Reducing inter-observer variability and interaction time of MR liver volumetry by combining automatic CNN-based liver segmentation and manual corrections.

PURPOSE: To compare manual corrections of liver masks produced by a fully automatic segmentation method based on convolutional neural networks (CNN) with manual routine segmentations in MR images in terms of inter-observer variability and interaction time. METHODS: For testing, patient's precise reference segmentations that fulfill the quality requirements for liver surgery were manually created. One radiologist and two radiology residents were asked to provide manual routine segmentations. We used our automatic segmentation method Liver-Net to produce liver masks for the test cases and asked a radiologist assistant and one further resident to correct the automatic results. All observers were asked to measure their interaction time. Both manual routine and corrected segmentations were compared with the reference annotations. RESULTS: The manual routine segmentations achieved a mean Dice index of 0.95 and a mean relative error (RVE) of 4.7%. The quality of liver masks produced by the Liver-Net was on average 0.95 Dice and 4.5% RVE. Liver masks resulting from manual corrections of automatically generated segmentations compared to routine results led to a significantly lower inter-observer variability (mean per case absolute RVE difference across observers 0.69%) when compared to manual routine ones (2.75%). The mean interaction time was 2 min for manual corrections and 10 min for manual routine segmentations. CONCLUSIONS: The quality of automatic liver segmentations is on par with those from manual routines. Using automatic liver masks in the clinical workflow could lead to a reduction of segmentation time and a more consistent liver volume estimation across different observers.

Uncertainty-aware asynchronous scattered motion interpolation using Gaussian process regression.

We address the problem of interpolating randomly non-uniformly spatiotemporally scattered uncertain motion measurements, which arises in the context of soft tissue motion estimation. Soft tissue motion estimation is of great interest in the field of image-guided soft-tissue intervention and surgery navigation, because it enables the registration of pre-interventional/pre-operative navigation information on deformable soft-tissue organs. To formally define the measurements as spatiotemporally scattered motion signal samples, we propose a novel motion field representation. To perform the interpolation of the motion measurements in an uncertainty-aware optimal unbiased fashion, we devise a novel Gaussian process (GP) regression model with a non-constant-mean prior and an anisotropic covariance function and show through an extensive evaluation that it outperforms the state-of-the-art GP models that have been deployed previously for similar tasks. The employment of GP regression enables the quantification of uncertainty in the interpolation result, which would allow the amount of uncertainty present in the registered navigation information governing the decisions of the surgeon or intervention specialist to be conveyed.

Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing.

Automatic liver tumor segmentation would have a big impact on liver therapy planning procedures and follow-up assessment, thanks to standardization and incorporation of full volumetric information. In this work, we develop a fully automatic method for liver tumor segmentation in CT images based on a 2D fully convolutional neural network with an object-based postprocessing step. We describe our experiments on the LiTS challenge training data set and evaluate segmentation and detection performance. Our proposed design cascading two models working on voxel- and object-level allowed for a significant reduction of false positive findings by 85% when compared with the raw neural network output. In comparison with the human performance, our approach achieves a similar segmentation quality for detected tumors (mean Dice 0.69 vs. 0.72), but is inferior in the detection performance (recall 63% vs. 92%). Finally, we describe how we participated in the LiTS challenge and achieved state-of-the-art performance.

Automated quantification of steatosis: agreement with stereological point counting.

BACKGROUND: Steatosis is routinely assessed histologically in clinical practice and research. Automated image analysis can reduce the effort of quantifying steatosis. Since reproducibility is essential for practical use, we have evaluated different analysis methods in terms of their agreement with stereological point counting (SPC) performed by a hepatologist. METHODS: The evaluation was based on a large and representative data set of 970 histological images from human patients with different liver diseases. Three of the evaluated methods were built on previously published approaches. One method incorporated a new approach to improve the robustness to image variability. RESULTS: The new method showed the strongest agreement with the expert. At 20× resolution, it reproduced steatosis area fractions with a mean absolute error of 0.011 for absent or mild steatosis and 0.036 for moderate or severe steatosis. At 10× resolution, it was more accurate than and twice as fast as all other methods at 20× resolution. When compared with SPC performed by two additional human observers, its error was substantially lower than one and only slightly above the other observer. CONCLUSIONS: The results suggest that the new method can be a suitable automated replacement for SPC. Before further improvements can be verified, it is necessary to thoroughly assess the variability of SPC between human observers.

Training Nuclei Detection Algorithms with Simple Annotations.

BACKGROUND: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. METHODS: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. RESULTS: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. CONCLUSIONS: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.

Registration of histological whole slide images guided by vessel structures.

INTRODUCTION: The registration of histological whole slide images is an important prerequisite for modern histological image analysis. A partial reconstruction of the original volume allows e.g. colocalization analysis of tissue parameters or high-detail reconstructions of anatomical structures in 3D. METHODS: In this paper, we present an automatic staining-invariant registration method, and as part of that, introduce a novel vessel-based rigid registration algorithm using a custom similarity measure. The method is based on an iterative best-fit matching of prominent vessel structures. RESULTS: We evaluated our method on a sophisticated synthetic dataset as well as on real histological whole slide images. Based on labeled vessel structures we compared the relative differences for corresponding structures. The average positional error was close to 0, the median for the size change factor was 1, and the median overlap was 0.77. CONCLUSION: The results show that our approach is very robust and creates high quality reconstructions. The key element for the resulting quality is our novel rigid registration algorithm.

Breast image registration and deformation modeling.

Image-based examination of the breast facilitates the detection of breast diseases, particularly of present benign and malignant lesions. For computer-aided processing of serial and multimodal clinical data, both for visual correlation and quantitative analysis, automated image-registration methods are an indispensable tool. The wide range of modalities and the high variability of breast appearance have led to a large diversity of proposed approaches for tissue deformation modeling and image registration. In this article, we review current developments in breast image registration techniques, and comment on their clinical relevance, individual capabilities, and open challenges.

Boundary estimation of fiber bundles derived from diffusion tensor images.

PURPOSE: Diffusion tensor imaging (DTI) is a non-invasive imaging technique that allows estimating the location of white matter tracts based on the measurement of water diffusion properties. Using DTI data, the fiber bundle boundary can be determined to gain information about eloquent structures, which is of major interest for neurosurgical interventions. In this paper, a novel approach for boundary estimation is presented. METHODS: DTI in combination with diverse segmentation algorithms allows estimating the position and course of fiber tracts in the human brain. For additional information about the expansion of the fiber bundle, the introduced iterative approach uses the centerline of a tracked fiber bundle between two regions of interest (ROI). After sampling along this centerline, rays are sent out radially, discrete 2D contours are calculated, and the fiber bundle boundary is estimated in a stepwise manner. For this purpose, each ray is analyzed using several criteria, including anisotropy parameters and angle parameters, to find the boundary point. RESULTS: The novel method for automatically calculating the boundaries has been applied to several artificially generated DTI datasets. Multiple parameters were varied: number of rays per plane, sampling rate and sampled points along the rays. For the DTI data used in the experiments, the method yielded a dice similarity coefficient (DSC) between 74.7 and 91.5%. CONCLUSIONS: In this paper, a novel approach to retrieve significant information about the fiber bundle boundary from DTI data is presented. The method is a contribution to gather important knowledge about high-risk structures in neurosurgical interventions.