NSTL国家科技图书文献中心

1. A chest imaging diagnosis report generation method based on dual-channel transmodal memory network NSTL国家科技图书文献中心

Dong Z. | Lian J.... - 《Biomedical signal processing and control》 - 2025,100(Feb. Pt.A) - 1.1～1.14 - 共14页

摘要： the proposed network on the IU X-ray and the MIMIC | information load and* workload with low relevance of images* | and texts. Here we propose a chest CT imaging | integrate image and* text feature information, improve the* | relevance of the cross-modal networks and* automatically*

关键词： Automatic report generation | Cross-modal network | Encoderdecoder framework | IU X-ray and MIMIC-CXR | LSTM gate

2. Label correlated contrastive learning for medical report generation NSTL国家科技图书文献中心

Liu, Xinyao | Xin, Junchang ... - 《Computer Methods and Programs in Biomedicine》 - 2025,258 - 108482～108482 - 共12页

摘要： and MIMIC-CXR. Specifically, on IU X-ray dataset | experiments are conducted on widely used datasets, IU X-ray | 0.198 and* 0.392, respectively. On MIMIC-CXR dataset* | Background and* Objective: Automatic generation* | radiologists and* the possibility of errors due to the*

关键词： Medical report generation | Chest X-ray | Attention mechanism | Contrastive learning

3. Data-Efficient Radiology Report Generation via Similar Report Features Enhancement NSTL国家科技图书文献中心

Yanfeng Li | Jinghan Sun ... - 《Applications of Medical Artificial Intelligence》 - International Workshop on Applications of Medical Artificial Intelligence | International Conference on Medical Image Computing and Computer Assisted Intervention - 2025, - 252～262 - 共11页

摘要： MIMIC-CXR and IU X-ray benchmarks with the same | MIMIC-CXR and comparable results on IU-Xray | diagnostic process and* reducing human error. However* | image-report pairs and* generate accurate radiology* | , highlighting not only its effectiveness and* potential to*

关键词： Radiology report generation | Similar reports retriever | Textual features enhancement | Transformer

4. Multi-granularity Semantic Guided Transformer for Radiology Report Generation NSTL国家科技图书文献中心

Yu Song | Xiaojin Hua ... - 《Natural Language Processing and Chinese Computing,Part III》 - CCF International Conference on Natural Language Processing and Chinese Computing - 2025, - 458～472 - 共15页

摘要： generation datasets, COV-CTR, COVID-19 CT, IU X-Ray and | MIMIC-CXR. The experiments show that the SA~3RT model | . Existing approaches based on the Transformer paradigm and | visual representations and* ignores multilevel semantic* | Aware and* Attention Refine Transformer (SA~3RT) model*

关键词： Radiology report generation | Attention | Clustering | Semantic

5. DACG: Dual Attention and Context Guidance model for radiology report generation NSTL国家科技图书文献中心

Lang, Wangyu | Liu, Zhi ... - 《Medical image analysis》 - 2025,99 - 103377～103377 - 共9页

摘要： IU X-ray* and MIMIC-CXR datasets. Further analysis* | radiologists to write radiology reports and* greatly help* | of clinical doctors writing reports and* has* | issues of visual and* textual data bias and long text* | radiological images only account fora small portion, and* most*

关键词： Dual attention | Context guidance | Radiology report generation

6. Toward an enhanced automatic medical report generator based on large transformer models NSTL国家科技图书文献中心

Olanda,Prieto-Ordaz | Graciela,Ramirez-Alo...... - 《Neural computing & applications》 - 2025,37(1) - 43～62 - 共20页

摘要： SOTA methods considering the IU X-ray and MIMIC-CXR | role in primary health care, and* with increasing* | competitive and* state-of-the-art (SOTA) performance. To* | collections are BLEU, METEOR, ROUGE-L, and* CIDEr. ETB-MII* | achieves competitive results across BLEU and* ROUGE-L*

关键词： Medical report generation | Transformer models | Encoder-decoder architecture | Data augmentation

7. HF-CMN: a medical report generation model for heart failure NSTL国家科技图书文献中心

Yan, Liangquan | Zhao, Jumin ... - 《Medical and Biological Engineering and Computing》 - 2025,63(2) - 399～415 - 共17页

摘要： advanced methods on benchmark datasets MIMIC-CXR* and IU X* | with heart failure and* outperforms most other* | -Ray. Further analysis confirms that our method | achieves superior alignment between images and* texts* | Heart failure represents the ultimate stage in

关键词： Radiology report generation | Heart failure | Alignment | Multi-modal

8. Multifocal region-assisted cross-modality learning for chest X-ray report generation NSTL国家科技图书文献中心

Lian J. | Dong Z.... - 《Computers in Biology and Medicine》 - 2024,183 - 109187～109187 - 共6页

摘要： experiments on the IU-Xray and* MIMIC-CXR datasets to* | trainable X-ray* image representation. We then combine our* | cardiovascular disease, tumors, and* other chronic illnesses has* | models and* natural language generation models to* | address the significant visual and* textual disparities*

关键词： Automatic report generation | CLIP | Cross-modal | Encoder–decoder | IU X-ray and MIMIC-CXR

9. Generating Chest Radiology Report Findings Using a Multimodal Method NSTL国家科技图书文献中心

Chenyu Wang | Vladimir Janjic ... - 《Medical Image Understanding and Analysis: 28th Annual Conference, MIUA 2024, Manchester, UK, July 24-26, 2024, Proceedings, Part I》 - Annual Conference on Medical Image Understanding and Analysis - 2024, - 188～201 - 共14页

摘要： on two public datasets, MIMIC-CXR and IU X-ray | Automatic report generation from chest x-ray | imaging (CXR) could potentially alleviate the workload | of radiologists and* improve clinical efficacy. We* | methods, R2Gen and* CvT2DistilGPT2. We report experiments*

关键词： Radiology report generation | Chest x-ray | Convolutional neural network | Transformer | Multimodal learning

10. AERMNet: Attention-enhanced relational memory network for medical image report generation NSTL国家科技图书文献中心

Zeng, Xianhua | Liao, Tianxing ... - 《Computer Methods and Programs in Biomedicine: An International Journal Devoted to the Development, Implementation and Exchange of Computing Methodology and Software Systems in Biomedical Research and Medical Practice》 - 2024,244 - 107979～107979 - 共6页

摘要： Fetal heart (FH), Ultrasound, IU X-Ray and MIMIC-CXR | IU X-Ray, Bleu2 improving by 9.7% on MIMIC-CXR | Background and* objectives: The automatic* | doctors in reducing their workload and* improving the* | efficiency and* accuracy of diagnosis. However, among the*

摘要： the proposed network on the IU X-ray and the MIMIC | information load and* workload with low relevance of images* | and texts. Here we propose a chest CT imaging | integrate image and* text feature information, improve the* | relevance of the cross-modal networks and* automatically*

关键词： Automatic report generation | Cross-modal network | Encoderdecoder framework | IU X-ray and MIMIC-CXR | LSTM gate

摘要： and MIMIC-CXR. Specifically, on IU X-ray dataset | experiments are conducted on widely used datasets, IU X-ray | 0.198 and* 0.392, respectively. On MIMIC-CXR dataset* | Background and* Objective: Automatic generation* | radiologists and* the possibility of errors due to the*

关键词： Medical report generation | Chest X-ray | Attention mechanism | Contrastive learning

摘要： MIMIC-CXR and IU X-ray benchmarks with the same | MIMIC-CXR and comparable results on IU-Xray | diagnostic process and* reducing human error. However* | image-report pairs and* generate accurate radiology* | , highlighting not only its effectiveness and* potential to*

关键词： Radiology report generation | Similar reports retriever | Textual features enhancement | Transformer

摘要： generation datasets, COV-CTR, COVID-19 CT, IU X-Ray and | MIMIC-CXR. The experiments show that the SA~3RT model | . Existing approaches based on the Transformer paradigm and | visual representations and* ignores multilevel semantic* | Aware and* Attention Refine Transformer (SA~3RT) model*

关键词： Radiology report generation | Attention | Clustering | Semantic

摘要： IU X-ray* and MIMIC-CXR datasets. Further analysis* | radiologists to write radiology reports and* greatly help* | of clinical doctors writing reports and* has* | issues of visual and* textual data bias and long text* | radiological images only account fora small portion, and* most*

关键词： Dual attention | Context guidance | Radiology report generation

摘要： SOTA methods considering the IU X-ray and MIMIC-CXR | role in primary health care, and* with increasing* | competitive and* state-of-the-art (SOTA) performance. To* | collections are BLEU, METEOR, ROUGE-L, and* CIDEr. ETB-MII* | achieves competitive results across BLEU and* ROUGE-L*

关键词： Medical report generation | Transformer models | Encoder-decoder architecture | Data augmentation

摘要： advanced methods on benchmark datasets MIMIC-CXR* and IU X* | with heart failure and* outperforms most other* | -Ray. Further analysis confirms that our method | achieves superior alignment between images and* texts* | Heart failure represents the ultimate stage in

关键词： Radiology report generation | Heart failure | Alignment | Multi-modal

关键词： Automatic report generation | CLIP | Cross-modal | Encoder–decoder | IU X-ray and MIMIC-CXR

摘要： on two public datasets, MIMIC-CXR and IU X-ray | Automatic report generation from chest x-ray | imaging (CXR) could potentially alleviate the workload | of radiologists and* improve clinical efficacy. We* | methods, R2Gen and* CvT2DistilGPT2. We report experiments*

关键词： Radiology report generation | Chest x-ray | Convolutional neural network | Transformer | Multimodal learning

摘要： Fetal heart (FH), Ultrasound, IU X-Ray and MIMIC-CXR | IU X-Ray, Bleu2 improving by 9.7% on MIMIC-CXR | Background and* objectives: The automatic* | doctors in reducing their workload and* improving the* | efficiency and* accuracy of diagnosis. However, among the*

关键词： Relational memory | Double LSTM | Interaction | Context information | Medical image report generation

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： the proposed network on the IU X-ray and the MIMIC | information load and workload with low relevance of images | and texts. Here we propose a chest CT imaging | integrate image and text feature information, improve the | relevance of the cross-modal networks and automatically

关键词： Automatic report generation | Cross-modal network | Encoderdecoder framework | IU X-ray and MIMIC-CXR | LSTM gate

摘要： and MIMIC-CXR. Specifically, on IU X-ray dataset | experiments are conducted on widely used datasets, IU X-ray | 0.198 and 0.392, respectively. On MIMIC-CXR dataset | Background and Objective: Automatic generation | radiologists and the possibility of errors due to the

关键词： Medical report generation | Chest X-ray | Attention mechanism | Contrastive learning

摘要： MIMIC-CXR and IU X-ray benchmarks with the same | MIMIC-CXR and comparable results on IU-Xray | diagnostic process and reducing human error. However | image-report pairs and generate accurate radiology | , highlighting not only its effectiveness and potential to

关键词： Radiology report generation | Similar reports retriever | Textual features enhancement | Transformer

摘要： generation datasets, COV-CTR, COVID-19 CT, IU X-Ray and | MIMIC-CXR. The experiments show that the SA~3RT model | . Existing approaches based on the Transformer paradigm and | visual representations and ignores multilevel semantic | Aware and Attention Refine Transformer (SA~3RT) model

关键词： Radiology report generation | Attention | Clustering | Semantic

摘要： IU X-ray and MIMIC-CXR datasets. Further analysis | radiologists to write radiology reports and greatly help | of clinical doctors writing reports and has | issues of visual and textual data bias and long text | radiological images only account fora small portion, and most

关键词： Dual attention | Context guidance | Radiology report generation

摘要： SOTA methods considering the IU X-ray and MIMIC-CXR | role in primary health care, and with increasing | competitive and state-of-the-art (SOTA) performance. To | collections are BLEU, METEOR, ROUGE-L, and CIDEr. ETB-MII | achieves competitive results across BLEU and ROUGE-L

关键词： Medical report generation | Transformer models | Encoder-decoder architecture | Data augmentation

摘要： advanced methods on benchmark datasets MIMIC-CXR and IU X | with heart failure and outperforms most other | -Ray. Further analysis confirms that our method | achieves superior alignment between images and texts | Heart failure represents the ultimate stage in

关键词： Radiology report generation | Heart failure | Alignment | Multi-modal

摘要： experiments on the IU-Xray and MIMIC-CXR datasets to | trainable X-ray image representation. We then combine our | cardiovascular disease, tumors, and other chronic illnesses has | models and natural language generation models to | address the significant visual and textual disparities

关键词： Automatic report generation | CLIP | Cross-modal | Encoder–decoder | IU X-ray and MIMIC-CXR

摘要： on two public datasets, MIMIC-CXR and IU X-ray | Automatic report generation from chest x-ray | imaging (CXR) could potentially alleviate the workload | of radiologists and improve clinical efficacy. We | methods, R2Gen and CvT2DistilGPT2. We report experiments

关键词： Radiology report generation | Chest x-ray | Convolutional neural network | Transformer | Multimodal learning

摘要： Fetal heart (FH), Ultrasound, IU X-Ray and MIMIC-CXR | IU X-Ray, Bleu2 improving by 9.7% on MIMIC-CXR | Background and objectives: The automatic | doctors in reducing their workload and improving the | efficiency and accuracy of diagnosis. However, among the

关键词： Relational memory | Double LSTM | Interaction | Context information | Medical image report generation

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： the proposed network on the IU X-ray and the MIMIC | information load and* workload with low relevance of images* | and texts. Here we propose a chest CT imaging | integrate image and* text feature information, improve the* | relevance of the cross-modal networks and* automatically*

摘要： and MIMIC-CXR. Specifically, on IU X-ray dataset | experiments are conducted on widely used datasets, IU X-ray | 0.198 and* 0.392, respectively. On MIMIC-CXR dataset* | Background and* Objective: Automatic generation* | radiologists and* the possibility of errors due to the*

摘要： MIMIC-CXR and IU X-ray benchmarks with the same | MIMIC-CXR and comparable results on IU-Xray | diagnostic process and* reducing human error. However* | image-report pairs and* generate accurate radiology* | , highlighting not only its effectiveness and* potential to*

摘要： IU X-ray* and MIMIC-CXR datasets. Further analysis* | radiologists to write radiology reports and* greatly help* | of clinical doctors writing reports and* has* | issues of visual and* textual data bias and long text* | radiological images only account fora small portion, and* most*

摘要： SOTA methods considering the IU X-ray and MIMIC-CXR | role in primary health care, and* with increasing* | competitive and* state-of-the-art (SOTA) performance. To* | collections are BLEU, METEOR, ROUGE-L, and* CIDEr. ETB-MII* | achieves competitive results across BLEU and* ROUGE-L*

摘要： advanced methods on benchmark datasets MIMIC-CXR* and IU X* | with heart failure and* outperforms most other* | -Ray. Further analysis confirms that our method | achieves superior alignment between images and* texts* | Heart failure represents the ultimate stage in

摘要： on two public datasets, MIMIC-CXR and IU X-ray | Automatic report generation from chest x-ray | imaging (CXR) could potentially alleviate the workload | of radiologists and* improve clinical efficacy. We* | methods, R2Gen and* CvT2DistilGPT2. We report experiments*

摘要： Fetal heart (FH), Ultrasound, IU X-Ray and MIMIC-CXR | IU X-Ray, Bleu2 improving by 9.7% on MIMIC-CXR | Background and* objectives: The automatic* | doctors in reducing their workload and* improving the* | efficiency and* accuracy of diagnosis. However, among the*