Multicentric clinical evaluation of a computed tomography-based fully automated deep neural network for aortic maximum diameter and volumetric measurements.

OBJECTIVE: This study aims to evaluate a fully automatic deep learning-based method (augmented radiology for vascular aneurysm [ARVA]) for aortic segmentation and simultaneous diameter and volume measurements. METHODS: A clinical validation dataset was constructed from preoperative and postoperative aortic computed tomography angiography (CTA) scans for assessing these functions. The dataset totaled 350 computed tomography angiography scans from 216 patients treated at two different hospitals. ARVA's ability to segment the aorta into seven morphologically based aortic segments and measure maximum outer-to-outer wall transverse diameters and compute volumes for each was compared with the measurements of six experts (ground truth) and thirteen clinicians. RESULTS: Ground truth (experts') measurements of diameters and volumes were manually performed for all aortic segments. The median absolute diameter difference between ground truth and ARVA was 1.6 mm (95% confidence interval [CI], 1.5-1.7; and 1.6 mm [95% CI, 1.6-1.7]) between ground truth and clinicians. ARVA produced measurements within the clinical acceptable range with a proportion of 85.5% (95% CI, 83.5-86.3) compared with the clinicians' 86.0% (95% CI, 83.9-86.0). The median volume similarity error ranged from 0.93 to 0.95 in the main trunk and achieved 0.88 in the iliac arteries. CONCLUSIONS: This study demonstrates the reliability of a fully automated artificial intelligence-driven solution capable of quick aortic segmentation and analysis of both diameter and volume for each segment.

Adhesion-related small bowel obstruction: deep learning for automatic transition-zone detection by CT.

BACKGROUND: To train a machine-learning model to locate the transition zone (TZ) of adhesion-related small bowel obstruction (SBO) on CT scans. MATERIALS AND METHODS: We used 562 CTs performed in 2005-2018 in 404 patients with adhesion-related SBO. Annotation of the TZs was performed by experienced radiologists and trained residents using bounding boxes. Preprocessing involved using a pretrained model to extract the abdominopelvic region. We modeled TZ localization as a binary classification problem by splitting the abdominopelvic region into 125 patches. We then trained a neural network model to classify each patch as containing or not containing a TZ. We coupled this with a trained probabilistic estimation of presence of a TZ in each patch. The models were first evaluated by computing the area under the receiver operating characteristics curve (AUROC). Then, to assess the clinical benefit, we measured the proportion of total abdominopelvic volume classified as containing a TZ for several different false-negative rates. RESULTS: The probability of containing a TZ was highest for the hypogastric region (56.9%). The coupled classification network and probability mapping produced an AUROC of 0.93. For a 15% proportion of volume classified as containing TZs, the probability of highlighted patches containing a TZ was 92%. CONCLUSION: Modeling TZ localization by coupling convolutional neural network classification and probabilistic localization estimation shows the way to a possible automatic TZ detection, a complex radiological task with a major clinical impact.

Pre-surgical and Post-surgical Aortic Aneurysm Maximum Diameter Measurement: Full Automation by Artificial Intelligence.

OBJECTIVE: The aim of this study was to evaluate an automatic, deep learning based method (Augmented Radiology for Vascular Aneurysm [ARVA]), to detect and assess maximum aortic diameter, providing cross sectional outer to outer aortic wall measurements. METHODS: Accurate external aortic wall diameter measurement is performed along the entire aorta, from the ascending aorta to the iliac bifurcations, on both pre- and post-operative contrast enhanced computed tomography angiography (CTA) scans. A training database of 489 CTAs was used to train a pipeline of neural networks for automatic external aortic wall measurements. Another database of 62 CTAs, including controls, aneurysmal aortas, and aortic dissections scanned before and/or after endovascular or open repair, was used for validation. The measurements of maximum external aortic wall diameter made by ARVA were compared with those of seven clinicians on this validation dataset. RESULTS: The median absolute difference with respect to expert's measurements ranged from 1 mm to 2 mm among all annotators, while ARVA reported a median absolute difference of 1.2 mm. CONCLUSION: The performance of the automatic maximum aortic diameter method falls within the interannotator variability, making it a potentially reliable solution for assisting clinical practice.

Imaging Biomarkers of Tumor Response in Neuroendocrine Liver Metastases Treated with Transarterial Chemoembolization: Can Enhancing Tumor Burden of the Whole Liver Help Predict Patient Survival?

Purpose To investigate whether whole-liver enhancing tumor burden [ETB] can serve as an imaging biomarker and help predict survival better than World Health Organization (WHO), Response Evaluation Criteria in Solid Tumors (RECIST), modified RECIST (mRECIST), and European Association for the Study of the Liver (EASL) methods in patients with multifocal, bilobar neuroendocrine liver metastases (NELM) after the first transarterial chemoembolization (TACE) procedure. Materials and Methods This HIPAA-compliant, institutional review board-approved retrospective study included 51 patients (mean age, 57.8 years ± 13.2; range, 13.5-85.8 years) with multifocal, bilobar NELM treated with TACE. The largest area (WHO), longest diameter (RECIST), longest enhancing diameter (mRECIST), largest enhancing area (EASL), and largest enhancing volume (ETB) were measured at baseline and after the first TACE on contrast material-enhanced magnetic resonance images. With three-dimensional software, ETB was measured as more than 2 standard deviations the signal intensity of a region of interest in normal liver. Response was assessed with WHO, RECIST, mRECIST, and EASL methods according to their respective criteria. For ETB response, a decrease in enhancement of at least 30%, 50%, and 65% was analyzed by using the Akaike information criterion. Survival analysis included Kaplan-Meier curves and Cox regressions. Results Treatment response occurred in 5.9% (WHO criteria), 2.0% (RECIST), 25.5% (mRECIST), and 23.5% (EASL criteria) of patients. With 30%, 50%, and 65% cutoffs, ETB response was seen in 60.8%, 39.2%, and 21.6% of patients, respectively, and was the only biomarker associated with a survival difference between responders and nonresponders (45.0 months vs 10.0 months, 84.3 months vs 16.7 months, and 85.2 months vs 21.2 months, respectively; P < .01 for all). The 50% cutoff provided the best survival model (hazard ratio [HR]: 0.2; 95% confidence interval [CI]: 0.1, 0.4). At multivariate analysis, ETB response was an independent predictor of survival (HR: 0.2; 95% CI: 0.1, 0.6). Conclusion Volumetric ETB is an early treatment response biomarker and surrogate for survival in patients with multifocal, bilobar NELM after the first TACE procedure. © RSNA, 2016.

Tagged template deformation.

Model-based approaches are very popular for medical image segmentation as they carry useful prior information on the target structure. Among them, the implicit template deformation framework recently bridged the gap between the efficiency and flexibility of level-set region competition and the robustness of atlas deformation approaches. This paper generalizes this method by introducing the notion of tagged templates. A tagged template is an implicit model in which different subregions are defined. In each of these subregions, specific image features can be used with various confidence levels. The tags can be either set manually or automatically learnt via a process also hereby described. This generalization therefore greatly widens the scope of potential clinical application of implicit template deformation while maintaining its appealing algorithmic efficiency. We show the great potential of our approach in myocardium segmentation of ultrasound images.

Rapid assessment of liver volumetry by a novel automated segmentation algorithm.

OBJECTIVE: This study aimed to evaluate a novel segmentation software for automated liver volumetry and segmentation regarding segmentation speed and interobserver variability. METHODS: Computed tomographic scans of 20 patients without underlying liver disease and 10 patients with liver metastasis from colorectal cancer were analyzed by a novel segmentation software. Liver segmentation was performed after manual placement of specific landmarks into 9 segments according to the Couinaud model as well as into 4 segments, the latter being import for surgery planning. Time for segmentation was measured and the obtained segmental and total liver volumes between the different readers were compared calculating intraclass correlations (ICCs). Volumes of liver tumor burden were evaluated similarly. RESULTS: Liver segmentation could be performed rapidly 3 minutes or less. Comparison of total liver volumes revealed a perfect ICC of greater than 0.997. Segmental liver volumes within the 9-part segmentation provided fair to moderate correlation for the left lobe and good to excellent correlations for the right lobe. When applying a 4-part segmentation relevant to clinical practice, strong to perfect agreement was observed. Similarly tumor volumes showed perfect ICC (>0.998). CONCLUSIONS: Rapid determination of total and segmental liver volumes can be obtained using a novel segmentation software suitable for daily clinical practice.

Semiautomatic volumetric tumor segmentation for hepatocellular carcinoma: comparison between C-arm cone beam computed tomography and MRI.

RATIONALE AND OBJECTIVES: To evaluate the precision and reproducibility of a semiautomatic tumor segmentation software in measuring tumor volume of hepatocellular carcinoma (HCC) before the first transarterial chemo-embolization (TACE) on contrast-enhancement magnetic resonance imaging (CE-MRI) and intraprocedural dual-phase C-arm cone beam computed tomography (DP-CBCT) images. MATERIALS AND METHODS: Nineteen HCCs were targeted in 19 patients (one per patient) who underwent baseline diagnostic CE-MRI and an intraprocedural DP-CBCT. The images were obtained from CE-MRI (arterial phase of an intravenous contrast medium injection) and DP-CBCT (delayed phase of an intra-arterial contrast medium injection) before the actual embolization. Three readers measured tumor volumes using a semiautomatic three-dimensional volumetric segmentation software that used a region-growing method employing non-Euclidean radial basis functions. Segmentation time and spatial position were recorded. The tumor volume measurements between image sets were compared using linear regression and Student's t-test, and evaluated with intraclass-correlation analysis (ICC). The inter-rater Dice similarity coefficient (DSC) assessed the segmentation spatial localization. RESULTS: All 19 HCCs were analyzed. On CE-MRI and DP-CBCT examinations, respectively, 1) the mean segmented tumor volumes were 87 ± 8 cm(3) (2-873) and 92 ± 10 cm(3) (1-954), with no statistical difference of segmented volumes by readers of each tumor between the two imaging modalities and the mean time required for segmentation was 66 ± 45 seconds (21-173) and 85 ± 34 seconds (17-214) (P = .19); 2) the ICCs were 0.99 and 0.974, showing a strong correlation among readers; and 3) the inter-rater DSCs showed a good to excellent inter-user agreement on the spatial localization of the tumor segmentation (0.70 ± 0.07 and 0.74 ± 0.05, P = .07). CONCLUSION: This study shows a strong correlation, a high precision, and excellent reproducibility of semiautomatic tumor segmentation software in measuring tumor volume on CE-MRI and DP-CBCT images. The use of the segmentation software on DP-CBCT and CE-MRI can be a valuable and highly accurate tool to measure the volume of hepatic tumors.

Joint co-segmentation and registration of 3D ultrasound images.

Contrast-enhanced ultrasound (CEUS) allows a visualization of the vascularization and complements the anatomical information provided by conventional ultrasound (US). However, these images are inherently subject to noise and shadows, which hinders standard segmentation algorithms. In this paper, we propose to use simultaneously the different information coming from 3D US and CEUS images to address the problem of kidney segmentation. To that end, we introduce a generic framework for joint co-segmentation and registration that seeks objects having the same shape in several images. From this framework, we derive both an ellipsoid co-detection and a model-based co-segmentation algorithm. These methods rely on voxel-classification maps that we estimate using random forests in a structured way. This yields a fast and fully automated pipeline, in which an ellipsoid is first estimated to locate the kidney in both US and CEUS volumes and then deformed to segment it accurately. The proposed method outperforms state-of-the-art results (by dividing the kidney volume error by two) on a clinically representative database of 64 images.

Registration of free-breathing 3D+t abdominal perfusion CT images via co-segmentation.

Dynamic contrast-enhanced computed tomography (DCE-CT) is a valuable imaging modality to assess tissues properties, particularly in tumours, by estimating pharmacokinetic parameters from the evolution of pixels intensities in 3D+t acquisitions. However, this requires a registration of the whole sequence of volumes, which is challenging especially when the patient breathes freely. In this paper, we propose a generic, fast and automatic method to address this problem. As standard iconic registration methods are not robust to contrast intake, we rather rely on the segmentation of the organ of interest. This segmentation is performed jointly with the registration of the sequence within a novel co-segmentation framework. Our approach is based on implicit template deformation, that we extend to a co-segmentation algorithm which provides as outputs both a segmentation of the organ of interest in every image and stabilising transformations for the whole sequence. The proposed method is validated on 15 datasets acquired from patients with renal lesions and shows improvement in terms of registration and estimation of pharmacokinetic parameters over the state-of-the-art method.

Incorporating shape variability in image segmentation via implicit template deformation.

Implicit template deformation is a model-based segmentation framework that was successfully applied in several medical applications. In this paper, we propose a method to learn and use prior knowledge on shape variability in such framework. This shape prior is learnt via an original and dedicated process in which both an optimal template and principal modes of variations are estimated from a collection of shapes. This learning strategy requires neither a pre-alignment of the training shapes nor one-to-one correspondences between shape sample points. We then generalize the implicit template deformation formulation to automatically select the most plausible deformation as a shape prior. This novel framework maintains the two main properties of implicit template deformation: topology preservation and computational efficiency. Our approach can be applied to any organ with a possibly complex shape but fixed topology. We validate our method on myocardium segmentation from cardiac magnetic resonance short-axis images and demonstrate segmentation improvement over standard template deformation.

Comparison of semi-automatic volumetric VX2 hepatic tumor segmentation from cone beam CT and multi-detector CT with histology in rabbit models.

RATIONALE AND OBJECTIVES: The purpose of this study was to compare tumor volume in a VX2 rabbit model as calculated using semiautomatic tumor segmentation from C-arm cone-beam computed tomography (CBCT) and multidetector computed tomography (MDCT) to the actual tumor volume. MATERIALS AND METHODS: Twenty VX2 tumors in 20 adult male New Zealand rabbits (one tumor per rabbit) were imaged with CBCT (using an intra-arterial contrast medium injection) and MDCT (using an intravenous contrast injection). All tumor volumes were measured using semiautomatic three-dimensional volumetric segmentation software. The software uses a region-growing method using non-Euclidean radial basis functions. After imaging, the tumors were excised for pathologic volume measurement. The imaging-based tumor volume measurements were compared to the pathologic volumes using linear regression, with Pearson's test, and correlated using Bland-Altman analysis. RESULTS: Average tumor volumes were 3.5 ± 1.6 cm(3) (range, 1.4-7.2 cm(3)) on pathology, 3.8 ± 1.6 cm(3) (range, 1.3-7.3 cm(3)) on CBCT, and 3.9 ± 1.6 (range, 1.8-7.5 cm(3)) on MDCT (P < .001). A strong correlation between volumes on pathology and CBCT and also with MDCT was observed (Pearson's correlation coefficient = 0.993 and 0.996, P < .001, for CBCT and MDCT, respectively). Bland-Altman analysis showed that MDCT tended to overestimate tumor volume, and there was stronger agreement for tumor volume between CBCT and pathology than with MDCT, possibly because of the intra-arterial contrast injection. CONCLUSIONS: Tumor volume as measured using semiautomatic tumor segmentation software showed a strong correlation with the "real volume" measured on pathology. The segmentation software on CBCT and MDCT can be a useful tool for volumetric hepatic tumor assessment.

Quantitative and volumetric European Association for the Study of the Liver and Response Evaluation Criteria in Solid Tumors measurements: feasibility of a semiautomated software method to assess tumor response after transcatheter arterial chemoembolization.

PURPOSE: To show that hepatic tumor volume and enhancement pattern measurements can be obtained in a time-efficient and reproducible manner on a voxel-by-voxel basis to provide a true three-dimensional (3D) volumetric assessment. MATERIALS AND METHODS: Magnetic resonance (MR) imaging data obtained from 20 patients recruited for a single-institution prospective study were retrospectively evaluated. All patients had a diagnosis of hepatocellular carcinoma (HCC) and underwent drug-eluting beads (DEB) transcatheter arterial chemoembolization for the first time. All patients had undergone contrast-enhanced MR imaging before and after DEB transcatheter arterial chemoembolization; poor image quality excluded 3 patients, resulting in a final count of 17 patients. Volumetric RECIST (vRECIST) and quantitative EASL (qEASL) were measured, and segmentation and processing times were recorded. RESULTS: There were 34 scans analyzed. The time for semiautomatic segmentation was 65 seconds±33 (range, 40-200 seconds). vRECIST and qEASL of each tumor were computed<1 minute for each. CONCLUSIONS: Semiautomatic quantitative tumor enhancement (qEASL) and volume (vRECIST) assessment is feasible in a workflow-efficient time frame. Clinical correlation is necessary, but vRECIST and qEASL could become part of the assessment of intraarterial therapy for interventional radiologists.

Real-time 3D image segmentation by user-constrained template deformation.

We describe an algorithm for 3D interactive image segmentation by non-rigid implicit template deformation, with two main original features. First, our formulation incorporates user input as inside/outside labeled points to drive the deformation and improve both robustness and accuracy. This yields inequality constraints, solved using an Augmented Lagrangian approach. Secondly, a fast implementation of non-rigid template-to-image registration enables interactions with a real-time visual feedback. We validated this generic technique on 21 Contrast-Enhanced Ultrasound images of kidneys and obtained accurate segmentation results (Dice > 0.93) in less than 3 clicks in average.

Automatic detection and segmentation of kidneys in 3D CT images using random forests.

Kidney segmentation in 3D CT images allows extracting useful information for nephrologists. For practical use in clinical routine, such an algorithm should be fast, automatic and robust to contrast-agent enhancement and fields of view. By combining and refining state-of-the-art techniques (random forests and template deformation), we demonstrate the possibility of building an algorithm that meets these requirements. Kidneys are localized with random forests following a coarse-to-fine strategy. Their initial positions detected with global contextual information are refined with a cascade of local regression forests. A classification forest is then used to obtain a probabilistic segmentation of both kidneys. The final segmentation is performed with an implicit template deformation algorithm driven by these kidney probability maps. Our method has been validated on a highly heterogeneous database of 233 CT scans from 89 patients. 80% of the kidneys were accurately detected and segmented (Dice coefficient > 0.90) in a few seconds per volume.