Synthetic Augmentation for Anatomical Landmark Localization using DDPMs

Deep learning techniques for anatomical landmark localization (ALL) have shown great success, but their reliance on large annotated datasets remains a problem due to the tedious and costly nature of medical data acquisition and annotation. While traditional data augmentation, variational autoencoders (VAEs), and generative adversarial networks (GANs) have already been used to synthetically expand medical datasets, diffusion-based generative models have recently started to gain attention for their ability to generate high-quality synthetic images. In this study, we explore the use of denoising diffusion probabilistic models (DDPMs) for generating medical images and their corresponding heatmaps of landmarks to enhance the training of a supervised deep learning model for ALL. Our novel approach involves a DDPM with a 2-channel input, incorporating both the original medical image and its heatmap of annotated landmarks. We also propose a novel way to assess the quality of the generated images using a Markov Random Field (MRF) model for landmark matching and a Statistical Shape Model (SSM) to check landmark plausibility, before we evaluate the DDPM-augmented dataset in the context of an ALL task involving hand X-Rays.

Feature graphs for interpretable unsupervised tree ensembles: centrality, interaction, and application in disease subtyping

Interpretable machine learning has emerged as central in leveraging artificial intelligence within high-stakes domains such as healthcare, where understanding the rationale behind model predictions is as critical as achieving high predictive accuracy. In this context, feature selection assumes a pivotal role in enhancing model interpretability by identifying the most important input features in black-box models. While random forests are frequently used in biomedicine for their remarkable performance on tabular datasets, the accuracy gained from aggregating decision trees comes at the expense of interpretability. Consequently, feature selection for enhancing interpretability in random forests has been extensively explored in supervised settings. However, its investigation in the unsupervised regime remains notably limited. To address this gap, the study introduces novel methods to construct feature graphs from unsupervised random forests and feature selection strategies to derive effective feature combinations from these graphs. Feature graphs are constructed for the entire dataset as well as individual clusters leveraging the parent-child node splits within the trees, such that feature centrality captures their relevance to the clustering task, while edge weights reflect the discriminating power of feature pairs. Graph-based feature selection methods are extensively evaluated on synthetic and benchmark datasets both in terms of their ability to reduce dimensionality while improving clustering performance, as well as to enhance model interpretability. An application on omics data for disease subtyping identifies the top features for each cluster, showcasing the potential of the proposed approach to enhance interpretability in clustering analyses and its utility in a real-world biomedical application.

Federated unsupervised random forest for privacy-preserving patient stratification

In the realm of precision medicine, effective patient stratification and disease subtyping demand innovative methodologies tailored for multi-omics data. Clustering techniques applied to multi-omics data have become instrumental in identifying distinct subgroups of patients, enabling a finer-grained understanding of disease variability. This work establishes a powerful framework for advancing precision medicine through unsupervised random-forest-based clustering and federated computing. We introduce a novel multi-omics clustering approach utilizing unsupervised random-forests. The unsupervised nature of the random forest enables the determination of cluster-specific feature importance, unraveling key molecular contributors to distinct patient groups. Moreover, our methodology is designed for federated execution, a crucial aspect in the medical domain where privacy concerns are paramount. We have validated our approach on machine learning benchmark data sets as well as on cancer data from The Cancer Genome Atlas (TCGA). Our method is competitive with the state-of-the-art in terms of disease subtyping, but at the same time substantially improves the cluster interpretability. Experiments indicate that local clustering performance can be improved through federated computing.

Teeth Localization and Lesion Segmentation in CBCT Images using SpatialConfiguration-Net and U-Net

The localization of teeth and segmentation of periapical lesions in cone-beam computed tomography (CBCT) images are crucial tasks for clinical diagnosis and treatment planning, which are often time-consuming and require a high level of expertise. However, automating these tasks is challenging due to variations in shape, size, and orientation of lesions, as well as similar topologies among teeth. Moreover, the small volumes occupied by lesions in CBCT images pose a class imbalance problem that needs to be addressed. In this study, we propose a deep learning-based method utilizing two convolutional neural networks: the SpatialConfiguration-Net (SCN) and a modified version of the U-Net. The SCN accurately predicts the coordinates of all teeth present in an image, enabling precise cropping of teeth volumes that are then fed into the U-Net which detects lesions via segmentation. To address class imbalance, we compare the performance of three reweighting loss functions. After evaluation on 144 CBCT images, our method achieves a 97.3% accuracy for teeth localization, along with a promising sensitivity and specificity of 0.97 and 0.88, respectively, for subsequent lesion detection.

CaRe-CNN: Cascading Refinement CNN for Myocardial Infarct Segmentation with Microvascular Obstructions

Late gadolinium enhanced (LGE) magnetic resonance (MR) imaging is widely established to assess the viability of myocardial tissue of patients after acute myocardial infarction (MI). We propose the Cascading Refinement CNN (CaRe-CNN), which is a fully 3D, end-to-end trained, 3-stage CNN cascade that exploits the hierarchical structure of such labeled cardiac data. Throughout the three stages of the cascade, the label definition changes and CaRe-CNN learns to gradually refine its intermediate predictions accordingly. Furthermore, to obtain more consistent qualitative predictions, we propose a series of post-processing steps that take anatomical constraints into account. Our CaRe-CNN was submitted to the FIMH 2023 MYOSAIQ challenge, where it ranked second out of 18 participating teams. CaRe-CNN showed great improvements most notably when segmenting the difficult but clinically most relevant myocardial infarct tissue (MIT) as well as microvascular obstructions (MVO). When computing the average scores over all labels, our method obtained the best score in eight out of ten metrics. Thus, accurate cardiac segmentation after acute MI via our CaRe-CNN allows generating patient-specific models of the heart serving as an important step towards personalized medicine.

Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection

With the advancement in robotics, it is becoming increasingly common for large factories and warehouses to incorporate visual SLAM (vSLAM) enabled automated robots that operate closely next to humans. This makes any adversarial attacks on vSLAM components potentially detrimental to humans working alongside them. Loop Closure Detection (LCD) is a crucial component in vSLAM that minimizes the accumulation of drift in mapping, since even a small drift can accumulate into a significant drift over time. A prior work by Kim et al., SymbioLCD2, unified visual features and semantic objects into a single graph structure for finding loop closure candidates. While this provided a performance improvement over visual feature-based LCD, it also created a single point of vulnerability for potential graph-based adversarial attacks. Unlike previously reported visual-patch based attacks, small graph perturbations are far more challenging to detect, making them a more significant threat. In this paper, we present Adversarial-LCD, a novel black-box evasion attack framework that employs an eigencentrality-based perturbation method and an SVM-RBF surrogate model with a Weisfeiler-Lehman feature extractor for attacking graph-based LCD. Our evaluation shows that the attack performance of Adversarial-LCD with the SVM-RBF surrogate model was superior to that of other machine learning surrogate algorithms, including SVM-linear, SVM-polynomial, and Bayesian classifier, demonstrating the effectiveness of our attack framework. Furthermore, we show that our eigencentrality-based perturbation method outperforms other algorithms, such as Random-walk and Shortest-path, highlighting the efficiency of Adversarial-LCD's perturbation selection method.

MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision

We present MedShapeNet, a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D surgical instrument models. Prior to the deep learning era, the broad application of statistical shape models (SSMs) in medical image analysis is evidence that shapes have been commonly used to describe medical data. Nowadays, however, state-of-the-art (SOTA) deep learning algorithms in medical imaging are predominantly voxel-based. In computer vision, on the contrary, shapes (including, voxel occupancy grids, meshes, point clouds and implicit surface models) are preferred data representations in 3D, as seen from the numerous shape-related publications in premier vision conferences, such as the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), as well as the increasing popularity of ShapeNet (about 51,300 models) and Princeton ModelNet (127,915 models) in computer vision research. MedShapeNet is created as an alternative to these commonly used shape benchmarks to facilitate the translation of data-driven vision algorithms to medical applications, and it extends the opportunities to adapt SOTA vision algorithms to solve critical medical problems. Besides, the majority of the medical shapes in MedShapeNet are modeled directly on the imaging data of real patients, and therefore it complements well existing shape benchmarks comprising of computer-aided design (CAD) models. MedShapeNet currently includes more than 100,000 medical shapes, and provides annotations in the form of paired data. It is therefore also a freely available repository of 3D models for extended reality (virtual reality - VR, augmented reality - AR, mixed reality - MR) and medical 3D printing. This white paper describes in detail the motivations behind MedShapeNet, the shape acquisition procedures, the use cases, as well as the usage of the online shape search portal: https://medshapenet.ikim.nrw/

Closing the Loop: Graph Networks to Unify Semantic Objects and Visual Features for Multi-object Scenes

In Simultaneous Localization and Mapping (SLAM), Loop Closure Detection (LCD) is essential to minimize drift when recognizing previously visited places. Visual Bag-of-Words (vBoW) has been an LCD algorithm of choice for many state-of-the-art SLAM systems. It uses a set of visual features to provide robust place recognition but fails to perceive the semantics or spatial relationship between feature points. Previous work has mainly focused on addressing these issues by combining vBoW with semantic and spatial information from objects in the scene. However, they are unable to exploit spatial information of local visual features and lack a structure that unifies semantic objects and visual features, therefore limiting the symbiosis between the two components. This paper proposes SymbioLCD2, which creates a unified graph structure to integrate semantic objects and visual features symbiotically. Our novel graph-based LCD system utilizes the unified graph structure by applying a Weisfeiler-Lehman graph kernel with temporal constraints to robustly predict loop closure candidates. Evaluation of the proposed system shows that having a unified graph structure incorporating semantic objects and visual features improves LCD prediction accuracy, illustrating that the proposed graph structure provides a strong symbiosis between these two complementary components. It also outperforms other Machine Learning algorithms - such as SVM, Decision Tree, Random Forest, Neural Network and GNN based Graph Matching Networks. Furthermore, it has shown good performance in detecting loop closure candidates earlier than state-of-the-art SLAM systems, demonstrating that extended semantic and spatial awareness from the unified graph structure significantly impacts LCD performance.

SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words

Loop closure detection is an essential tool of Simultaneous Localization and Mapping (SLAM) to minimize drift in its localization. Many state-of-the-art loop closure detection (LCD) algorithms use visual Bag-of-Words (vBoW), which is robust against partial occlusions in a scene but cannot perceive the semantics or spatial relationships between feature points. CNN object extraction can address those issues, by providing semantic labels and spatial relationships between objects in a scene. Previous work has mainly focused on replacing vBoW with CNN-derived features. In this paper, we propose SymbioLCD, a novel ensemble-based LCD that utilizes both CNN-extracted objects and vBoW features for LCD candidate prediction. When used in tandem, the added elements of object semantics and spatial-awareness create a more robust and symbiotic loop closure detection system. The proposed SymbioLCD uses scale-invariant spatial and semantic matching, Hausdorff distance with temporal constraints, and a Random Forest that utilizes combined information from both CNN-extracted objects and vBoW features for predicting accurate loop closure candidates. Evaluation of the proposed method shows it outperforms other Machine Learning (ML) algorithms - such as SVM, Decision Tree and Neural Network, and demonstrates that there is a strong symbiosis between CNN-extracted object information and vBoW features which assists accurate LCD candidate prediction. Furthermore, it is able to perceive loop closure candidates earlier than state-of-the-art SLAM algorithms, utilizing added spatial and semantic information from CNN-extracted objects.

Modeling Annotation Uncertainty with Gaussian Heatmaps in Landmark Localization

In landmark localization, due to ambiguities in defining their exact position, landmark annotations may suffer from large observer variabilities, which result in uncertain annotations. To model the annotation ambiguities of the training dataset, we propose to learn anisotropic Gaussian parameters modeling the shape of the target heatmap during optimization. Furthermore, our method models the prediction uncertainty of individual samples by fitting anisotropic Gaussian functions to the predicted heatmaps during inference. Besides state-of-the-art results, our experiments on datasets of hand radiographs and lateral cephalograms also show that Gaussian functions are correlated with both localization accuracy and observer variability. As a final experiment, we show the importance of integrating the uncertainty into decision making by measuring the influence of the predicted location uncertainty on the classification of anatomical abnormalities in lateral cephalograms.