Improving Spleen Volume Estimation Via Computer-assisted Segmentation on Clinically Acquired CT Scans

Splenic Volume Index Determined Using Computed Tomography upon Admission Is Associated with Readmission for Heart Failure Among Patients with Acute Decompensated Heart Failure

The spleen is associated with inflammation, and the size of the spleen is affected by hemodynamic congestion and sympathetic stimulation. However, the association between splenic size and prognosis in patients with heart failure remains unknown. Between January 2015 and March 2017, we analyzed 125 patients with acute decompensated heart failure who were assessed by computed tomography (CT) on the day of admission. The spleen was measured by 3-dimensional CT and then the patients were assigned to groups according to their median splenic volume indexes (SpVi; splenic volume/body surface area). We then compared their baseline characteristics and rates of readmission for heart failure after one year. The median SpVi was 63.7 (interquartile range: 44.7-95.3) cm³/m². Age did not significantly differ between the groups. Patients with a high SpVi had more significantly enlarged left atria and left ventricles. Multiple regression analysis identified significant positive correlations between SpVi and posterior wall thickness as well as left ventricular mass index. Kaplan-Meier analysis revealed lower event-free rates in the patients with a high, than a low SpVi (P = 0.041, log-rank test). After adjustment for potential cofounding factors, SpVi was independently associated with readmission for heart failure (Hazard ratio, 2.25; 95% confidence interval, 1.01-5.02; P = 0.047). In conclusion, increased splenic volume is independently associated with readmission for heart failure among patients with acute decompensated heart failure.

CT Volumetry of Convoluted Objects-A Simple Method Using Volume Averaging

Accurate measurement of object volumes using computed tomography is often important but can be challenging, especially for finely convoluted objects with severe marginal blurring from volume averaging. We aimed to test the accuracy of a simple method for volumetry by constructing, scanning and analyzing a phantom object with these characteristics which consisted of a cluster of small lucite beads embedded in petroleum jelly. Our method involves drawing simple regions of interest containing the entirety of the object and a portion of the surrounding material and using its density, along with the densities of pure lucite and petroleum jelly and the slice thickness to calculate the volume of the object in each slice. Comparison of our results with the object’s true volume showed the technique to be highly accurate, irrespective of slice thickness, image noise, reconstruction planes, spatial resolution and variations in regions of interest. We conclude that the method can be easily used for accurate volumetry in clinical and research scans without the need for specialized volumetry computer programs.

Validation and estimation of spleen volume via computer-assisted segmentation on clinically acquired CT scans

Purpose: Deep learning is a promising technique for spleen segmentation. Our study aims to validate the reproducibility of deep learning-based spleen volume estimation by performing spleen segmentation on clinically acquired computed tomography (CT) scans from patients with myeloproliferative neoplasms. Approach: As approved by the institutional review board, we obtained 138 de-identified abdominal CT scans. A sum of voxel volume on an expert annotator's segmentations establishes the ground truth (estimation 1). We used our deep convolutional neural network (estimation 2) alongside traditional linear estimations (estimation 3 and 4) to estimate spleen volumes independently. Dice coefficient, Hausdorff distance,R 2 coefficient, Pearson R coefficient, the absolute difference in volume, and the relative difference in volume were calculated for 2 to 4 against the ground truth to compare and assess methods' performances. We re-labeled on scan-rescan on a subset of 40 studies to evaluate method reproducibility. Results: Calculated against the ground truth, theR 2 coefficients for our method (estimation 2) and linear method (estimation 3 and 4) are 0.998, 0.954, and 0.973, respectively. The Pearson R coefficients for the estimations against the ground truth are 0.999, 0.963, and 0.978, respectively (paired t -tests produced p < 0.05 between 2 and 3, and 2 and 4). Conclusion: The deep convolutional neural network algorithm shows excellent potential in rendering more precise spleen volume estimations. Our computer-aided segmentation exhibits reasonable improvements in splenic volume estimation accuracy.

High-resolution 3D abdominal segmentation with random patch network fusion

Deep learning for three dimensional (3D) abdominal organ segmentation on high-resolution computed tomography (CT) is a challenging topic, in part due to the limited memory provide by graphics processing units (GPU) and large number of parameters and in 3D fully convolutional networks (FCN). Two prevalent strategies, lower resolution with wider field of view and higher resolution with limited field of view, have been explored but have been presented with varying degrees of success. In this paper, we propose a novel patch-based network with random spatial initialization and statistical fusion on overlapping regions of interest (ROIs). We evaluate the proposed approach using three datasets consisting of 260 subjects with varying numbers of manual labels. Compared with the canonical "coarse-to-fine" baseline methods, the proposed method increases the performance on multi-organ segmentation from 0.799 to 0.856 in terms of mean DSC score (p-value < 0.01 with paired t-test). The effect of different numbers of patches is evaluated by increasing the depth of coverage (expected number of patches evaluated per voxel). In addition, our method outperforms other state-of-the-art methods in abdominal organ segmentation. In conclusion, the approach provides a memory-conservative framework to enable 3D segmentation on high-resolution CT. The approach is compatible with many base network structures, without substantially increasing the complexity during inference. Given a CT scan with at high resolution, a low-res section (left panel) is trained with multi-channel segmentation. The low-res part contains down-sampling and normalization in order to preserve the complete spatial information. Interpolation and random patch sampling (mid panel) is employed to collect patches. The high-dimensional probability maps are acquired (right panel) from integration of all patches on field of views.

Research on Intelligent Traffic Monitoring System Based on Image Recognition Technology

With the rapid development of China’s national economy, the number of cars on domestic expressways and in cities has greatly increased. Cities have more and more facilities, such as roads and parking lots, while traffic control and safety management requirements are increasing. In Japan and overseas, Intelligent Transportation System (ITS) has become the main direction of current traffic management development and image recognition based on image recognition technology. As one of the core technologies of computer intelligent transportation system, computer technology is an important part of intelligent transportation system. The wide application of this technology will make a great contribution to the automation of traffic management in China.

Robust Multicontrast MRI Spleen Segmentation for Splenomegaly Using Multi-Atlas Segmentation

OBJECTIVE

Magnetic resonance imaging (MRI) is an essential imaging modality in noninvasive splenomegaly diagnosis. However, it is challenging to achieve spleen volume measurement from three-dimensional MRI given the diverse structural variations of human abdomens as well as the wide variety of clinical MRI acquisition schemes. Multi-atlas segmentation (MAS) approaches have been widely used and validated to handle heterogeneous anatomical scenarios. In this paper, we propose to use MAS for clinical MRI spleen segmentation for splenomegaly.

METHODS

First, an automated segmentation method using the selective and iterative method for performance level estimation (SIMPLE) atlas selection is used to address the concerns of inhomogeneity for clinical splenomegaly MRI. Then, to further control outliers, semiautomated craniocaudal spleen length-based SIMPLE atlas selection (L-SIMPLE) is proposed to integrate a spatial prior in a Bayesian fashion and guide iterative atlas selection. Last, a graph cuts refinement is employed to achieve the final segmentation from the probability maps from MAS.

RESULTS

A clinical cohort of 55 MRI volumes (28 T1 weighted and 27 T2 weighted) was used to evaluate both automated and semiautomated methods.

CONCLUSION

The results demonstrated that both methods achieved median Dice , and outliers were alleviated by the L-SIMPLE (≍1 min manual efforts per scan), which achieved 0.97 Pearson correlation of volume measurements with the manual segmentation.

SIGNIFICANCE

In this paper, spleen segmentation on MRI splenomegaly using MAS has been performed.

Fully Convolutional Neural Networks Improve Abdominal Organ Segmentation

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI's with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI's acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI's with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities.