Mesenteric vasculature-guided small bowel segmentation on 3-D CT

Towards an EKG for SBO: A Neural Network for Detection and Characterization of Bowel Obstruction on CT

A neural network was developed to detect and characterize bowel obstruction, a common cause of acute abdominal pain. In this retrospective study, 202 CT scans of 165 patients with bowel obstruction from March to June 2022 were included and partitioned into training and test data sets. A multi-channel neural network was trained to segment the gastrointestinal tract, and to predict the diameter and the longitudinal position ("longitude") along the gastrointestinal tract using a novel embedding. Its performance was compared to manual segmentations using the Dice score, and to manual measurements of the diameter and longitude using intraclass correlation coefficients (ICC). ROC curves as well as sensitivity and specificity were calculated for diameters above a clinical threshold for obstruction, and for longitudes corresponding to small bowel. In the test data set, Dice score for segmentation of the gastrointestinal tract was 78 ± 8%. ICC between measured and predicted diameters was 0.72, indicating moderate agreement. ICC between measured and predicted longitude was 0.85, indicating good agreement. AUROC was 0.90 for detection of dilated bowel, and was 0.95 and 0.90 for differentiation of the proximal and distal gastrointestinal tract respectively. Overall sensitivity and specificity for dilated small bowel were 0.83 and 0.90. Since obstruction is diagnosed based on the diameter and longitude of the bowel, this neural network and embedding may enable detection and characterization of this important disease on CT.

Visual Image Annotation for Bowel Obstruction: Repeatability and Agreement with Manual Annotation and Neural Networks

Bowel obstruction is a common cause of acute abdominal pain. The development of algorithms for automated detection and characterization of bowel obstruction on CT has been limited by the effort required for manual annotation. Visual image annotation with an eye tracking device may mitigate that limitation. The purpose of this study is to assess the agreement between visual and manual annotations for bowel segmentation and diameter measurement, and to assess agreement with convolutional neural networks (CNNs) trained using that data. Sixty CT scans of 50 patients with bowel obstruction from March to June 2022 were retrospectively included and partitioned into training and test data sets. An eye tracking device was used to record 3-dimensional coordinates within the scans, while a radiologist cast their gaze at the centerline of the bowel, and adjusted the size of a superimposed ROI to approximate the diameter of the bowel. For each scan, 59.4 ± 15.1 segments, 847.9 ± 228.1 gaze locations, and 5.8 ± 1.2 m of bowel were recorded. 2d and 3d CNNs were trained using this data to predict bowel segmentation and diameter maps from the CT scans. For comparisons between two repetitions of visual annotation, CNN predictions, and manual annotations, Dice scores for bowel segmentation ranged from 0.69 ± 0.17 to 0.81 ± 0.04 and intraclass correlations [95% CI] for diameter measurement ranged from 0.672 [0.490-0.782] to 0.940 [0.933-0.947]. Thus, visual image annotation is a promising technique for training CNNs to perform bowel segmentation and diameter measurement in CT scans of patients with bowel obstruction.

BowelNet: Joint Semantic-Geometric Ensemble Learning for Bowel Segmentation From Both Partially and Fully Labeled CT Images

Accurate bowel segmentation is essential for diagnosis and treatment of bowel cancers. Unfortunately, segmenting the entire bowel in CT images is quite challenging due to unclear boundary, large shape, size, and appearance variations, as well as diverse filling status within the bowel. In this paper, we present a novel two-stage framework, named BowelNet, to handle the challenging task of bowel segmentation in CT images, with two stages of 1) jointly localizing all types of the bowel, and 2) finely segmenting each type of the bowel. Specifically, in the first stage, we learn a unified localization network from both partially- and fully-labeled CT images to robustly detect all types of the bowel. To better capture unclear bowel boundary and learn complex bowel shapes, in the second stage, we propose to jointly learn semantic information (i.e., bowel segmentation mask) and geometric representations (i.e., bowel boundary and bowel skeleton) for fine bowel segmentation in a multi-task learning scheme. Moreover, we further propose to learn a meta segmentation network via pseudo labels to improve segmentation accuracy. By evaluating on a large abdominal CT dataset, our proposed BowelNet method can achieve Dice scores of 0.764, 0.848, 0.835, 0.774, and 0.824 in segmenting the duodenum, jejunum-ileum, colon, sigmoid, and rectum, respectively. These results demonstrate the effectiveness of our proposed BowelNet framework in segmenting the entire bowel from CT images.

Deep Reinforcement Learning for Small Bowel Path Tracking using Different Types of Annotations

Small bowel path tracking is a challenging problem considering its many folds and contact along its course. For the same reason, it is very costly to achieve the ground-truth (GT) path of the small bowel in 3D. In this work, we propose to train a deep reinforcement learning tracker using datasets with different types of annotations. Specifically, we utilize CT scans that have only GT small bowel segmentation as well as ones with the GT path. It is enabled by designing a unique environment that is compatible for both, including a reward definable even without the GT path. The performed experiments proved the validity of the proposed method. The proposed method holds a high degree of usability in this problem by being able to utilize the scans with weak annotations, and thus by possibly reducing the required annotation cost.

GRAPH-BASED SMALL BOWEL PATH TRACKING WITH CYLINDRICAL CONSTRAINTS

We present a new graph-based method for small bowel path tracking based on cylindrical constraints. A distinctive characteristic of the small bowel compared to other organs is the contact between parts of itself along its course, which makes the path tracking difficult together with the indistinct appearance of the wall. It causes the tracked path to easily cross over the walls when relying on low-level features like the wall detection. To circumvent this, a series of cylinders that are fitted along the course of the small bowel are used to guide the tracking to more reliable directions. It is implemented as soft constraints using a new cost function. The proposed method is evaluated against ground-truth paths that are all connected from start to end of the small bowel for 10 abdominal CT scans. The proposed method showed clear improvements compared to the baseline method in tracking the path without making an error. Improvements of 6.6% and 17.0%, in terms of the tracked length, were observed for two different settings related to the small bowel segmentation.

A Graph-theoretic Algorithm for Small Bowel Path Tracking in CT Scans

We present a novel graph-theoretic method for small bowel path tracking. It is formulated as finding the minimum cost path between given start and end nodes on a graph that is constructed based on the bowel wall detection. We observed that a trivial solution with many short-cuts is easily made even with the wall detection, where the tracked path penetrates indistinct walls around the contact between different parts of the small bowel. Thus, we propose to include must-pass nodes in finding the path to better cover the entire course of the small bowel. The proposed method does not entail training with ground-truth paths while the previous methods do. We acquired ground-truth paths that are all connected from start to end of the small bowel for 10 abdominal CT scans, which enables the evaluation of the path tracking for the entire course of the small bowel. The proposed method showed clear improvements in terms of several metrics compared to the baseline method. The maximum length of the path that is tracked without an error per scan, by the proposed method, is above 800mm on average.

Unsupervised Domain Adaptation for Small Bowel Segmentation using Disentangled Representation

We present a novel unsupervised domain adaptation method for small bowel segmentation based on feature disentanglement. To make the domain adaptation more controllable, we disentangle intensity and non-intensity features within a unique two-stream auto-encoding architecture, and selectively adapt the non-intensity features that are believed to be more transferable across domains. The segmentation prediction is performed by aggregating the disentangled features. We evaluated our method using intravenous contrast-enhanced abdominal CT scans with and without oral contrast, which are used as source and target domains, respectively. The proposed method showed clear improvements in terms of three different metrics compared to other domain adaptation methods that are without the feature disentanglement. The method brings small bowel segmentation closer to clinical application.

Vessel network extraction and analysis of mouse pulmonary vasculature via X-ray micro-computed tomographic imaging

In this work, non-invasive high-spatial resolution three-dimensional (3D) X-ray micro-computed tomography (μCT) of healthy mouse lung vasculature is performed. Methodologies are presented for filtering, segmenting, and skeletonizing the collected 3D images. Novel methods for the removal of spurious branch artefacts from the skeletonized 3D image are introduced, and these novel methods involve a combination of distance transform gradients, diameter-length ratios, and the fast marching method (FMM). These new techniques of spurious branch removal result in the consistent removal of spurious branches without compromising the connectivity of the pulmonary circuit. Analysis of the filtered, skeletonized, and segmented 3D images is performed using a newly developed Vessel Network Extraction algorithm to fully characterize the morphology of the mouse pulmonary circuit. The removal of spurious branches from the skeletonized image results in an accurate representation of the pulmonary circuit with significantly less variability in vessel diameter and vessel length in each generation. The branching morphology of a full pulmonary circuit is characterized by the mean diameter per generation and number of vessels per generation. The methods presented in this paper lead to a significant improvement in the characterization of 3D vasculature imaging, allow for automatic separation of arteries and veins, and for the characterization of generations containing capillaries and intrapulmonary arteriovenous anastomoses (IPAVA).

Image Annotation by Eye Tracking: Accuracy and Precision of Centerlines of Obstructed Small-Bowel Segments Placed Using Eye Trackers

Small-bowel obstruction (SBO) is a common and important disease, for which machine learning tools have yet to be developed. Image annotation is a critical first step for development of such tools. This study assesses whether image annotation by eye tracking is sufficiently accurate and precise to serve as a first step in the development of machine learning tools for detection of SBO on CT. Seven subjects diagnosed with SBO by CT were included in the study. For each subject, an obstructed segment of bowel was chosen. Three observers annotated the centerline of the segment by manual fiducial placement and by visual fiducial placement using a Tobii 4c eye tracker. Each annotation was repeated three times. The distance between centerlines was calculated after alignment using dynamic time warping (DTW) and statistically compared to clinical thresholds for diagnosis of SBO. Intra-observer DTW distance between manual and visual centerlines was calculated as a measure of accuracy. These distances were 1.1 ± 0.2, 1.3 ± 0.4, and 1.8 ± 0.2 cm for the three observers and were less than 1.5 cm for two of three observers (P < 0.01). Intra- and inter-observer DTW distances between centerlines placed with each method were calculated as measures of precision. These distances were 0.6 ± 0.1 and 0.8 ± 0.2 cm for manual centerlines, 1.1 ± 0.4 and 1.9 ± 0.6 cm for visual centerlines, and were less than 3.0 cm in all cases (P < 0.01). Results suggest that eye tracking-based annotation is sufficiently accurate and precise for small-bowel centerline annotation for use in machine learning-based applications.

Deep Small Bowel Segmentation with Cylindrical Topological Constraints

We present a novel method for small bowel segmentation where a cylindrical topological constraint based on persistent homology is applied. To address the touching issue which could break the applied constraint, we propose to augment a network with an additional branch to predict an inner cylinder of the small bowel. Since the inner cylinder is free of the touching issue, a cylindrical shape constraint applied on this augmented branch guides the network to generate a topologically correct segmentation. For strict evaluation, we achieved an abdominal computed tomography dataset with dense segmentation ground-truths. The proposed method showed clear improvements in terms of four different metrics compared to the baseline method, and also showed the statistical significance from a paired t-test.

Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation

PURPOSE

The purpose of this study was to report procedures developed to annotate abdominal computed tomography (CT) images from subjects without pancreatic disease that will be used as the input for deep convolutional neural networks (DNN) for development of deep learning algorithms for automatic recognition of a normal pancreas.

MATERIALS AND METHODS

Dual-phase contrast-enhanced volumetric CT acquired from 2005 to 2009 from potential kidney donors were retrospectively assessed. Four trained human annotators manually and sequentially annotated 22 structures in each datasets, then expert radiologists confirmed the annotation. For efficient annotation and data management, a commercial software package that supports three-dimensional segmentation was used.

RESULTS

A total of 1150 dual-phase CT datasets from 575 subjects were annotated. There were 229 men and 346 women (mean age: 45±12years; range: 18-79years). The mean intra-observer intra-subject dual-phase CT volume difference of all annotated structures was 4.27mL (7.65%). The deep network prediction for multi-organ segmentation showed high fidelity with 89.4% and 1.29mm in terms of mean Dice similarity coefficients and mean surface distances, respectively.

CONCLUSIONS

A reliable data collection/annotation process for abdominal structures was developed. This process can be used to generate large datasets appropriate for deep learning.

Are we at a crossroads or a plateau? Radiomics and machine learning in abdominal oncology imaging

Advances in radiomics and machine learning have driven a technology boom in the automated analysis of radiology images. For the past several years, expectations have been nearly boundless for these new technologies to revolutionize radiology image analysis and interpretation. In this editorial, I compare the expectations with the realities with particular attention to applications in abdominal oncology imaging. I explore whether these technologies will leave us at a crossroads to an exciting future or to a sustained plateau and disillusionment.

Multimedia-enhanced Radiology Reports: Concept, Components, and Challenges

Multimedia-enhanced radiology report (MERR) development is defined and described from an informatics perspective, in which the MERR is seen as a superior information-communicating entity. Recent technical advances, such as the hyperlinking of report text directly to annotated images, improve MERR information content and accessibility compared with text-only reports. The MERR is analyzed by its components, which include hypertext, tables, graphs, embedded images, and their interconnections. The authors highlight the advantages of each component for improving the radiologist's communication of report content information and the user's ability to extract information. Requirements for MERR implementation (eg, integration of picture archiving and communication systems, radiology information systems, and electronic medical record systems) and the authors' initial experiences and challenges in MERR implementation at the National Institutes of Health are reviewed. The transition to MERRs has provided advantages over use of traditional text-only radiology reports because of the capacity to include hyperlinked report text that directs clinicians to image annotations, images, tables, and graphs. A framework is provided for thinking about the MERR from the user's perspective. Additional applications of emerging technologies (eg, artificial intelligence and machine learning) are described in the crafting of what the authors believe is the radiology report of the future. ^©RSNA, 2018.

Enhancement of Vascular Structures in 3D and 2D Angiographic Images

A number of imaging techniques are being used for diagnosis and treatment of vascular pathologies like stenoses, aneurysms, embolisms, malformations and remodelings, which may affect a wide range of anatomical sites. For computer-aided detection and highlighting of potential sites of pathology or to improve visualization and segmentation, angiographic images are often enhanced by Hessian based filters. These filters aim to indicate elongated and/or rounded structures by an enhancement function based on Hessian eigenvalues. However, established enhancement functions generally produce a response, which exhibits deficiencies such as poor and non-uniform response for vessels of different sizes and varying contrast, at bifurcations and aneurysms. This may compromise subsequent analysis of the enhanced images. This paper has three important contributions: i) reviews several established enhancement functions and elaborates their deficiencies, ii) proposes a novel enhancement function, which overcomes the deficiencies of the established functions, and iii) quantitatively evaluates and compares the novel and the established enhancement functions on clinical image datasets of the lung, cerebral and fundus vasculatures.

Progress in Fully Automated Abdominal CT Interpretation

OBJECTIVE

Automated analysis of abdominal CT has advanced markedly over just the last few years. Fully automated assessment of organs, lymph nodes, adipose tissue, muscle, bowel, spine, and tumors are some examples where tremendous progress has been made. Computer-aided detection of lesions has also improved dramatically.

CONCLUSION

This article reviews the progress and provides insights into what is in store in the near future for automated analysis for abdominal CT, ultimately leading to fully automated interpretation.

A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex

Contrast is a distinctive visual attribute that indicates the quality of an image. Computed Tomography (CT) images are often characterized as poor quality due to their low-contrast nature. Although many innovative ideas have been proposed to overcome this problem, the outcomes, especially in terms of accuracy, visual quality and speed, are falling short and there remains considerable room for improvement. Therefore, an improved version of the single-scale Retinex algorithm is proposed to enhance the contrast while preserving the standard brightness and natural appearance, with low implementation time and without accentuating the noise for CT images. The novelties of the proposed algorithm consist of tuning the standard single-scale Retinex, adding a normalized-ameliorated Sigmoid function and adapting some parameters to improve its enhancement ability. The proposed algorithm is tested with synthetically and naturally degraded low-contrast CT images, and its performance is also verified with contemporary enhancement techniques using two prevalent quality evaluation metrics-SSIM and UIQI. The results obtained from intensive experiments exhibited significant improvement not only in enhancing the contrast but also in increasing the visual quality of the processed images. Finally, the proposed low-complexity algorithm provided satisfactory results with no apparent errors and outperformed all the comparative methods.

Mesenteric CT angiography for diagnosis of primary small intestinal space-occupying lesions

AIM: To investigate the diagnostic value of mesenteric computed tomography (CT) angiography in elderly patients with primary small intestinal space-occupying lesions.

METHODS: A retrospective analysis was performed of 100 elderly patients with primary small intestinal lesions who underwent mesenteric CT angiography. Two radiologists localized and diagnosed the lesions using artery location method and Cole's method. The diagnostic accuracy was compared between different methods and radiologists.

RESULTS: Of the 100 cases of small intestinal lesions detected by CT angiography, 28 showed arterial enlargement, 21 showed venous enlargement and tortuosity, 29 produced tumor vessels, and 47 had enlargement and thickening of the vasa recta on the mesenteric side. The accuracy of artery location method and Cole's method was 99% and 85%, respectively, and both were accurate in venous localization in the duodenum and ileocecal regions. The accuracy of the artery location method was relatively low in the ileum and jejunum (76.6% and 55.6%). Two radiologists had high consistency (Kappa = 1.00, P = 0.000) when using the artery location method, and moderate consistency (Kappa = 0.54, P = 0.000) when using the Coles method. There was no significant difference in localization accuracy between the two physicians (P > 0.05).

CONCLUSION: Mesenteric CT angiography can clearly show the blood supplying vessels of primary small intestinal lesions and therefore contribute to the localization and qualitative diagnosis of these lesions.

Sequential Monte Carlo tracking of the marginal artery by multiple cue fusion and random forest regression

Given the potential importance of marginal artery localization in automated registration in computed tomography colonography (CTC), we have devised a semi-automated method of marginal vessel detection employing sequential Monte Carlo tracking (also known as particle filtering tracking) by multiple cue fusion based on intensity, vesselness, organ detection, and minimum spanning tree information for poorly enhanced vessel segments. We then employed a random forest algorithm for intelligent cue fusion and decision making which achieved high sensitivity and robustness. After applying a vessel pruning procedure to the tracking results, we achieved statistically significantly improved precision compared to a baseline Hessian detection method (2.7% versus 75.2%, p<0.001). This method also showed statistically significantly improved recall rate compared to a 2-cue baseline method using fewer vessel cues (30.7% versus 67.7%, p<0.001). These results demonstrate that marginal artery localization on CTC is feasible by combining a discriminative classifier (i.e., random forest) with a sequential Monte Carlo tracking mechanism. In so doing, we present the effective application of an anatomical probability map to vessel pruning as well as a supplementary spatial coordinate system for colonic segmentation and registration when this task has been confounded by colon lumen collapse.