This study aimed to assess the performance of a deep learning algorithm in helping radiologist achieve improved efficiency and accuracy in chest radiograph diagnosis. We adopted a deep learning algorithm to concurrently detect the presence of normal findings and 13 different abnormalities in chest radiographs and evaluated its performance in assisting radiologists. Each competing radiologist had to determine the presence or absence of these signs based on the label provided by the AI. The 100 radiographs were randomly divided into two sets for evaluation: one without AI assistance (control group) and one with AI assistance (test group). The accuracy, false-positive rate, false-negative rate, and analysis time of 111 radiologists (29 senior, 32 intermediate, and 50 junior) were evaluated. A radiologist was given an initial score of 14 points for each image read, with 1 point deducted for an incorrect answer and 0 points given for a correct answer. The final score for each doctor was automatically calculated by the backend calculator. We calculated the mean scores of each radiologist in the two groups (the control group and the test group) and calculated the mean scores to evaluate the performance of the radiologists with and without AI assistance. The average score of the 111 radiologists was 597 (587–605) in the control group and 619 (612–626) in the test group (P < 0.001). The time spent by the 111 radiologists on the control and test groups was 3279 (2972–3941) and 1926 (1710–2432) s, respectively (P < 0.001). The performance of the 111 radiologists in the two groups was evaluated by the area under the receiver operating characteristic curve (AUC). The radiologists showed better performance on the test group of radiographs in terms of normal findings, pulmonary fibrosis, heart shadow enlargement, mass, pleural effusion, and pulmonary consolidation recognition, with AUCs of 1.0, 0.950, 0.991, 1.0, 0.993, and 0.982, respectively. The radiologists alone showed better performance in aortic calcification (0.993), calcification (0.933), cavity (0.963), nodule (0.923), pleural thickening (0.957), and rib fracture (0.987) recognition. This competition verified the positive effects of deep learning methods in assisting radiologists in interpreting chest X-rays. AI assistance can help to improve both the efficacy and efficiency of radiologists.

Purpose: We aimed to assess the classification performance of a computed tomography (CT)-based radiomic signature for discriminating invasive and non-invasive lung adenocarcinoma. Patients and Methods: A total of 192 patients (training cohort, n=116; validation cohort, n=76) with pathologically confirmed lung adenocarcinoma were retrospectively enrolled in the present study. Radiomic features were extracted from preoperative unenhanced chest CT images to build a radiomic signature. Predictive performance of the radiomic signature were evaluated using an intra-cross validation cohort. Diagnostic performance of the radiomic signature was assessed via receiver operating characteristic (ROC) analysis. Results: The radiomic signature consisted of 14 selected features and demonstrated good discrimination performance between invasive and non-invasive adenocarcinoma. The area under the ROC curve (AUC) for the training cohort was 0.83 (sensitivity, 0.84 ; specificity, 0.78; accuracy, 0.82), while that for the validation cohort was 0.77 (sensitivity, 0.94; specificity, 0.52 ; accuracy, 0.82). Conclusion: The CT-based radiomic signature exhibited good classification performance for discriminating invasive and non-invasive lung adenocarcinoma, and may represent a valuable biomarker for determining therapeutic strategies in this patient population.

Aim: The aim of the study was to investigate the diagnostic value of radiomics models based on computed tomography (CT) in distinguishing between benign and malignant thyroid nodules. Materials and Methods: We conducted a retrospective analysis of the clinical and imaging data of 172 patients with pathology-confirmed thyroid nodules (83 benign nodules and 89 malignant nodules). All patients underwent a plain CT scan + arterial and venous contrast enhancement before the operation. Using the stratified random sampling method, patients were divided into a training group (121 cases) and a test group (51 cases) at a ratio of 7:3. A.K. software was used to extract radiomics features from the preoperative CT images, and minimum redundancy maximum relevance and least absolute shrinkage and selection operator regression analyses were then used for feature screening and model construction. Receiver operating characteristic (ROC) curves were constructed for the training and test groups to verify model performance and evaluate the efficacy of the radiomics features in identifying benign and malignant thyroid nodules. We then used the most efficient models to construct a nomogram. For the training group, 1-way analysis of variance and multivariate logistic regression analysis were used to screen statistically significant clinical features, and the radiomics scores were combined to construct a radiomics nomogram. We used ROC curve analysis to evaluate the predictive performance of the model. Results: Screening yielded 21 radiomics features that were used to construct a model for differentiating between benign and malignant thyroid nodules. For the training group, the area under the ROC curve of the prediction models for the noncontrast, arterial phase, and venous phase scans were 0.86 (95% confidence interval [CI], 0.79–0.92), 0.89 (95% CI, 0.83–0.95), and 0.88 (95% CI, 0.82–0.94), respectively, and the corresponding diagnostic accuracy was 0.78, 0.84, and 0.83. For the test group, the corresponding 3-phase under the ROC curves for the test group were 0.76 (95% CI, 0.63–0.90), 0.78 (95% CI, 0.65–0.91), and 0.76 (95% CI, 0.62–0.90), and the corresponding accuracy was 0.63, 0.77, and 0.75. Thus, the arterial phase model exhibited the best diagnostic performance. The multivariate logistic regression results showed that morphology regularity and the cystic degeneration ratio were independent clinical risk factors for predicting benign and malignant thyroid nodules. The arterial phase radiomics score and clinically independent factors were then used to construct a nomogram. The nomogram had good discriminability for the training group (0.93; 95% CI, 0.88–0.98) and the test group (0.84; 95% CI, 0.73–0.95), achieving significantly higher accuracies than the radiomics score and clinical characteristics alone. Conclusions: The radiomics nomogram constructed by combining radiomics characteristics and clinical risk factors was efficacious for distinguishing benign and malignant thyroid nodules.

Background: To develop and validate a preoperative nomogram model combining the radiomics signature and clinical features for preoperative prediction of visceral pleural invasion (VPI) in lung nodules presenting as part‐solid density.Methods: We retrospectively reviewed 156 patients with pathologically confirmed invasive lung adenocarcinomas after surgery from January 2016 to August 2019. The patients were split into training and validation sets by a ratio of 7:3. The radiomic features were extracted with the aid of FeAture Explorer Pro (FAE). A CT‐based radiomics model was constructed to predict the presence of VPI and internally validated. Multivariable regression analysis was conducted to construct a nomogram model, and the performance of the models were evaluated with the area under the receiver operating characteristic curve (AUC) and compared with each other.Results: The enrolled patients were split into training (n = 109) and validation sets (n = 47). A total of 806 features were extracted and the selected 10 optimal features were used in the construction of the radiomics model among the 707 stable features. The AUC of the nomogram model was 0.888 (95% CI: 0.762–0.961), which was superior to the clinical model (0.787, 95% CI: 0.643–0.893; p = 0.049) and comparable to the radiomics model (0.879, 95% CI: 0.751–0.965; p > 0.05). The nomogram model achieved a sensitivity of 90.5% and a specificity of 76.9% in the validation dataset.Conclusions: The nomogram model could be considered as a noninvasive method to predict VPI with either highly sensitive or highly specific diagnoses depending on clinical needs.

Objective: We explored whether radiomics features extracted from diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) images can predict the clinical outcome of patients with acute ischaemic stroke. This study was conducted to investigate and validate a radiomics nomogram for predicting acute ischaemic stroke prognosis.Methods: A total of 257 patients with acute ischaemic stroke from three clinical centres were retrospectively assessed from February 2019 to July 2022. According to the modified Rankin scale (mRS) at 3 months, the patients were divided into a favourable outcome group (mRS of 0–2) and an unfavourable outcome group (mRS of 3−6). The high-throughput features from the regions of interest (ROIs) within the radiologist-drawn contour by AK software were extracted. We used two feature selection methods, minimum redundancy and maximum (mRMR) and the least absolute shrinkage and selection operator algorithm (LASSO), to select the features. Three radiomics models (DWI, FLAIR, and DWI-FLAIR) were established. A radiomics nomogram with patient characteristics and radiomics signature was built using a multivariate logistic regression model. The performance of the nomogram was evaluated in the test and validation sets. Ultimately, decision curve analysis was implemented to assess the clinical value of the nomogram.Results: The FLAIR, DWI, and DWI-FLAIR radiomics model exhibited good prediction performance, with area under the curve (AUCs) of 0.922 (95% CI: 0.876−0.968), 0.875 (95% CI: 0.815−0.935), and 0.895 (95% CI: 0.840−0.950). The radiomics nomogram with clinical characteristics including the overall cerebral small vessel disease (CSVD) burden score, hemorrhagic transformation (HT) and admission National Institutes of Health Stroke Scale score (NIHSS) score and the FLAIR Radscore presented good discriminatory potential in the training set (AUC = 0.94; 95% CI: 0.90−0.98) and test set (AUC = 0.94; 95% CI: 0.87−1), which was validated in the validation set 1 (AUC = 0.95; 95% CI: 0.88−1) and validation set 2 (AUC = 0.90; 95% CI: 0.768−1). In addition, it demonstrated good calibration, and decision curve analysis confirmed the clinical value of this nomogram.Conclusion: This non-invasive clinical-FLIAR radiomics nomogram shows good performance in predicting ischaemic stroke prognosis after thrombolysis.