Radiology Report Generation Research Articles

Collaboration between clinicians and vision-language models in radiology report generation.

Automated radiology report generation has the potential to improve patient care and reduce the workload of radiologists. However, the path toward real-world adoption has been stymied by the challenge of evaluating the clinical quality of artificial intelligence (AI)-generated reports. We build a state-of-the-art report generation system for chest radiographs, called Flamingo-CXR, and perform an expert evaluation of AI-generated reports by engaging a panel of board-certified radiologists. We observe a wide distribution of preferences across the panel and across clinical settings, with 56.1% of Flamingo-CXR intensive care reports evaluated to be preferable or equivalent to clinician reports, by half or more of the panel, rising to 77.7% for in/outpatient X-rays overall and to 94% for the subset of cases with no pertinent abnormal findings. Errors were observed in human-written reports and Flamingo-CXR reports, with 24.8% of in/outpatient cases containing clinically significant errors in both report types, 22.8% in Flamingo-CXR reports only and 14.0% in human reports only. For reports that contain errors we develop an assistive setting, a demonstration of clinician-AI collaboration for radiology report composition, indicating new possibilities for potential clinical utility.

Artificial Intelligence in CT Diagnosis: Current Status and Future Prospects for Ear Diseases

The human ear, with its complex structures like the ossicular chain, cochlea, and auditory nerve, plays a crucial role in hearing and balance. Common ear diseases, such as hearing loss, tinnitus, facial paralysis and vertigo, affect the quality of life of millions in China. Computed tomography (CT) has seen significant advancements since its introduction to China in 2000. The resolution improves from millimeter to sub-millimeter levels, and further, to 10 μm through bone-dedicated CT technology. The advancements have made CT the preferred method for diagnosing various ear conditions, including congenital malformations, trauma, inflammation, and neoplasm. Artificial intelligence (AI) has brought significant breakthroughs in CT diagnosis. Automatic segmentation of ear structures has dramatically improved with the advent of ultra-high-resolution computed tomography (U-HRCT). AI-driven measurement tools are enhancing the precision and personalization of surgical planning, while deep learning-based anomaly detection is utilized to address the challenges of detecting diverse ear lesions. Furthermore, AI-driven natural language processing and large language models are revolutionizing the generation of radiology reports, providing accurate and standardized diagnostic information. Despite ongoing challenges, the integration of AI into CT is expected to advance the otological field, leading to more precise and personalized treatment for ear diseases.

DACG: Dual Attention and Context Guidance model for radiology report generation

Medical images are an essential basis for radiologists to write radiology reports and greatly help subsequent clinical treatment. The task of generating automatic radiology reports aims to alleviate the burden of clinical doctors writing reports and has received increasing attention this year, becoming an important research hotspot. However, there are severe issues of visual and textual data bias and long text generation in the medical field. Firstly, Abnormal areas in radiological images only account for a small portion, and most radiological reports only involve descriptions of normal findings. Secondly, there are still significant challenges in generating longer and more accurate descriptive texts for radiology report generation tasks. In this paper, we propose a new Dual Attention and Context Guidance (DACG) model to alleviate visual and textual data bias and promote the generation of long texts. We use a Dual Attention Module, including a Position Attention Block and a Channel Attention Block, to extract finer position and channel features from medical images, enhancing the image feature extraction ability of the encoder. We use the Context Guidance Module to integrate contextual information into the decoder and supervise the generation of long texts. The experimental results show that our proposed model achieves state-of-the-art performance on the most commonly used IU X-ray and MIMIC-CXR datasets. Further analysis also proves that our model can improve reporting through more accurate anomaly detection and more detailed descriptions. The source code is available at https://github.com/LangWY/DACG.

Joint Imbalance Adaptation for Radiology Report Generation.

Radiology report generation, translating radiological images into precise and clinically relevant description, may face the data imbalance challenge - medical tokens appear less frequently than regular tokens; and normal entries are significantly more than abnormal ones. However, very few studies consider the imbalance issues, not even with conjugate imbalance factors. In this study, we propose a Joint Imbalance Adaptation (JIMA) model to promote task robustness by leveraging token and label imbalance. JIMA predicts entity distributions from images and generates reports based on these distributions and image features. We employ a hard-to-easy learning strategy that mitigates overfitting to frequent labels and tokens, thereby encouraging the model to focus more on rare labels and clinical tokens. JIMA shows notable improvements (16.75% - 50.50% on average) across evaluation metrics on IU X-ray and MIMIC-CXR datasets. Our ablation analysis proves that JIMA's enhanced handling of infrequent tokens and abnormal labels counts the major contribution. Human evaluation and case study experiments further validate that JIMA can generate more clinically accurate reports. Data imbalance (e.g., infrequent tokens and abnormal labels) leads to the underperformance of radiology report generation. Our curriculum learning strategy successfully reduce data imbalance impacts by reducing overfitting on frequent patterns and underfitting on infrequent patterns. While data imbalance remains challenging, our approach opens new directions for the generation task.

Interactive dual-stream contrastive learning for radiology report generation

Radiology report generation automates diagnostic narrative synthesis from medical imaging data. Current report generation methods primarily employ knowledge graphs for image enhancement, neglecting the interpretability and guiding function of the knowledge graphs themselves. Additionally, few approaches leverage the stable modal alignment information from multimodal pre-trained models to facilitate the generation of radiology reports. We propose the Terms-Guided Radiology Report Generation (TGR), a simple and practical model for generating reports guided primarily by anatomical terms. Specifically, we utilize a dual-stream visual feature extraction module comprised of detail extraction module and a frozen multimodal pre-trained model to separately extract visual detail features and semantic features. Furthermore, a Visual Enhancement Module (VEM) is proposed to further enrich the visual features, thereby facilitating the generation of a list of anatomical terms. We integrate anatomical terms with image features and proceed to engage contrastive learning with frozen text embeddings, utilizing the stable feature space from these embeddings to boost modal alignment capabilities further. Our model incorporates the capability for manual input, enabling it to generate a list of organs for specifically focused abnormal areas or to produce more accurate single-sentence descriptions based on selected anatomical terms. Comprehensive experiments demonstrate the effectiveness of our method in report generation tasks, our TGR-S model reduces training parameters by 38.9% while performing comparably to current state-of-the-art models, and our TGR-B model exceeds the best baseline models across multiple metrics.

DKA-RG: Disease-Knowledge-Enhanced Fine-Grained Image–Text Alignment for Automatic Radiology Report Generation

Automatic radiology report generation is a task that combines artificial intelligence and medical information processing, and it fully relies on computer vision and natural language processing techniques. Nowadays, automatic radiology report generation is still a very challenging task because it requires semantically adequate alignment of data from two modalities: radiology images and text. Existing approaches tend to focus on coarse-grained alignment at the global level and do not take into account the disease characteristics of radiology images at fine-grained semantics, which results in the generated reports potentially omitting key disease diagnostic descriptions. In this work, we propose a new approach, disease-knowledge-enhanced fine-grained image–text alignment for automatic radiology report generation (DKA-RG). The method combines global and disease-level alignment, thus facilitating the extraction of fine-grained disease features by the model. Our approach also introduces a knowledge graph to inject medical domain expertise into the model. Our proposed DKA-RG consists of two training steps: the image–report alignment stage and the image-to-report generation stage. In the alignment stage, we use global contrastive learning to align images and texts from a high level and also augment disease contrastive learning with medical knowledge to enhance the disease detection capability. In the report generation stage, the report text generated from the images is more accurate in describing the disease information thanks to sufficient alignment. Through extensive quantitative and qualitative experiments on two widely used datasets, we validate the effectiveness of our DKA-RG on the task of radiology report generation. Our DKA-RG achieves superior performance on multiple types of metrics (natural language generation and clinical efficacy metrics) compared to existing methods, demonstrating that the method can improve the reliability and accuracy of automatic radiology report generation systems.

An open chest X-ray dataset with benchmarks for automatic radiology report generation in French

Medical report generation (MRG), which aims to automatically generate a textual description of a specific medical image (e.g., a chest X-ray), has recently received increasing research interest. Building on the success of image captioning, MRG has become achievable. However, generating language-specific radiology reports poses a challenge for data-driven models due to their reliance on paired image-report chest X-ray datasets, which are labor-intensive, time-consuming, and costly. In this paper, we introduce a chest X-ray benchmark dataset, namely CASIA-CXR, consisting of high-resolution chest radiographs accompanied by narrative reports originally written in French. To the best of our knowledge, this is the first public chest radiograph dataset with medical reports in this particular language. Importantly, we propose a simple yet effective multimodal encoder–decoder contextually-guided framework for medical report generation in French. We validated our framework through intra-language and cross-language contextual analysis, supplemented by expert evaluation performed by radiologists. The dataset is freely available at: https://www.casia-cxr.net/.

Multi-Grained Radiology Report Generation With Sentence-Level Image-Language Contrastive Learning.

The automatic generation of accurate radiology reports is of great clinical importance and has drawn growing research interest. However, it is still a challenging task due to the imbalance between normal and abnormal descriptions and the multi-sentence and multi-topic nature of radiology reports. These features result in significant challenges to generating accurate descriptions for medical images, especially the important abnormal findings. Previous methods to tackle these problems rely heavily on extra manual annotations, which are expensive to acquire. We propose a multi-grained report generation framework incorporating sentence-level image-sentence contrastive learning, which does not require any extra labeling but effectively learns knowledge from the image-report pairs. We first introduce contrastive learning as an auxiliary task for image feature learning. Different from previous contrastive methods, we exploit the multi-topic nature of imaging reports and perform fine-grained contrastive learning by extracting sentence topics and contents and contrasting between sentence contents and refined image contents guided by sentence topics. This forces the model to learn distinct abnormal image features for each specific topic. During generation, we use two decoders to first generate coarse sentence topics and then the fine-grained text of each sentence. We directly supervise the intermediate topics using sentence topics learned by our contrastive objective. This strengthens the generation constraint and enables independent fine-tuning of the decoders using reinforcement learning, which further boosts model performance. Experiments on two large-scale datasets MIMIC-CXR and IU-Xray demonstrate that our approach outperforms existing state-of-the-art methods, evaluated by both language generation metrics and clinical accuracy.

Improving radiology report generation with multi-grained abnormality prediction

Conventional data-driven approaches for radiology report generation face a problem that the descriptions of the normal regions in the real data are much more than the that for abnormal ones, which potentially leads to the bias of losing focus on abnormalities. Previous work showed promising results owing to the fact that most of the content in reports are described within normal range, which, although fluent, has the limitation of tending to favor the evaluation metrics rather than produce useful hints for human judgment and model learning. To this end, we propose to explicitly predict abnormalities for radiology report generation, following a multi-task learning scheme to drive the model paying more attention on the abnormal regions with multi-grained information, including abnormalities in different granularities, so as to tackle the aforementioned limitation for report generation. In doing so, we propose a disease detector (DD) to identify coarse-grained abnormality, and a medical concept detector (MCD) to associate the predicted disease with the predefined fine-grained pathological concepts. To integrate the information from the proposed abnormality prediction, we design a dual-stream adaptive decoder that takes such information into account with a gate unit controls the integration at each generation step. Extensive experiment results on two widely used benchmark datasets indicate that our method achieves 29.8% and 34.2% performance improvement over the baseline on the natural language generation (NLG) metrics and clinical efficacy (CE) metrics respectively, demonstrate the superiority of the proposed approach.

Merlin: A Vision Language Foundation Model for 3D Computed Tomography.

Over 85 million computed tomography (CT) scans are performed annually in the US, of which approximately one quarter focus on the abdomen. Given the current shortage of both general and specialized radiologists, there is a large impetus to use artificial intelligence to alleviate the burden of interpreting these complex imaging studies while simultaneously using the images to extract novel physiological insights. Prior state-of-the-art approaches for automated medical image interpretation leverage vision language models (VLMs) that utilize both the image and the corresponding textual radiology reports. However, current medical VLMs are generally limited to 2D images and short reports. To overcome these shortcomings for abdominal CT interpretation, we introduce Merlin - a 3D VLM that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining without requiring additional manual annotations. We train Merlin using a high-quality clinical dataset of paired CT scans (6+ million images from 15,331 CTs), EHR diagnosis codes (1.8+ million codes), and radiology reports (6+ million tokens) for training. We comprehensively evaluate Merlin on 6 task types and 752 individual tasks. The non-adapted (off-the-shelf) tasks include zero-shot findings classification (31 findings), phenotype classification (692 phenotypes), and zero-shot cross-modal retrieval (image to findings and image to impressions), while model adapted tasks include 5-year chronic disease prediction (6 diseases), radiology report generation, and 3D semantic segmentation (20 organs). We perform internal validation on a test set of 5,137 CTs, and external validation on 7,000 clinical CTs and on two public CT datasets (VerSe, TotalSegmentator). Beyond these clinically-relevant evaluations, we assess the efficacy of various network architectures and training strategies to depict that Merlin has favorable performance to existing task-specific baselines. We derive data scaling laws to empirically assess training data needs for requisite downstream task performance. Furthermore, unlike conventional VLMs that require hundreds of GPUs for training, we perform all training on a single GPU. This computationally efficient design can help democratize foundation model training, especially for health systems with compute constraints. We plan to release our trained models, code, and dataset, pending manual removal of all protected health information.

CSAMDT: Conditional Self Attention Memory-Driven Transformers for Radiology Report Generation from Chest X-Ray.

A radiology report plays a crucial role in guiding patient treatment, but writing these reports is a time-consuming task that demands a radiologist's expertise. In response to this challenge, researchers in the subfields of artificial intelligence for healthcare have explored techniques for automatically interpreting radiographic images and generating free-text reports, while much of the research on medical report creation has focused on image captioning methods without adequately addressing particular report aspects. This study introduces a Conditional Self Attention Memory-Driven Transformer model for generating radiological reports. The model operates in two phases: initially, a multi-label classification model, utilizing ResNet152 v2 as an encoder, is employed for feature extraction and multiple disease diagnosis. In the second phase, the Conditional Self Attention Memory-Driven Transformer serves as a decoder, utilizing self-attention memory-driven transformers to generate text reports. Comprehensive experimentation was conducted to compare existing and proposed techniques based on Bilingual Evaluation Understudy (BLEU) scores ranging from 1 to 4. The model outperforms the other state-of-the-art techniques by increasing the BLEU 1 (0.475), BLEU 2 (0.358), BLEU 3 (0.229), and BLEU 4 (0.165) respectively. This study's findings can alleviate radiologists' workloads and enhance clinical workflows by introducing an autonomous radiological report generation system.

Improving Radiology Report Generation Quality and Diversity through Reinforcement Learning and Text Augmentation.

Deep learning is revolutionizing radiology report generation (RRG) with the adoption of vision encoder-decoder (VED) frameworks, which transform radiographs into detailed medical reports. Traditional methods, however, often generate reports of limited diversity and struggle with generalization. Our research introduces reinforcement learning and text augmentation to tackle these issues, significantly improving report quality and variability. By employing RadGraph as a reward metric and innovating in text augmentation, we surpass existing benchmarks like BLEU4, ROUGE-L, F1CheXbert, and RadGraph, setting new standards for report accuracy and diversity on MIMIC-CXR and Open-i datasets. Our VED model achieves F1-scores of 66.2 for CheXbert and 37.8 for RadGraph on the MIMIC-CXR dataset, and 54.7 and 45.6, respectively, on Open-i. These outcomes represent a significant breakthrough in the RRG field. The findings and implementation of the proposed approach, aimed at enhancing diagnostic precision and radiological interpretations in clinical settings, are publicly available on GitHub to encourage further advancements in the field.

CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation.

Radiology report generation (RRG) has gained increasing research attention because of its huge potential to mitigate medical resource shortages and aid the process of disease decision making by radiologists. Recent advancements in Radiology Report Generation (RRG) are largely driven by improving a model's capabilities in encoding single-modal feature representations, while few studies explicitly explore the cross-modal alignment between image regions and words. Radiologists typically focus first on abnormal image regions before composing the corresponding text descriptions, thus cross-modal alignment is of great importance to learn a RRG model which is aware of abnormalities in the image. Motivated by this, we propose a Class Activation Map guided Attention Network (CAMANet) which explicitly promotes cross-modal alignment by employing aggregated class activation maps to supervise cross-modal attention learning, and simultaneously enrich the discriminative information. Experimental results demonstrate that CAMANet outperforms previous SOTA methods on two commonly used RRG benchmarks.

TSGET: Two-Stage Global Enhanced Transformer for Automatic Radiology Report Generation

TSGET: Two-Stage Global Enhanced Transformer for Automatic Radiology Report Generation

Bootstrapping Large Language Models for Radiology Report Generation

Radiology report generation (RRG) aims to automatically generate a free-text description from a specific clinical radiograph, e.g., chest X-Ray images. Existing approaches tend to perform RRG with specific models trained on the public yet limited data from scratch, where they often lead to inferior performance owing to the problem of inefficient capabilities in both aligning visual and textual features and generating informative reports accordingly. Currently, large language models (LLMs) offered a promising solution to text generation with their power in learning from big data, especially for cross-modal scenarios such as RRG. However, most existing LLMs are pre-trained on general data, and suffer from the same problem of conventional approaches caused by knowledge gap between general and medical domain if they are applied to RRG. Therefore in this paper, we propose an approach to bootstrapping LLMs for RRG with a in-domain instance induction and a coarse-to-fine decoding process. Specifically, the in-domain instance induction process learns to align the LLM to radiology reports from general texts through contrastive learning. The coarse-to-fine decoding performs a text elevating process for those reports from the ranker, further enhanced with visual features and refinement prompts. Experimental results on two prevailing RRG datasets, namely, IU X-Ray and MIMIC-CXR, demonstrate the superiority of our approach to previous state-of-the-art solutions. Further analyses illustrate that, for the LLM, the induction process enables it to better align with the medical domain and the coarse-to-fine generation allows it to conduct more precise text generation.

Automatic Radiology Reports Generation via Memory Alignment Network

The automatic generation of radiology reports is of great significance, which can reduce the workload of doctors and improve the accuracy and reliability of medical diagnosis and treatment, and has attracted wide attention in recent years. Cross-modal mapping between images and text, a key component of generating high-quality reports, is challenging due to the lack of corresponding annotations. Despite its importance, previous studies have often overlooked it or lacked adequate designs for this crucial component. In this paper, we propose a method with memory alignment embedding to assist the model in aligning visual and textual features to generate a coherent and informative report. Specifically, we first get the memory alignment embedding by querying the memory matrix, where the query is derived from a combination of the visual features and their corresponding positional embeddings. Then the alignment between the visual and textual features can be guided by the memory alignment embedding during the generation process. The comparison experiments with other alignment methods show that the proposed alignment method is less costly and more effective. The proposed approach achieves better performance than state-of-the-art approaches on two public datasets IU X-Ray and MIMIC-CXR, which further demonstrates the effectiveness of the proposed alignment method.

S3-Net: A Self-Supervised Dual-Stream Network for Radiology Report Generation.

Intelligent medicine is eager to automatically generate radiology reports to ease the tedious work of radiologists. Previous researches mainly focused on the text generation with encoder-decoder structure, while CNN networks for visual features ignored the long-range dependencies correlated with textual information. Besides, few studies exploit cross-modal mappings to promote radiology report generation. To alleviate the above problems, we propose a novel end-to-end radiology report generation model dubbed Self-Supervised dual-Stream Network (S3-Net). Specifically, a Dual-Stream Visual Feature Extractor (DSVFE) composed of ResNet and SwinTransformer is proposed to capture more abundant and effective visual features, where the former focuses on local response and the latter explores long-range dependencies. Then, we introduced the Fusion Alignment Module (FAM) to fuse the dual-stream visual features and facilitate alignment between visual features and text features. Furthermore, the Self-Supervised Learning with Mask(SSLM) is introduced to further enhance the visual feature representation ability. Experimental results on two mainstream radiology reporting datasets (IU X-ray and MIMIC-CXR) show that our proposed approach outperforms previous models in terms of language generation metrics.

Beyond images: an integrative multi-modal approach to chest x-ray report generation.

Image-to-text radiology report generation aims to automatically produce radiology reports that describe the findings in medical images. Most existing methods focus solely on the image data, disregarding the other patient information accessible to radiologists. In this paper, we present a novel multi-modal deep neural network framework for generating chest x-rays reports by integrating structured patient data, such as vital signs and symptoms, alongside unstructured clinical notes. We introduce a conditioned cross-multi-head attention module to fuse these heterogeneous data modalities, bridging the semantic gap between visual and textual data. Experiments demonstrate substantial improvements from using additional modalities compared to relying on images alone. Notably, our model achieves the highest reported performance on the ROUGE-L metric compared to relevant state-of-the-art models in the literature. Furthermore, we employed both human evaluation and clinical semantic similarity measurement alongside word-overlap metrics to improve the depth of quantitative analysis. A human evaluation, conducted by a board-certified radiologist, confirms the model's accuracy in identifying high-level findings, however, it also highlights that more improvement is needed to capture nuanced details and clinical context.

Vision-Language Model for Generating Textual Descriptions From Clinical Images: Model Development and Validation Study.

The automatic generation of radiology reports, which seeks to create a free-text description from a clinical radiograph, is emerging as a pivotal intersection between clinical medicine and artificial intelligence. Leveraging natural language processing technologies can accelerate report creation, enhancing health care quality and standardization. However, most existing studies have not yet fully tapped into the combined potential of advanced language and vision models. The purpose of this study was to explore the integration of pretrained vision-language models into radiology report generation. This would enable the vision-language model to automatically convert clinical images into high-quality textual reports. In our research, we introduced a radiology report generation model named ClinicalBLIP, building upon the foundational InstructBLIP model and refining it using clinical image-to-text data sets. A multistage fine-tuning approach via low-rank adaptation was proposed to deepen the semantic comprehension of the visual encoder and the large language model for clinical imagery. Furthermore, prior knowledge was integrated through prompt learning to enhance the precision of the reports generated. Experiments were conducted on both the IU X-RAY and MIMIC-CXR data sets, with ClinicalBLIP compared to several leading methods. Experimental results revealed that ClinicalBLIP obtained superior scores of 0.570/0.365 and 0.534/0.313 on the IU X-RAY/MIMIC-CXR test sets for the Metric for Evaluation of Translation with Explicit Ordering (METEOR) and the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) evaluations, respectively. This performance notably surpasses that of existing state-of-the-art methods. Further evaluations confirmed the effectiveness of the multistage fine-tuning and the integration of prior information, leading to substantial improvements. The proposed ClinicalBLIP model demonstrated robustness and effectiveness in enhancing clinical radiology report generation, suggesting significant promise for real-world clinical applications.

Intensive vision-guided network for radiology report generation

Objective. Automatic radiology report generation is booming due to its huge application potential for the healthcare industry. However, existing computer vision and natural language processing approaches to tackle this problem are limited in two aspects. First, when extracting image features, most of them neglect multi-view reasoning in vision and model single-view structure of medical images, such as space-view or channel-view. However, clinicians rely on multi-view imaging information for comprehensive judgment in daily clinical diagnosis. Second, when generating reports, they overlook context reasoning with multi-modal information and focus on pure textual optimization utilizing retrieval-based methods. We aim to address these two issues by proposing a model that better simulates clinicians perspectives and generates more accurate reports. Approach. Given the above limitation in feature extraction, we propose a globally-intensive attention (GIA) module in the medical image encoder to simulate and integrate multi-view vision perception. GIA aims to learn three types of vision perception: depth view, space view, and pixel view. On the other hand, to address the above problem in report generation, we explore how to involve multi-modal signals to generate precisely matched reports, i.e. how to integrate previously predicted words with region-aware visual content in next word prediction. Specifically, we design a visual knowledge-guided decoder (VKGD), which can adaptively consider how much the model needs to rely on visual information and previously predicted text to assist next word prediction. Hence, our final intensive vision-guided network framework includes a GIA-guided visual encoder and the VKGD. Main results. Experiments on two commonly-used datasets IU X-RAY and MIMIC-CXR demonstrate the superior ability of our method compared with other state-of-the-art approaches. Significance. Our model explores the potential of simulating clinicians perspectives and automatically generates more accurate reports, which promotes the exploration of medical automation and intelligence.