Using an artificial intelligence model to detect and localize visible clinically significant prostate cancer in prostate magnetic resonance imaging: a multicenter external validation study.

Background: An increasing number of patients with suspected clinically significant prostate cancer (csPCa) are undergoing prostate multiparametric magnetic resonance imaging (mpMRI). The role of artificial intelligence (AI) algorithms in interpreting prostate mpMRI needs to be tested with multicenter external data. This study aimed to investigate the diagnostic efficacy of an AI model in detecting and localizing visible csPCa on mpMRI a multicenter external data set. Methods: The data of 2,105 patients suspected of having prostate cancer from four hospitals were retrospectively collected to develop an AI model to detect and localize suspicious csPCa. The lesions were annotated based on pathology records by two radiologists. Diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) values were used as the input for the three-dimensional U-Net framework. Subsequently, the model was validated using an external data set comprising the data of 557 patients from three hospitals. Sensitivity, specificity, and accuracy were employed to evaluate the diagnostic efficacy of the model. Results: At the lesion level, the model had a sensitivity of 0.654. At the overall sextant level, the model had a sensitivity, specificity, and accuracy of 0.846, 0.884, and 0.874, respectively. At the patient level, the model had a sensitivity, specificity, and accuracy of 0.943, 0.776, and 0.849, respectively. The AI-predicted accuracy for the csPCa patients (231/245, 0.943) was significantly higher than that for the non-csPCa patients (242/312, 0.776) (P<0.001). The lesion number and tumor volume were greater in the correctly diagnosed patients than the incorrectly diagnosed patients (both P<0.001). Among the positive patients, those with lower average ADC values had a higher rate of correct diagnosis than those with higher average ADC values (P=0.01). Conclusions: The AI model exhibited acceptable accuracy in detecting and localizing visible csPCa at the patient and sextant levels. However, further improvements need to be made to enhance the sensitivity of the model at the lesion level.

Artificial intelligence as diagnostic aiding tool in cases of Prostate Imaging Reporting and Data System category 3: the results of retrospective multi-center cohort study.

PURPOSE: To study the effect of artificial intelligence (AI) on the diagnostic performance of radiologists in interpreting prostate mpMRI images of the PI-RADS 3 category. METHODS: In this multicenter study, 16 radiologists were invited to interpret prostate mpMRI cases with and without AI. The study included a total of 87 cases initially diagnosed as PI-RADS 3 by radiologists without AI, with 28 cases being clinically significant cancers (csPCa) and 59 cases being non-csPCa. The study compared the diagnostic efficacy between readings without and with AI, the reading time, and confidence levels. RESULTS: AI changed the diagnosis in 65 out of 87 cases. Among the 59 non-csPCa cases, 41 were correctly downgraded to PI-RADS 1-2, and 9 were incorrectly upgraded to PI-RADS 4-5. For the 28 csPCa cases, 20 were correctly upgraded to PI-RADS 4-5, and 5 were incorrectly downgraded to PI-RADS 1-2. Radiologists assisted by AI achieved higher diagnostic specificity and accuracy than those without AI [0.695 vs 0.000 and 0.736 vs 0.322, both P < 0.001]. Sensitivity with AI was not significantly different from that without AI [0.821 vs 1.000, P = 1.000]. AI reduced reading time significantly compared to without AI (mean: 351 seconds, P < 0.001). The diagnostic confidence score with AI was significantly higher than that without AI (Cohen Kappa: -0.016). CONCLUSION: With the help of AI, there was an improvement in the diagnostic accuracy of PI-RADS category 3 cases by radiologists. There is also an increase in diagnostic efficiency and diagnostic confidence.

A multicenter study of artificial intelligence-aided software for detecting visible clinically significant prostate cancer on mpMRI.

BACKGROUND: AI-based software may improve the performance of radiologists when detecting clinically significant prostate cancer (csPCa). This study aims to compare the performance of radiologists in detecting MRI-visible csPCa on MRI with and without AI-based software. MATERIALS AND METHODS: In total, 480 multiparametric MRI (mpMRI) images were retrospectively collected from eleven different MR devices, with 349 csPCa lesions in 180 (37.5%) cases. The csPCa areas were annotated based on pathology. Sixteen radiologists from four hospitals participated in reading. Each radiologist was randomly assigned to 30 cases and diagnosed twice. Half cases were interpreted without AI, and the other half were interpreted with AI. After four weeks, the cases were read again in switched mode. The mean diagnostic performance was compared using sensitivity and specificity on lesion level and patient level. The median reading time and diagnostic confidence were assessed. RESULTS: On lesion level, AI-aided improved the sensitivity from 40.1% to 59.0% (18.9% increased; 95% confidence interval (CI) [11.5, 26.1]; p < .001). On patient level, AI-aided improved the specificity from 57.7 to 71.7% (14.0% increase, 95% CI [6.4, 21.4]; p < .001) while preserving the sensitivity (88.3% vs. 93.9%, p = 0.06). AI-aided reduced the median reading time of one case by 56.3% from 423 to 185 s (238-s decrease, 95% CI [219, 260]; p < .001), and the median diagnostic confidence score was increased by 10.3% from 3.9 to 4.3 (0.4-score increase, 95% CI [0.3, 0.5]; p < .001). CONCLUSIONS: AI software improves the performance of radiologists by reducing false positive detection of prostate cancer patients and also improving reading times and diagnostic confidence. CLINICAL RELEVANCE STATEMENT: This study involves the process of data collection, randomization and crossover reading procedure.

Exploration of CT manifestations of different clinical types of novel coronavirus pneumonia.

BACKGROUND: To explore computed tomography (CT) characteristics of the 2019 novel coronavirus (COVID-19) pneumonia and explore variations among the different clinical types. METHODS: Clinical and CT imaging data of 43 patients diagnosed with COVID-19 in our hospital and the cooperative hospital between January 15-30, 2020 were collected (27 male and 16 female). Patients were classified as common type (26 cases, 60%), severe type (14 cases, 33%) or critical type (three cases, 7%) according to the new coronavirus pneumonia treatment scheme (sixth edition). Patient clinical data and CT images were analyzed and evaluated. RESULTS: Fever was the main symptom in common type COVID-19 cases (23/26, 88.46%). Both severe and critical type COVID-19 patients had fever and cough symptoms, and dyspnea was observed in all three critical COVID-19 patients. CT manifestations in the common type COVID-19 cohort were bilateral involvement (20/26, 71%), multiple lesions (14/26, 54%), ground-glass density shadow (17/26, 65%), and some cases were accompanied by local consolidation (9/26, 35%), which is consistent with early stage COVID-19 CT performance. CT manifestations in the severe and critical types involved both lungs. Severe COVID-19 cases predominantly consisted of multiple mixed-density lesions (10/14, 71%), and a few patients showed diffuse lung glass density shadows in both lungs (4/14, 29%), which is consistent with the progression stage COVID-19 CT performance. Critical COVID-19 cases exhibited mixed-density lesions, and two cases displayed "white lung", which is the CT manifestation at the severe COVID-19 stage. Only one critical COVID-19 patient had pleural effusion. CONCLUSIONS: The CT manifestations of COVID-19 are specific and there are variations between different clinical types. Thus, CT is an important clinical tool for early diagnosis and assessment of the severity of COVID-19.

Utility of chest CT in diagnosis of COVID-19 pneumonia.

PURPOSE: We aimed to explore the imaging findings of computed tomography (CT) in diagnosing coronavirus disease 2019 (COVID-19) and its clinical value for further evaluation of suspected cases. METHODS: Files of 155 patients visiting the fever clinics at our hospital and affiliated hospitals from January 20th to February 9th, 2020 were searched. Among them, 140 cases (including 82 males and 58 females) were included as suspected COVID-19 cases based on clinical and epidemiological history; the CT image features of 70 cases with suggestive findings on CT, confirmed by positive nucleic acid test were analyzed and evaluated. The sensitivity and specificity of CT in diagnosing COVID-19 were evaluated in patients with epidemiological history. RESULTS: Of the 70 patients, 84.3% showed bilateral lung involvement on CT; 27 cases (38.6%) showed ground-glass opacity (GGO), which was mostly distributed in the subpleural area (55.7%), and this sign was mainly observed in early COVID-19 patients. In addition, 41 cases (58.6%) manifested GGO combined with focal consolidation opacity, 2 (2.8%) had flake-like consolidation opacity, with involvements of the periphery of lung field and the central zone (44.3%), and this sign was mostly observed in severe or critical patients. Concomitant signs such as pleural effusion and mediastinal lymph node enlargement were rare. Among patients with epidemiological history, the sensitivity of CT in diagnosing COVID-19 was 89.7% (70/78), and the specificity was 88.7% (55/62). CONCLUSION: CT shows high sensitivity and specificity in diagnosing COVID-19. CT is an important examination method in evaluation of suspected cases and assessment of disease severity.