Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images.

Segmentation masks of pathological areas are useful in many medical applications, such as brain tumour and stroke management. Moreover, healthy counterfactuals of diseased images can be used to enhance radiologists' training files and to improve the interpretability of segmentation models. In this work, we present a weakly supervised method to generate a healthy version of a diseased image and then use it to obtain a pixel-wise anomaly map. To do so, we start by considering a saliency map that approximately covers the pathological areas, obtained with ACAT. Then, we propose a technique that allows to perform targeted modifications to these regions, while preserving the rest of the image. In particular, we employ a diffusion model trained on healthy samples and combine Denoising Diffusion Probabilistic Model (DDPM) and Denoising Diffusion Implicit Model (DDIM) at each step of the sampling process. DDPM is used to modify the areas affected by a lesion within the saliency map, while DDIM guarantees reconstruction of the normal anatomy outside of it. The two parts are also fused at each timestep, to guarantee the generation of a sample with a coherent appearance and a seamless transition between edited and unedited parts. We verify that when our method is applied to healthy samples, the input images are reconstructed without significant modifications. We compare our approach with alternative weakly supervised methods on the task of brain lesion segmentation, achieving the highest mean Dice and IoU scores among the models considered.

From data to diagnosis: skin cancer image datasets for artificial intelligence.

Artificial intelligence (AI) solutions for skin cancer diagnosis continue to gain momentum, edging closer towards broad clinical use. These AI models, particularly deep-learning architectures, require large digital image datasets for development. This review provides an overview of the datasets used to develop AI algorithms and highlights the importance of dataset transparency for the evaluation of algorithm generalizability across varying populations and settings. Current challenges for curation of clinically valuable datasets are detailed, which include dataset shifts arising from demographic variations and differences in data collection methodologies, along with inconsistencies in labelling. These shifts can lead to differential algorithm performance, compromise of clinical utility, and the propagation of discriminatory biases when developed algorithms are implemented in mismatched populations. Limited representation of rare skin cancers and minoritized groups in existing datasets are highlighted, which can further skew algorithm performance. Strategies to address these challenges are presented, which include improving transparency, representation and interoperability. Federated learning and generative methods, which may improve dataset size and diversity without compromising privacy, are also examined. Lastly, we discuss model-level techniques that may address biases entrained through the use of datasets derived from routine clinical care. As the role of AI in skin cancer diagnosis becomes more prominent, ensuring the robustness of underlying datasets is increasingly important.

The Scottish Medical Imaging Archive: 57.3 Million Radiology Studies Linked to Their Medical Records.

Keywords: MRI, Imaging Sequences, Ultrasound, Mammography, CT, Angiography, Conventional Radiography Published under a CC BY 4.0 license. See also the commentary by Whitman and Vining in this issue.

Self-supervised monocular depth estimation for high field of view colonoscopy cameras.

Optical colonoscopy is the gold standard procedure to detect colorectal cancer, the fourth most common cancer in the United Kingdom. Up to 22%-28% of polyps can be missed during the procedure that is associated with interval cancer. A vision-based autonomous soft endorobot for colonoscopy can drastically improve the accuracy of the procedure by inspecting the colon more systematically with reduced discomfort. A three-dimensional understanding of the environment is essential for robot navigation and can also improve the adenoma detection rate. Monocular depth estimation with deep learning methods has progressed substantially, but collecting ground-truth depth maps remains a challenge as no 3D camera can be fitted to a standard colonoscope. This work addresses this issue by using a self-supervised monocular depth estimation model that directly learns depth from video sequences with view synthesis. In addition, our model accommodates wide field-of-view cameras typically used in colonoscopy and specific challenges such as deformable surfaces, specular lighting, non-Lambertian surfaces, and high occlusion. We performed qualitative analysis on a synthetic data set, a quantitative examination of the colonoscopy training model, and real colonoscopy videos in near real-time.

Retinal imaging in Alzheimer's disease.

Identifying biomarkers of Alzheimer's disease (AD) will accelerate the understanding of its pathophysiology, facilitate screening and risk stratification, and aid in developing new therapies. Developments in non-invasive retinal imaging technologies, including optical coherence tomography (OCT), OCT angiography and digital retinal photography, have provided a means to study neuronal and vascular structures in the retina in people with AD. Both qualitative and quantitative measurements from these retinal imaging technologies (eg, thinning of peripapillary retinal nerve fibre layer, inner retinal layer, and choroidal layer, reduced capillary density, abnormal vasodilatory response) have been shown to be associated with cognitive function impairment and risk of AD. The development of computer algorithms for respective retinal imaging methods has further enhanced the potential of retinal imaging as a viable tool for rapid, early detection and screening of AD. In this review, we present an update of current retinal imaging techniques and their potential applications in AD research. We also discuss the newer retinal imaging techniques and future directions in this expanding field.

Changes in retinal vascular diameters in senior and geriatric cats in association with variation in systemic blood pressure.

OBJECTIVES: Early diagnosis of arterial hypertension is essential to prevent target organ damage. In humans, retinal arteriolar narrowing predicts hypertension. This blinded prospective observational study investigated the retinal vessel diameters in senior and geriatric cats of varying systolic blood pressure (SBP) status and evaluated retinal vascular changes in hypertensive cats after treatment. METHODS: Cats with a median age of 14 years (range 9.1-22 years) were categorised into five groups: group 1, healthy normotensive (SBP <140 mmHg; n = 40) cats; group 2, pre-hypertensive (SBP 140-160 mmHg; n = 14) cats; group 3, cats with chronic kidney disease (CKD) and normotensive (n = 26); group 4, cats with CKD and pre-hypertensive (n = 13); and group 5, hypertensive cats (SBP >160 mmHg, n = 15). Colour fundus images (Optibrand ClearView) were assessed for hypertensive lesions. Retinal vascular diameters and bifurcation angles were annotated and calculated using the Vascular Assessment and Measurement Platform for Images of the Retina annotation tool (VAMPIRE-AT). When available, measurements were obtained at 3 and 6 months after amlodipine besylate treatment. RESULTS: Ten hypertensive cats had retinal lesions, most commonly intraretinal haemorrhages and retinal exudates. Arteriole and venule diameters decreased significantly with increasing age (-0.17 ± 0.05 pixels/year [P = 0.0004]; -0.19 ± 0.05 pixels/year). Adjusted means ± SEM for arteriole and venule diameter (pixels) were 6.3 ± 0.2 and 8.9 ± 0.2 (group 1); 7.6 ± 0.3 and 10.1 ± 0.4 (group 2); 6.9 ± 0.2 and 9.5 ± 0.3 (group 3); 7.4 ± 0.3 and 10.0 ± 0.4 (group 4); and 7.0 ± 0.3 and 9.8 ± 0.4 (group 5). Group 1 arteriole and venule diameters were significantly lower than those of groups 2 and 4. Group 2 arteriole bifurcation angle was significantly narrower than those of groups 1 and 3. Post-treatment, vessel diameters decreased significantly at 3 and 6 months in seven hypertensive cats. CONCLUSIONS AND RELEVANCE: Increased age was associated with reduced vascular diameters. Longitudinal studies are required to assess if vessel diameters are a risk indicator for hypertension in cats.

Retinal Vessel Analysis as a Novel Screening Tool to Identify Childhood Acute Lymphoblastic Leukemia Survivors at Risk of Cardiovascular Disease.

BACKGROUND: Microvascular endothelial dysfunction is central to the pathogenesis of cardiovascular disease (CVD). The eye offers direct access for endothelial health assessment via the retinal microvasculature. The aim of the study was to investigate whether image-based retinal vessel analysis is a feasible method of assessing endothelial health in survivors of childhood acute lymphoblastic leukemia (cALL). MATERIALS AND METHODS: Cardiovascular risk factors (CRFs) were estimated using the 30-year Framingham Risk Score in 73 childhood leukemia survivors (median age: 25; median years from diagnosis: 19) and 78 healthy controls (median age: 23). Radial arterial stiffness was measured using pulse wave analyzer, while endothelial activation markers were measured by soluble intercellular adhesion molecule 1 (sICAM-1) and soluble vascular cell adhesion molecule 1 (sVCAM-1). Retinal fundus images were analyzed for central retinal artery/vein equivalents (CRAE/CRVE) and arteriolar-venular ratio (AVR). RESULTS: cALL survivors had higher CRF (P<0.0001), arterial stiffness (P=0.001), and sVCAM-1 (P=0.007) compared with controls. Survivors also had significantly higher CRVE (P=0.021) while AVR was significantly lower (P=0.026) in survivors compared with controls, compatible with endothelial dysfunction. In cALL survivors with intermediate risk for CVD, CRAE, and AVR are significantly lower, while sVCAM-1 and sICAM-1 are significantly higher when compared with survivors with low CVD risk after adjusting with covariates (age, sex, and smoking status). CONCLUSIONS: cALL survivors have an increased risk of CVD compared with age-matched peers. The survivors demonstrated microvasculopathy, as measured by retinal vascular analysis, in addition to physical and biochemical evidence of endothelial dysfunction. These changes predate other measures of CVD. Retinal vessel analysis may be utilized as a robust screening tool for identifying survivors at increased risk for developing CVD.

Structure Prediction for Gland Segmentation With Hand-Crafted and Deep Convolutional Features.

We present a novel method to segment instances of glandular structures from colon histopathology images. We use a structure learning approach which represents local spatial configurations of class labels, capturing structural information normally ignored by sliding-window methods. This allows us to reveal different spatial structures of pixel labels (e.g., locations between adjacent glands, or far from glands), and to identify correctly neighboring glandular structures as separate instances. Exemplars of label structures are obtained via clustering and used to train support vector machine classifiers. The label structures predicted are then combined and post-processed to obtain segmentation maps. We combine hand-crafted, multi-scale image features with features computed by a deep convolutional network trained to map images to segmentation maps. We evaluate the proposed method on the public domain GlaS data set, which allows extensive comparisons with recent, alternative methods. Using the GlaS contest protocol, our method achieves the overall best performance.

Evaluation of coronary artery disease as a risk factor for reticular pseudodrusen.

PURPOSE: Reticular pseudodrusen (RPD) are a risk factor for late age-related macular degeneration (AMD). Associations between RPD and coronary artery disease (CAD) have been reported from small case-control studies. This study investigated the association of RPD within a predominantly CAD cohort. METHODS: A subgroup of subjects from a multicentre randomised controlled trial of CT coronary angiography (CTCA) underwent ultrawide field (UWF) retinal imaging CAD determined by CTCA and was categorised as normal, non-obstructive or obstructive. Specific AMD features in UWF images were graded. Standardised grids were used to record the spatial location of AMD features, including RPD. Multivariate confounder adjusted regression models assessed the association between RPD and CAD. RESULTS: The 534 participants were aged 27-75 years (mean 58±9 years; 425 (80%) ≥50 years) with a male preponderance (56%). Within the study sample, 178 (33%) had no CAD, 351 (66%) had CAD. RPD was detected in 30 participants (5.6%) and bilaterally in 23. Most participants with bilateral RPD had intermediate AMD 17 (74%). After adjustment for potential confounders (age, sex, drusen >125 µm, smoking status), multivariate analysis found no significant association between CAD and RPD (OR 1.31; 95% CI (0.57 to 3.01); p=0.52). A significant association was identified between RPD and intermediate AMD (OR 3.18; 95% CI (1.61 to 6.27); p=0.001). CONCLUSION: We found no evidence to support an association between CAD and RPD. RPD was strongly associated with intermediate AMD features. TRIAL REGISTRATION NUMBER: NCT01149590, Post results.

Sub-Category Classifiers for Multiple-Instance Learning and its Application to Retinal Nerve Fiber Layer Visibility Classification.

We propose a novel multiple instance learning method to assess the visibility (visible/not visible) of the retinal nerve fiber layer (RNFL) in fundus camera images. Using only image-level labels, our approach learns to classify the images as well as to localize the RNFL visible regions. We transform the original feature space to a discriminative subspace, and learn a region-level classifier in that subspace. We propose a margin-based loss function to jointly learn this subspace and the region-level classifier. Experiments with a RNFL dataset containing 884 images annotated by two ophthalmologists give a system-annotator agreement (kappa values) of 0:73 and 0:72 respectively, with an inter-annotator agreement of 0:73. Our system agrees better with the more experienced annotator. Comparative tests with three public datasets (MESSIDOR and DR for diabetic retinopathy, UCSB for breast cancer) show that our novel MIL approach improves performance over the state-of-the-art. Our Matlab code is publicly available at https://github.com/ManiShiyam/Sub-category-classifiersfor- Multiple-Instance-Learning/wiki.

Assessment of Ischemic Index in Retinal Vascular Diseases Using Ultra-Wide-Field Fluorescein Angiography: Single Versus Summarized Image.

BACKGROUND AND OBJECTIVE: To compare a single image with a computer-generated summarized image from the ultra-wide-field fluorescein angiogram (UWFFA) sequence for evaluation of ischemic index (ISI). MATERIALS AND METHODS: UWFFA sequences from patients with diabetic retinopathy (DR) (n=5), branch retinal vein occlusion (BRVO) (n=5), and central retinal vein occlusion (CRVO) (n=5) were evaluated by six graders. A single image best illustrating retinal non-perfusion was compared to a summarized image generated by computerized superimposition of angiograms. Non-perfused and ungradable retinal areas were outlined and the ISI between the single and summarized images was compared. RESULTS: The mean ISI in the single versus (vs) summarized images was 17% vs 15% in BRVO (p=0.12), 48% vs 48% in CRVO (p=0.67), and 25% vs 23% in DR (p=0.005). Inter-grader agreement of ISI in single versus summarized images was 0.43 vs 0.40 in BRVO, 0.69 vs 0.71 in CRVO, and 0.53 vs 0.34 in DR. CONCLUSION: Computer-generated summarized images were similar to single images for grading ISI in BRVO and CRVO, but underestimated it in DR.

A dynamic 3D foot reconstruction system.

Foot problems are varied and range from simple disorders through to complex diseases and joint deformities. Wherever possible, the use of insoles, or orthoses, is preferred over surgery. Current insole design techniques are based on static measurements of the foot, despite the fact that orthoses are prevalently used in dynamic conditions while walking or running. This paper presents the design and implementation of a structured-light prototype system providing dense three dimensional (3D) measurements of the foot in motion, and its use to show that foot measurements in dynamic conditions differ significantly from their static counterparts. The input to the system is a video sequence of a foot during a single step; the output is a 3D reconstruction of the plantar surface of the foot for each frame of the input. Engineering and clinical tests were carried out for the validation of the system. The accuracy of the system was found to be 0.34 mm with planar test objects. In tests with real feet, the system proved repeatable, with reconstruction differences between trials one week apart averaging 2.44 mm (static case) and 2.81 mm (dynamic case). Furthermore, a study was performed to compare the effective length of the foot between static and dynamic reconstructions using the 4D system. Results showed an average increase of 9 mm for the dynamic case. This increase is substantial for orthotics design, cannot be captured by a static system, and its subject-specific measurement is crucial for the design of effective foot orthoses.