Mask of truth: model sensitivity to unexpected regions of medical images

The development of larger models for medical image analysis has led to increased performance. However, it also affected our ability to explain and validate model decisions. Models can use non-relevant parts of images, also called spurious correlations or shortcuts, to obtain high performance on benchmark datasets but fail in real-world scenarios. In this work, we challenge the capacity of convolutional neural networks (CNN) to classify chest X-rays and eye fundus images while masking out clinically relevant parts of the image. We show that all models trained on the PadChest dataset, irrespective of the masking strategy, are able to obtain an Area Under the Curve (AUC) above random. Moreover, the models trained on full images obtain good performance on images without the region of interest (ROI), even superior to the one obtained on images only containing the ROI. We also reveal a possible spurious correlation in the Chaksu dataset while the performances are more aligned with the expectation of an unbiased model. We go beyond the performance analysis with the usage of the explainability method SHAP and the analysis of embeddings. We asked a radiology resident to interpret chest X-rays under different masking to complement our findings with clinical knowledge. Our code is available at https://github.com/TheoSourget/MMC_Masking and https://github.com/TheoSourget/MMC_Masking_EyeFundus

PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation

Radiology report generation (RRG) aims to create free-text radiology reports from clinical imaging. Grounded radiology report generation (GRRG) extends RRG by including the localisation of individual findings on the image. Currently, there are no manually annotated chest X-ray (CXR) datasets to train GRRG models. In this work, we present a dataset called PadChest-GR (Grounded-Reporting) derived from PadChest aimed at training GRRG models for CXR images. We curate a public bi-lingual dataset of 4,555 CXR studies with grounded reports (3,099 abnormal and 1,456 normal), each containing complete lists of sentences describing individual present (positive) and absent (negative) findings in English and Spanish. In total, PadChest-GR contains 7,037 positive and 3,422 negative finding sentences. Every positive finding sentence is associated with up to two independent sets of bounding boxes labelled by different readers and has categorical labels for finding type, locations, and progression. To the best of our knowledge, PadChest-GR is the first manually curated dataset designed to train GRRG models for understanding and interpreting radiological images and generated text. By including detailed localization and comprehensive annotations of all clinically relevant findings, it provides a valuable resource for developing and evaluating GRRG models from CXR images. PadChest-GR can be downloaded under request from https://bimcv.cipf.es/bimcv-projects/padchest-gr/

Unsupervised Training of Neural Cellular Automata on Edge Devices

The disparity in access to machine learning tools for medical imaging across different regions significantly limits the potential for universal healthcare innovation, particularly in remote areas. Our research addresses this issue by implementing Neural Cellular Automata (NCA) training directly on smartphones for accessible X-ray lung segmentation. We confirm the practicality and feasibility of deploying and training these advanced models on five Android devices, improving medical diagnostics accessibility and bridging the tech divide to extend machine learning benefits in medical imaging to low- and middle-income countries (LMICs). We further enhance this approach with an unsupervised adaptation method using the novel Variance-Weighted Segmentation Loss (VWSL), which efficiently learns from unlabeled data by minimizing the variance from multiple NCA predictions. This strategy notably improves model adaptability and performance across diverse medical imaging contexts without the need for extensive computational resources or labeled datasets, effectively lowering the participation threshold. Our methodology, tested on three multisite X-ray datasets -- Padchest, ChestX-ray8, and MIMIC-III -- demonstrates improvements in segmentation Dice accuracy by 0.7 to 2.8%, compared to the classic Med-NCA. Additionally, in extreme cases where no digital copy is available and images must be captured by a phone from an X-ray lightbox or monitor, VWSL enhances Dice accuracy by 5-20%, demonstrating the method's robustness even with suboptimal image sources.

Augmenting Chest X-ray Datasets with Non-Expert Annotations

The advancement of machine learning algorithms in medical image analysis requires the expansion of training datasets. A popular and cost-effective approach is automated annotation extraction from free-text medical reports, primarily due to the high costs associated with expert clinicians annotating chest X-ray images. However, it has been shown that the resulting datasets are susceptible to biases and shortcuts. Another strategy to increase the size of a dataset is crowdsourcing, a widely adopted practice in general computer vision with some success in medical image analysis. In a similar vein to crowdsourcing, we enhance two publicly available chest X-ray datasets by incorporating non-expert annotations. However, instead of using diagnostic labels, we annotate shortcuts in the form of tubes. We collect 3.5k chest drain annotations for CXR14, and 1k annotations for 4 different tube types in PadChest. We train a chest drain detector with the non-expert annotations that generalizes well to expert labels. Moreover, we compare our annotations to those provided by experts and show "moderate" to "almost perfect" agreement. Finally, we present a pathology agreement study to raise awareness about ground truth annotations. We make our annotations and code available.

CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images

The development of successful artificial intelligence models for chest X-ray analysis relies on large, diverse datasets with high-quality annotations. While several databases of chest X-ray images have been released, most include disease diagnosis labels but lack detailed pixel-level anatomical segmentation labels. To address this gap, we introduce an extensive chest X-ray multi-center segmentation dataset with uniform and fine-grain anatomical annotations for images coming from six well-known publicly available databases: CANDID-PTX, ChestX-ray8, Chexpert, MIMIC-CXR-JPG, Padchest, and VinDr-CXR, resulting in 676,803 segmentation masks. Our methodology utilizes the HybridGNet model to ensure consistent and high-quality segmentations across all datasets. Rigorous validation, including expert physician evaluation and automatic quality control, was conducted to validate the resulting masks. Additionally, we provide individualized quality indices per mask and an overall quality estimation per dataset. This dataset serves as a valuable resource for the broader scientific community, streamlining the development and assessment of innovative methodologies in chest X-ray analysis. The CheXmask dataset is publicly available at: \url{https://physionet.org/content/chexmask-cxr-segmentation-data/}.

Explainable Knowledge Distillation for On-device Chest X-Ray Classification

Automated multi-label chest X-rays (CXR) image classification has achieved substantial progress in clinical diagnosis via utilizing sophisticated deep learning approaches. However, most deep models have high computational demands, which makes them less feasible for compact devices with low computational requirements. To overcome this problem, we propose a knowledge distillation (KD) strategy to create the compact deep learning model for the real-time multi-label CXR image classification. We study different alternatives of CNNs and Transforms as the teacher to distill the knowledge to a smaller student. Then, we employed explainable artificial intelligence (XAI) to provide the visual explanation for the model decision improved by the KD. Our results on three benchmark CXR datasets show that our KD strategy provides the improved performance on the compact student model, thus being the feasible choice for many limited hardware platforms. For instance, when using DenseNet161 as the teacher network, EEEA-Net-C2 achieved an AUC of 83.7%, 87.1%, and 88.7% on the ChestX-ray14, CheXpert, and PadChest datasets, respectively, with fewer parameters of 4.7 million and computational cost of 0.3 billion FLOPS.

Deep learning for understanding multilabel imbalanced Chest X-ray datasets

Over the last few years, convolutional neural networks (CNNs) have dominated the field of computer vision thanks to their ability to extract features and their outstanding performance in classification problems, for example in the automatic analysis of X-rays. Unfortunately, these neural networks are considered black-box algorithms, i.e. it is impossible to understand how the algorithm has achieved the final result. To apply these algorithms in different fields and test how the methodology works, we need to use eXplainable AI techniques. Most of the work in the medical field focuses on binary or multiclass classification problems. However, in many real-life situations, such as chest X-rays, radiological signs of different diseases can appear at the same time. This gives rise to what is known as "multilabel classification problems". A disadvantage of these tasks is class imbalance, i.e. different labels do not have the same number of samples. The main contribution of this paper is a Deep Learning methodology for imbalanced, multilabel chest X-ray datasets. It establishes a baseline for the currently underutilised PadChest dataset and a new eXplainable AI technique based on heatmaps. This technique also includes probabilities and inter-model matching. The results of our system are promising, especially considering the number of labels used. Furthermore, the heatmaps match the expected areas, i.e. they mark the areas that an expert would use to make the decision.

CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI

Rapidly expanding Clinical AI applications worldwide have the potential to impact to all areas of medical practice. Medical imaging applications constitute a vast majority of approved clinical AI applications. Though healthcare systems are eager to adopt AI solutions a fundamental question remains: \textit{what happens after the AI model goes into production?} We use the CheXpert and PadChest public datasets to build and test a medical imaging AI drift monitoring workflow that tracks data and model drift without contemporaneous ground truth. We simulate drift in multiple experiments to compare model performance with our novel multi-modal drift metric, which uses DICOM metadata, image appearance representation from a variational autoencoder (VAE), and model output probabilities as input. Through experimentation, we demonstrate a strong proxy for ground truth performance using unsupervised distributional shifts in relevant metadata, predicted probabilities, and VAE latent representation. Our key contributions include (1) proof-of-concept for medical imaging drift detection including use of VAE and domain specific statistical methods (2) a multi-modal methodology for measuring and unifying drift metrics (3) new insights into the challenges and solutions for observing deployed medical imaging AI (4) creation of open-source tools enabling others to easily run their own workflows or scenarios. This work has important implications for addressing the translation gap related to continuous medical imaging AI model monitoring in dynamic healthcare environments.

Effect of large-scale pre-training on full and few-shot transfer learning for natural and medical images

Transfer learning aims to exploit pre-trained models for more efficient follow-up training on wide range of downstream tasks and datasets, enabling successful training also on small data. Recent line of work posits strong benefits for model generalization and transfer when model size, data size, and compute budget are increased for the pre-training. It remains however still largely unclear whether the observed transfer improvement due to increase in scale also holds when source and target data distributions are far apart from each other. In this work we conduct large-scale pre-training on large source datasets of either natural (ImageNet-21k/1k) or medical chest X-Ray images and compare full and few-shot transfer using different target datasets from both natural and medical imaging domains. Our observations provide evidence that while pre-training and transfer on closely related datasets do show clear benefit of increasing model and data size during pre-training, such benefits are not clearly visible when source and target datasets are further apart. These observations hold across both full and few-shot transfer and indicate that scaling laws pointing to improvement of generalization and transfer with increasing model and data size are incomplete and should be revised by taking into account the type and proximity of the source and target data, to correctly predict the effect of model and data scale during pre-training on transfer. Remarkably, in full shot transfer to a large X-Ray chest imaging target (PadChest), the largest model pre-trained on ImageNet-21k slightly outperforms best models pre-trained on large X-Ray chest imaging data. This indicates possibility to obtain high quality models for domain-specific transfer even without access to large domain-specific data, by pre-training instead on comparably very large, generic source data.

Deep Hiearchical Multi-Label Classification Applied to Chest X-Ray Abnormality Taxonomies

CXRs are a crucial and extraordinarily common diagnostic tool, leading to heavy research for CAD solutions. However, both high classification accuracy and meaningful model predictions that respect and incorporate clinical taxonomies are crucial for CAD usability. To this end, we present a deep HMLC approach for CXR CAD. Different than other hierarchical systems, we show that first training the network to model conditional probability directly and then refining it with unconditional probabilities is key in boosting performance. In addition, we also formulate a numerically stable cross-entropy loss function for unconditional probabilities that provides concrete performance improvements. Finally, we demonstrate that HMLC can be an effective means to manage missing or incomplete labels. To the best of our knowledge, we are the first to apply HMLC to medical imaging CAD. We extensively evaluate our approach on detecting abnormality labels from the CXR arm of the PLCO dataset, which comprises over $198,000$ manually annotated CXRs. When using complete labels, we report a mean AUC of 0.887, the highest yet reported for this dataset. These results are supported by ancillary experiments on the PadChest dataset, where we also report significant improvements, 1.2% and 4.1% in AUC and AP, respectively over strong "flat" classifiers. Finally, we demonstrate that our HMLC approach can much better handle incompletely labelled data. These performance improvements, combined with the inherent usefulness of taxonomic predictions, indicate that our approach represents a useful step forward for CXR CAD.