ObjectiveTo explore the efficacy of artificial intelligence (AI) detection on pulmonary nodule compared with multidisciplinary team (MDT) in regional medical center.MethodsWe retrospectively analyzed the clinical data of 102 patients with lung nodules in the Xiamen Fifth Hospital from April to December 2020. There were 57 males and 45 females at age of 36-90 (48.8±11.6) years. The preoperative chest CT was imported into AI system to record the detected lung nodules. The detection rate of pulmonary nodules by AI system was calculated, and the sensitivity, specificity of AI in the different diagnosis of benign and malignant pulmonary was calculated and compared with manual film reading by MDT.ResultsA total of 322 nodules were detected by AI software system, and 305 nodules were manually detected by physicians (P<0.05). Among them, 113 pulmonary nodules were diagnosed by pathologist. Thirty-eight of 40 lung cancer nodules were AI high-risk nodules, the sensitivity was 95.0%, and 25 of 73 benign nodules were AI high-risk nodules, the specificity was 65.8%. Lung cancer nodules were correctly diagnosed by MDT, but benign nodules were still considered as lung cancer at the first diagnosis in 10 patients.ConclusionAI assisted diagnosis system has strong performance in the detection of pulmonary nodules, but it can not content itself with clinical needs in the differentiation of benign and malignant pulmonary nodules. The artificial intelligence system can be used as an auxiliary tool for MDT to detect pulmonary nodules in regional medical center.
ObjectiveTo investigate the clinical value of artificial intelligence (AI)-assisted chest computed tomography (CT) in the diagnosis of peripheral lung shadow. MethodsThe CT image data of 810 patients with peripheral pulmonary shadow treated by thoracic surgery in Tianjin Chest Hospital Affiliated to Tianjin University from January 2018 to July 2019 were retrospectively analyzed using AI-assisted chest CT imaging diagnosis system. There were 339 males and 471 females with a median age of 63 years. The malignant probability of preoperative AI-assisted diagnosis of peripheral pulmonary shadow was compared with the results of postoperative pathology. ResultsThe pathological diagnosis of 810 patients with peripheral pulmonary shadow was lung cancer in 627 (77.4%) patients, precancerous lesion in 30 (3.7%) patients and benign lesion in 153 (18.9%) patients. The median probability of malignant AI diagnosis before operation was 86.0% (lung cancer), 90.0% (precancerous lesion) and 37.0% (benign lesion), respectively. According to the analysis of receiver operating characteristic (ROC) curve of AI malignant probability distribution in this group of patients, the area under the ROC curve was 0.882. The critical value of malignant probability for diagnosis of lung cancer was 75.0% with a sensitivity of 0.856 and specificity of 0.814. A total of 571 patients were diagnosed with AI malignancy probability≥75.0%, among whom 537 patients were pathologically diagnosed as lung cancer with a positive predictive value of 94.0% (537/571). ConclusionThe AI-assisted chest CT diagnosis system has a high accuracy in the diagnosis of peripheral lung cancer with malignant probability≥75.0% as the diagnostic threshold.
Objective To develop an automatic diagnostic tool based on deep learning for lumbar spine stability and validate diagnostic accuracy. Methods Preoperative lumbar hyper-flexion and hyper-extension X-ray films were collected from 153 patients with lumbar disease. The following 5 key points were marked by 3 orthopedic surgeons: L4 posteroinferior, anterior inferior angles as well as L5 posterosuperior, anterior superior, and posterior inferior angles. The labeling results of each surgeon were preserved independently, and a total of three sets of labeling results were obtained. A total of 306 lumbar X-ray films were randomly divided into training (n=156), validation (n=50), and test (n=100) sets in a ratio of 3∶1∶2. A new neural network architecture, Swin-PGNet was proposed, which was trained using annotated radiograph images to automatically locate the lumbar vertebral key points and calculate L4, 5 intervertebral Cobb angle and L4 lumbar sliding distance through the predicted key points. The mean error and intra-class correlation coefficient (ICC) were used as an evaluation index, to compare the differences between surgeons’ annotations and Swin-PGNet on the three tasks (key point positioning, Cobb angle measurement, and lumbar sliding distance measurement). Meanwhile, the change of Cobb angle more than 11° was taken as the criterion of lumbar instability, and the lumbar sliding distance more than 3 mm was taken as the criterion of lumbar spondylolisthesis. The accuracy of surgeon annotation and Swin-PGNet in judging lumbar instability was compared. Results ① Key point: The mean error of key point location by Swin-PGNet was (1.407±0.939) mm, and by different surgeons was (3.034±2.612) mm. ② Cobb angle: The mean error of Swin-PGNet was (2.062±1.352)° and the mean error of surgeons was (3.580±2.338)°. There was no significant difference between Swin-PGNet and surgeons (P>0.05), but there was a significant difference between different surgeons (P<0.05). ③ Lumbar sliding distance: The mean error of Swin-PGNet was (1.656±0.878) mm and the mean error of surgeons was (1.884±1.612) mm. There was no significant difference between Swin-PGNet and surgeons and between different surgeons (P>0.05). The accuracy of lumbar instability diagnosed by surgeons and Swin-PGNet was 75.3% and 84.0%, respectively. The accuracy of lumbar spondylolisthesis diagnosed by surgeons and Swin-PGNet was 70.7% and 71.3%, respectively. There was no significant difference between Swin-PGNet and surgeons, as well as between different surgeons (P>0.05). ④ Consistency of lumbar stability diagnosis: The ICC of Cobb angle among different surgeons was 0.913 [95%CI (0.898, 0.934)] (P<0.05), and the ICC of lumbar sliding distance was 0.741 [95%CI (0.729, 0.796)] (P<0.05). The result showed that the annotating of the three surgeons were consistent. The ICC of Cobb angle between Swin-PGNet and surgeons was 0.922 [95%CI (0.891, 0.938)] (P<0.05), and the ICC of lumbar sliding distance was 0.748 [95%CI(0.726, 0.783)] (P<0.05). The result showed that the annotating of Swin-PGNet were consistent with those of surgeons. ConclusionThe automatic diagnostic tool for lumbar instability constructed based on deep learning can realize the automatic identification of lumbar instability and spondylolisthesis accurately and conveniently, which can effectively assist clinical diagnosis.
Myocardial infarction (MI) has the characteristics of high mortality rate, strong suddenness and invisibility. There are problems such as the delayed diagnosis, misdiagnosis and missed diagnosis in clinical practice. Electrocardiogram (ECG) examination is the simplest and fastest way to diagnose MI. The research on MI intelligent auxiliary diagnosis based on ECG is of great significance. On the basis of the pathophysiological mechanism of MI and characteristic changes in ECG, feature point extraction and morphology recognition of ECG, along with intelligent auxiliary diagnosis method of MI based on machine learning and deep learning are all summarized. The models, datasets, the number of ECG, the number of leads, input modes, evaluation methods and effects of different methods are compared. Finally, future research directions and development trends are pointed out, including data enhancement of MI, feature points and dynamic features extraction of ECG, the generalization and clinical interpretability of models, which are expected to provide references for researchers in related fields of MI intelligent auxiliary diagnosis.
In recent years, three-dimensional (3D) technology has been more and more widely used in the auxiliary diagnosis and treatment of structural heart disease (SHD), and is also an important basis for the application of other technologies such as artificial intelligence. However, there are still some problems to be solved in the clinical application of 3D technology. In this paper, the application of 3D technology in SHD field is reviewed, and the future development of 3D technology is prospected.