A deep-learning model for intracranial aneurysm detection on CT angiography images in China: a stepwise, multicentre, early-stage clinical validation study.

BACKGROUND: Artificial intelligence (AI) models in real-world implementation are scarce. Our study aimed to develop a CT angiography (CTA)-based AI model for intracranial aneurysm detection, assess how it helps clinicians improve diagnostic performance, and validate its application in real-world clinical implementation. METHODS: We developed a deep-learning model using 16 546 head and neck CTA examination images from 14 517 patients at eight Chinese hospitals. Using an adapted, stepwise implementation and evaluation, 120 certified clinicians from 15 geographically different hospitals were recruited. Initially, the AI model was externally validated with images of 900 digital subtraction angiography-verified CTA cases (examinations) and compared with the performance of 24 clinicians who each viewed 300 of these cases (stage 1). Next, as a further external validation a multi-reader multi-case study enrolled 48 clinicians to individually review 298 digital subtraction angiography-verified CTA cases (stage 2). The clinicians reviewed each CTA examination twice (ie, with and without the AI model), separated by a 4-week washout period. Then, a randomised open-label comparison study enrolled 48 clinicians to assess the acceptance and performance of this AI model (stage 3). Finally, the model was prospectively deployed and validated in 1562 real-world clinical CTA cases. FINDINGS: The AI model in the internal dataset achieved a patient-level diagnostic sensitivity of 0·957 (95% CI 0·939-0·971) and a higher patient-level diagnostic sensitivity than clinicians (0·943 [0·921-0·961] vs 0·658 [0·644-0·672]; p<0·0001) in the external dataset. In the multi-reader multi-case study, the AI-assisted strategy improved clinicians' diagnostic performance both on a per-patient basis (the area under the receiver operating characteristic curves [AUCs]; 0·795 [0·761-0·830] without AI vs 0·878 [0·850-0·906] with AI; p<0·0001) and a per-aneurysm basis (the area under the weighted alternative free-response receiver operating characteristic curves; 0·765 [0·732-0·799] vs 0·865 [0·839-0·891]; p<0·0001). Reading time decreased with the aid of the AI model (87·5 s vs 82·7 s, p<0·0001). In the randomised open-label comparison study, clinicians in the AI-assisted group had a high acceptance of the AI model (92·6% adoption rate), and a higher AUC when compared with the control group (0·858 [95% CI 0·850-0·866] vs 0·789 [0·780-0·799]; p<0·0001). In the prospective study, the AI model had a 0·51% (8/1570) error rate due to poor-quality CTA images and recognition failure. The model had a high negative predictive value of 0·998 (0·994-1·000) and significantly improved the diagnostic performance of clinicians; AUC improved from 0·787 (95% CI 0·766-0·808) to 0·909 (0·894-0·923; p<0·0001) and patient-level sensitivity improved from 0·590 (0·511-0·666) to 0·825 (0·759-0·880; p<0·0001). INTERPRETATION: This AI model demonstrated strong clinical potential for intracranial aneurysm detection with improved clinician diagnostic performance, high acceptance, and practical implementation in real-world clinical cases. FUNDING: National Natural Science Foundation of China. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

Associations between R.E.N.A.L. nephrometry score and survival outcomes in renal tumours.

OBJECTIVE: The radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score could be used to predict surgical outcomes and renal tumour aggressiveness. We aimed to analyse its associations with survival outcomes. METHODS: We included 1368 patients with sporadic, unilateral and non-metastatic renal tumours who received curative nephrectomy in Zhongshan Hospital from January 2009 to September 2019. Radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores were assigned by three urologists based on preoperative CT/MRI scans. Correlations between parameters or sum of radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores, overall survival and recurrence-free survival were analysed by Kaplan-Meier analyses and the multivariate Cox regression model. We further compared survival outcomes between patients who received partial nephrectomy and patients who received radical nephrectomy. RESULTS: We observed statistically significant associations between all components of radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores and oncologic outcomes, including R (radius) (overall survival, P < 0.001; recurrence-free survival , P < 0.001), E (exophytic/endophytic) (overall survival, P = 0.003; recurrence-free survival, P < 0.001), N (nearness) (overall survival, P = 0.063; recurrence-free survival, P < 0.001), A (anterior/posterior) (overall survival, P < 0.001; recurrence-free survival, P = 0.005), L (location) (overall survival, P = 0.008; recurrence-free survival, P < 0.001) and suffix 'h' (overall survival, P = 0.237; recurrence-free survival, P = 0.034). Kaplan-Meier curves of overall survival and recurrence-free survival rates were significantly different when stratified by radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score complexity group (overall survival, P < 0.001; recurrence-free survival, P < 0.001). After adjusting for tumour stage and grade, radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score as continuous variables was an adverse independent risk factor for survival outcomes [P = 0.027, hazard ratio (95% confidence interval) = 1.151 (1.016-1.303)] and recurrence-free survival [P < 0.001, hazard ratio (95% confidence interval) = 1.299 (1.125-1.501)]. For tumours with radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores of 4 and 5, partial nephrectomy showed a survival benefit than radical nephrectomy. CONCLUSION: Both components and complexity groups of the radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score are associated with survival outcomes in renal tumour patients.

Radiomics signature for predicting postoperative disease-free survival of patients with gastric cancer: development and validation of a predictive nomogram.

PURPOSE Radiomics can be used to determine the prognosis of gastric cancer (GC). The objective of this study was to predict the disease-free survival (DFS) after GC surgery based on computed tomography-enhanced images combined with clinical features. METHODS Clinical, imaging, and pathological data of patients who underwent gastric adenocarcinoma resection from June 2015 to May 2019 were retrospectively analyzed. The primary outcome was DFS. Radiomics features were selected using Least Absolute Shrinkage and Selection Operator algorithm and converted into the Rad-score. A nomogram was constructed based on the Radscore and other clinical factors. The Rad-score and nomogram were validated in the training and validation groups. RESULTS Totally, 179 patients were randomly divided into the training (n=124) and validation (n=55) groups. In the training group, validation group, and overall population, the Rad-score could be divided into categories indicating low, moderate, and high risk of recurrence, metastasis, or death; all risk categories showed a significant difference between the training, validation, and overall population groups (all P < .001). Positive lymph nodes (hazard ratio (HR)=3.07, 95% CI: 1.52-6.23, P=.002), cancer antigen-125 (HR=3.24, 95% CI: 1.54-6.80, P=.002), and the Radscore (HR=0.73, 95% CI: 0.61-0.87, P < .001) were independently associated with DFS. These 3 variables were used to construct a nomogram. In the training group, the areas under the curve at 3 years were 0.758 and 0.776 for the Rad-score and the nomogram, respectively, while they were both 1.000 in the validation group. The net benefit rate was analyzed using a decision curve in the training and validation groups, and the nomogram was superior to the single Rad-score. CONCLUSION Rad-score is an independent factor for DFS after gastrectomy for GC. The nomogram established in this study could be an effective tool for the clinical prediction of DFS after gastrectomy.

Binary Particle Swarm Optimization Intelligent Feature Optimization Algorithm-Based Magnetic Resonance Image in the Diagnosis of Adrenal Tumor.

This research was aimed to explore the application value of magnetic resonance imaging (MRI) based on binary particle swarm optimization algorithm (BPSO) in the diagnosis of adrenal tumors. 120 patients with adrenal tumors admitted to the hospital were selected and randomly divided into the control group (conventional MRI examination) and the observation group (MRI examination based on the BPSO intelligent feature optimization algorithm), with 60 cases in each group. The sensitivity, specificity, accuracy, and Kappa of the diagnostic methods were compared between the two groups. The results showed that the calculation rate of the BPSO algorithm was the best under the same processing effect (P < 0.05). Optimization algorithm-based MRI is used in the diagnosis of adrenal tumors, and the results showed that the sensitivity, specificity, accuracy, and Kappa (83.33%, 79.17%, 81.67%, and 0.69) of the observation group were higher than those of the control group (50%, 75%, 58.33%, and 0.45). The similarity of tumor location results in the observation group (89.24%) was significantly higher than that in the control group (65.9%) (P < 0.05). In conclusion, compared with SFFS and other algorithms, the BPSO algorithm has more advantages in calculation speed. MRI based on the BPSO intelligent feature optimization algorithm has a good diagnostic effect and higher accuracy in adrenal tumors, showing the good development prospects of computer intelligence technology in the field of medicine.

Application of CT Imaging in the Diagnosis of Cerebral Hemorrhage and Cerebral Infarction Nerve Damage.

OBJECTIVE: This article analyzes computed tomography (CT) angiography and CT perfusion imaging parameters of patients with cerebral hemorrhage and cerebral infarction, and explores its diagnostic value and clinical significance in the diagnosis of cerebral hemorrhage and cerebral infarction. METHODS: This article selected 52 patients with ischemic cerebrovascular disease who were treated in our neurology department from January 2015 to December 2018. Twenty of these patients had transient ischemic attacks, and 32 had neurologic damage. According to the onset time, patients with cerebral infarction were divided into 12 cases in group A (onset time <6 hours) and 20 cases in group B (onset time >6 hours). CT perfusion imaging was performed within 24 hours after the onset of cerebral hemorrhage. Patients immediately underwent CT perfusion imaging in the cerebral infarction group, and recorded the CT perfusion imaging parameters to analyze the nerve damage. RESULTS: The results showed that among the 20 patients with cerebral hemorrhage, 14 cases had anterior circulation cerebral hemorrhage, and 6 cases had posterior circulation cerebral hemorrhage. No lesions were found on CT and magnetic resonance imaging. CT angiography of 20 patients with cerebral hemorrhage showed that 18 patients had vascular lesions. In the cerebral infarction group, 30 cases developed vascular disease. CONCLUSIONS: Studies have confirmed that changes in brain CT perfusion imaging parameters can reflect changes in brain blood perfusion to diagnose nerve damage, and mean transit time and time to peak are the most sensitive during the diagnosis. CT angiography can detect the degree of stenosis and has important clinical value for the etiology of cerebral hemorrhage and cerebral infarction.