This paper presents segmentation of multiple organ regions from non-contrast CT volume based on deep learning. Also, we report usefulness of fine-tuning using a small number of training data for multi-organ regions segmentation. In medical image analysis system, it is vital to recognize patient specific anatomical structures in medical images such as CT volumes. We have studied on a multi-organ regions segmentation method from contrast-enhanced abdominal CT volume using 3D U-Net. Since non-contrast CT volumes are also usually used in the medical field, segmentation of multi-organ regions from non-contrast CT volume is also important for the medical image analysis system. In this study, we extract multi-organ regions from non-contrast CT volume using 3D U-Net and a small number of training data. We perform fine-tuning from a pre-trained model obtained from the previous studies. The pre-trained 3D U-Net model is trained by a large number of contrast enhanced CT volumes. Then, fine-tuning is performed using a small number of non-contrast CT volumes. The experimental results showed that the fine-tuned 3D U-Net model could extract multi-organ regions from non-contrast CT volume. The proposed training scheme using fine-tuning is useful for segmenting multi-organ regions using a small number of training data.
Coronary artery disease (CAD) is a condition where there is blood-flow reduction in the coronary artery due to plaque build-up. The current standard to diagnose CAD severity is fractional flow reserve (FFR) using the ratio of distal and proximal stenotic pressure measurements. This work investigated the use of a machine-learning classifier of CAD severity. Sixty-four coronary CT angiographies (CCTA) were collected at 70% through the cardiac R-R cycle. Eight straightened curved planar reformations (SCPRs) were reconstructed from each CCTA considering 45° increments around the coronary artery centerline. FFR measurements were considered ground truth to train a convolutional neural network to predict CAD severity based on the 0.80 FFR threshold. Classification accuracy and area under the receiver operating characteristic curve (AUROC) were used to assess the network’s predictive capacity. SCPR data were optimized using class-activation maps, and the network was re-trained and assessed in the same manner. Subgroup analysis of the network’s performance was carried out considering different coronary artery branches and patient FFR measurements in and out of the FFR grey-zone. Different network input conditions were assessed such as SCPR slice-thickness and SCPR reconstruction using the minimum or average value across the vessel centerline. Network for CAD severity prediction was significantly higher (P<0.05) using thicker SCPR slices. No significant difference was found in network performance using SCPRs from different coronary artery branches, or considering SCPR reconstruction using the minimum or average value. This work indicates that a CNN can predict CAD severity using coronary artery SCPRs.
KEYWORDS: 3D modeling, Arteries, 3D metrology, Computational fluid dynamics, Computed tomography, Gold, Computer simulations, 3D printing, 3D imaging standards, Angiography
Purpose: Various CT-FFR methods are being proposed as a non-invasive method to estimate cardiac disease severity. 3D printed patient specific cardiovascular models with high geometric accuracy can be used to simulate blood flow conditions and perform precise and repeatable benchtop flow experiments for validation of such methods. Materials and Methods: Twelve patient-specific 3D printed cardiac phantoms were created from CT Angiography (CTA) scans using a compliant 3D printing material. Pressure sensors were connected to the aortic root and distal ends of the three main coronary arteries to measure benchtop pressure gradients for each stenosed vessel. The patient geometries were used in Canon Medical Systems 1D fluid dynamics algorithm to calculate the CT- FFR. In addition, a 3D computational fluid dynamics simulation was done using ANSYS to estimate pressure gradients across the coronary arteries. Experimental data and 1D and 3D flow simulations were compared to the standard catheter lab FFR measurement (Invasive-FFR). Results: The average percent difference in Benchtop FFR/Invasive FFR, CT-FFR/Invasive FFR, and CFDFFR/Invasive FFR was 0.05, 0.06, and 0.07 respectively. The average time it took for the CT-FFR simulation was ~35 minutes and it took ~15 hours for the CFD-FFR simulation but can vary based on the number of iterations the user defines the software to run. Conclusions: Benchtop FFR proved to be highly accurate when compared to both 1D and 3D CFD software and therefore, 3D printing of patient specific coronary phantoms is a quality tool for CT-FFR software validation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.