RESUMEN
The aim of our study is to validate a totally automated deep learning (DL)-based segmentation pipeline to screen abdominal aortic aneurysms (AAA) in computed tomography angiography (CTA) scans. We retrospectively evaluated 73 thoraco-abdominal CTAs (48 AAA and 25 control CTA) by means of a DL-based segmentation pipeline built on a 2.5D convolutional neural network (CNN) architecture to segment lumen and thrombus of the aorta. The maximum aortic diameter of the abdominal tract was compared using a threshold value (30 mm). Blinded manual measurements from a radiologist were done in order to create a true comparison. The screening pipeline was tested on 48 patients with aneurysm and 25 without aneurysm. The average diameter manually measured was 51.1 ± 14.4 mm for patients with aneurysms and 21.7 ± 3.6 mm for patients without aneurysms. The pipeline correctly classified 47 AAA out of 48 and 24 control patients out of 25 with 97% accuracy, 98% sensitivity, and 96% specificity. The automated pipeline of aneurysm measurements in the abdominal tract reported a median error with regard to the maximum abdominal diameter measurement of 1.3 mm. Our approach allowed for the maximum diameter of 51.2 ± 14.3 mm in patients with aneurysm and 22.0 ± 4.0 mm in patients without an aneurysm. The DL-based screening for AAA is a feasible and accurate method, calling for further validation using a larger pool of diagnostic images towards its clinical use.
Asunto(s)
Aneurisma de la Aorta Abdominal , Angiografía por Tomografía Computarizada , Humanos , Angiografía por Tomografía Computarizada/métodos , Inteligencia Artificial , Estudios Retrospectivos , Aneurisma de la Aorta Abdominal/diagnóstico por imagen , Tomografía Computarizada por Rayos XRESUMEN
Idiopathic pulmonary fibrosis, the archetype of pulmonary fibrosis (PF), is a chronic lung disease of a poor prognosis, characterized by progressively worsening of lung function. Although histology is still the gold standard for PF assessment in preclinical practice, histological data typically involve less than 1% of total lung volume and are not amenable to longitudinal studies. A miniaturized version of computed tomography (µCT) has been introduced to radiologically examine lung in preclinical murine models of PF. The linear relationship between X-ray attenuation and tissue density allows lung densitometry on total lung volume. However, the huge density changes caused by PF usually require manual segmentation by trained operators, limiting µCT deployment in preclinical routine. Deep learning approaches have achieved state-of-the-art performance in medical image segmentation. In this work, we propose a fully automated deep learning approach to segment right and left lung on µCT imaging and subsequently derive lung densitometry. Our pipeline first employs a convolutional network (CNN) for pre-processing at low-resolution and then a 2.5D CNN for higher-resolution segmentation, combining computational advantage of 2D and ability to address 3D spatial coherence without compromising accuracy. Finally, lungs are divided into compartments based on air content assessed by density. We validated this pipeline on 72 mice with different grades of PF, achieving a Dice score of 0.967 on test set. Our tests demonstrate that this automated tool allows for rapid and comprehensive analysis of µCT scans of PF murine models, thus laying the ground for its wider exploitation in preclinical settings.
Asunto(s)
Aprendizaje Profundo , Fibrosis Pulmonar , Animales , Ratones , Fibrosis Pulmonar/diagnóstico por imagen , Microtomografía por Rayos X , Modelos Animales de Enfermedad , DensitometríaRESUMEN
This work aimed to automatically segment and classify the coronary arteries with either normal or anomalous origin from the aorta (AAOCA) using convolutional neural networks (CNNs), seeking to enhance and fasten clinician diagnosis. We implemented three single-view 2D Attention U-Nets with 3D view integration and trained them to automatically segment the aortic root and coronary arteries of 124 computed tomography angiographies (CTAs), with normal coronaries or AAOCA. Furthermore, we automatically classified the segmented geometries as normal or AAOCA using a decision tree model. For CTAs in the test set (n = 13), we obtained median Dice score coefficients of 0.95 and 0.84 for the aortic root and the coronary arteries, respectively. Moreover, the classification between normal and AAOCA showed excellent performance with accuracy, precision, and recall all equal to 1 in the test set. We developed a deep learning-based method to automatically segment and classify normal coronary and AAOCA. Our results represent a step towards an automatic screening and risk profiling of patients with AAOCA, based on CTA.
RESUMEN
PURPOSE: Although segmentation of Abdominal Aortic Aneurysms (AAA) thrombus is a crucial step for both the planning of endovascular treatment and the monitoring of the intervention's outcome, it is still performed manually implying time consuming operations as well as operator dependency. The present paper proposes a fully automatic pipeline to segment the intraluminal thrombus in AAA from contrast-enhanced Computed Tomography Angiography (CTA) images and to subsequently analyze AAA geometry. METHODS: A deep-learning-based pipeline is developed to localize and segment the thrombus from the CTA scans. The thrombus is first identified in the whole sub-sampled CTA, then multi-view U-Nets are combined together to segment the thrombus from the identified region of interest. Polygonal models are generated for the thrombus and the lumen. The lumen centerline is automatically extracted from the lumen mesh and used to compute the aneurysm and lumen diameters. RESULTS: The proposed multi-view integration approach returns an improvement in thrombus segmentation with respect to the single-view prediction. The thrombus segmentation model is trained over a training set of 63 CTA and a validation set of 8 CTA scans. By comparing the thrombus segmentation predicted by the model with the ground truth data, a Dice Similarity Coefficient (DSC) of 0.89 ± 0.04 is achieved. The AAA geometry analysis provided an Intraclass Correlation Coefficient (ICC) of 0.92 and a mean-absolute difference of 3.2 ± 2.4 mm, for the measurements of the total diameter of the aneurysm. Validation of both thrombus segmentation and aneurysm geometry analysis is performed over a test set of 14 CTA scans. CONCLUSION: The developed deep learning models can effectively segment the thrombus from patients affected by AAA. Moreover, the diameters automatically extracted from the AAA show high correlation with those manually measured by experts.
Asunto(s)
Aneurisma de la Aorta Abdominal , Aprendizaje Profundo , Trombosis , Aneurisma de la Aorta Abdominal/diagnóstico por imagen , Aneurisma de la Aorta Abdominal/cirugía , Angiografía por Tomografía Computarizada/métodos , Humanos , Trombosis/diagnóstico por imagenRESUMEN
PURPOSE: The quantitative analysis of contrast-enhanced Computed Tomography Angiography (CTA) is essential to assess aortic anatomy, identify pathologies, and perform preoperative planning in vascular surgery. To overcome the limitations given by manual and semi-automatic segmentation tools, we apply a deep learning-based pipeline to automatically segment the CTA scans of the aortic lumen, from the ascending aorta to the iliac arteries, accounting for 3D spatial coherence. METHODS: A first convolutional neural network (CNN) is used to coarsely segment and locate the aorta in the whole sub-sampled CTA volume, then three single-view CNNs are used to effectively segment the aortic lumen from axial, sagittal, and coronal planes under higher resolution. Finally, the predictions of the three orthogonal networks are integrated to obtain a segmentation with spatial coherence. RESULTS: The coarse segmentation performed to identify the aortic lumen achieved a Dice coefficient (DSC) of 0.92 ± 0.01. Single-view axial, sagittal, and coronal CNNs provided a DSC of 0.92 ± 0.02, 0.92 ± 0.04, and 0.91 ± 0.02, respectively. Multi-view integration provided a DSC of 0.93 ± 0.02 and an average surface distance of 0.80 ± 0.26 mm on a test set of 10 CTA scans. The generation of the ground truth dataset took about 150 h and the overall training process took 18 h. In prediction phase, the adopted pipeline takes around 25 ± 1 s to get the final segmentation. CONCLUSION: The achieved results show that the proposed pipeline can effectively localize and segment the aortic lumen in subjects with aneurysm.