Intracranial aneurysm is a common life-threatening disease. Computed tomography angiography is recommended as the standard diagnosis tool; yet, interpretation can be time-consuming and challenging. We present a specific deep-learning-based model trained on 1,177 digital subtraction angiography verified bone-removal computed tomography angiography cases. The model has good tolerance to image quality and is tested with different manufacturers. Simulated real-world studies are conducted in consecutive internal and external cohorts, in which it achieves an improved patient-level sensitivity and lesion-level sensitivity compared to that of radiologists and expert neurosurgeons. A specific cohort of suspected acute ischemic stroke is employed and it is found that 99.0% predicted-negative cases can be trusted with high confidence, leading to a potential reduction in human workload. A prospective study is warranted to determine whether the algorithm could improve patients’ care in comparison to clinicians’ assessment.

Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accuratelyannotated datasets. If with the noisy-labeled images, the training procedure will immediately encounter difficulties, leading to a suboptimal classifier. This problem is even more crucial in the medical field, given that the annotation quality requires great expertise. In this paper, we propose an effective iterative learning framework for noisy-labeled medical image classification, to combat the lacking of high quality annotated medical data. Specifically, an online uncertainty sample mining method is proposed to eliminate the disturbance from noisylabeled images. Next, we design a sample re-weighting strategy to preserve the usefulness of correctly-labeled hard samples. Our proposed method is validated on skin lesion classification task, and achieved very promising results.

On the basis of the findings in the small series of patients evaluated, contrast-enhanced dual-energy CTA had diagnostic image quality at a lower radiation dose than digital subtraction CTA and high diagnostic accuracy compared with 3D DSA in the detection of intracranial aneurysms.

The purpose of the study was to compare the ability of dual energy CT (DECT) and perfusion scintigraphy (PS) to detect pulmonary embolism (PE) in a rabbit model. Gelfoam (n = 20) or saline (n = 4) was injected into the femoral vein of rabbits. After 2 h, DECT pulmonary angiography (CTPA) was used to create blood flow imaging (BFI) and fusion images. The rabbits then underwent PS. Pathological determination of locations and numbers of lung lobes with PE was recorded. The sensitivity and specificity for BFI, CTPA, fused images and PS were calculated using the pathological results as reference standards. Compared with pathological evaluation, CTPA correctly identified PE in 40 lobes and absence of emboli in 80 lobes, corresponding to a sensitivity and specificity of 100%. BFI and fused images correctly identified PE in 40 lobes and the absence of emboli in 78 lobes, corresponding to a sensitivity and specificity of 100% and 98%, respectively. PS correctly detected 27 lobes with PE and 65 lobes without PE, corresponding to a sensitivity and specificity of 68% and 81%, respectively. BFI, CTPA and fused images derived from a single contrast-enhanced DECT provide a higher diagnostic accuracy of detecting PE than PS in a rabbit model.