Noise is inherent to low-dose CT acquisition. We propose to train a convolutional neural network (CNN) jointly with an adversarial CNN to estimate routine-dose CT images from low-dose CT images and ...hence reduce noise. A generator CNN was trained to transform low-dose CT images into routine-dose CT images using voxelwise loss minimization. An adversarial discriminator CNN was simultaneously trained to distinguish the output of the generator from routine-dose CT images. The performance of this discriminator was used as an adversarial loss for the generator. Experiments were performed using CT images of an anthropomorphic phantom containing calcium inserts, as well as patient non-contrast-enhanced cardiac CT images. The phantom and patients were scanned at 20% and 100% routine clinical dose. Three training strategies were compared: the first used only voxelwise loss, the second combined voxelwise loss and adversarial loss, and the third used only adversarial loss. The results showed that training with only voxelwise loss resulted in the highest peak signal-to-noise ratio with respect to reference routine-dose images. However, CNNs trained with adversarial loss captured image statistics of routine-dose images better. Noise reduction improved quantification of low-density calcified inserts in phantom CT images and allowed coronary calcium scoring in low-dose patient CT images with high noise levels. Testing took less than 10 s per CT volume. CNN-based low-dose CT noise reduction in the image domain is feasible. Training with an adversarial network improves the CNNs ability to generate images with an appearance similar to that of reference routine-dose CT images.
•Unsupervised Deep Learning Image Registration (DLIR) is feasible for affine and deformable image registration.•The method is unsupervised; no registration examples are necessary to train a ConvNet ...for image registration.•Once a ConvNet is trained, image registration can be performed on unseen images in one-shot.•Registration, including image resampling, is near real-time.•Unsupervised DLIR yields image registration performance similar to a conventional approach.
Display omitted
Image registration, the process of aligning two or more images, is the core technique of many (semi-)automatic medical image analysis tasks. Recent studies have shown that deep learning methods, notably convolutional neural networks (ConvNets), can be used for image registration. Thus far training of ConvNets for registration was supervised using predefined example registrations. However, obtaining example registrations is not trivial. To circumvent the need for predefined examples, and thereby to increase convenience of training ConvNets for image registration, we propose the Deep Learning Image Registration (DLIR) framework for unsupervised affine and deformable image registration. In the DLIR framework ConvNets are trained for image registration by exploiting image similarity analogous to conventional intensity-based image registration. After a ConvNet has been trained with the DLIR framework, it can be used to register pairs of unseen images in one shot. We propose flexible ConvNets designs for affine image registration and for deformable image registration. By stacking multiple of these ConvNets into a larger architecture, we are able to perform coarse-to-fine image registration. We show for registration of cardiac cine MRI and registration of chest CT that performance of the DLIR framework is comparable to conventional image registration while being several orders of magnitude faster.
Medical image registration is an important task in medical image processing. It refers to the process of aligning data sets, possibly from different modalities (e.g., magnetic resonance and computed ...tomography), different time points (e.g., follow-up scans), and/or different subjects (in case of population studies). A large number of methods for image registration are described in the literature. Unfortunately, there is not one method that works for all applications. We have therefore developed elastix, a publicly available computer program for intensity-based medical image registration. The software consists of a collection of algorithms that are commonly used to solve medical image registration problems. The modular design of elastix allows the user to quickly configure, test, and compare different registration methods for a specific application. The command-line interface enables automated processing of large numbers of data sets, by means of scripting. The usage of elastix for comparing different registration methods is illustrated with three example experiments, in which individual components of the registration method are varied.
The introduction of fast digital slide scanners that provide whole slide images has led to a revival of interest in image analysis applications in pathology. Segmentation of cells and nuclei is an ...important first step towards automatic analysis of digitized microscopy images. We therefore developed an automated nuclei segmentation method that works with hematoxylin and eosin (H&E) stained breast cancer histopathology images, which represent regions of whole digital slides. The procedure can be divided into four main steps: 1) pre-processing with color unmixing and morphological operators, 2) marker-controlled watershed segmentation at multiple scales and with different markers, 3) post-processing for rejection of false regions and 4) merging of the results from multiple scales. The procedure was developed on a set of 21 breast cancer cases (subset A) and tested on a separate validation set of 18 cases (subset B). The evaluation was done in terms of both detection accuracy (sensitivity and positive predictive value) and segmentation accuracy (Dice coefficient). The mean estimated sensitivity for subset A was 0.875 (±0.092) and for subset B 0.853 (±0.077). The mean estimated positive predictive value was 0.904 (±0.075) and 0.886 (±0.069) for subsets A and B, respectively. For both subsets, the distribution of the Dice coefficients had a high peak around 0.9, with the vast majority of segmentations having values larger than 0.8.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Various types of atherosclerotic plaque and varying grades of stenosis could lead to different management of patients with a coronary artery disease. Therefore, it is crucial to detect and classify ...the type of coronary artery plaque, as well as to detect and determine the degree of coronary artery stenosis. This paper includes retrospectively collected clinically obtained coronary CT angiography (CCTA) scans of 163 patients. In these, the centerlines of the coronary arteries were extracted and used to reconstruct multi-planar reformatted (MPR) images for the coronary arteries. To define the reference standard, the presence and the type of plaque in the coronary arteries (no plaque, non-calcified, mixed, calcified), as well as the presence and the anatomical significance of coronary stenosis (no stenosis, non-significant, i.e., <50% luminal narrowing, and significant, i.e., ≥50% luminal narrowing) were manually annotated in the MPR images by identifying the start- and end-points of the segment of the artery affected by the plaque. To perform an automatic analysis, a multi-task recurrent convolutional neural network is applied on coronary artery MPR images. First, a 3D convolutional neural network is utilized to extract features along the coronary artery. Subsequently, the extracted features are aggregated by a recurrent neural network that performs two simultaneous multi-class classification tasks. In the first task, the network detects and characterizes the type of the coronary artery plaque. In the second task, the network detects and determines the anatomical significance of the coronary artery stenosis. The network was trained and tested using the CCTA images of 98 and 65 patients, respectively. For detection and characterization of coronary plaque, the method was achieved an accuracy of 0.77. For detection of stenosis and determination of its anatomical significance, the method was achieved an accuracy of 0.80. The results demonstrate that automatic detection and classification of coronary artery plaque and stenosis are feasible. This may enable automated triage of patients to those without coronary plaque and those with coronary plaque and stenosis in need for further cardiovascular workup.
Accurate classification of focal liver lesions is an important part of liver disease diagnostics. In clinical practice, the lesion type is often determined from the abdominal MR examination, which ...includes T2-weighted and dynamic contrast enhanced (DCE) MR images. To date, only T2-weighted images are exploited for automatic classification of focal liver lesions. In this study additional MR sequences and risk factors are used for automatic classification to improve the results and to make a step forward to a clinically useful aid for radiologists.
Clinical MRI data sets of 95 patients with in total 125 benign lesions (40 adenomas, 29 cysts and 56 hemangiomas) and 88 malignant lesions (30 hepatocellular carcinomas (HCC) and 58 metastases) were included in this study. Contrast curve, gray level histogram, and gray level co-occurrence matrix texture features were extracted from the DCE-MR and T2-weighted images. In addition, risk factors including the presence of steatosis, cirrhosis, and a known primary tumor were used as features. Fifty features with the highest ANOVA F-score were selected and fed to an extremely randomized trees classifier. The classifier evaluation was performed using the leave-one-out principle and receiver operating characteristic (ROC) curve analysis.
The overall accuracy for the classification of the five major focal liver lesion types is 0.77. The sensitivity/specificity is 0.80/0.78, 0.93/0.93, 0.84/0.82, 0.73/0.56, and 0.62/0.77 for adenoma, cyst, hemangioma, HCC, and metastasis, respectively.
The proposed classification system using features derived from clinical DCE-MR and T2-weighted images, with additional risk factors is able to differentiate five common types of lesions and is a step forward to a clinically useful aid for focal liver lesion diagnosis.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
This paper presents an overview of methods that have been proposed for the analysis of breast cancer histopathology images. This research area has become particularly relevant with the advent of ...whole slide imaging (WSI) scanners, which can perform cost-effective and high-throughput histopathology slide digitization, and which aim at replacing the optical microscope as the primary tool used by pathologist. Breast cancer is the most prevalent form of cancers among women, and image analysis methods that target this disease have a huge potential to reduce the workload in a typical pathology lab and to improve the quality of the interpretation. This paper is meant as an introduction for nonexperts. It starts with an overview of the tissue preparation, staining and slide digitization processes followed by a discussion of the different image processing techniques and applications, ranging from analysis of tissue staining to computer-aided diagnosis, and prognosis of breast cancer patients.
An overview is presented of the medical image processing literature on mutual-information-based registration. The aim of the survey is threefold: an introduction for those new to the field, an ...overview for those working in the field, and a reference for those searching for literature on a specific application. Methods are classified according to the different aspects of mutual-information-based registration. The main division is in aspects of the methodology and of the application. The part on methodology describes choices made on facets such as preprocessing of images, gray value interpolation, optimization, adaptations to the mutual information measure, and different types of geometrical transformations. The part on applications is a reference of the literature available on different modalities, on interpatient registration and on different anatomical objects. Comparison studies including mutual information are also considered. The paper starts with a description of entropy and mutual information and it closes with a discussion on past achievements and some future challenges.
•A coronary artery centerline extraction method for cardiac CT angiography is proposed.•The method iteratively tracks a coronary artery centerline using a single seed point.•Artery direction and ...radius estimates are provided by a convolutional neural network.•The iterative tracking method allows highly accurate and fast centerline extraction.•Using this method coronary artery trees can be interactively extracted within seconds.
Display omitted
Coronary artery centerline extraction in cardiac CT angiography (CCTA) images is a prerequisite for evaluation of stenoses and atherosclerotic plaque. In this work, we propose an algorithm that extracts coronary artery centerlines in CCTA using a convolutional neural network (CNN).
In the proposed method, a 3D dilated CNN is trained to predict the most likely direction and radius of an artery at any given point in a CCTA image based on a local image patch. Starting from a single seed point placed manually or automatically anywhere in a coronary artery, a tracker follows the vessel centerline in two directions using the predictions of the CNN. Tracking is terminated when no direction can be identified with high certainty. The CNN is trained using manually annotated centerlines in training images. No image preprocessing is required, so that the process is guided solely by the local image values around the tracker’s location.
The CNN was trained using a training set consisting of 8 CCTA images with a total of 32 manually annotated centerlines provided in the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08). Evaluation was performed within the CAT08 challenge using a test set consisting of 24 CCTA test images in which 96 centerlines were extracted. The extracted centerlines had an average overlap of 93.7% with manually annotated reference centerlines. Extracted centerline points were highly accurate, with an average distance of 0.21 mm to reference centerline points. Based on these results the method ranks third among 25 publicly evaluated methods in CAT08. In a second test set consisting of 50 CCTA scans acquired at our institution (UMCU), an expert placed 5448 markers in the coronary arteries, along with radius measurements. Each marker was used as a seed point to extract a single centerline, which was compared to the other markers placed by the expert. This showed strong correspondence between extracted centerlines and manually placed markers. In a third test set containing 36 CCTA scans from the MICCAI 2014 Challenge on Automatic Coronary Calcium Scoring (orCaScore), fully automatic seeding and centerline extraction was evaluated using a segment-wise analysis. This showed that the algorithm is able to fully-automatically extract on average 92% of clinically relevant coronary artery segments. Finally, the limits of agreement between reference and automatic artery radius measurements were found to be below the size of one voxel in both the CAT08 dataset and the UMCU dataset. Extraction of a centerline based on a single seed point required on average 0.4 ± 0.1 s and fully automatic coronary tree extraction required around 20 s.
The proposed method is able to accurately and efficiently determine the direction and radius of coronary arteries based on information derived directly from the image data. The method can be trained with limited training data, and once trained allows fast automatic or interactive extraction of coronary artery trees from CCTA images.
Objectives
To evaluate the added value of deep learning (DL) analysis of the left ventricular myocardium (LVM) in resting coronary CT angiography (CCTA) over determination of coronary degree of ...stenosis (DS), for identification of patients with functionally significant coronary artery stenosis.
Methods
Patients who underwent CCTA prior to an invasive fractional flow reserve (FFR) measurement were retrospectively selected. Highest DS from CCTA was used to classify patients as having non-significant (≤ 24% DS), intermediate (25–69% DS), or significant stenosis (≥ 70% DS). Patients with intermediate stenosis were referred for fully automatic DL analysis of the LVM. The DL algorithm characterized the LVM, and likely encoded information regarding shape, texture, contrast enhancement, and more. Based on these encodings, features were extracted and patients classified as having a non-significant or significant stenosis. Diagnostic performance of the combined method was evaluated and compared to DS evaluation only. Functionally significant stenosis was defined as FFR ≤ 0.8 or presence of angiographic high-grade stenosis (≥ 90% DS).
Results
The final study population consisted of 126 patients (77% male, 59 ± 9 years). Eighty-one patients (64%) had a functionally significant stenosis. The proposed method resulted in improved discrimination (AUC = 0.76) compared to classification based on DS only (AUC = 0.68). Sensitivity and specificity were 92.6% and 31.1% for DS only (≥ 50% indicating functionally significant stenosis), and 84.6% and 48.4% for the proposed method.
Conclusion
The combination of DS with DL analysis of the LVM in intermediate-degree coronary stenosis may result in improved diagnostic performance for identification of patients with functionally significant coronary artery stenosis.
Key Points
• Assessment of degree of coronary stenosis on CCTA has consistently high sensitivity and negative predictive value, but has limited specificity for identifying the functional significance of a stenosis.
• Deep learning algorithms are able to learn complex patterns and relationships directly from the images without prior specification of which image features represent presence of disease, and thereby may be more sensitive to subtle changes in the LVM caused by functionally significant stenosis.
• Addition of deep learning analysis of the left ventricular myocardium to the evaluation of degree of coronary artery stenosis improves diagnostic performance and increases specificity of resting CCTA. This could potentially decrease the number of patients undergoing invasive coronary angiography.