In medical image analysis, automated segmentation of multi-component anatomical entities, with the possible presence of variable anomalies or pathologies, is a challenging task. In this work, we develop a multi-step approach using U-Net-based models to initially detect anomalies (bone marrow lesions, bone cysts) in the distal femur, proximal tibia and patella from 3D magnetic resonance (MR) images in individuals with varying grades of knee osteoarthritis. Subsequently, the extracted data are used for downstream tasks involving semantic segmentation of individual bone and cartilage volumes as well as bone anomalies. For anomaly detection, U-Net-based models were developed to reconstruct bone volume profiles of the femur and tibia in images via inpainting so anomalous bone regions could be replaced with close to normal appearances. The reconstruction error was used to detect bone anomalies. An anomaly-aware segmentation network, which was compared to anomaly-naïve segmentation networks, was used to provide a final automated segmentation of the individual femoral, tibial and patellar bone and cartilage volumes from the knee MR images which contain a spectrum of bone anomalies. The anomaly-aware segmentation approach provided up to 58% reduction in Hausdorff distances for bone segmentations compared to the results from anomaly-naïve segmentation networks. In addition, the anomaly-aware networks were able to detect bone anomalies in the MR images with greater sensitivity and specificity (area under the receiver operating characteristic curve [AUC] up to 0.896) compared to anomaly-naïve segmentation networks (AUC up to 0.874).

Deep learning models are powerful tools for addressing challenging medical imaging problems. However, for an ever-growing range of applications, interpreting a model’s prediction remains non-trivial. Understanding decisions made by black-box algorithms is critical, and assessing their fairness and susceptibility to bias is a key step towards healthcare deployment. In this paper, we propose DBCE (Deformation Based Counterfactual Explainability). We optimise a diffeomorphic transformation that deforms a given input image to change the prediction of the model. This provides anatomically meaningful saliency maps indicating tissue atrophy and expansion, which can be easily interpreted by clinicians. In our test case, DBCE replicates the transition of a patient from healthy control (HC) to Alzheimer’s disease (AD). We benchmark DBCE against three commonly used saliency methods. We show that it provides more meaningful saliency maps when applied to one subject and disease-consistent atrophy patterns when used over a larger cohort. In addition, our method fulfils a recent sanity check and is repeatable for different model initialisations in contrast to classical sensitivity-based methods.

Cortical thickness (CTh) is routinely used to quantify grey matter atrophy as it is a significant biomarker in studying neurodegenerative and neurological conditions. Clinical studies commonly employ one of several available CTh estimation software tools to estimate CTh from brain MRI scans. In recent years, machine learning-based methods emerged as a faster alternative to the main-stream CTh estimation methods (e.g. FreeSurfer). Evaluation and comparison of CTh estimation methods often include various metrics and downstream tasks, but none fully covers the sensitivity to sub-voxel atrophy characteristic of neurodegeneration. In addition, current evaluation methods do not provide a framework for the intra-method region-wise evaluation of CTh estimation methods. Therefore, we propose a method for brain MRI synthesis capable of generating a range of sub-voxel atrophy levels (global and local) with quantifiable changes from the baseline scan. We further create a synthetic test set and evaluate four different CTh estimation methods: FreeSurfer (cross-sectional), FreeSurfer (longitudinal), DL+DiReCT and HerstonNet. DL+DiReCT showed superior sensitivity to sub-voxel atrophy over other methods in our testing framework. The obtained results indicate that our synthetic test set is suitable for benchmarking CTh estimation methods on both global and local scales as well as regional inter-and intra-method performance comparison.

In this paper, we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object. To conserve the template mesh’s topological properties, we train our model over a set of diffeomorphic transformations. This new implementation of a flow Ordinary Differential Equation (ODE) framework benefits from a small GPU memory footprint, allowing the generation of surfaces with several hundred thousand vertices. To reduce topological errors introduced by its discrete resolution, we derive numeric conditions which improve the manifoldness of the predicted triangle mesh. To exhibit the utility of CorticalFlow, we demonstrate its performance for the challenging task of brain cortical surface reconstruction. In contrast to the current state-of-the-art, CorticalFlow produces superior surfaces while reducing the computation time from nine and a half minutes to one second. More significantly, CorticalFlow enforces the generation of anatomically plausible surfaces; the absence of which has been a major impediment restricting the clinical relevance of such surface reconstruction methods.

The study of neurodegenerative diseases relies on the reconstruction and analysis of the brain cortex from magnetic resonance imaging (MRI). Traditional frameworks for this task like FreeSurfer demand lengthy runtimes, while its accelerated variant FastSurfer still relies on a voxel-wise segmentation which is limited by its resolution to capture narrow continuous objects as cortical surfaces. Having these limitations in mind, we propose DeepCSR, a 3D deep learning framework for cortical surface reconstruction from MRI. Towards this end, we train a neural network model with hypercolumn features to predict implicit surface representations for points in a brain template space. After training, the cortical surface at a desired level of detail is obtained by evaluating surface representations at specific coordinates, and subsequently applying a topology correction algorithm and an isosurface extraction method. Thanks to the continuous nature of this approach and the efficacy of its hypercolumn features scheme, DeepCSR efficiently reconstructs cortical surfaces at high resolution capturing fine details in the cortical folding. Moreover, DeepCSR is as accurate, more precise, and faster than the widely used FreeSurfer toolbox and its deep learning powered variant FastSurfer on reconstructing cortical surfaces from MRI which should facilitate large-scale medical studies and new healthcare applications.

In clinics, the information about the appearance and location of brain tumors is essential to assist doctors in diagnosis and treatment. Automatic brain tumor segmentation on the images acquired by magnetic resonance imaging (MRI) is a common way to attain this information. However, MR images are not quantitative and can exhibit significant variation in signal depending on a range of factors, which increases the difficulty of training an automatic segmentation network and applying it to new MR images. To deal with this issue, this paper proposes to learn a sample-adaptive intensity lookup table (LuT) that dynamically transforms the intensity contrast of each input MR image to adapt to the following segmentation task. Specifically, the proposed deep SA-LuT-Net framework consists of a LuT module and a segmentation module, trained in an end-to-end manner: the LuT module learns a sample-specific nonlinear intensity mapping function through communication with the segmentation module, aiming at improving the final segmentation performance. In order to make the LuT learning sample-adaptive, we parameterize the intensity mapping function by exploring two families of non-linear functions (i.e., piece-wise linear and power functions) and predict the function parameters for each given sample. These sample-specific parameters make the intensity mapping adaptive to samples. We develop our SA-LuT-Nets separately based on two backbone networks for segmentation, i.e., DMFNet and the modified 3D Unet, and validate them on BRATS2018 and BRATS2019 datasets for brain tumor segmentation. Our experimental results clearly demonstrate the superior performance of the proposed SA-LuT-Nets using either single or multiple MR modalities. It not only significantly improves the two baselines (DMFNet and the modified 3D Unet), but also wins a set of state-of-the-art segmentation methods. Moreover, we show that, the LuTs learnt using one segmentation model could also be applied to improving the performance of another segmentation model, indicating the general segmentation information captured by LuTs.

Generative adversarial network (GAN) has been widely explored for cross-modality medical image synthesis. The existing GAN models usually adversarially learn a global sample space mapping from the source-modality to the target-modality and then indiscriminately apply this mapping to all samples in the whole space for prediction. However, due to the scarcity of training samples in contrast to the complicated nature of medical image synthesis, learning a single global sample space mapping that is "optimal" to all samples is very challenging, if not intractable. To address this issue, this paper proposes sample-adaptive GAN models, which not only cater for the global sample space mapping between the source- and the target-modalities but also explore the local space around each given sample to extract its unique characteristic. Specifically, the proposed sample-adaptive GANs decompose the entire learning model into two cooperative paths. The baseline path learns a common GAN model by fitting all the training samples as usual for the global sample space mapping. The new sample-adaptive path additionally models each sample by learning its relationship with its neighboring training samples and using the target-modality features of these training samples as auxiliary information for synthesis. Enhanced by this sample-adaptive path, the proposed sample-adaptive GANs are able to flexibly adjust themselves to different samples, and therefore optimize the synthesis performance. Our models have been verified on three cross-modality MR image synthesis tasks from two public datasets, and they significantly outperform the state-of-the-art methods in comparison. Moreover, the experiment also indicates that our sample-adaptive strategy could be utilized to improve various backbone GAN models. It complements the existing GANs models and can be readily integrated when needed.

Magnetic resonance (MR) imaging is a widely used medical imaging protocol that can be configured to provide different contrasts between the tissues in human body. By setting different scanning parameters, each MR imaging modality reflects the unique visual characteristic of scanned body part, benefiting the subsequent analysis from multiple perspectives. To utilize the complementary information from multiple imaging modalities, cross-modality MR image synthesis has aroused increasing research interest recently. However, most existing methods only focus on minimizing pixel/voxel-wise intensity difference but ignore the textural details of image content structure, which affects the quality of synthesized images. In this paper, we propose edge-aware generative adversarial networks (Ea-GANs) for cross-modality MR image synthesis. Specifically, we integrate edge information, which reflects the textural structure of image content and depicts the boundaries of different objects in images, to reduce this gap. Corresponding to different learning strategies, two frameworks are proposed, i.e., a generator-induced Ea-GAN (gEa-GAN) and a discriminator-induced Ea-GAN (dEa-GAN). The gEa-GAN incorporates the edge information via its generator, while the dEa-GAN further does this from both the generator and the discriminator so that the edge similarity is also adversarially learned. In addition, the proposed Ea-GANs are 3D-based and utilize hierarchical features to capture contextual information. The experimental results demonstrate that the proposed Ea-GANs, especially the dEa-GAN, outperform multiple state-of-the-art methods for cross-modality MR image synthesis in both qualitative and quantitative measures. Moreover, the dEa-GAN also shows excellent generality to generic image synthesis tasks on benchmark datasets about facades, maps, and cityscapes.

Active contour techniques have been widely employed for medical image segmentation. Significant effort has been focused on the use of training data to build prior statistical models applicable specifically to problems where the objects of interest are embedded in cluttered background. Usually, the training data consist of whole shapes of certain organs or structures obtained manually by clinical experts. The resulting prior models enforce segmentation accuracy uniformly over the entire structure or structures to be identified. In this paper, we consider a new coupled prior shape model which is demonstrated to provide high accuracy, specifically in the region of the interest where precision is most needed for the application of the segmentation of the femur and tibia in magnetic resonance (MR) images. Experimental results for the segmentation of MR images of human knees demonstrate that the combination of the new coupled prior shape and a directional edge force provides the improved segmentation performance. Moreover, the new approach allows for equivalent accurate identification of bone marrow lesions, a promising biomarker related to osteoarthritis, to the current state of the art but requires significantly less manual interaction.

OBJECTIVE: As large-scale medical imaging studies are becoming more common, there is an increasing reliance on automated software to extract quantitative information from these images. As the size of the cohorts keeps increasing with large studies, there is a also a need for tools that allow results from automated image processing and analysis to be presented in a way that enables fast and efficient quality checking, tagging and reporting on cases in which automatic processing failed or was problematic. MATERIALS AND METHODS: MilxXplore is an open source visualization platform, which provides an interface to navigate and explore imaging data in a web browser, giving the end user the opportunity to perform quality control and reporting in a user friendly, collaborative and efficient way. DISCUSSION: Compared to existing software solutions that often provide an overview of the results at the subject's level, MilxXplore pools the results of individual subjects and time points together, allowing easy and efficient navigation and browsing through the different acquisitions of a subject over time, and comparing the results against the rest of the population. CONCLUSIONS: MilxXplore is fast, flexible and allows remote quality checks of processed imaging data, facilitating data sharing and collaboration across multiple locations, and can be easily integrated into a cloud computing pipeline. With the growing trend of open data and open science, such a tool will become increasingly important to share and publish results of imaging analysis.

BACKGROUND AND OBJECTIVES: Advances in MRI hardware and sequences are continually increasing the amount and complexity of data such as those generated in high-resolution three-dimensional (3D) scanning of the spine. Efficient informatics tools offer considerable opportunities for research and clinically based analyses of magnetic resonance studies. In this work, we present and validate a suite of informatics tools for automated detection of degenerative changes in lumbar intervertebral discs (IVD) from both 3D isotropic and routine two-dimensional (2D) clinical T2-weighted MRI. MATERIALS AND METHODS: An automated segmentation approach was used to extract morphological (traditional 2D radiological measures and novel 3D shape descriptors) and signal appearance (extracted from signal intensity histograms) features. The features were validated against manual reference, compared between 2D and 3D MRI scans and used for quantification and classification of IVD degeneration across magnetic resonance datasets containing IVD with early and advanced stages of degeneration. RESULTS AND CONCLUSIONS: Combination of the novel 3D-based shape and signal intensity features on 3D (area under receiver operating curve (AUC) 0.984) and 2D (AUC 0.988) magnetic resonance data deliver a significant improvement in automated classification of IVD degeneration, compared to the combination of previously used 2D radiological measurement and signal intensity features (AUC 0.976 and 0.983, respectively). Further work is required regarding the usefulness of 2D and 3D shape data in relation to clinical scores of lower back pain. The results reveal the potential of the proposed informatics system for computer-aided IVD diagnosis from MRI in large-scale research studies and as a possible adjunct for clinical diagnosis.

Accurate localization of the prostate and its surrounding tissue is essential in the treatment of prostate cancer. This paper presents a novel approach to fully automatically segment the prostate, including its seminal vesicles, within a few minutes of a magnetic resonance (MR) scan acquired without an endorectal coil. Such MR images are important in external beam radiation therapy, where using an endorectal coil is highly undesirable. The segmentation is obtained using a deformable model that is trained on-the-fly so that it is specific to the patient's scan. This case specific deformable model consists of a patient specific initialized triangulated surface and image feature model that are trained during its initialization. The image feature model is used to deform the initialized surface by template matching image features (via normalized cross-correlation) to the features of the scan. The resulting deformations are regularized over the surface via well established simple surface smoothing algorithms, which is then made anatomically valid via an optimized shape model. Mean and median Dice's similarity coefficients (DSCs) of 0.85 and 0.87 were achieved when segmenting 3T MR clinical scans of 50 patients. The median DSC result was equal to the inter-rater DSC and had a mean absolute surface error of 1.85 mm. The approach is showed to perform well near the apex and seminal vesicles of the prostate.

In this paper, we present a segmentation scheme that automatically and accurately segments all the cartilages from magnetic resonance (MR) images of nonpathological knees. Our scheme involves the automatic segmentation of the bones using a three-dimensional active shape model, the extraction of the expected bone-cartilage interface (BCI), and cartilage segmentation from the BCI using a deformable model that utilizes localization, patient specific tissue estimation and a model of the thickness variation. The accuracy of this scheme was experimentally validated using leave one out experiments on a database of fat suppressed spoiled gradient recall MR images. The scheme was compared to three state of the art approaches, tissue classification, a modified semi-automatic watershed algorithm and nonrigid registration (B-spline based free form deformation). Our scheme obtained an average Dice similarity coefficient (DSC) of (0.83, 0.83, 0.85) for the (patellar, tibial, femoral) cartilages, while (0.82, 0.81, 0.86) was obtained with a tissue classifier and (0.73, 0.79, 0.76) was obtained with nonrigid registration. The average DSC obtained for all the cartilages using a semi-automatic watershed algorithm (0.90) was slightly higher than our approach (0.89), however unlike this approach we segment each cartilage as a separate object. The effectiveness of our approach for quantitative analysis was evaluated using volume and thickness measures with a median volume difference error of (5.92, 4.65, 5.69) and absolute Laplacian thickness difference of (0.13, 0.24, 0.12) mm.