damage repair, the DNA-PK kinase is also implicated in transcriptional regulation and RNA metabolism, with an illuminated impact on tumor progression and therapeutic responses. However, the efforts to identify DNA-PK regulated transcriptomes are limited by short-read sequencing to resolve the full complexity of the transcriptome. Therefore, we leveraged the PacBio Single Molecule, Real-Time (SMRT) Sequencing platform to study the transcriptome after DNA-PK inactivation to further underscore the importance of its role in diseases. Our analysis revealed additional novel transcriptome and complex gene structures in the DNA-PK inactivated cells, identifying 8,355 high-confidence new isoforms from 3,197 annotated genes and 523 novel genes. Among them, 380 lncRNAs were identified. We validated these findings using computational approaches and confirmatory transcript quantification with short-read sequencing. Several novel isoforms representing distinct splicing events have been validated through PCR experiments. Our analyses provide novel insights into DNA-PK function in transcriptome regulation and RNA metabolism.