Rethinking Foundation Models for Medical Image Classification through a Benchmark Study on MedMNIST

Foundation models are widely employed in medical image analysis, due to their high adaptability and generalizability for downstream tasks. With the increasing number of foundation models being released, model selection has become an important issue. In this work, we study the capabilities of foundation models in medical image classification tasks by conducting a benchmark study on the MedMNIST dataset. Specifically, we adopt various foundation models ranging from convolutional to Transformer-based models and implement both end-to-end training and linear probing for all classification tasks. The results demonstrate the significant potential of these pre-trained models when transferred for medical image classification. We further conduct experiments with different image sizes and various sizes of training data. By analyzing all the results, we provide preliminary, yet useful insights and conclusions on this topic.

KneeXNeT: An Ensemble-Based Approach for Knee Radiographic Evaluation

Knee osteoarthritis (OA) is the most common joint disorder and a leading cause of disability. Diagnosing OA severity typically requires expert assessment of X-ray images and is commonly based on the Kellgren-Lawrence grading system, a time-intensive process. This study aimed to develop an automated deep learning model to classify knee OA severity, reducing the need for expert evaluation. First, we evaluated ten state-of-the-art deep learning models, achieving a top accuracy of 0.69 with individual models. To address class imbalance, we employed weighted sampling, improving accuracy to 0.70. We further applied Smooth-GradCAM++ to visualize decision-influencing regions, enhancing the explainability of the best-performing model. Finally, we developed ensemble models using majority voting and a shallow neural network. Our ensemble model, KneeXNet, achieved the highest accuracy of 0.72, demonstrating its potential as an automated tool for knee OA assessment.

Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting

The growing capabilities of AI models are leading to their wider use, including in safety-critical domains. Explainable AI (XAI) aims to make these models safer to use by making their inference process more transparent. However, current explainability methods are seldom evaluated in the way they are intended to be used: by real-world end users. To address this, we conducted a large-scale user study with 85 healthcare practitioners in the context of human-AI collaborative chest X-ray analysis. We evaluated three types of explanations: visual explanations (saliency maps), natural language explanations, and a combination of both modalities. We specifically examined how different explanation types influence users depending on whether the AI advice and explanations are factually correct. We find that text-based explanations lead to significant over-reliance, which is alleviated by combining them with saliency maps. We also observe that the quality of explanations, that is, how much factually correct information they entail, and how much this aligns with AI correctness, significantly impacts the usefulness of the different explanation types.

Deep Learning Models to Automate the Scoring of Hand Radiographs for Rheumatoid Arthritis

The van der Heijde modification of the Sharp (SvdH) score is a widely used radiographic scoring method to quantify damage in Rheumatoid Arthritis (RA) in clinical trials. However, its complexity with a necessity to score each individual joint, and the expertise required limit its application in clinical practice, especially in disease progression measurement. In this work, we addressed this limitation by developing a bespoke, automated pipeline that is capable of predicting the SvdH score and RA severity from hand radiographs without the need to localise the joints first. Using hand radiographs from RA and suspected RA patients, we first investigated the performance of the state-of-the-art architectures in predicting the total SvdH score for hands and wrists and its corresponding severity class. Secondly, we leveraged publicly available data sets to perform transfer learning with different finetuning schemes and ensemble learning, which resulted in substantial improvement in model performance being on par with an experienced human reader. The best model for RA scoring achieved a Pearson's correlation coefficient (PCC) of 0.925 and root mean squared error (RMSE) of 18.02, while the best model for RA severity classification achieved an accuracy of 0.358 and PCC of 0.859. Our score prediction model attained almost comparable accuracy with experienced radiologists (PCC = 0.97, RMSE = 18.75). Finally, using Grad-CAM, we showed that our models could focus on the anatomical structures in hands and wrists which clinicians deemed as relevant to RA progression in the majority of cases.

Paired Diffusion: Generation of related, synthetic PET-CT-Segmentation scans using Linked Denoising Diffusion Probabilistic Models

The rapid advancement of Artificial Intelligence (AI) in biomedical imaging and radiotherapy is hindered by the limited availability of large imaging data repositories. With recent research and improvements in denoising diffusion probabilistic models (DDPM), high quality synthetic medical scans are now possible. Despite this, there is currently no way of generating multiple related images, such as a corresponding ground truth which can be used to train models, so synthetic scans are often manually annotated before use. This research introduces a novel architecture that is able to generate multiple, related PET-CT-tumour mask pairs using paired networks and conditional encoders. Our approach includes innovative, time step-controlled mechanisms and a `noise-seeding' strategy to improve DDPM sampling consistency. While our model requires a modified perceptual loss function to ensure accurate feature alignment we show generation of clearly aligned synthetic images and improvement in segmentation accuracy with generated images.

Multi-Task Cooperative Learning via Searching for Flat Minima

Multi-task learning (MTL) has shown great potential in medical image analysis, improving the generalizability of the learned features and the performance in individual tasks. However, most of the work on MTL focuses on either architecture design or gradient manipulation, while in both scenarios, features are learned in a competitive manner. In this work, we propose to formulate MTL as a multi/bi-level optimization problem, and therefore force features to learn from each task in a cooperative approach. Specifically, we update the sub-model for each task alternatively taking advantage of the learned sub-models of the other tasks. To alleviate the negative transfer problem during the optimization, we search for flat minima for the current objective function with regard to features from other tasks. To demonstrate the effectiveness of the proposed approach, we validate our method on three publicly available datasets. The proposed method shows the advantage of cooperative learning, and yields promising results when compared with the state-of-the-art MTL approaches. The code will be available online.

VertXNet: An Ensemble Method for Vertebrae Segmentation and Identification of Spinal X-Ray

Reliable vertebrae annotations are key to perform analysis of spinal X-ray images. However, obtaining annotation of vertebrae from those images is usually carried out manually due to its complexity (i.e. small structures with varying shape), making it a costly and tedious process. To accelerate this process, we proposed an ensemble pipeline, VertXNet, that combines two state-of-the-art (SOTA) segmentation models (respectively U-Net and Mask R-CNN) to automatically segment and label vertebrae in X-ray spinal images. Moreover, VertXNet introduces a rule-based approach that allows to robustly infer vertebrae labels (by locating the 'reference' vertebrae which are easier to segment than others) for a given spinal X-ray image. We evaluated the proposed pipeline on three spinal X-ray datasets (two internal and one publicly available), and compared against vertebrae annotated by radiologists. Our experimental results have shown that the proposed pipeline outperformed two SOTA segmentation models on our test dataset (MEASURE 1) with a mean Dice of 0.90, vs. a mean Dice of 0.73 for Mask R-CNN and 0.72 for U-Net. To further evaluate the generalization ability of VertXNet, the pre-trained pipeline was directly tested on two additional datasets (PREVENT and NHANES II) and consistent performance was observed with a mean Dice of 0.89 and 0.88, respectively. Overall, VertXNet demonstrated significantly improved performance for vertebra segmentation and labeling for spinal X-ray imaging, and evaluation on both in-house clinical trial data and publicly available data further proved its generalization.

VertXNet: Automatic Segmentation and Identification of Lumbar and Cervical Vertebrae from Spinal X-ray Images

Manual annotation of vertebrae on spinal X-ray imaging is costly and time-consuming due to bone shape complexity and image quality variations. In this study, we address this challenge by proposing an ensemble method called VertXNet, to automatically segment and label vertebrae in X-ray spinal images. VertXNet combines two state-of-the-art segmentation models, namely U-Net and Mask R-CNN to improve vertebrae segmentation. A main feature of VertXNet is to also infer vertebrae labels thanks to its Mask R-CNN component (trained to detect 'reference' vertebrae) on a given spinal X-ray image. VertXNet was evaluated on an in-house dataset of lateral cervical and lumbar X-ray imaging for ankylosing spondylitis (AS) patients. Our results show that VertXNet can accurately label spinal X-rays (mean Dice of 0.9). It can be used to circumvent the lack of annotated vertebrae without requiring human expert review. This step is crucial to investigate clinical associations by solving the lack of segmentation, a common bottleneck for most computational imaging projects.

Recurrent Image Registration using Mutual Attention based Network

Image registration is an important task in medical imaging which estimates the spatial transformation between different images. Many previous studies have used learning-based methods for multi-stage registration to perform 3D image registration to improve performance. The performance of the multi-stage approach, however, is limited by the size of the receptive field where complex motion does not occur at a single spatial scale. We propose a new registration network combining recursive network architecture and mutual attention mechanism to overcome these limitations. Compared with the previous deep learning methods, our network based on the recursive structure achieves the highest accuracy in lung Computed Tomography (CT) data set (Dice score of 92\% and average surface distance of 3.8mm for lungs) and one of the most accurate results in abdominal CT data set with 9 organs of various sizes (Dice score of 55\% and average surface distance of 7.8mm). We also showed that adding 3 recursive networks is sufficient to achieve the state-of-the-art results without a significant increase in the inference time.

Residual Aligner Network

Image registration is important for medical imaging, the estimation of the spatial transformation between different images. Many previous studies have used learning-based methods for coarse-to-fine registration to efficiently perform 3D image registration. The coarse-to-fine approach, however, is limited when dealing with the different motions of nearby objects. Here we propose a novel Motion-Aware (MA) structure that captures the different motions in a region. The MA structure incorporates a novel Residual Aligner (RA) module which predicts the multi-head displacement field used to disentangle the different motions of multiple neighbouring objects. Compared with other deep learning methods, the network based on the MA structure and RA module achieve one of the most accurate unsupervised inter-subject registration on the 9 organs of assorted sizes in abdominal CT scans, with the highest-ranked registration of the veins (Dice Similarity Coefficient / Average surface distance: 62\%/4.9mm for the vena cava and 34\%/7.9mm for the portal and splenic vein), with a half-sized structure and more efficient computation. Applied to the segmentation of lungs in chest CT scans, the new network achieves results which were indistinguishable from the best-ranked networks (94\%/3.0mm). Additionally, the theorem on predicted motion pattern and the design of MA structure are validated by further analysis.