To assess the performance of a Deep Neural Network (DNN)-based prototype algorithm for automated PE detection on CTPA scans. Patients who had previously undergone CTPA with three different systems (SOMATOM Force, go.Top, and Definition AS; Siemens Healthineers, Forchheim, Germany) because of suspected PE from September 2022 to January 2023 were retrospectively enrolled in this study (n = 1,000, 58.8 % women). For detailed evaluation, all PE were divided into three location-based subgroups: central arteries, lobar branches, and peripheral regions. Clinical reports served as ground truth. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were determined to evaluate the performance of DNN-based PE detection. Cases were excluded due to incomplete data (n = 32), inconclusive report (n = 17), insufficient contrast detected in the pulmonary trunk (n = 40), or failure of the preprocessing algorithms (n = 8). Therefore, the final cohort included 903 cases with a PE prevalence of 12 % (n = 110). The model achieved a sensitivity, specificity, PPV, and NPV of 84.6, 95.1, 70.5, and 97.8 %, respectively, and delivered an overall accuracy of 93.8 %. Among the false positive cases (n = 39), common sources of error included lung masses, pneumonia, and contrast flow artifacts. Common sources of false negatives (n = 17) included chronic and subsegmental PEs. The proposed DNN-based algorithm provides excellent performance for the detection of PE, suggesting its potential utility to support radiologists in clinical reading and exam prioritization.

Current lung cancer screening guidelines recommend annual low-dose computed tomography (LDCT) for high-risk individuals. However, the effectiveness of LDCT in non-high-risk individuals remains inadequately explored. With the incidence of lung cancer steadily increasing among non-high-risk individuals, this study aims to assess the risk of lung cancer in non-high-risk individuals and evaluate the potential of thin-section LDCT reconstruction combined with artificial intelligence (LDCT-TRAI) as a screening tool. A real-world cohort study on lung cancer screening was conducted at the West China Hospital of Sichuan University from January 2010 to July 2021. Participants were screened using either LDCT-TRAI or traditional thick-section LDCT without AI (traditional LDCT) . The AI system employed was the uAI-ChestCare software. Lung cancer diagnoses were confirmed through pathological examination. Among the 259 121 enrolled non-high-risk participants, 87 260 (33.7%) had positive screening results. Within 1 year, 728 (0.3%) participants were diagnosed with lung cancer, of whom 87.1% (634/728) were never-smokers, and 92.7% (675/728) presented with stage I disease. Compared with traditional LDCT, LDCT-TRAI demonstrated a higher lung cancer detection rate (0.3% vs. 0.2%, <i>P</i> < 0.001), particularly for stage I cancers (94.4% vs. 83.2%, <i>P</i> < 0.001), and was associated with improved survival outcomes (5-year overall survival rate: 95.4% vs. 81.3%, <i>P</i> < 0.0001). These findings highlight the importance of expanding lung cancer screening to non-high-risk populations, especially never-smokers. LDCT-TRAI outperformed traditional LDCT in detecting early-stage cancers and improving survival outcomes, underscoring its potential as a more effective screening tool for early lung cancer detection in this population.

Artificial Intelligence (AI) has been shown to enhance fracture-detection-accuracy, but the most effective AI-implementation in clinical practice is less well understood. In the current study, four approaches to AI-implementation are evaluated for their impact on AI-effectiveness. Retrospective single-center study based on all consecutive, around-the-clock radiographic examinations for suspected fractures, and accompanying clinical-practice radiologist-diagnoses, between January and March 2023. These image-sets were independently analysed by a dedicated bone-fracture-detection-AI. Findings were combined with radiologist clinical-practice diagnoses to simulate the four AI-implementation methods deemed most relevant to clinical workflows: AI-standalone (radiologist-findings not consulted); AI-problem-solving (AI-findings consulted when radiologist in doubt); AI-triage (radiologist-findings consulted when AI in doubt); and AI-safety net (AI-findings consulted when radiologist diagnosis negative). Reference-standard diagnoses were established by two senior musculoskeletal-radiologists (by consensus in cases of disagreement). Radiologist- and radiologist + AI diagnoses were compared for false negatives (FN), false positives (FP) and their clinical consequences. Experience-level-subgroups radiologists-in-training-, non-musculoskeletal-radiologists, and dedicated musculoskeletal-radiologists were analysed separately. 1508 image-sets were included (1227 unique patients; 40 radiologist-readers). Radiologist results were: 2.7 % FN (40/1508), 28 with clinical consequences; 1.2 % FP (18/1508), 2 received full-fracture treatments (11.1 %). All AI-implementation methods changed overall FN and FP with statistical significance (p < 0.001): AI-standalone 1.5 % FN (23/1508; 11 consequences), 6.8 % FP (103/1508); AI-problem-solving 3.2 % FN (48/1508; 31 consequences), 0.6 % FP (9/1508); AI-triage 2.1 % FN (32/1508; 18 consequences), 1.7 % FP (26/1508); AI-safety net 0.07 % FN (1/1508; 1 consequence), 7.6 % FP (115/1508). Subgroups show similar trends, except AI-triage increased FN for all subgroups except radiologists-in-training. Implementation methods have a large impact on AI-effectiveness. These results suggest AI should not be considered for problem-solving or triage at this time; AI standalone performs better than either and may be a source of assistance where radiologists are unavailable. Best results were obtained implementing AI as safety net, which eliminates missed fractures with serious clinical consequences; even though false positives are increased, unnecessary treatments are limited.

In the healthcare field, brain tumor causes irregular development of cells in the brain. One of the popular ways to identify the brain tumor and its progression is magnetic resonance imaging (MRI). However, existing methods often suffer from high computational complexity, noise interference, and limited accuracy, which affect the early diagnosis of brain tumor. For resolving such issues, a high-performance computing model, such as big data-based detection, is utilized. As a result, this work proposes a novel approach named parallel quantum dilated convolutional neural network (PQDCNN)-based brain tumor detection using the Map-Reducer. The data partitioning is the prime process, which is done using the Fuzzy local information C-means clustering (FLICM). The partitioned data is subjected to the map reducer. In the mapper, the Medav filtering removes the noise, and the tumor area segmentation is done by a transformer model named TransBTSV2. After segmenting the tumor part, image augmentation and feature extraction are done. In the reducer phase, the brain tumor is detected using the proposed PQDCNN. Furthermore, the efficiency of PQDCNN is validated using the accuracy, sensitivity, and specificity metrics, and the ideal values of 91.52%, 91.69%, and 92.26% are achieved.

To compare prostate cancer lesion detection using conventional and artificial intelligence (AI)-assisted image interpretation at multiparametric MRI (mpMRI). A retrospective study of 53 consecutive patients who underwent prostate mpMRI and subsequent prostate tissue sampling was performed. Two board-certified radiologists (with 4 and 12 years of experience) blinded to the clinical information interpreted anonymized exams using the PI-RADS v2.1 framework without and with an AI-assistance tool. The AI software tool provided radiologists with gland segmentation and automated lesion detection assigning a probability score for the likelihood of the presence of clinically significant prostate cancer (csPCa). The reference standard for all cases was the prostate pathology from systematic and targeted biopsies. Statistical analyses assessed interrater agreement and compared diagnostic performances with and without AI assistance. Within the entire cohort, 42 patients (79 %) harbored Gleason-positive disease, with 25 patients (47 %) having csPCa. Radiologists' diagnostic performance for csPCa was significantly improved over conventional interpretation with AI assistance (reader A: AUC 0.82 vs. 0.72, p = 0.03; reader B: AUC 0.78 vs. 0.69, p = 0.03). Without AI assistance, 81 % (n = 36; 95 % CI: 0.89-0.91) of the lesions were scored similarly by radiologists for lesion-level characteristics, and with AI assistance, 59 % (26, 0.82-0.89) of the lesions were scored similarly. For reader A, there was a significant difference in PI-RADS scores (p = 0.02) between AI-assisted and non-assisted assessments. Signficant differences were not detected for reader B. AI-assisted prostate mMRI interpretation improved radiologist diagnostic performance over conventional interpretation independent of reader experience.

Segmentation is a critical process in medical image interpretation. It is also essential for preparing training datasets for machine learning (ML)-based solutions. Despite technological advancements, achieving fully automatic segmentation is still challenging. User interaction is required to initiate the process, either by defining points or regions of interest, or by verifying and refining the output. One of the complex structures that requires semi-automatic segmentation procedures or manually defined training datasets is the lumbar spine. Automating the placement of a point within each lumbar vertebral body could significantly reduce user interaction in these procedures. A new method for automatically locating lumbar vertebral bodies in sagittal magnetic resonance images (MRI) is presented. The method integrates different image processing techniques and relies on the vertebral body morphology. Testing was mainly performed using 50 MRI scans that were previously annotated manually by placing a point at the centre of each lumbar vertebral body. A complementary public dataset was also used to assess robustness. Evaluation metrics included the correct labelling of each structure, the inclusion of each point within the corresponding vertebral body area, and the accuracy of the locations relative to the vertebral body centres using root mean squared error (RMSE) and mean absolute error (MAE). A one-sample Student's t-test was also performed to find the distance beyond which differences are considered significant (α = 0.05). All lumbar vertebral bodies from the primary dataset were correctly labelled, and the average RMSE and MAE between the automatic and manual locations were less than 5 mm. Distances to the vertebral body centres were found to be significantly less than 4.33 mm with a p-value < 0.05, and significantly less than half the average minimum diameter of a lumbar vertebral body with a p-value < 0.00001. Results from the complementary public dataset include high labelling and inclusion rates (85.1% and 94.3%, respectively), and similar accuracy values. The proposed method successfully achieves robust and accurate automatic placement of points within each lumbar vertebral body. The automation of this process enables the transition from semi-automatic to fully automatic methods, thus reducing error-prone and time-consuming user interaction, and facilitating the creation of training datasets for ML-based solutions.

This study assessed the diagnostic accuracy and prognostic implications of an artificial intelligence (AI) tool for coronary artery calcification (CAC) assessment on nongated, noncontrast thoracic computed tomography (CT). A single-centre retrospective analysis of 75 consecutive patients per age group (<40, 40-49, 50-59, 60-69, 70-79, 80-89, and ≥90 years) undergoing non-gated, non-contrast CT (January-December 2015) was conducted. AI analysis reported CAC presence and generated an Agatston score, and the performance was compared with baseline CT reports and a dedicated radiologist re-review. Interobserver variability between AI and radiologist assessments was measured using Cohen's κ. All-cause mortality was recorded, and its association with AI-detected CAC was tested. A total of 291 patients (mean age: 64 ± 19, 51% female) were included, with 80% (234/291) of AI reports passing radiologist quality assessment. CAC was reported on 7% (17/234) of initial clinical reports, 58% (135/234) on radiologist re-review, and 57% (134/234) by AI analysis. After manual quality assurance (QA) assessment, the AI tool demonstrated high sensitivity (96%), specificity (96%), positive predictive value (95%), and negative predictive value (97%) for CAC detection compared with radiologist re-review. Interobserver agreement was strong for CAC prevalence (κ = 0.92) and moderate for severity grading (κ = 0.60). AI-detected CAC presence and severity predicted all-cause mortality (p < 0.001). The AI tool exhibited feasible analysis potential for non-contrast, non-gated thoracic CTs, offering prognostic insights if integrated into routine practice. Nonetheless, manual quality assessment remains essential. This AI tool represents a potential enhancement to CAC detection and reporting on routine noncardiac chest CT.

Cerebral aneurysms pose a significant risk to patient safety, particularly when ruptured, emphasizing the need for early detection and accurate prediction. Traditional diagnostic methods, reliant on clinician-based evaluations, face challenges in sensitivity and consistency, prompting the exploration of deep learning (DL) systems for improved performance. This systematic review and meta-analysis assessed the performance of DL models in detecting and predicting intracranial aneurysms compared to clinician-based evaluations. Imaging modalities included CT angiography (CTA), digital subtraction angiography (DSA), and time-of-flight MR angiography (TOF-MRA). Data on lesion-wise sensitivity, specificity, and the impact of DL assistance on clinician performance were analyzed. Subgroup analyses evaluated DL sensitivity by aneurysm size and location, and interrater agreement was measured using Fleiss' κ. DL systems achieved an overall lesion-wise sensitivity of 90 % and specificity of 94 %, outperforming human diagnostics. Clinician specificity improved significantly with DL assistance, increasing from 83 % to 85 % in the patient-wise scenario and from 93 % to 95 % in the lesion-wise scenario. Similarly, clinician sensitivity also showed notable improvement with DL assistance, rising from 82 % to 96 % in the patient-wise scenario and from 82 % to 88 % in the lesion-wise scenario. Subgroup analysis showed DL sensitivity varied with aneurysm size and location, reaching 100 % for aneurysms larger than 10 mm. Additionally, DL assistance improved interrater agreement among clinicians, with Fleiss' κ increasing from 0.668 to 0.862. DL models demonstrate transformative potential in managing cerebral aneurysms by enhancing diagnostic accuracy, reducing missed cases, and supporting clinical decision-making. However, further validation in diverse clinical settings and seamless integration into standard workflows are necessary to fully realize the benefits of DL-driven diagnostics.

Mitral valve (MV) assessment is key to diagnosing valvular disease and to addressing its serious downstream complications. Cardiac magnetic resonance (CMR) has become an essential diagnostic tool in MV disease, offering detailed views of the valve structure and function, and overcoming the limitations of other imaging modalities. Automated detection of the MV leaflets in CMR could enable rapid and precise assessments that enhance diagnostic accuracy. To address this gap, we introduce DeepValve, the first deep learning (DL) pipeline for MV detection using CMR. Within DeepValve, we tested three valve detection models: a keypoint-regression model (UNET-REG), a segmentation model (UNET-SEG) and a hybrid model based on keypoint detection (DSNT-REG). We also propose metrics for evaluating the quality of MV detection, including Procrustes-based metrics (UNET-REG, DSNT-REG) and customized Dice-based metrics (UNET-SEG). We developed and tested our models on a clinical dataset comprising 120 CMR images from patients with confirmed MV disease (mitral valve prolapse and mitral annular disjunction). Our results show that DSNT-REG delivered the best regression performance, accurately locating landmark locations. UNET-SEG achieved satisfactory Dice and customized Dice scores, also accurately predicting valve location and topology. Overall, our work represents a critical first step towards automated MV assessment using DL in CMR and paving the way for improved clinical assessment in MV disease.

Lung cancer is one of the leading causes of cancer-related mortality worldwide, with most cases diagnosed at advanced stages where curative treatment options are limited. Low-dose computed tomography (LDCT) for lung cancer screening (LCS) of individuals selected based on age and smoking history has shown a significant reduction in lung cancer-specific mortality. The number needed to screen to prevent one death from lung cancer is lower than that for breast cancer, cervical cancer, and colorectal cancer. Despite the substantial impact on reducing lung cancer-related mortality and proof that LCS with LDCT is effective, uptake of LCS has been low and LCS eligibility criteria remain imperfect. While LCS programs have historically faced patient recruitment challenges, research suggests that there are novel opportunities to both identify and improve screening for at-risk populations. In this review, we discuss the global obstacles to implementing LCS programs and strategies to overcome barriers in resource-limited settings. We explore successful approaches to promote LCS through robust engagement with community partners. Finally, we examine opportunities to enhance LCS in at-risk populations not captured by current eligibility criteria, including never smokers and individuals with a family history of lung cancer, with a focus on early detection through novel artificial intelligence technologies.