Hallucinations are spurious structures not present in the ground truth, posing a critical challenge in medical image reconstruction, especially for data-driven conditional models. We hypothesize that combining an unconditional diffusion model with data consistency, trained on a diverse dataset, can reduce these hallucinations. Based on this, we propose DynamicDPS, a diffusion-based framework that integrates conditional and unconditional diffusion models to enhance low-quality medical images while systematically reducing hallucinations. Our approach first generates an initial reconstruction using a conditional model, then refines it with an adaptive diffusion-based inverse problem solver. DynamicDPS skips early stage in the reverse process by selecting an optimal starting time point per sample and applies Wolfe's line search for adaptive step sizes, improving both efficiency and image fidelity. Using diffusion priors and data consistency, our method effectively reduces hallucinations from any conditional model output. We validate its effectiveness in Image Quality Transfer for low-field MRI enhancement. Extensive evaluations on synthetic and real MR scans, including a downstream task for tissue volume estimation, show that DynamicDPS reduces hallucinations, improving relative volume estimation by over 15% for critical tissues while using only 5% of the sampling steps required by baseline diffusion models. As a model-agnostic and fine-tuning-free approach, DynamicDPS offers a robust solution for hallucination reduction in medical imaging. The code will be made publicly available upon publication.

We introduce Lavender, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image generation models such as Stable Diffusion. Specifically, Lavender aligns the text-vision attention in the VLM transformer with the equivalent used by Stable Diffusion during SFT, instead of adapting separate encoders. This alignment enriches the model's visual understanding and significantly boosts performance across in- and out-of-distribution tasks. Lavender requires just 0.13 million training examples, 2.5% of typical large-scale SFT datasets, and fine-tunes on standard hardware (8 GPUs) in a single day. It consistently improves state-of-the-art open-source multimodal LLMs (e.g., Llama-3.2-11B, MiniCPM-Llama3-v2.5), achieving up to 30% gains and a 68% boost on challenging out-of-distribution medical QA tasks. By efficiently transferring the visual expertise of image generators with minimal supervision, Lavender offers a scalable solution for more accurate vision-language systems. All code, training data, and models will be shared at https://astrazeneca.github.io/vlm/.

Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge. Recent studies have identified specific attention heads within the Transformer architecture, known as retrieval heads, responsible for extracting relevant contextual information. We hypothesise that masking these retrieval heads can induce hallucinations and that contrasting the outputs of the base LLM and the masked LLM can reduce hallucinations. To this end, we propose Decoding by Contrasting Retrieval Heads (DeCoRe), a novel training-free decoding strategy that amplifies information found in the context and model parameters. DeCoRe mitigates potentially hallucinated responses by dynamically contrasting the outputs of the base LLM and the masked LLM, using conditional entropy as a guide. Our extensive experiments confirm that DeCoRe significantly improves performance on tasks requiring high contextual faithfulness, such as summarisation (XSum by 18.6%), instruction following (MemoTrap by 10.9%), and open-book question answering (NQ-Open by 2.4% and NQ-Swap by 5.5%).

Medical Vision-Language Pre-training (MedVLP) has made significant progress in enabling zero-shot tasks for medical image understanding. However, training MedVLP models typically requires large-scale datasets with paired, high-quality image-text data, which are scarce in the medical domain. Recent advancements in Large Language Models (LLMs) and diffusion models have made it possible to generate large-scale synthetic image-text pairs. This raises the question: "Can MedVLP succeed using purely synthetic data?" To address this, we use off-the-shelf generative models to create synthetic radiology reports and paired Chest X-ray (CXR) images, and propose an automated pipeline to build a diverse, high-quality synthetic dataset, enabling a rigorous study that isolates model and training settings, focusing entirely from the data perspective. Our results show that MedVLP models trained exclusively on synthetic data outperform those trained on real data by 3.8% in averaged AUC on zero-shot classification. Moreover, using a combination of synthetic and real data leads to a further improvement of 9.07%. Additionally, MedVLP models trained on synthetic or mixed data consistently outperform those trained on real data in zero-shot grounding, as well as in fine-tuned classification and segmentation tasks. Our analysis suggests MedVLP trained on well-designed synthetic data can outperform models trained on real datasets, which may be limited by low-quality samples and long-tailed distributions.

Textural Inversion, a prompt learning method, learns a singular embedding for a new "word" to represent image style and appearance, allowing it to be integrated into natural language sentences to generate novel synthesised images. However, identifying and integrating multiple object-level concepts within one scene poses significant challenges even when embeddings for individual concepts are attainable. This is further confirmed by our empirical tests. To address this challenge, we introduce a framework for Multi-Concept Prompt Learning (MCPL), where multiple new "words" are simultaneously learned from a single sentence-image pair. To enhance the accuracy of word-concept correlation, we propose three regularisation techniques: Attention Masking (AttnMask) to concentrate learning on relevant areas; Prompts Contrastive Loss (PromptCL) to separate the embeddings of different concepts; and Bind adjective (Bind adj.) to associate new "words" with known words. We evaluate via image generation, editing, and attention visualisation with diverse images. Extensive quantitative comparisons demonstrate that our method can learn more semantically disentangled concepts with enhanced word-concept correlation. Additionally, we introduce a novel dataset and evaluation protocol tailored for this new task of learning object-level concepts.

We study pseudo labelling and its generalisation for semi-supervised segmentation of medical images. Pseudo labelling has achieved great empirical successes in semi-supervised learning, by utilising raw inferences on unlabelled data as pseudo labels for self-training. In our paper, we build a connection between pseudo labelling and the Expectation Maximization algorithm which partially explains its empirical successes. We thereby realise that the original pseudo labelling is an empirical estimation of its underlying full formulation. Following this insight, we demonstrate the full generalisation of pseudo labels under Bayes' principle, called Bayesian Pseudo Labels. We then provide a variational approach to learn to approximate Bayesian Pseudo Labels, by learning a threshold to select good quality pseudo labels. In the rest of the paper, we demonstrate the applications of Pseudo Labelling and its generalisation Bayesian Psuedo Labelling in semi-supervised segmentation of medical images on: 1) 3D binary segmentation of lung vessels from CT volumes; 2) 2D multi class segmentation of brain tumours from MRI volumes; 3) 3D binary segmentation of brain tumours from MRI volumes. We also show that pseudo labels can enhance the robustness of the learnt representations.

The lack of labels is one of the fundamental constraints in deep learning based methods for image classification and segmentation, especially in applications such as medical imaging. Semi-supervised learning (SSL) is a promising method to address the challenge of labels carcity. The state-of-the-art SSL methods utilise consistency regularisation to learn unlabelled predictions which are invariant to perturbations on the prediction confidence. However, such SSL approaches rely on hand-crafted augmentation techniques which could be sub-optimal. In this paper, we propose MisMatch, a novel consistency based semi-supervised segmentation method. MisMatch automatically learns to produce paired predictions with increasedand decreased confidences. MisMatch consists of an encoder and two decoders. One decoder learns positive attention for regions of interest (RoI) on unlabelled data thereby generating higher confidence predictions of RoI. The other decoder learns negative attention for RoI on the same unlabelled data thereby generating lower confidence predictions. We then apply a consistency regularisation between the paired predictions of the decoders. For evaluation, we first perform extensive cross-validation on a CT-based pulmonary vessel segmentation task and show that MisMatch statistically outperforms state-of-the-art semi-supervised methods when only 6.25% of the total labels are used. Furthermore MisMatch performance using 6.25% ofthe total labels is comparable to state-of-the-art methodsthat utilise all available labels. In a second experiment, MisMatch outperforms state-of-the-art methods on an MRI-based brain tumour segmentation task.