Medical image segmentation with knowledge-guided robust active contours

Few-shot segmentation framework for lung nodules via an optimized active contour model

BACKGROUND

Accurate segmentation of lung nodules is crucial for the early diagnosis and treatment of lung cancer in clinical practice. However, the similarity between lung nodules and surrounding tissues has made their segmentation a longstanding challenge.

PURPOSE

Existing deep learning and active contour models each have their limitations. This paper aims to integrate the strengths of both approaches while mitigating their respective shortcomings.

METHODS

In this paper, we propose a few-shot segmentation framework that combines a deep neural network with an active contour model. We introduce heat kernel convolutions and high-order total variation into the active contour model and solve the challenging nonsmooth optimization problem using the alternating direction method of multipliers. Additionally, we use the presegmentation results obtained from training a deep neural network on a small sample set as the initial contours for our optimized active contour model, addressing the difficulty of manually setting the initial contours.

RESULTS

We compared our proposed method with state-of-the-art methods for segmentation effectiveness using clinical computed tomography (CT) images acquired from two different hospitals and the publicly available LIDC dataset. The results demonstrate that our proposed method achieved outstanding segmentation performance according to both visual and quantitative indicators.

CONCLUSION

Our approach utilizes the output of few-shot network training as prior information, avoiding the need to select the initial contour in the active contour model. Additionally, it provides mathematical interpretability to the deep learning, reducing its dependency on the quantity of training samples.

Deep Learning for Automatic Segmentation of Hybrid Optoacoustic Ultrasound (OPUS) Images

The highly complementary information provided by multispectral optoacoustics and pulse-echo ultrasound have recently prompted development of hybrid imaging instruments bringing together the unique contrast advantages of both modalities. In the hybrid optoacoustic ultrasound (OPUS) combination, images retrieved by one modality may further be used to improve the reconstruction accuracy of the other. In this regard, image segmentation plays a major role as it can aid improving the image quality and quantification abilities by facilitating modeling of light and sound propagation through the imaged tissues and surrounding coupling medium. Here, we propose an automated approach for surface segmentation in whole-body mouse OPUS imaging using a deep convolutional neural network (CNN). The method has shown robust performance, attaining accurate segmentation of the animal boundary in both optoacoustic and pulse-echo ultrasound images, as evinced by quantitative performance evaluation using Dice coefficient metrics.

Supervised Brain Tumor Segmentation Based on Gradient and Context-Sensitive Features

Gliomas have the highest mortality rate and prevalence among the primary brain tumors. In this study, we proposed a supervised brain tumor segmentation method which detects diverse tumoral structures of both high grade gliomas and low grade gliomas in magnetic resonance imaging (MRI) images based on two types of features, the gradient features and the context-sensitive features. Two-dimensional gradient and three-dimensional gradient information was fully utilized to capture the gradient change. Furthermore, we proposed a circular context-sensitive feature which captures context information effectively. These features, totally 62, were compressed and optimized based on an mRMR algorithm, and random forest was used to classify voxels based on the compact feature set. To overcome the class-imbalanced problem of MRI data, our model was trained on a class-balanced region of interest dataset. We evaluated the proposed method based on the 2015 Brain Tumor Segmentation Challenge database, and the experimental results show a competitive performance.

Thoracic cavity definition for 3D PET/CT analysis and visualization

X-ray computed tomography (CT) and positron emission tomography (PET) serve as the standard imaging modalities for lung-cancer management. CT gives anatomical details on diagnostic regions of interest (ROIs), while PET gives highly specific functional information. During the lung-cancer management process, a patient receives a co-registered whole-body PET/CT scan pair and a dedicated high-resolution chest CT scan. With these data, multimodal PET/CT ROI information can be gleaned to facilitate disease management. Effective image segmentation of the thoracic cavity, however, is needed to focus attention on the central chest. We present an automatic method for thoracic cavity segmentation from 3D CT scans. We then demonstrate how the method facilitates 3D ROI localization and visualization in patient multimodal imaging studies. Our segmentation method draws upon digital topological and morphological operations, active-contour analysis, and key organ landmarks. Using a large patient database, the method showed high agreement to ground-truth regions, with a mean coverage=99.2% and leakage=0.52%. Furthermore, it enabled extremely fast computation. For PET/CT lesion analysis, the segmentation method reduced ROI search space by 97.7% for a whole-body scan, or nearly 3 times greater than that achieved by a lung mask. Despite this reduction, we achieved 100% true-positive ROI detection, while also reducing the false-positive (FP) detection rate by >5 times over that achieved with a lung mask. Finally, the method greatly improved PET/CT visualization by eliminating false PET-avid obscurations arising from the heart, bones, and liver. In particular, PET MIP views and fused PET/CT renderings depicted unprecedented clarity of the lesions and neighboring anatomical structures truly relevant to lung-cancer assessment.

Optimized Retroperitoneoscopic Excision of Large (>25 cm) Adult Polycystic Kidneys Using 3-Dimensional Image Reconstruction and Preresection Ultrasound-Guided Aspiration: Technique and Early Outcomes

BACKGROUND

Laparoscopic excision of large polycystic kidneys remains a challenging procedure. Most of the literature describes transperitoneal approaches. Alterations in anatomy due to size of kidneys can make vascular and hilar control difficult. Retroperitoneal access with direct control of pedicle avoids risks without dissection for structures anterior to the kidneys. The technique of retroperitoneoscopic excision of massively enlarged kidneys is described with early outcomes.

METHODS

Patient DICOM images of kidneys were segmented and reconstructed for 3-dimensional visualization before surgery. Total excision of large polycystic kidneys was performed in 10 patients (11 procedures). After creation of retroperitoneal space, renal pedicle dissection was started with the incision of thinned out Gerota's fascia. Occasionally aspiration of large cysts using ultrasound assistance created space for precise dissection. Following control of vascular pedicle under laparoscopic vision, further aspiration of cysts was accomplished with the help of 3-dimensional reconstructed kidney. Postaspiration, remaining renal specimen was extracted through a small incision using an endobag or as an intact specimen.

RESULTS

The operative time was between 180 and 240 minutes (median 200 minutes). Intraoperative blood loss was 100 to 300 mL (median 175 mL). Median time to control pedicle was 12 minutes (range 10-25 minutes). The postoperative periods were uneventful, except for blockage of arteriovenous fistula in 1 patient. Mean hospital stay was 7 days (range 6-14 days).

CONCLUSIONS

The retroperitoneasocopic approach to large polycystic kidneys under the guidance of 3-dimensional image reconstruction, occasionally with the assistance of ultrasound aspiration is technically feasible, safe, with good perioperative outcomes. It facilitates early control of vascular pedicle with minimal risk of intraoperative bleeding.

Optimal Parameter Setting of Active-Contours Using Differential Evolution and Expert-Segmented Sample Image

Generally, tissue extraction (segmentation) is one of the most challenging tasks in medical image processing. Inaccurate segmentation propagates errors to the subsequent steps in the image processing chain. Thus, in any image processing chain, the role of segmentation is in fact critical because it has a significant impact on the accuracy of the final results, such as those of feature extraction. The appearance of variant noise types makes medical image segmentation a more complicated task. Thus far, many approaches for image segmentation have been proposed, including the well-known active contour (snake) model. This method minimizes the energy associated with the target’s contour, which is the sum of the internal and external energy. Although this model has strong characteristics, it suffers from sensitivity to its control parameters. Finding the optimal parameter values is not a trivial task, because the parameters are correlated and problem-dependent. To overcome this problem, this paper proposes a new approach for setting snake’s optimal parameters, which utilizes an expertsegmented gold (ground-truth) image and an optimization algorithm to determine the optimal values for snake’s seven control parameters. The proposed approach was tested on three different medical image test suites: prostate ultrasound (33 images), breast ultrasound (30 images), and lung X-Ray images (48 images). In the current approach, the DE algorithm is employed as a global optimizer. The scheme introduced in this paper is general enough to allow snake to be replaced by any other segmentation algorithm, such as the level set method. For experimental verification, 111 images were utilized. In a comparison with the prepared gold images, the overall error rate is shown to be less than 3%. We explain the proposed approach and the experiments in detail.

Computer-aided measurement of liver volumes in CT by means of geodesic active contour segmentation coupled with level-set algorithms

PURPOSE

Computerized liver extraction from hepatic CT images is challenging because the liver often abuts other organs of a similar density. The purpose of this study was to develop a computer-aided measurement of liver volumes in hepatic CT.

METHODS

The authors developed a computerized liver extraction scheme based on geodesic active contour segmentation coupled with level-set contour evolution. First, an anisotropic diffusion filter was applied to portal-venous-phase CT images for noise reduction while preserving the liver structure, followed by a scale-specific gradient magnitude filter to enhance the liver boundaries. Then, a nonlinear grayscale converter enhanced the contrast of the liver parenchyma. By using the liver-parenchyma-enhanced image as a speed function, a fast-marching level-set algorithm generated an initial contour that roughly estimated the liver shape. A geodesic active contour segmentation algorithm coupled with level-set contour evolution refined the initial contour to define the liver boundaries more precisely. The liver volume was then calculated using these refined boundaries. Hepatic CT scans of 15 prospective liver donors were obtained under a liver transplant protocol with a multidetector CT system. The liver volumes extracted by the computerized scheme were compared to those traced manually by a radiologist, used as "gold standard."

RESULTS

The mean liver volume obtained with our scheme was 1504 cc, whereas the mean gold standard manual volume was 1457 cc, resulting in a mean absolute difference of 105 cc (7.2%). The computer-estimated liver volumetrics agreed excellently with the gold-standard manual volumetrics (intraclass correlation coefficient was 0.95) with no statistically significant difference (F = 0.77; p(F < or = f) = 0.32). The average accuracy, sensitivity, specificity, and percent volume error were 98.4%, 91.1%, 99.1%, and 7.2%, respectively. Computerized CT liver volumetry would require substantially less completion time (compared to an average of 39 min per case by manual segmentation).

CONCLUSIONS

The computerized liver extraction scheme provides an efficient and accurate way of measuring liver volumes in CT.

Specially adapted interactive tools for an improved 3D-segmentation of the spine

For imaging purposes of the spine, segmented image data provides the basis for a variety of modern clinical applications. However, the anatomical complex structure of the spine as well as the extensive degenerative bony deformations apparent in the clinical situation, generally complicate the application of a fully automated segmentation. To serve the special needs for image segmentation of the spine anatomy a newly developed software system is presented, that implements specially adapted interactive tools, taking its 'axis'-skeletal structure into account. A standardized protocol combines the newly developed interactive tools (rotation transformation, warped dissection plane) with standard segmentation tools to provide both a fast and accurate segmentation procedure. The introduced software environment has been valuable for the segmentation of cervical, thoracic and lumbar spines segments based on clinical routine and research images.