Alison Q. O'Neil

Pedro Sanchez, Antanas Kascenas, Xiao Liu et al.

Reducing the requirement for densely annotated masks in medical image segmentation is important due to cost constraints. In this paper, we consider the problem of inferring pixel-level predictions of brain lesions by only using image-level labels for training. By leveraging recent advances in generative diffusion probabilistic models (DPM), we synthesize counterfactuals of "How would a patient appear if X pathology was not present?". The difference image between the observed patient state and the healthy counterfactual can be used for inferring the location of pathology. We generate counterfactuals that correspond to the minimal change of the input such that it is transformed to healthy domain. This requires training with healthy and unhealthy data in DPMs. We improve on previous counterfactual DPMs by manipulating the generation process with implicit guidance along with attention conditioning instead of using classifiers. Code is available at https://github.com/vios-s/Diff-SCM.

Xiao Liu, Spyridon Thermos, Pedro Sanchez et al.

Training medical image segmentation models usually requires a large amount of labeled data. By contrast, humans can quickly learn to accurately recognise anatomy of interest from medical (e.g. MRI and CT) images with some limited guidance. Such recognition ability can easily generalise to new images from different clinical centres. This rapid and generalisable learning ability is mostly due to the compositional structure of image patterns in the human brain, which is less incorporated in medical image segmentation. In this paper, we model the compositional components (i.e. patterns) of human anatomy as learnable von-Mises-Fisher (vMF) kernels, which are robust to images collected from different domains (e.g. clinical centres). The image features can be decomposed to (or composed by) the components with the composing operations, i.e. the vMF likelihoods. The vMF likelihoods tell how likely each anatomical part is at each position of the image. Hence, the segmentation mask can be predicted based on the vMF likelihoods. Moreover, with a reconstruction module, unlabeled data can also be used to learn the vMF kernels and likelihoods by recombining them to reconstruct the input image. Extensive experiments show that the proposed vMFNet achieves improved generalisation performance on two benchmarks, especially when annotations are limited. Code is publicly available at: https://github.com/vios-s/vMFNet.

Antanas Kascenas, Pedro Sanchez, Patrick Schrempf et al.

Pathological brain lesions exhibit diverse appearance in brain images, in terms of intensity, texture, shape, size, and location. Comprehensive sets of data and annotations are difficult to acquire. Therefore, unsupervised anomaly detection approaches have been proposed using only normal data for training, with the aim of detecting outlier anomalous voxels at test time. Denoising methods, for instance classical denoising autoencoders (DAEs) and more recently emerging diffusion models, are a promising approach, however naive application of pixelwise noise leads to poor anomaly detection performance. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes, with similar noise parameter adjustments giving good performance for both DAEs and diffusion models. Visual inspection of the reconstructions suggests that the training noise influences the trade-off between the extent of the detail that is reconstructed and the extent of erasure of anomalies, both of which contribute to better anomaly detection performance. We validate our findings on two real-world datasets (tumor detection in brain MRI and hemorrhage/ischemia/tumor detection in brain CT), showing good detection on diverse anomaly appearances. Overall, we find that a DAE trained with coarse noise is a fast and simple method that gives state-of-the-art accuracy. Diffusion models applied to anomaly detection are as yet in their infancy and provide a promising avenue for further research.

Konstantinos Vilouras, Xiao Liu, Pedro Sanchez et al.

Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one. However, distillation objectives are susceptible to sub-population shifts, a common scenario in medical imaging analysis which refers to groups/domains of data that are underrepresented in the training set. For instance, training models on health data acquired from multiple scanners or hospitals can yield subpar performance for minority groups. In this paper, inspired by distributionally robust optimization (DRO) techniques, we address this shortcoming by proposing a group-aware distillation loss. During optimization, a set of weights is updated based on the per-group losses at a given iteration. This way, our method can dynamically focus on groups that have low performance during training. We empirically validate our method, GroupDistil on two benchmark datasets (natural images and cardiac MRIs) and show consistent improvement in terms of worst-group accuracy.

Xiao Liu, Pedro Sanchez, Spyridon Thermos et al.

Deep learning models often need sufficient supervision (i.e. labelled data) in order to be trained effectively. By contrast, humans can swiftly learn to identify important anatomy in medical images like MRI and CT scans, with minimal guidance. This recognition capability easily generalises to new images from different medical facilities and to new tasks in different settings. This rapid and generalisable learning ability is largely due to the compositional structure of image patterns in the human brain, which are not well represented in current medical models. In this paper, we study the utilisation of compositionality in learning more interpretable and generalisable representations for medical image segmentation. Overall, we propose that the underlying generative factors that are used to generate the medical images satisfy compositional equivariance property, where each factor is compositional (e.g. corresponds to the structures in human anatomy) and also equivariant to the task. Hence, a good representation that approximates well the ground truth factor has to be compositionally equivariant. By modelling the compositional representations with learnable von-Mises-Fisher (vMF) kernels, we explore how different design and learning biases can be used to enforce the representations to be more compositionally equivariant under un-, weakly-, and semi-supervised settings. Extensive results show that our methods achieve the best performance over several strong baselines on the task of semi-supervised domain-generalised medical image segmentation. Code will be made publicly available upon acceptance at https://github.com/vios-s.

Francesco Dalla Serra, Chaoyang Wang, Fani Deligianni et al.

The task of radiology reporting comprises describing and interpreting the medical findings in radiographic images, including description of their location and appearance. Automated approaches to radiology reporting require the image to be encoded into a suitable token representation for input to the language model. Previous methods commonly use convolutional neural networks to encode an image into a series of image-level feature map representations. However, the generated reports often exhibit realistic style but imperfect accuracy. Inspired by recent works for image captioning in the general domain in which each visual token corresponds to an object detected in an image, we investigate whether using local tokens corresponding to anatomical structures can improve the quality of the generated reports. We introduce a novel adaptation of Faster R-CNN in which finding detection is performed for the candidate bounding boxes extracted during anatomical structure localisation. We use the resulting bounding box feature representations as our set of finding-aware anatomical tokens. This encourages the extracted anatomical tokens to be informative about the findings they contain (required for the final task of radiology reporting). Evaluating on the MIMIC-CXR dataset of chest X-Ray images, we show that task-aware anatomical tokens give state-of-the-art performance when integrated into an automated reporting pipeline, yielding generated reports with improved clinical accuracy.

Xiao Liu, Antanas Kascenas, Hannah Watson et al.

For brain tumour segmentation, deep learning models can achieve human expert-level performance given a large amount of data and pixel-level annotations. However, the expensive exercise of obtaining pixel-level annotations for large amounts of data is not always feasible, and performance is often heavily reduced in a low-annotated data regime. To tackle this challenge, we adapt a mixed supervision framework, vMFNet, to learn robust compositional representations using unsupervised learning and weak supervision alongside non-exhaustive pixel-level pathology labels. In particular, we use the BraTS dataset to simulate a collection of 2-point expert pathology annotations indicating the top and bottom slice of the tumour (or tumour sub-regions: peritumoural edema, GD-enhancing tumour, and the necrotic / non-enhancing tumour) in each MRI volume, from which weak image-level labels that indicate the presence or absence of the tumour (or the tumour sub-regions) in the image are constructed. Then, vMFNet models the encoded image features with von-Mises-Fisher (vMF) distributions, via learnable and compositional vMF kernels which capture information about structures in the images. We show that good tumour segmentation performance can be achieved with a large amount of weakly labelled data but only a small amount of fully-annotated data. Interestingly, emergent learning of anatomical structures occurs in the compositional representation even given only supervision relating to pathology (tumour).

Xiao Liu, Spyridon Thermos, Pedro Sanchez et al.

Learning disentangled representations requires either supervision or the introduction of specific model designs and learning constraints as biases. InfoGAN is a popular disentanglement framework that learns unsupervised disentangled representations by maximising the mutual information between latent representations and their corresponding generated images. Maximisation of mutual information is achieved by introducing an auxiliary network and training with a latent regression loss. In this short exploratory paper, we study the use of the Hilbert-Schmidt Independence Criterion (HSIC) to approximate mutual information between latent representation and image, termed HSIC-InfoGAN. Directly optimising the HSIC loss avoids the need for an additional auxiliary network. We qualitatively compare the level of disentanglement in each model, suggest a strategy to tune the hyperparameters of HSIC-InfoGAN, and discuss the potential of HSIC-InfoGAN for medical applications.

Joseph S. Boyle, Antanas Kascenas, Pat Lok et al.

The task of assigning diagnostic ICD codes to patient hospital admissions is typically performed by expert human coders. Efforts towards automated ICD coding are dominated by supervised deep learning models. However, difficulties in learning to predict the large number of rare codes remain a barrier to adoption in clinical practice. In this work, we leverage off-the-shelf pre-trained generative large language models (LLMs) to develop a practical solution that is suitable for zero-shot and few-shot code assignment, with no need for further task-specific training. Unsupervised pre-training alone does not guarantee precise knowledge of the ICD ontology and specialist clinical coding task, therefore we frame the task as information extraction, providing a description of each coded concept and asking the model to retrieve related mentions. For efficiency, rather than iterating over all codes, we leverage the hierarchical nature of the ICD ontology to sparsely search for relevant codes.

Konstantinos Vilouras, Ilias Stogiannidis, Junyu Yan et al.

Latent Diffusion Models have shown remarkable results in text-guided image synthesis in recent years. In the domain of natural (RGB) images, recent works have shown that such models can be adapted to various vision-language downstream tasks with little to no supervision involved. On the contrary, text-to-image Latent Diffusion Models remain relatively underexplored in the field of medical imaging, primarily due to limited data availability (e.g., due to privacy concerns). In this work, focusing on the chest X-ray modality, we first demonstrate that a standard text-conditioned Latent Diffusion Model has not learned to align clinically relevant information in free-text radiology reports with the corresponding areas of the given scan. Then, to alleviate this issue, we propose a fine-tuning framework to improve multi-modal alignment in a pre-trained model such that it can be efficiently repurposed for downstream tasks such as phrase grounding. Our method sets a new state-of-the-art on a standard benchmark dataset (MS-CXR), while also exhibiting robust performance on out-of-distribution data (VinDr-CXR). Our code will be made publicly available.

Grzegorz Jacenków, Alison Q. O'Neil, Sotirios A. Tsaftaris

When a clinician refers a patient for an imaging exam, they include the reason (e.g. relevant patient history, suspected disease) in the scan request; this appears as the indication field in the radiology report. The interpretation and reporting of the image are substantially influenced by this request text, steering the radiologist to focus on particular aspects of the image. We use the indication field to drive better image classification, by taking a transformer network which is unimodally pre-trained on text (BERT) and fine-tuning it for multimodal classification of a dual image-text input. We evaluate the method on the MIMIC-CXR dataset, and present ablation studies to investigate the effect of the indication field on the classification performance. The experimental results show our approach achieves 87.8 average micro AUROC, outperforming the state-of-the-art methods for unimodal (84.4) and multimodal (86.0) classification. Our code is available at https://github.com/jacenkow/mmbt.

Grzegorz Jacenków, Alison Q. O'Neil, Brian Mohr et al.

We consider the problem of integrating non-imaging information into segmentation networks to improve performance. Conditioning layers such as FiLM provide the means to selectively amplify or suppress the contribution of different feature maps in a linear fashion. However, spatial dependency is difficult to learn within a convolutional paradigm. In this paper, we propose a mechanism to allow for spatial localisation conditioned on non-imaging information, using a feature-wise attention mechanism comprising a differentiable parametrised function (e.g. Gaussian), prior to applying the feature-wise modulation. We name our method INstance modulation with SpatIal DEpendency (INSIDE). The conditioning information might comprise any factors that relate to spatial or spatio-temporal information such as lesion location, size, and cardiac cycle phase. Our method can be trained end-to-end and does not require additional supervision. We evaluate the method on two datasets: a new CLEVR-Seg dataset where we segment objects based on location, and the ACDC dataset conditioned on cardiac phase and slice location within the volume. Code and the CLEVR-Seg dataset are available at https://github.com/jacenkow/inside.

Konstantinos Vilouras, Pedro Sanchez, Alison Q. O'Neil et al.

Localizing the exact pathological regions in a given medical scan is an important imaging problem that traditionally requires a large amount of bounding box ground truth annotations to be accurately solved. However, there exist alternative, potentially weaker, forms of supervision, such as accompanying free-text reports, which are readily available. The task of performing localization with textual guidance is commonly referred to as phrase grounding. In this work, we use a publicly available Foundation Model, namely the Latent Diffusion Model, to perform this challenging task. This choice is supported by the fact that the Latent Diffusion Model, despite being generative in nature, contains cross-attention mechanisms that implicitly align visual and textual features, thus leading to intermediate representations that are suitable for the task at hand. In addition, we aim to perform this task in a zero-shot manner, i.e., without any training on the target task, meaning that the model's weights remain frozen. To this end, we devise strategies to select features and also refine them via post-processing without extra learnable parameters. We compare our proposed method with state-of-the-art approaches which explicitly enforce image-text alignment in a joint embedding space via contrastive learning. Results on a popular chest X-ray benchmark indicate that our method is competitive with SOTA on different types of pathology, and even outperforms them on average in terms of two metrics (mean IoU and AUC-ROC). Source code will be released upon acceptance at https://github.com/vios-s.

Jesse Phitidis, Alison Q. O'Neil, William N. Whiteley et al.

Cerebrovascular diseases (CVD) can lead to stroke and dementia. Stroke is the second leading cause of death world wide and dementia incidence is increasing by the year. There are several markers of CVD that are visible on brain imaging, including: white matter hyperintensities (WMH), acute and chronic ischaemic stroke lesions (ISL), lacunes, enlarged perivascular spaces (PVS), acute and chronic haemorrhagic lesions, and cerebral microbleeds (CMB). Brain atrophy also occurs in CVD. These markers are important for patient management and intervention, since they indicate elevated risk of future stroke and dementia. We systematically reviewed automated systems designed to support radiologists reporting on these CVD imaging findings. We considered commercially available software and research publications which identify at least two CVD markers. In total, we included 29 commercial products and 13 research publications. Two distinct types of commercial support system were available: those which identify acute stroke lesions (haemorrhagic and ischaemic) from computed tomography (CT) scans, mainly for the purpose of patient triage; and those which measure WMH and atrophy regionally and longitudinally. In research, WMH and ISL were the markers most frequently analysed together, from magnetic resonance imaging (MRI) scans; lacunes and PVS were each targeted only twice and CMB only once. For stroke, commercially available systems largely support the emergency setting, whilst research systems consider also follow-up and routine scans. The systems to quantify WMH and atrophy are focused on neurodegenerative disease support, where these CVD markers are also of significance. There are currently no openly validated systems, commercially, or in research, performing a comprehensive joint analysis of all CVD markers (WMH, ISL, lacunes, PVS, haemorrhagic lesions, CMB, and atrophy).

Francesco Dalla Serra, Patrick Schrempf, Chaoyang Wang et al.

We present a novel approach to Chest X-ray (CXR) Visual Question Answering (VQA), addressing both single-image image-difference questions. Single-image questions focus on abnormalities within a specific CXR ("What abnormalities are seen in image X?"), while image-difference questions compare two longitudinal CXRs acquired at different time points ("What are the differences between image X and Y?"). We further explore how the integration of radiology reports can enhance the performance of VQA models. While previous approaches have demonstrated the utility of radiology reports during the pre-training phase, we extend this idea by showing that the reports can also be leveraged as additional input to improve the VQA model's predicted answers. First, we propose a unified method that handles both types of questions and auto-regressively generates the answers. For single-image questions, the model is provided with a single CXR. For image-difference questions, the model is provided with two CXRs from the same patient, captured at different time points, enabling the model to detect and describe temporal changes. Taking inspiration from 'Chain-of-Thought reasoning', we demonstrate that performance on the CXR VQA task can be improved by grounding the answer generator module with a radiology report predicted for the same CXR. In our approach, the VQA model is divided into two steps: i) Report Generation (RG) and ii) Answer Generation (AG). Our results demonstrate that incorporating predicted radiology reports as evidence to the AG model enhances performance on both single-image and image-difference questions, achieving state-of-the-art results on the Medical-Diff-VQA dataset.

Xiao Liu, Pedro Sanchez, Spyridon Thermos et al.

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using modest amounts of data, or used directly in unseen domains achieving remarkable performance in the corresponding task. This alleviation of the data and annotation requirements offers tantalising prospects for applications in computer vision and healthcare. In this tutorial paper, we motivate the need for disentangled representations, revisit key concepts, and describe practical building blocks and criteria for learning such representations. We survey applications in medical imaging emphasising choices made in exemplar key works, and then discuss links to computer vision applications. We conclude by presenting limitations, challenges, and opportunities.

Marija Jegorova, Chaitanya Kaul, Charlie Mayor et al.

Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data. We provide a comprehensive survey of contemporary advances on several fronts, covering involuntary data leakage which is natural to ML models, potential malevolent leakage which is caused by privacy attacks, and currently available defence mechanisms. We focus on inference-time leakage, as the most likely scenario for publicly available models. We first discuss what leakage is in the context of different data, tasks, and model architectures. We then propose a taxonomy across involuntary and malevolent leakage, available defences, followed by the currently available assessment metrics and applications. We conclude with outstanding challenges and open questions, outlining some promising directions for future research.

Patrick Schrempf, Hannah Watson, Shadia Mikhael et al.

Training medical image analysis models requires large amounts of expertly annotated data which is time-consuming and expensive to obtain. Images are often accompanied by free-text radiology reports which are a rich source of information. In this paper, we tackle the automated extraction of structured labels from head CT reports for imaging of suspected stroke patients, using deep learning. Firstly, we propose a set of 31 labels which correspond to radiographic findings (e.g. hyperdensity) and clinical impressions (e.g. haemorrhage) related to neurological abnormalities. Secondly, inspired by previous work, we extend existing state-of-the-art neural network models with a label-dependent attention mechanism. Using this mechanism and simple synthetic data augmentation, we are able to robustly extract many labels with a single model, classified according to the radiologist's reporting (positive, uncertain, negative). This approach can be used in further research to effectively extract many labels from medical text.