Semi-automatic geographic atrophy segmentation for SD-OCT images

Geographic atrophy (GA) is a condition that is associated with retinal thinning and loss of the retinal pigment epithelium (RPE) layer. It appears in advanced stages of non-exudative age-related macular degeneration (AMD) and can lead to vision loss. We present a semi-automated GA segmentation algorithm for spectral-domain optical coherence tomography (SD-OCT) images. The method first identifies and segments a surface between the RPE and the choroid to generate retinal projection images in which the projection region is restricted to a sub-volume of the retina where the presence of GA can be identified. Subsequently, a geometric active contour model is employed to automatically detect and segment the extent of GA in the projection images. Two image data sets, consisting on 55 SD-OCT scans from twelve eyes in eight patients with GA and 56 SD-OCT scans from 56 eyes in 56 patients with GA, respectively, were utilized to qualitatively and quantitatively evaluate the proposed GA segmentation method. Experimental results suggest that the proposed algorithm can achieve high segmentation accuracy. The mean GA overlap ratios between our proposed method and outlines drawn in the SD-OCT scans, our method and outlines drawn in the fundus auto-fluorescence (FAF) images, and the commercial software (Carl Zeiss Meditec proprietary software, Cirrus version 6.0) and outlines drawn in FAF images were 72.60%, 65.88% and 59.83%, respectively.OCIS codes: (100.0100) Image processing, (110.4500) Optical coherence tomography, (170.4470) Ophthalmology     

MR-guided interventions for prostate cancer

MR imaging is currently the most effective diagnostic imaging tool for visualizing the anatomy and pathology of the prostate gland. Currently, the practicality and cost effectiveness of transrectal ultrasound dominates image guidance for needle-based prostate interventions. Challenges to the integration of diagnostic and interventional MR imaging have included the lack of real-time feed-back, the complexity of the imaging technique, and limited access to the perineum within the geometric constraints of the MR imaging scanner. Two basic strategies have been explored and clinically demonstrated in the literature: (1) coregistration of previously acquired diagnostic MR imaging to interventional TRUS or open scanner MR images, and (2) stereotactic needle interventions within conventional diagnostic scanners using careful patient positioning or the aid of simple manipulators. Currently, researchers are developing techniques that render MR imaging the method of choice for the direct guidance of many procedures. This article focuses on needle-based interventions for prostate cancer, including biopsy, brachytherapy, and thermal therapy With rapid progress in biologic imaging of the prostate gland, the authors believe that MR imaging guidance will play an increasing role in the diagnosis and treatment of prostate cancer.     

Semi-automatic segmentation and detection of aorta dissection wall in MDCT angiography

Aorta dissection is a serious vascular disease produced by a rupture of the tunica intima of the vessel wall that can be lethal to the patient. The related diagnosis is strongly based on images, where the multi-detector CT is the most generally used modality. We aim at developing a semi-automatic segmentation tool for aorta dissections, which will isolate the dissection (or flap) from the rest of the vascular structure. The proposed method is based on different stages, the first one being the semi-automatic extraction of the aorta centerline and its main branches, allowing an subsequent automatic segmentation of the outer wall of the aorta, based on a geodesic level set framework. This segmentation is then followed by an extraction the center of the dissected wall as a 3D mesh using an original algorithm based on the zero crossing of two vector fields. Our method has been applied to five datasets from three patients with chronic aortic dissection. The comparison with manually segmented dissections shows an average absolute distance value of about half a voxel. We believe that the proposed method, which tries to solve a problem that has attracted little attention to the medical image processing community, provides a new and interesting tool to isolate the intimal flap that can provide very useful information to the clinician.     

Magnetic resonance-guided prostate interventions

We review our experience using an open 0.5-T magnetic resonance (MR) interventional unit to guide procedures in the prostate. This system allows access to the patient and real-time MR imaging simultaneously and has made it possible to perform prostate biopsy and brachytherapy under MR guidance. We review MR imaging of the prostate and its use in targeted therapy, and describe our use of image processing methods such as image registration to further facilitate precise targeting. We describe current developments with a robot assist system being developed to aid radioactive seed placement.     

MR to ultrasound registration for image-guided prostate interventions

A deformable registration method is described that enables automatic alignment of magnetic resonance (MR) and 3D transrectal ultrasound (TRUS) images of the prostate gland. The method employs a novel "model-to-image" registration approach in which a deformable model of the gland surface, derived from an MR image, is registered automatically to a TRUS volume by maximising the likelihood of a particular model shape given a voxel-intensity-based feature that represents an estimate of surface normal vectors at the boundary of the gland. The deformation of the surface model is constrained by a patient-specific statistical model of gland deformation, which is trained using data provided by biomechanical simulations. Each simulation predicts the motion of a volumetric finite element mesh due to the random placement of a TRUS probe in the rectum. The use of biomechanical modelling in this way also allows a dense displacement field to be calculated within the prostate, which is then used to non-rigidly warp the MR image to match the TRUS image. Using data acquired from eight patients, and anatomical landmarks to quantify the registration accuracy, the median final RMS target registration error after performing 100 MR-TRUS registrations for each patient was 2.40 mm.     

Semi-automatic segmentation of myocardium at risk in T2-weighted cardiovascular magnetic resonance

Background

T2-weighted cardiovascular magnetic resonance (CMR) has been shown to be a promising technique for determination of ischemic myocardium, referred to as myocardium at risk (MaR), after an acute coronary event. Quantification of MaR in T2-weighted CMR has been proposed to be performed by manual delineation or the threshold methods of two standard deviations from remote (2SD), full width half maximum intensity (FWHM) or Otsu. However, manual delineation is subjective and threshold methods have inherent limitations related to threshold definition and lack of a priori information about cardiac anatomy and physiology. Therefore, the aim of this study was to develop an automatic segmentation algorithm for quantification of MaR using anatomical a priori information.

Methods

Forty-seven patients with first-time acute ST-elevation myocardial infarction underwent T2-weighted CMR within 1 week after admission. Endocardial and epicardial borders of the left ventricle, as well as the hyper enhanced MaR regions were manually delineated by experienced observers and used as reference method. A new automatic segmentation algorithm, called Segment MaR, defines the MaR region as the continuous region most probable of being MaR, by estimating the intensities of normal myocardium and MaR with an expectation maximization algorithm and restricting the MaR region by an a priori model of the maximal extent for the user defined culprit artery. The segmentation by Segment MaR was compared against inter observer variability of manual delineation and the threshold methods of 2SD, FWHM and Otsu.

Results

MaR was 32.9 ± 10.9% of left ventricular mass (LVM) when assessed by the reference observer and 31.0 ± 8.8% of LVM assessed by Segment MaR. The bias and correlation was, -1.9 ± 6.4% of LVM, R = 0.81 (p < 0.001) for Segment MaR, -2.3 ± 4.9%, R = 0.91 (p < 0.001) for inter observer variability of manual delineation, -7.7 ± 11.4%, R = 0.38 (p = 0.008) for 2SD, -21.0 ± 9.9%, R = 0.41 (p = 0.004) for FWHM, and 5.3 ± 9.6%, R = 0.47 (p < 0.001) for Otsu.

Conclusions

There is a good agreement between automatic Segment MaR and manually assessed MaR in T2-weighted CMR. Thus, the proposed algorithm seems to be a promising, objective method for standardized MaR quantification in T2-weighted CMR.     

"MRI Stealth" robot for prostate interventions.

The paper reports an important achievement in MRI instrumentation, a pneumatic, fully actuated robot located within the scanner alongside the patient and operating under remote control based on the images. Previous MRI robots commonly used piezoelectric actuation limiting their compatibility. Pneumatics is an ideal choice for MRI compatibility because it is decoupled from electromagnetism, but pneumatic actuators were hardly controllable. This achievement was possible due to a recent technology breakthrough, the invention of a new type of pneumatic motor, PneuStep 1, designed for the robot reported here with uncompromised MRI compatibility, high-precision, and medical safety. MrBot is one of the "MRI stealth" robots today (the second is described in this issue by Zangos et al.). Both of these systems are also multi-imager compatible, being able to operate with the imager of choice or cross-imaging modalities. For MRI compatibility the robot is exclusively constructed of nonmagnetic and dielectric materials such as plastics, ceramics, crystals, rubbers and is electricity free. Light-based encoding is used for feedback, so that all electric components are distally located outside the imager's room. MRI robots are modern, digital medical instruments in line with advanced imaging equipment and methods. These allow for accessing patients within closed bore scanners and performing interventions under direct (in scanner) imaging feedback. MRI robots could allow e.g. to biopsy small lesions imaged with cutting edge cancer imaging methods, or precisely deploy localized therapy at cancer foci. Our robot is the first to show the feasibility of fully automated in-scanner interventions. It is customized for the prostate and operates transperineally for needle interventions. It can accommodate various needle drivers for different percutaneous procedures such as biopsy, thermal ablations, or brachytherapy. The first needle driver is customized for fully automated low-dose radiation seed brachytherapy. This paper gives an introduction to the challenges of MRI robot compatibility and presents the solutions adopted in making the MrBot. Its multi-imager compatibility and other preclinical tests are included. The robot shows the technical feasibility of MRI-guided prostate interventions, yet its clinical utility is still to be determined.     

Semi-automatic liver tumor segmentation with hidden Markov measure field model and non-parametric distribution estimation

A novel liver tumor segmentation method for CT images is presented. The aim of this work was to reduce the manual labor and time required in the treatment planning of radiofrequency ablation (RFA), by providing accurate and automated tumor segmentations reliably. The developed method is semi-automatic, requiring only minimal user interaction. The segmentation is based on non-parametric intensity distribution estimation and a hidden Markov measure field model, with application of a spherical shape prior. A post-processing operation is also presented to remove the overflow to adjacent tissue. In addition to the conventional approach of using a single image as input data, an approach using images from multiple contrast phases was developed. The accuracy of the method was validated with two sets of patient data, and artificially generated samples. The patient data included preoperative RFA images and a public data set from “3D Liver Tumor Segmentation Challenge 2008”. The method achieved very high accuracy with the RFA data, and outperformed other methods evaluated with the public data set, receiving an average overlap error of 30.3% which represents an improvement of 2.3% points to the previously best performing semi-automatic method. The average volume difference was 23.5%, and the average, the RMS, and the maximum surface distance errors were 1.87, 2.43, and 8.09 mm, respectively. The method produced good results even for tumors with very low contrast and ambiguous borders, and the performance remained high with noisy image data.     

Atlas-based prostate segmentation using an hybrid registration

Purpose  This paper presents the preliminary results of a semi-automatic method for prostate segmentation of magnetic resonance images (MRI) which aims to be incorporated in a navigation system for prostate brachytherapy. Methods  The method is based on the registration of an anatomical atlas computed from a population of 18 MRI exams onto a patient image. An hybrid registration framework which couples an intensity-based registration with a robust point-matching algorithm is used for both atlas building and atlas registration. Results  The method has been validated on the same dataset that the one used to construct the atlas using the leave-one-out method. Results gives a mean error of 3.39 mm and a standard deviation of 1.95 mm with respect to expert segmentations. Conclusions  We think that this segmentation tool may be a very valuable help to the clinician for routine quantitative image exploitation.     

Semi-automatic sigmoid colon segmentation in CT for radiation therapy treatment planning via an iterative 2.5-D deep learning approach

Automatic sigmoid colon segmentation in CT for radiotherapy treatment planning is challenging due to complex organ shape, close distances to other organs, and large variations in size, shape, and filling status. The patient bowel is often not evacuated, and CT contrast enhancement is not used, which further increase problem difficulty. Deep learning (DL) has demonstrated its power in many segmentation problems. However, standard 2-D approaches cannot handle the sigmoid segmentation problem due to incomplete geometry information and 3-D approaches often encounters the challenge of a limited training data size. Motivated by human's behavior that segments the sigmoid slice by slice while considering connectivity between adjacent slices, we proposed an iterative 2.5-D DL approach to solve this problem. We constructed a network that took an axial CT slice, the sigmoid mask in this slice, and an adjacent CT slice to segment as input and output the predicted mask on the adjacent slice. We also considered other organ masks as prior information. We trained the iterative network with 50 patient cases using five-fold cross validation. The trained network was repeatedly applied to generate masks slice by slice. The method achieved average Dice similarity coefficients of 0.82 0.06 and 0.88 0.02 in 10 test cases without and with using prior information.     

MR-guided interventions of the prostate gland.

In recent years MR imaging has played an increasingly important role in the diagnosis and treatment of prostate cancer. MR imaging of the prostate allows a clear delineation of the anatomic structures and prostate tumors when performing interventions such as biopsies, brachytherapy or thermal therapy of the prostate gland. MRI robotic assistance will improve the accuracy of the interventions. Due to the advantages of MR imaging MR-guided prostate interventions will play an increasing role in future.     

Semi-automatic level set segmentation of liver tumors combining a spiral-scanning technique with supervised fuzzy pixel classification

In this paper, a specific method is presented to facilitate the semi-automatic segmentation of liver tumors and liver metastases in CT images. Accurate and reliable segmentation of tumors is essential for the follow-up of cancer treatment. The core of the algorithm is a level set method. The initialization is generated by a spiral-scanning technique based on dynamic programming. The level set evolves according to a speed image that is the result of a statistical pixel classification algorithm with supervised learning. This method is tested on CT images of the abdomen and compared with manual delineations of liver tumors. The described method outperformed the semi-automatic methods of the other participants of the “3D Liver Tumor Segmentation Challenge 2008”. Evaluating the algorithm on the provided test data leads to an average overlap error of 32.6% and an average volume difference of 17.9%. The average, the RMS and the maximum surface distance are 2.0, 2.6 and 10.1 mm, respectively.     

Statistical shape and texture model of quadrature phase information for prostate segmentation

Purpose  

Prostate volume estimation from segmentation of transrectal ultrasound (TRUS) images aids in diagnosis and treatment of prostate hypertrophy and cancer. Computer-aided accurate and computationally efficient prostate segmentation in TRUS images is a challenging task, owing to low signal-to-noise ratio, speckle noise, calcifications, and heterogeneous intensity distribution in the prostate region.     

Deep dense multi-path neural network for prostate segmentation in magnetic resonance imaging

Purpose

We propose an approach of 3D convolutional neural network to segment the prostate in MR images.

Methods

A 3D deep dense multi-path convolutional neural network that follows the framework of the encoder–decoder design is proposed. The encoder is built based upon densely connected layers that learn the high-level feature representation of the prostate. The decoder interprets the features and predicts the whole prostate volume by utilizing a residual layout and grouped convolution. A set of sub-volumes of MR images, centered at the prostate, is generated and fed into the proposed network for training purpose. The performance of the proposed network is compared to previously reported approaches.

Results

Two independent datasets were employed to assess the proposed network. In quantitative evaluations, the proposed network achieved 95.11 and 89.01 Dice coefficients for the two datasets. The segmentation results were robust to variations in MR images. In comparison experiments, the segmentation performance of the proposed network was comparable to the previously reported approaches. In qualitative evaluations, the segmentation results by the proposed network were well matched to the ground truth provided by human experts.

Conclusions

The proposed network is capable of segmenting the prostate in an accurate and robust manner. This approach can be applied to other types of medical images.

     

Asymmetric multi-task attention network for prostate bed segmentation in computed tomography images

Post-prostatectomy radiotherapy requires accurate annotation of the prostate bed (PB), i.e., the residual tissue after the operative removal of the prostate gland, to minimize side effects on surrounding organs-at-risk (OARs). However, PB segmentation in computed tomography (CT) images is a challenging task, even for experienced physicians. This is because PB is almost a “virtual” target with non-contrast boundaries and highly variable shapes depending on neighboring OARs. In this work, we propose an asymmetric multi-task attention network (AMTA-Net) for the concurrent segmentation of PB and surrounding OARs. Our AMTA-Net mimics experts in delineating the non-contrast PB by explicitly leveraging its critical dependency on the neighboring OARs (i.e., the bladder and rectum), which are relatively easy to distinguish in CT images. Specifically, we first adopt a U-Net as the backbone network for the low-level (or prerequisite) task of the OAR segmentation. Then, we build an attention sub-network upon the backbone U-Net with a series of cascaded attention modules, which can hierarchically transfer the OAR features and adaptively learn discriminative representations for the high-level (or primary) task of the PB segmentation. We comprehensively evaluate the proposed AMTA-Net on a clinical dataset composed of 186 CT images. According to the experimental results, our AMTA-Net significantly outperforms current clinical state-of-the-arts (i.e., atlas-based segmentation methods), indicating the value of our method in reducing time and labor in the clinical workflow. Our AMTA-Net also presents better performance than the technical state-of-the-arts (i.e., the deep learning-based segmentation methods), especially for the most indistinguishable and clinically critical part of the PB boundaries. Source code is released at https://github.com/superxuang/amta-net.     

Semi-automatic level-set based segmentation and stenosis quantification of the internal carotid artery in 3D CTA data sets

We present a new level-set based method to segment and quantify stenosed internal carotid arteries (ICAs) in 3D contrast-enhanced computed tomography angiography (CTA). Within these data sets it is a difficult task to evaluate the degree of stenoses deterministically even for the experienced physician because the actual vessel lumen is hardly distinguishable from calcified plaque and there is no sharp border between lumen and arterial wall. According to our knowledge no commercially available software package allows the detection of the boundary between lumen and plaque components. Therefore in the clinical environment physicians have to perform the evaluation manually. This approach suffers from both intra- and inter-observer variability. The limitation of the manual approach requires the development of a semi-automatic method that is able to achieve deterministic segmentation results of the internal carotid artery via level-set techniques. With the new method different kinds of plaques were almost completely excluded from the segmented regions. For an objective evaluation we also studied the method's performance with four different phantom data sets for which the ground truth of the degree of stenosis was known a priori. Finally, we applied the method to 10 ICAs and compared the obtained segmentations with manual measurements of three physicians.