Magnetic resonance imaging (MRI) is a cornerstone in the evaluation and monitoring of axial spondyloarthritis (axSpA), a chronic inflammatory condition primarily affecting the sacroiliac joints (SIJs), spine, entheses, and peripheral joints. Accurate quantification of axSpA-related changes on MRI is critical for effective research and patient management; however, current lesion detection and grading approaches suffer from substantial intra- and inter-reader variability, limiting their consistency and reliability. To address these challenges, we propose a fully automated machine learning system for SIJ delineation and lesion classification on coronal MRI. The end-to-end pipeline automatically extracts SIJ contours using a vector-field—based open-contour model and classifies the presence or absence of five lesion types (bone marrow oedema, ankylosis, sclerosis, erosions, and fatty lesions) using both T1-weighted and STIR sequences. A multi-reader learning framework is employed to explicitly model inter- and intra-reader variability by leveraging multiple readings and consensus labels. Model performance was evaluated using patient-wise cross-validation on data from the MEASURE-1 clinical trial and further validated on other clinical datasets (PREVENT, SURPASS). Lesion classification performance was assessed using area under the receiver operating characteristic curve (AUC), balanced accuracy, sensitivity, and specificity, while contouring accuracy was quantified using root-mean-square error, where we found that 95% of the whole test set had errors below 2.76mm. The proposed approach achieved AUCs ranging from 0.85 to 0.99 across the five lesion types, with the highest performance observed when using consensus-based labels, and results were comparable to expert inter-reader agreement. These findings demonstrate that fully automated SIJ delineation and lesion scoring can achieve expert-level performance and have the potential to reduce reader burden and variability in large-scale axSpA MRI studies.

Objectives This study aims to assess the performance of a fully automated deep learning (DL) system for detecting active and structural magnetic resonance imaging (MRI) lesions of the sacroiliac joints (SIJs) in axial spondyloarthritis (axSpA), and validate its generalisability across independent clinical trial datasets. Methods A 2-stage automated pipeline was developed to delineate left and right SIJs and detect 5 MRI-defined lesion types: 1 active lesion: bone marrow oedema (BMO), 4 structural lesions: erosions, fat lesions, sclerosis, and ankylosis. Lesions were assessed at the quadrant or joint level using paired T1-weighted and Short Tau Inversion Recovery sequences. Models were trained on the MEASURE 1 trial (132 patients) using consensus-based labels to address multireader variability and evaluated on 2 independent datasets (PREVENT-555 patients; SURPASS-414 patients). Performance was assessed using area under the curve (AUC), balanced accuracy, sensitivity, specificity, and kappa, and interpreted against expert reader evaluations, done according to the Berlin SIJ scoring method. Results Across all datasets, automated SIJ lesion detection against expert evaluations achieved performance comparable with expert interreader agreement. Structural lesions showed the strongest performance, particularly ankylosis (MEASURE 1 AUC: 0.97, SURPASS AUC: 0.99; balanced accuracy: 0.95 and 0.97). Robust results were also observed for erosions and fat lesions. BMO detection showed consistently high AUCs (0.85-0.93) with lower balanced accuracy (0.72-0.74). Model performance generalised across datasets without additional training. Conclusions A fully automated DL-based approach can reliably detect active and structural SIJ MRI lesions in axSpA with robust external validation, supporting its potential use to enhance the consistency and scalability of MRI assessment in clinical trials and observational studies.

The objective of this paper is to improve radiological gradings measured on MRIs of spines, by resampling scans so that the new view planes are better aligned with the target anatomy than the original sparse images. To this end, we adapt 3D Gaussian Splatting to form a volumetric reconstruction starting from sparse anisotropic MRIs, and imaging planes aligned with the anatomy relevant for clinical evaluation are then sampled and rendered. The novel view plane is optimal for diagnostic radiological grading of the target anatomy, whereas the original MRI is not. The resampled scans are then used to predict ordinal severity grades of localised stenosis conditions in spinal MRIs. We compare our method against Voxel Interpolation resampling, which takes the average of inverse-distance weighted nearest neighbour intensities for each target coordinate. Experiments show that across all stenosis conditions, resampled scans using Gaussian Splatting produce more accurate stenosis gradings compared to the raw scans which do not include the complete anatomy in-plane, as well as images resampled using Voxel Interpolation.

Objective To evaluate the performance of machine learning (ML) models for the automated scoring of spinal MRI bone marrow oedema (BMO) in patients with axial spondyloarthritis (axSpA) and compare them with expert scoring. Methods ML algorithms using SpineNet software were trained and validated on 3483 spinal MRIs from 686 axSpA patients across two clinical trial datasets. The scoring pipeline involved (i) detection and labelling of vertebral bodies and (ii) classification of vertebral units for the presence or absence of BMO. Two models were tested: Model 1, without manual segmentation, and Model 2, incorporating an intermediate manual segmentation step. Model outputs were compared with those of human experts using kappa statistics, balanced accuracy, sensitivity, specificity and AUC. Results Both models performed comparably to expert readers, regarding presence vs absence of BMO. Model 1 outperformed Model 2, with an AUC of 0.94 (vs 0.88), accuracy of 75.8% (vs 70.5%) and kappa of 0.50 (vs 0.31) using absolute reader consensus scoring as the external reference; this performance was similar to the expert inter-reader accuracy of 76.8% and kappa of 0.47 in a radiographic axSpA dataset. In a non-radiographic axSpA dataset, Model 1 achieved an AUC of 0.97 (vs 0.91 for Model 2), accuracy of 74.6% (vs 70%) and kappa of 0.52 (vs 0.27), comparable to the expert inter-reader accuracy of 74.2% and kappa of 0.46. Conclusion ML software shows potential for automated MRI BMO assessment in axSpA, offering benefits such as improved consistency, reduced labour costs and minimized inter- and intra-reader variability. Trial registration Clinicaltrials.gov, http://clinicaltrials.gov, MEASURE 1 study (NCT01358175); PREVENT study (NCT02696031).

We propose a general pipeline to automate the extraction of labels from radiology reports using large language models, which we validate on spinal MRI reports. The efficacy of our method is measured on two distinct conditions: spinal cancer and stenosis. Using open-source models, our method surpasses GPT-4 on a held-out set of reports. Furthermore, we show that the extracted labels can be used to train an imaging model to classify the identified conditions in the accompanying MR scans. Both the cancer and stenosis classifiers trained using automated labels achieve comparable performance to models trained using scans manually annotated by clinicians. Code can be found at https://github.com/robinyjpark/AutoLabelClassifier.

Spinal magnetic resonance (MR) scans are a vital tool for diagnosing the cause of back pain for many diseases and conditions. However, interpreting clinically useful information from these scans can be challenging, time-consuming and hard to reproduce across different radiologists. In this paper, we alleviate these problems by introducing a multi-stage automated pipeline for analysing spinal MR scans. This pipeline first detects and labels vertebral bodies across several commonly used sequences (e.g. T1w, T2w and STIR) and fields of view (e.g. lumbar, cervical, whole spine). Using these detections it then performs automated diagnosis for several spinal disorders, including intervertebral disc degenerative changes in T1w and T2w lumbar scans, and spinal metastases, cord compression and vertebral fractures. To achieve this, we propose a new method of vertebrae detection and labelling, using vector fields to group together detected vertebral landmarks and a language-modelling inspired beam search to determine the corresponding levels of the detections. We also employ a new transformer-based architecture to perform radiological grading which incorporates context from multiple vertebrae and sequences, as a real radiologist would. The performance of each stage of the pipeline is tested in isolation on several clinical datasets, each consisting of 66 to 421 scans. The outputs are compared to manual annotations of expert radiologists, demonstrating accurate vertebrae detection across a range of scan parameters. Similarly, the model's grading predictions for various types of disc degeneration and detection of spinal metastases closely match those of an expert radiologist. To aid future research, our code and trained models are made publicly available.

This work introduces a simple deep-learning based method to delineate contours by 'walking' along learnt unit vector fields. We demonstrate the effectiveness of our pipeline on the unique case of open contours on the task of delineating the sacroiliac joints (SIJs) in spinal MRIs. We show that: (i) 95% of the time the average root mean square error of the predicted contour against the original ground truth is below 4.5 pixels (2.5mm for a standard T1-weighted SIJ MRI), and (ii) the proposed method is better than the baseline of regressing vertices or landmarks of contours.

This paper explores training medical vision-language models (VLMs) -- where the visual and language inputs are embedded into a common space -- with a particular focus on scenarios where training data is limited, as is often the case in clinical datasets. We explore several candidate methods to improve low-data performance, including: (i) adapting generic pre-trained models to novel image and text domains (i.e. medical imaging and reports) via unimodal self-supervision; (ii) using local (e.g. GLoRIA) & global (e.g. InfoNCE) contrastive loss functions as well as a combination of the two; (iii) extra supervision during VLM training, via: (a) image- and text-only self-supervision, and (b) creating additional positive image-text pairs for training through augmentation and nearest-neighbour search. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports. Combined, they significantly improve retrieval compared to fine-tuning CLIP, roughly equivalent to training with the data. A similar pattern is found in the downstream task classification of CXR-related conditions with our method outperforming CLIP and also BioVIL, a strong CXR VLM benchmark, in the zero-shot and linear probing settings. We conclude with a set of recommendations for researchers aiming to train vision-language models on other medical imaging modalities when training data is scarce. To facilitate further research, we will make our code and models publicly available.

Study Design. This is a retrospective observational study to externally validate a deep learning image classification model. Objective. Deep learning models such as SpineNet offer the possibility of automating the process of disk degeneration (DD) classification from magnetic resonance imaging (MRI). External validation is an essential step to their development. The aim of this study was to externally validate SpineNet predictions for DD using Pfirrmann classification and Modic changes (MCs) on data from the Northern Finland Birth Cohort 1966 (NFBC1966). Summary of Data. We validated SpineNet using data from 1331 NFBC1966 participants for whom both lumbar spine MRI data and consensus DD gradings were available. Materials and Methods. SpineNet returned Pfirrmann grade and MC presence from T2-weighted sagittal lumbar MRI sequences from NFBC1966, a data set geographically and temporally separated from its training data set. A range of agreement and reliability metrics were used to compare predictions with expert radiologists. Subsets of data that match SpineNet training data more closely were also tested. Results. Balanced accuracy for DD was 78% (77%–79%) and for MC 86% (85%–86%). Interrater reliability for Pfirrmann grading was Lin concordance correlation coefficient=0.86 (0.85–0.87) and Cohen κ=0.68 (0.67–0.69). In a low back pain subset, these reliability metrics remained largely unchanged. In total, 20.83% of disks were rated differently by SpineNet compared with the human raters, but only 0.85% of disks had a grade difference >1. Interrater reliability for MC detection was κ=0.74 (0.72–0.75). In the low back pain subset, this metric was almost unchanged at κ=0.76 (0.73–0.79). Conclusions. In this study, SpineNet has been benchmarked against expert human raters in the research setting. It has matched human reliability and demonstrates robust performance despite the multiple challenges facing model generalizability.

This technical report presents SpineNetV2, an automated tool which: (i) detects and labels vertebral bodies in clinical spinal magnetic resonance (MR) scans across a range of commonly used sequences; and (ii) performs radiological grading of lumbar intervertebral discs in T2-weighted scans for a range of common degenerative changes. SpineNetV2 improves over the original SpineNet software in two ways: (1) The vertebral body detection stage is significantly faster, more accurate and works across a range of fields-of-view (as opposed to just lumbar scans). (2) Radiological grading adopts a more powerful architecture, adding several new grading schemes without loss in performance. A demo of the software is available at the project website: http://zeus.robots.ox.ac.uk/spinenet2/.

This paper proposes a novel transformer-based model architecture for medical imaging problems involving analysis of vertebrae. It considers two applications of such models in MR images: (a) detection of spinal metastases and the related conditions of vertebral fractures and metastatic cord compression, (b) radiological grading of common degenerative changes in intervertebral discs. Our contributions are as follows: (i) We propose a Spinal Context Transformer (SCT), a deep-learning architecture suited for the analysis of repeated anatomical structures in medical imaging such as vertebral bodies (VBs). Unlike previous related methods, SCT considers all VBs as viewed in all available image modalities together, making predictions for each based on context from the rest of the spinal column and all available imaging modalities. (ii) We apply the architecture to a novel and important task: detecting spinal metastases and the related conditions of cord compression and vertebral fractures/collapse from multi-series spinal MR scans. This is done using annotations extracted from free-text radiological reports as opposed to bespoke annotation. However, the resulting model shows strong agreement with vertebral-level bespoke radiologist annotations on the test set. (iii) We also apply SCT to an existing problem: radiological grading of inter-vertebral discs (IVDs) in lumbar MR scans for common degenerative changes.We show that by considering the context of vertebral bodies in the image, SCT improves the accuracy for several gradings compared to previously published model.

This paper explores the use of self-supervised deep learning in medical imaging in cases where two scan modalities are available for the same subject. Specifically, we use a large publicly-available dataset of over 20,000 subjects from the UK Biobank with both whole body Dixon technique magnetic resonance (MR) scans and also dual-energy x-ray absorptiometry (DXA) scans. We make three contributions: (i) We introduce a multi-modal image-matching contrastive framework, that is able to learn to match different-modality scans of the same subject with high accuracy. (ii) Without any adaption, we show that the correspondences learnt during this contrastive training step can be used to perform automatic cross-modal scan registration in a completely unsupervised manner. (iii) Finally, we use these registrations to transfer segmentation maps from the DXA scans to the MR scans where they are used to train a network to segment anatomical regions without requiring ground-truth MR examples. To aid further research, our code is publicly available (https://github.com/rwindsor1/biobank-self-supervised-alignment).

In this paper we introduce the Ladder Algorithm; a novel recurrent algorithm to detect repetitive structures in natural images with high accuracy using little training data. We then demonstrate the algorithm on the task of extracting vertebrae from whole spine magnetic resonance scans with only lumbar MR scans for training data. It is shown to achieve high performance with 99.8% precision and recall, exceeding current state of the art approaches for lumbar vertebrae detection in T1 and T2 weighted scans. It also generalises without retraining to whole spine images with minimal drop in accuracy, achieving 99.4% detection rate.

Background:Magnetic resonance imaging (MRI) offers a non-invasive and objective method of early diagnosis and classification, monitoring disease burden and treatment response for patients (pts) with axial spondyloarthritis (axSpA) including ankylosing spondylitis (AS).1Numerous scoring schemes such as the AS Spine MRI Activity (ASspiMRIa) score are available for the quantitative assessment of MRI, but are subject to intra- and inter-rater variability, labor intensive and costly. Nevertheless, quantification of MRI changes has become an important tool to demonstrate treatment success of biologic drugs in axSpA.Objectives:To evaluate the performance of machine learning (ML) based software for automated Berlin grading of spinal MRI bone marrow oedema in pts with AS and compare with expert scoring.Methods:Fully automated ML software (Figure) was developed to detect and label 23 vertebrae, define vertebral units (VU) as per the Berlin modification of the ASspiMRIa score, and score each VU as either 0 (score of 0) or 1 (score of 1, 2 or 3). The ML algorithm was based on the previously developed SpineNet software.2Analysis included 108 pts from the secukinumab MEASURE 1 study3, in which imaging was done using T1 and STIR sagittal MRI at baseline and Weeks 16, 52, 104, 156 and 208. Two expert readers, blinded to treatment and visit, evaluated all images by ASspiMRIa score. The scores from Reader 2 (R2) were binned into two groups: 0 vs 1, 2, or 3. As a result of multiple pt time points and expert reading sessions, the complete dataset comprised of 10,988 VU. Ten-way cross-validation at per-VU was used to train and validate the ML software. The dataset was split into 10 randomly selected subsets, ensuring that each pt appears in only one subset, after which 8 subsets were used for training the ML software, 1 was used to check for correct training and 1 was used for validation. The process was repeated ten times such that all 10 subsets were used for validation. Accuracy weighted for the frequency of each category, sensitivity and specificity were calculated using scores from R2 as reference. Intra-reader accuracy was also calculated.Results:Accuracy of the software in relation to expert reader scores was 67% with a sensitivity of 0.63 and specificity of 0.70. The intra-reader accuracy was 71% and 77% for R1 and R2, respectively. Individual VU scoring of the Software vs. R2 are presented in the Table as a confusion matrix.Conclusion:Automated scoring of MR images in AS pts provided moderate agreement to that of expert reader-based assessments. ML software has potential to provide an automated guided-reading approach to scoring MR images, which may enable further clinical insights.References:[1]Lukas C, et al. J Rheumatol. 2007;34:862-70.[2]Jamaludin A, et al. Eur Spine J. 2017;26:1374-83.[3]Baeten D, et al. N Engl J Med. 2015;373,2534-48.Figure.Processing pipeline of automated Berlin scoring softwareTable.Confusion matrix between the software and R2SoftwareScore = 0SoftwareScore = 1, 2 or 3Total VU scoredR2 Score = 07199 (70%)3068 (30%)10,267R2 Score = 1, 2 or 3251 (35%)475 (65%)7267,4503,54310,993Percentages calculated as a fraction over the total in each row. Overall accuracy is the average of the highlighted percentages.Disclosure of Interests:Amir Jamaludin: None declared, Rhydian Windsor: None declared, Sarim Ather: None declared, Timor Kadir: None declared, Andrew Zisserman: None declared, Juergen Braun Grant/research support from: Abbvie (Abbott), Amgen, BMS, Boehringer, Celgene, Celltrion, Centocor, Chugai, Eli Lilly and Company, Medac, MSD (Schering Plough), Mundipharma, Novartis, Pfizer (Wyeth), Roche, Sanofi- Aventis, and UCB Pharma, Consultant of: Abbvie (Abbott), Amgen, BMS, Boehringer, Celgene, Celltrion, Centocor, Chugai, EBEWE Pharma, Eli Lilly and Company, Medac, MSD (Schering-Plough), Mundipharma, Novartis, Pfizer (Wyeth), Roche, Sanofi-Aventis, and UCB Pharma, Speakers bureau: Abbvie (Abbott), Amgen, BMS, Boehringer, Celgene, Celltrion, Centocor, Chugai, EBEWE Pharma, Eli Lilly and Company, Medac, MSD (Schering-Plough), Mundipharma, Novartis, Pfizer (Wyeth), Roche, Sanofi-Aventis, and UCB Pharma, Lianne S. Gensler Grant/research support from: Pfizer, Novartis, UCB, Consultant of: AbbVie, Eli Lilly, GSK, Novartis, UCB, Pedro Machado Consultant of: Abbvie, Celgene, Janssen, Lilly, MSD, BMS, Novartis, Pfizer, Roche and UCB, Speakers bureau: AbbVie, Centocor, Eli Lilly, Janssen, MSD, Novartis, Pfizer and UCB Pharma, Mikkel Ǿstergaard Grant/research support from: AbbVie, Bristol-Myers Squibb, Celgene, Merck, and Novartis, Consultant of: AbbVie, Bristol-Myers Squibb, Boehringer Ingelheim, Celgene, Eli Lilly, Hospira, Janssen, Merck, Novartis, Novo Nordisk, Orion, Pfizer, Regeneron, Roche, Sandoz, Sanofi, and UCB, Speakers bureau: AbbVie, Bristol-Myers Squibb, Boehringer Ingelheim, Celgene, Eli Lilly, Hospira, Janssen, Merck, Novartis, Novo Nordisk, Orion, Pfizer, Regeneron, Roche, Sandoz, Sanofi, and UCB, Denis Poddubnyy Grant/research support from: AbbVie, MSD, Novartis, and Pfizer, Consultant of: AbbVie, Bristol-Myers Squibb, Eli Lilly, MSD, Novartis, Pfizer, Roche, UCB, Speakers bureau: AbbVie, Bristol-Myers Squibb, Eli Lilly, MSD, Novartis, Pfizer, Roche, UCB, Thibaud Coroller Shareholder of: Novartis, Employee of: Novartis, Brian Porter Shareholder of: Novartis, Employee of: Novartis, Shephard Mpofu Shareholder of: Novartis, Employee of: Novartis, Aimee Readie Shareholder of: Novartis, Employee of: Novartis

We propose a novel convolutional method for the detection and identification of vertebrae in whole spine MRIs. This involves using a learnt vector field to group detected vertebrae corners together into individual vertebral bodies and convolutional image-to-image translation followed by beam search to label vertebral levels in a self-consistent manner. The method can be applied without modification to lumbar, cervical and thoracic-only scans across a range of different MR sequences. The resulting system achieves 98.1% detection rate and 96.5% identification rate on a challenging clinical dataset of whole spine scans and matches or exceeds the performance of previous systems of detecting and labelling vertebrae in lumbar-only scans. Finally, we demonstrate the clinical applicability of this method, using it for automated scoliosis detection in both lumbar and whole spine MR scans.

Purpose.Studies in Italy have indicated the possibility of using photo-neutrons from high energy linac as a promising alternative neutron source to obtain intense neutron fluence rate for Boron Neutron Capture Therapy (BNCT) applications [1].In continuation to these efforts, this study was carried out with aims: 1) to select high intensity linear accelerator that can be used for photo-neutron production; 2) to select the best materials for photo-neutron production.Methods.Initially, photon planner fluence and photons distributions have been simulated for a range of medical linear accelerators to study photon intensity using BEAMnrc Monte Carlo code.Due to its high photon intensity, The FFF Linac was selected as a nominal source to study photo-neutrons.Monte Carlo Simulations were then performed for photo-neutrons production from flattening filter free (FFF) medical Linac using lead and tungsten convertors.Results.Our results showed that photo-neutrons flux and yield increase with both photon energy and convertor thickness, saturating at 7 cm (lead) and 6 cm (tungsten) convertors.The average photoneutrons energy produced ranged from 0.480 to 0.863 MeV for the tungsten convertor and from 0.586 to 1.214 MeV for the lead convertor.A photoneutrons flux of 3.971Â10 8 n/cm 2 s and 2.585Â10 8 n/ cm 2 s have been calculated for a 25 MeV medical linac equipped with 7 cm lead convertor and 6 cm tungsten convertor respectively.Conclusions.In conclusion the FFF linac presented a considerable feasibility toward having it as an alternative neutron source for BNCT with lead and tungsten as a suitable photoconverters.

Osteoarthritis (OA) is the most common type of arthritis and a major cause of chronic musculoskeletal pain and functional disability. While both pharmacologic and non-pharmacologic modalities are recommended in the management of OA, when patients with hip or knee OA do not obtain adequate pain relief and/or functional improvement, joint replacement surgery or other surgical interventions should be considered. Total joint arthroplasties are reliable and cost-effective treatments for patients with significant OA of the hip and knee. Evidence from cohort and observational studies has confirmed substantial improvements in pain relief with cumulative revision rates at 10 years following total hip (THA) and total knee arthroplasties (TKA) at 7% and 10%, respectively. Joint replacements have been used in most every synovial joint, although results for joints other than hip and knee replacement have not been as successful. The evolution of new device designs and surgical techniques highlights the need to better understand the risk to benefit ratio for different joint replacements and to identify the appropriate methodology for evaluating the efficacy and optimal outcomes of these new devices, designed to treat OA joints.