RESUMEN
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a machine learning approach for classifying disease progression in chest radiographs using weak labels automatically derived from radiology reports. Materials and Methods In this retrospective study, a twin neural network was developed to classify anatomy-specific disease progression into four categories: improved, unchanged, worsened, and new. A two-step weakly-supervised learning approach was employed, pretraining the model on 243,008 frontal chest radiographs from 63,877 MIMIC-CXR patients (mean age 51.7 years; female 34,813), and fine-tuning it on the subset with progression labels derived from consecutive studies. Model performance was evaluated for six pathologic observations on test datasets of unseen MIMIC-CXR patients. Area under the receiver operating characteristic (AUC) analysis was used to evaluate classification performance. The algorithm is also capable of generating bounding-box predictions to localize areas of new progression. Recall, precision, and mean average precision (mAP) were used to evaluate the new progression localization. One-tailed paired t tests were used to assess statistical significance. Results The model outperformed most baselines in progression classification, achieving macro AUC scores of 0.72 ± 0.004 for atelectasis, 0.75 ± 0.007 for consolidation, 0.76 ± 0.017 for edema, 0.81 ± 0.006 for effusion, 0.7 ± 0.032 for pneumonia, and 0.69 ± 0.01 for pneumothorax. For new observation localization, the model achieved mAP scores of 0.25 ± 0.03 for atelectasis, 0.34 ± 0.03 for consolidation, 0.33 ± 0.03 for edema, and 0.31 ± 0.03 for pneumothorax. Conclusion Disease progression classification models were developed on a large chest radiograph dataset, which can be used to monitor interval changes and detect new pathologies on chest radiographs. ©RSNA, 2024.
RESUMEN
This paper introduces an innovative methodology for producing high-quality 3D lung CT images guided by textual information. While diffusion-based generative models are increasingly used in medical imaging, current state-of-the-art approaches are limited to low-resolution outputs and underutilize radiology reports' abundant information. The radiology reports can enhance the generation process by providing additional guidance and offering fine-grained control over the synthesis of images. Nevertheless, expanding text-guided generation to high-resolution 3D images poses significant memory and anatomical detail-preserving challenges. Addressing the memory issue, we introduce a hierarchical scheme that uses a modified UNet architecture. We start by synthesizing low-resolution images conditioned on the text, serving as a foundation for subsequent generators for complete volumetric data. To ensure the anatomical plausibility of the generated samples, we provide further guidance by generating vascular, airway, and lobular segmentation masks in conjunction with the CT images. The model demonstrates the capability to use textual input and segmentation tasks to generate synthesized images. Algorithmic comparative assessments and blind evaluations conducted by 10 board-certified radiologists indicate that our approach exhibits superior performance compared to the most advanced models based on GAN and diffusion techniques, especially in accurately retaining crucial anatomical features such as fissure lines and airways. This innovation introduces novel possibilities. This study focuses on two main objectives: (1) the development of a method for creating images based on textual prompts and anatomical components, and (2) the capability to generate new images conditioning on anatomical elements. The advancements in image generation can be applied to enhance numerous downstream tasks.
RESUMEN
Monitoring cerebral neuronal activity via electroencephalography (EEG) during surgery can detect ischemia, a precursor to stroke. However, current neurophysiologist-based monitoring is prone to error. In this study, we evaluated machine learning (ML) for efficient and accurate ischemia detection. We trained supervised ML models on a dataset of 802 patients with intraoperative ischemia labels and evaluated them on an independent validation dataset of 30 patients with refined labels from five neurophysiologists. Our results show moderate-to-substantial agreement between neurophysiologists, with Cohen's kappa values between 0.59 and 0.74. Neurophysiologist performance ranged from 58-93% for sensitivity and 83-96% for specificity, while ML models demonstrated comparable ranges of 63-89% and 85-96%. Random Forest (RF), LightGBM (LGBM), and XGBoost RF achieved area under the receiver operating characteristic curve (AUROC) values of 0.92-0.93 and area under the precision-recall curve (AUPRC) values of 0.79-0.83. ML has the potential to improve intraoperative monitoring, enhancing patient safety and reducing costs.
RESUMEN
Continuous intraoperative monitoring with electroencephalo2 graphy (EEG) is commonly used to detect cerebral ischemia in high-risk surgical procedures such as carotid endarterectomy. Machine learning (ML) models that detect ischemia in real time can form the basis of automated intraoperative EEG monitoring. In this study, we describe and compare two time-series aware precision and recall metrics to the classical precision and recall metrics for evaluating the performance of ML models that detect ischemia. We trained six ML models to detect ischemia in intraoperative EEG and evaluated them with the area under the precision-recall curve (AUPRC) using time-series aware and classical approaches to compute precision and recall. The Support Vector Classification (SVC) model performed the best on the time-series aware metrics, while the Light Gradient Boosting Machine (LGBM) model performed the best on the classical metrics. Visual inspection of the probability outputs of the models alongside the actual ischemic periods revealed that the time-series aware AUPRC selected a model more likely to predict ischemia onset in a timely fashion than the model selected by classical AUPRC.
Asunto(s)
Isquemia , Monitoreo Intraoperatorio , Humanos , Factores de Tiempo , Área Bajo la Curva , ElectroencefalografíaRESUMEN
Large-scale volumetric medical images with annotation are rare, costly, and time prohibitive to acquire. Self-supervised learning (SSL) offers a promising pre-training and feature extraction solution for many downstream tasks, as it only uses unlabeled data. Recently, SSL methods based on instance discrimination have gained popularity in the medical imaging domain. However, SSL pre-trained encoders may use many clues in the image to discriminate an instance that are not necessarily disease-related. Moreover, pathological patterns are often subtle and heterogeneous, requiring the ability of the desired method to represent anatomy-specific features that are sensitive to abnormal changes in different body parts. In this work, we present a novel SSL framework, named DrasCLR, for 3D lung CT images to overcome these challenges. We propose two domain-specific contrastive learning strategies: one aims to capture subtle disease patterns inside a local anatomical region, and the other aims to represent severe disease patterns that span larger regions. We formulate the encoder using conditional hyper-parameterized network, in which the parameters are dependant on the anatomical location, to extract anatomically sensitive features. Extensive experiments on large-scale datasets of lung CT scans show that our method improves the performance of many downstream prediction and segmentation tasks. The patient-level representation improves the performance of the patient survival prediction task. We show how our method can detect emphysema subtypes via dense prediction. We demonstrate that fine-tuning the pre-trained model can significantly reduce annotation efforts without sacrificing emphysema detection accuracy. Our ablation study highlights the importance of incorporating anatomical context into the SSL framework. Our codes are available at https://github.com/batmanlab/DrasCLR.
Asunto(s)
Enfisema , Humanos , Tórax , Tomografía Computarizada por Rayos X , Aprendizaje Automático SupervisadoRESUMEN
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc. Blackbox models are flexible but difficult to explain, while interpretable models are inherently explainable. Yet, interpretable models require extensive ML knowledge and tend to be less flexible and underperforming than their Blackbox variants. This paper aims to blur the distinction between a post hoc explanation of a Blackbox and constructing interpretable models. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each interpretable model specializes in a subset of samples and explains them using First Order Logic (FOL), providing basic reasoning on concepts from the Blackbox. We route the remaining samples through a flexible residual. We repeat the method on the residual network until all the interpretable models explain the desired proportion of data. Our extensive experiments show that our route, interpret, and repeat approach (1) identifies a diverse set of instance-specific concepts with high concept completeness via MoIE without compromising in performance, (2) identifies the relatively "harder" samples to explain via residuals, (3) outperforms the interpretable by-design models by significant margins during test-time interventions, and (4) fixes the shortcut learned by the original Blackbox. The code for MoIE is publicly available at: https://github.com/batmanlab/ICML-2023-Route-interpret-repeat.
RESUMEN
A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie close to the decision boundary. The model should also refrain from making overconfident decisions on samples that lie far outside its training distribution, far-out-of-distribution (far-OOD), or on unseen samples from novel classes that lie near its training distribution (near-OOD). This paper proposes an application of counterfactual explanations in fixing an over-confident classifier. Specifically, we propose to fine-tune a given pre-trained classifier using augmentations from a counterfactual explainer (ACE) to fix its uncertainty characteristics while retaining its predictive performance. We perform extensive experiments with detecting far-OOD, near-OOD, and ambiguous samples. Our empirical results show that the revised model have improved uncertainty measures, and its performance is competitive to the state-of-the-art methods.
RESUMEN
Studying small effects or subtle neuroanatomical variation requires large-scale sample size data. As a result, combining neuroimaging data from multiple datasets is necessary. Variation in acquisition protocols, magnetic field strength, scanner build, and many other non-biologically related factors can introduce undesirable bias into studies. Hence, harmonization is required to remove the bias-inducing factors from the data. ComBat is one of the most common methods applied to features from structural images. ComBat models the data using a hierarchical Bayesian model and uses the empirical Bayes approach to infer the distribution of the unknown factors. The empirical Bayes harmonization method is computationally efficient and provides valid point estimates. However, it tends to underestimate uncertainty. This paper investigates a new approach, fully Bayesian ComBat, where Monte Carlo sampling is used for statistical inference. When comparing fully Bayesian and empirical Bayesian ComBat, we found Empirical Bayesian ComBat more effectively removed scanner strength information and was much more computationally efficient. Conversely, fully Bayesian ComBat better preserved biological disease and age-related information while performing more accurate harmonization on traveling subjects. The fully Bayesian approach generates a rich posterior distribution, which is useful for generating simulated imaging features for improving classifier performance in a limited data setting. We show the generative capacity of our model for augmenting and improving the detection of patients with Alzheimer's disease. Posterior distributions for harmonized imaging measures can also be used for brain-wide uncertainty comparison and more principled downstream statistical analysis.Code for our new fully Bayesian ComBat extension is available at https://github.com/batmanlab/BayesComBat.
Asunto(s)
Encéfalo , Neuroimagen , Humanos , Teorema de Bayes , Encéfalo/diagnóstico por imagen , Proyectos de InvestigaciónRESUMEN
Rationale: Chronic obstructive pulmonary disease (COPD) is characterized by pathologic changes in the airways, lung parenchyma, and persistent inflammation, but the links between lung structural changes and blood transcriptome patterns have not been fully described. Objections: The objective of this study was to identify novel relationships between lung structural changes measured by chest computed tomography (CT) and blood transcriptome patterns measured by blood RNA sequencing (RNA-seq). Methods: CT scan images and blood RNA-seq gene expression from 1223 participants in the COPD Genetic Epidemiology (COPDGene®) study were jointly analyzed using deep learning to identify shared aspects of inflammation and lung structural changes that we labeled image-expression axes (IEAs). We related IEAs to COPD-related measurements and prospective health outcomes through regression and Cox proportional hazards models and tested them for biological pathway enrichment. Results: We identified 2 distinct IEAs: IEAemph which captures an emphysema-predominant process with a strong positive correlation to CT emphysema and a negative correlation to forced expiratory volume in 1 second and body mass index (BMI); and IEAairway which captures an airway-predominant process with a positive correlation to BMI and airway wall thickness and a negative correlation to emphysema. Pathway enrichment analysis identified 29 and 13 pathways significantly associated with IEAemph and IEAairway, respectively (adjusted p<0.001). Conclusions: Integration of CT scans and blood RNA-seq data identified 2 IEAs that capture distinct inflammatory processes associated with emphysema and airway-predominant COPD.
RESUMEN
We propose a BlackBox Counterfactual Explainer, designed to explain image classification models for medical applications. Classical approaches (e.g., , saliency maps) that assess feature importance do not explain how imaging features in important anatomical regions are relevant to the classification decision. Such reasoning is crucial for transparent decision-making in healthcare applications. Our framework explains the decision for a target class by gradually exaggerating the semantic effect of the class in a query image. We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision changes from its original class to its negation. Our proposed loss function preserves essential details (e.g., support devices) in the generated images. We used counterfactual explanations from our framework to audit a classifier trained on a chest X-ray dataset with multiple labels. Clinical evaluation of model explanations is a challenging task. We proposed clinically-relevant quantitative metrics such as cardiothoracic ratio and the score of a healthy costophrenic recess to evaluate our explanations. We used these metrics to quantify the counterfactual changes between the populations with negative and positive decisions for a diagnosis by the given classifier. We conducted a human-grounded experiment with diagnostic radiology residents to compare different styles of explanations (no explanation, saliency map, cycleGAN explanation, and our counterfactual explanation) by evaluating different aspects of explanations: (1) understandability, (2) classifier's decision justification, (3) visual quality, (d) identity preservation, and (5) overall helpfulness of an explanation to the users. Our results show that our counterfactual explanation was the only explanation method that significantly improved the users' understanding of the classifier's decision compared to the no-explanation baseline. Our metrics established a benchmark for evaluating model explanation methods in medical images. Our explanations revealed that the classifier relied on clinically relevant radiographic features for its diagnostic decisions, thus making its decision-making process more transparent to the end-user.
Asunto(s)
Benchmarking , Radiología , Humanos , SemánticaRESUMEN
Domain Adaptation (DA) has recently been of strong interest in the medical imaging community. While a large variety of DA techniques have been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality Domain Adaptation. The goal of the challenge is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are commonly performed using contrast-enhanced T1 (ceT1) MR imaging. However, there is growing interest in using non-contrast imaging sequences such as high-resolution T2 (hrT2) imaging. For this reason, we established an unsupervised cross-modality segmentation benchmark. The training dataset provides annotated ceT1 scans (N=105) and unpaired non-annotated hrT2 scans (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 scans as provided in the testing set (N=137). This problem is particularly challenging given the large intensity distribution gap across the modalities and the small volume of the structures. A total of 55 teams from 16 countries submitted predictions to the validation leaderboard. Among them, 16 teams from 9 different countries submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice score - VS: 88.4%; Cochleas: 85.7%) and close to full supervision (median Dice score - VS: 92.5%; Cochleas: 87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.
Asunto(s)
Neuroma Acústico , Humanos , Neuroma Acústico/diagnóstico por imagenRESUMEN
Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and poses problems when deploying them in safety-critical applications. This paper aims to better understand the effects of spurious features through the lens of the learning dynamics of the internal neurons during the training process. We make the following observations: (1) While previous works highlight the harmful effects of spurious features on the generalization ability of DNNs, we emphasize that not all spurious features are harmful. Spurious features can be "benign" or "harmful" depending on whether they are "harder" or "easier" to learn than the core features for a given model. This definition is model and dataset dependent. (2) We build upon this premise and use instance difficulty methods (like Prediction Depth (Baldock et al., 2021)) to quantify "easiness" for a given model and to identify this behavior during the training phase. (3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN's early layers. In other words, easy features learned by the initial layers of a DNN early during the training can (potentially) hurt model generalization. We verify our claims on medical and vision datasets, both simulated and real, and justify the empirical success of our hypothesis by showing the theoretical connections between Prediction Depth and information-theoretic concepts like ð±-usable information (Ethayarajh et al., 2021). Lastly, our experiments show that monitoring only accuracy during training (as is common in machine learning pipelines) is insufficient to detect spurious features. We, therefore, highlight the need for monitoring early training dynamics using suitable instance difficulty metrics.
RESUMEN
Building generalizable AI models is one of the primary challenges in the healthcare domain. While radiologists rely on generalizable descriptive rules of abnormality, Neural Network (NN) models suffer even with a slight shift in input distribution (e.g., scanner type). Fine-tuning a model to transfer knowledge from one domain to another requires a significant amount of labeled data in the target domain. In this paper, we develop an interpretable model that can be efficiently fine-tuned to an unseen target domain with minimal computational cost. We assume the interpretable component of NN to be approximately domain-invariant. However, interpretable models typically underperform compared to their Blackbox (BB) variants. We start with a BB in the source domain and distill it into a mixture of shallow interpretable models using human-understandable concepts. As each interpretable model covers a subset of data, a mixture of interpretable models achieves comparable performance as BB. Further, we use the pseudo-labeling technique from semi-supervised learning (SSL) to learn the concept classifier in the target domain, followed by fine-tuning the interpretable models in the target domain. We evaluate our model using a real-life large-scale chest-X-ray (CXR) classification dataset. The code is available at: https://github.com/batmanlab/MICCAI-2023-Route-interpret-repeat-CXRs.
RESUMEN
Magnetic resonance elastography (MRE) is a medical imaging modality that non-invasively quantifies tissue stiffness (elasticity) and is commonly used for diagnosing liver fibrosis. Constructing an elasticity map of tissue requires solving an inverse problem involving a partial differential equation (PDE). Current numerical techniques to solve the inverse problem are noise-sensitive and require explicit specification of physical relationships. In this work, we apply physics-informed neural networks to solve the inverse problem of tissue elasticity reconstruction. Our method does not rely on numerical differentiation and can be extended to learn relevant correlations from anatomical images while respecting physical constraints. We evaluate our approach on simulated data and in vivo data from a cohort of patients with non-alcoholic fatty liver disease (NAFLD). Compared to numerical baselines, our method is more robust to noise and more accurate on realistic data, and its performance is further enhanced by incorporating anatomical information.
RESUMEN
Despite the proliferation of generative models, achieving fast sampling during inference without compromising sample diversity and quality remains challenging. Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. The Denoising Diffusion Generative Adversarial Networks (DDGAN) attempted to circumvent this limitation by integrating a GAN model for larger jumps in the diffusion process. However, DDGAN encountered scalability limitations when applied to large datasets. To address these limitations, we introduce a novel approach that tackles the problem by matching implicit and explicit factors. More specifically, our approach involves utilizing an implicit model to match the marginal distributions of noisy data and the explicit conditional distribution of the forward diffusion. This combination allows us to effectively match the joint denoising distributions. Unlike DDPM but similar to DDGAN, we do not enforce a parametric distribution for the reverse step, enabling us to take large steps during inference. Similar to the DDPM but unlike DDGAN, we take advantage of the exact form of the diffusion process. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps. The code is available at https://github.com/xuyanwu/SIDDMs.
RESUMEN
Knowledge distillation has been used to capture the knowledge of a teacher model and distill it into a student model with some desirable characteristics such as being smaller, more efficient, or more generalizable. In this paper, we propose a framework for distilling the knowledge of a powerful discriminative model such as a neural network into commonly used graphical models known to be more interpretable (e.g., topic models, autoregressive Hidden Markov Models). Posterior of latent variables in these graphical models (e.g., topic proportions in topic models) is often used as feature representation for predictive tasks. However, these posterior-derived features are known to have poor predictive performance compared to the features learned via purely discriminative approaches. Our framework constrains variational inference for posterior variables in graphical models with a similarity preserving constraint. This constraint distills the knowledge of the discriminative model into the graphical model by ensuring that input pairs with (dis)similar representation in the teacher model also have (dis)similar representation in the student model. By adding this constraint to the variational inference scheme, we guide the graphical model to be a reasonable density model for the data while having predictive features which are as close as possible to those of a discriminative model. To make our framework applicable to a wide range of graphical models, we build upon the Automatic Differentiation Variational Inference (ADVI), a black-box inference framework for graphical models. We demonstrate the effectiveness of our framework on two real-world tasks of disease subtyping and disease trajectory modeling.
RESUMEN
INTRODUCTION: Oral epithelial dysplasia (OED) is a precursor lesion to oral squamous cell carcinoma, a disease with a reported overall survival rate of 56 percent across all stages. Accurate detection of OED is critical as progression to oral cancer can be impeded with complete excision of premalignant lesions. However, previous research has demonstrated that the task of grading of OED, even when performed by highly trained experts, is subject to high rates of reader variability and misdiagnosis. Thus, our study aims to develop a convolutional neural network (CNN) model that can identify regions suspicious for OED whole-slide pathology images. METHODS: During model development, we optimized key training hyperparameters including loss function on 112 pathologist annotated cases between the training and validation sets. Then, we compared OED segmentation and classification metrics between two well-established CNN architectures for medical imaging, DeepLabv3+ and UNet++. To further assess generalizability, we assessed case-level performance of a held-out test set of 44 whole-slide images. RESULTS: DeepLabv3+ outperformed UNet++ in overall accuracy, precision, and segmentation metrics in a 4-fold cross validation study. When applied to the held-out test set, our best performing DeepLabv3+ model achieved an overall accuracy and F1-Score of 93.3 percent and 90.9 percent, respectively. CONCLUSION: The present study trained and implemented a CNN-based deep learning model for identification and segmentation of oral epithelial dysplasia (OED) with reasonable success. Computer assisted detection was shown to be feasible in detecting premalignant/precancerous oral lesions, laying groundwork for eventual clinical implementation.
Asunto(s)
Carcinoma de Células Escamosas , Neoplasias de Cabeza y Cuello , Neoplasias de la Boca , Lesiones Precancerosas , Carcinoma de Células Escamosas/diagnóstico por imagen , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Neoplasias de la Boca/diagnóstico por imagen , Neoplasias de la Boca/patología , Redes Neurales de la Computación , Lesiones Precancerosas/diagnósticoRESUMEN
Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image. The hierarchical design has two advantages: First, the memory demand for training on high-resolution images is amortized among sub-volumes. Furthermore, anchoring the high-resolution sub-volumes to a single low-resolution image ensures anatomical consistency between sub-volumes. During inference, our model can directly generate full high-resolution images. We also incorporate an encoder with a similar hierarchical structure into the model to extract features from the images. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation. We also demonstrate clinical applications of the proposed model in data augmentation and clinical-relevant feature extraction.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Imagenología Tridimensional , Artefactos , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Tomografía Computarizada por Rayos XRESUMEN
An organ segmentation method that can generalize to unseen contrasts and scanner settings can significantly reduce the need for retraining of deep learning models. Domain Generalization (DG) aims to achieve this goal. However, most DG methods for segmentation require training data from multiple domains during training. We propose a novel adversarial domain generalization method for organ segmentation trained on data from a single domain. We synthesize the new domains via learning an adversarial domain synthesizer (ADS) and presume that the synthetic domains cover a large enough area of plausible distributions so that unseen domains can be interpolated from synthetic domains. We propose a mutual information regularizer to enforce the semantic consistency between images from the synthetic domains, which can be estimated by patch-level contrastive learning. We evaluate our method for various organ segmentation for unseen modalities, scanning protocols, and scanner sites.
RESUMEN
Creating a large-scale dataset of abnormality annotation on medical images is a labor-intensive and costly task. Leveraging weak supervision from readily available data such as radiology reports can compensate lack of large-scale data for anomaly detection methods. However, most of the current methods only use image-level pathological observations, failing to utilize the relevant anatomy mentions in reports. Furthermore, Natural Language Processing (NLP)-mined weak labels are noisy due to label sparsity and linguistic ambiguity. We propose an Anatomy-Guided chest X-ray Network (AGXNet) to address these issues of weak annotation. Our framework consists of a cascade of two networks, one responsible for identifying anatomical abnormalities and the second responsible for pathological observations. The critical component in our framework is an anatomy-guided attention module that aids the downstream observation network in focusing on the relevant anatomical regions generated by the anatomy network. We use Positive Unlabeled (PU) learning to account for the fact that lack of mention does not necessarily mean a negative label. Our quantitative and qualitative results on the MIMIC-CXR dataset demonstrate the effectiveness of AGXNet in disease and anatomical abnormality localization. Experiments on the NIH Chest X-ray dataset show that the learned feature representations are transferable and can achieve the state-of-the-art performances in disease classification and competitive disease localization results. Our code is available at https://github.com/batmanlab/AGXNet.