The DOI matches its Crossref record; 27 of the 28 references it cites were found in a registry or an index.
On the Automatic Generation of Medical Imaging Reports
Open accessAbstract
Medical imaging is widely used in clinical practice for diagnosis and treatment.Report-writing can be error-prone for unexperienced physicians, and timeconsuming and tedious for experienced physicians.To address these issues, we study the automatic generation of medical imaging reports.This task presents several challenges.First, a complete report contains multiple heterogeneous forms of information, including findings and tags.Second, abnormal regions in medical images are difficult to identify.Third, the reports are typically long, containing multiple sentences.To cope with these challenges, we (1) build a multi-task learning framework which jointly performs the prediction of tags and the generation of paragraphs, (2) propose a co-attention mechanism to localize regions containing abnormalities and generate narrations for them, (3) develop a hierarchical LSTM model to generate long paragraphs.We demonstrate the effectiveness of the proposed methods on two publicly available datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Recently, deep learning methods have also been used for automated generation of radiology reports , typically incorporating long-short-term-memory (LSTM) network models to generate the textual paragraphs [314, 315, 316, 317], and also to identify findings in radiology reports [318, 319, 320].”
From An overview of deep learning in medical imaging focusing on MRI (2019) · cites this paper as [314]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 5×
“Results in Table 3 show that Ours-CoAttention and VGG-19 [17] network performs very similar for tag prediction.”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“than adopting a single-layer LSTM (Hochreiter and Schmidhuber, 1997), which is less capable of modeling long word sequences, we leverage the compositional nature of the report and adopt a hierarchical LSTM to produce long texts.”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We used the Adam (Kingma and Ba, 2014) optimizer for parameter learning.”
MethodBLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318 · cited 7×
“Note that the only difference between Ours-NoAttention and CNN-RNN [18] in Table 1 is that Ours-NoAttention adopts a hierarchical LSTM decoder while CNNRNN [18] only adopts a single-layer LSTM.”
BackgroundMethodInfluentialLong-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228
CIDEr: Consensus-based image description evaluation
Vedantam, R., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299087 · Cited by 4,845 · cited 2×
“We report the paragraph generation (upper part of Table 1) and one sentence generation (lower part of Table 1) results using the following captioning evaluation tools: BLEU [13], METEOR [4], ROUGE [12] and CIDER [17].”
MethodMeteor Universal: Language Specific Translation Evaluation for Any Target Language
Denkowski, M., & Lavie, A. (2014) · WMT@ACL · doi:10.3115/v1/w14-3348 · Cited by 2,108 · cited 2×
“We report the paragraph generation (upper part of Table 1) and one sentence generation (lower part of Table 1) results using the following captioning evaluation tools: BLEU [13], METEOR [4], ROUGE [12] and CIDER [17].”
MethodImage Captioning with Semantic Attention
You, Q., Jin, H., Wang, Z., Chen, F., & Luo, J. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.503 · Cited by 1,869 · cited 6×
“We first compare our method with several state-of-the-art image captioning models: CNN-RNN [19], LRCN [5], Soft ATT [20], ATT-RK [21].”
BackgroundMethodInfluential
Research works printed but not linked: 2
- Jimmy Ba, Volodymyr Mnih, and Koray Kavukcuoglu. 2015. Multiple object recognition with visual atten- tion. ICLR.
- Chin-Yew Lin. 2004. Rouge: A package for auto- matic evaluation of summaries. In Text summariza- tion branches out: Proceedings of the ACL-04 work- shop, volume 8. Barcelona, Spain.
Cited by
Sorted by citations
Items 201–300 of 429
Topicwise Separable Sentence Retrieval for Medical Report Generation
Zhao, J., Yang, Z., Chen, Z., Fu, H., & Wan, L. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3507076 · Cited by 9
“Previous generation-based works adapt RNN [4], [5] or Transformers [6]–[8] for report generation.”
BackgroundMethodFang, J., Xing, S., Li, K., Guo, Z., Li, G., & Yu, C. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107562 · Cited by 6
Yi, X., Fu, Y., Bi, E., Liang, J., Zhang, H., Yu, J., Li, Q., Hua, R., & Wang, R. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108102 · Cited by 7
EfficienTransNet: An Automated Chest X-ray Report Generation Paradigm
Mondal, C., Pham, D.-S., Gupta, A., Ghosh, S., Tan, T., & Gedeon, T. (2023) · International Workshop on Multimodal and Responsible Affective Computing (MRAC) · doi:10.1145/3607865.3616174 · Cited by 5
Synergy of GPT-3 Summarization and Vision-Encoder-Decoder for Chest X-ray Captioning
Jnaini, A., Shirazi, H. M., & Homayouni, H. (2024) · IEEE Canadian Conference on Electrical and Computer Engineering (CCECE) · doi:10.1109/ccece59415.2024.10667261 · Cited by 5
“The TieNet framework [10], which uses both visual and semantic attention for natural language generation (NLG) on medical datasets, represents a significant advancement in this area.”
BackgroundMethodIntegrating MedCLIP and Cross-Modal Fusion for Automatic Radiology Report Generation
Han, Q., Liu, J., Qin, Z., & Zheng, Z. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825240 · Cited by 6
Context-Guided Medical Visual Question Answering
Arsalane, W., Chikontwe, P., Luna, M., Kang, M., & Park, S. H. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-79103-1_25 · Cited by 5
Privacy-Preserving Chest X-Ray Report Generation via Multimodal Federated Learning with ViT and GPT2
Hossain, M. Z., Ahmed, M., Samu, M. S. S., & Islam, M. R. (2025) · Biomedical Materials & Devices · doi:10.1007/s44174-025-00538-4 · Cited by 6
Pandey, A., Paliwal, B., Dhall, A., Subramanian, R., & Mahapatra, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87444-5_4 · Cited by 5
EDDIE-Transformer: Enriched Disease Embedding Transformer for X-Ray Report Generation
Nguyen, H. T., Nie, D., Badamdorj, T., Liu, Y., Hong, L., Truong, J., & Cheng, L. (2022) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi52829.2022.9761459 · Cited by 6
“However, in radiology, the visual features are often not semantic enough to generate accurate sentences; thus, some works try to co-attend learned visual features and semantic features such as disease tags [1, 12].”
BackgroundInfluentialReport Generation on Chest X-rays using Deep Learning
Kumar, M. A., Ganta, S., & Chinni, G. R. (2023) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs56967.2023.10142637 · Cited by 5
“Jing et al [10] The paper reviews the current techniques for auto creation of reports from diagnostic imaging.”
MethodAttention Enhanced Network with Semantic Inspector for Medical Image Report Generation
Lin, Y., Tang, Q. J., Wang, H., Huang, C., Ekong, F., Wang, X., Xiao, F., & Yu, Y. (2023) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai59109.2023.00043 · Cited by 5
“To solve this challenge,[6, 7] proposed hierarchical LSTM in decoder.”
BackgroundMethodSemantic and Visual Attention-Driven Multi-LSTM Network for Automated Clinical Report Generation
Huang, C., Shen, J., Hu, B., Haqqani, M. A. A., Lee, T. J., Kooner, K., Zhang, N., & Zhang, J. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-63592-2_18 · Cited by 6
Symbiotic Fusion of Evolving Anatomical Landscapes for Intelligent Diagnostic Narratives
Du, H., Zhuang, Y., & Xu, J. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822272 · Cited by 5
Spatial Semantic-Preserving Latent Space Learning for Accelerated DWI Diagnostic Report Generation
Gasimova, A., Seegoolam, G., Chen, L., Bentley, P., & Rueckert, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59728-3_33 · Cited by 5
Intensive vision-guided network for radiology report generation
Zheng, F., Li, M., Wang, Y., Yu, W., Wang, R., Chen, Z., Xiao, N., & Lu, Y. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad1995 · Cited by 5
“(2018) construct a multi-task learning framework which contains a co-attention module and a hierarchical LSTM module to better generate paragraphs of medical reports.”
BackgroundInfluentialMulti-view contrastive learning and symptom extraction insights for medical report generation
Bai, Q., Zou, X., Alhaskawi, A., Dong, Y., Zhou, H., Ezzi, S. H. A., Kota, V. G., AbdullaAbdulla, M. H. H., Abdalbary, S. A., Hu, X., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-00570-w · Cited by 5
Jaiswal, T., Pandey, M., & Tripathi, P. (2025) · IETE Journal of Research · doi:10.1080/03772063.2025.2519536 · Cited by 5
Yin, H., Wu, W., & Hao, Y. (2024) · Electronics · doi:10.3390/electronics13163306 · Cited by 7
Zhu, Z., Cheng, X., Zhang, Y., Chen, Z., Long, Q., Li, H., Huang, Z., Wu, X., & Zheng, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72384-1_29 · Cited by 4
Shu, K., Jia, Y., Zhang, Z., & Gao, J. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822532 · Cited by 4
“Automatic Medical Imaging Narrative generation systems [2], [3] have emerged as a promising solution to assist radiologists by generating textual descriptions directly from radiological images.”
Explainable Medical Image Captioning
Kamal, M. S., Nimmy, S. F., Islam, R., et al. (2025) · doi:10.1145/3701716.3717549 · Cited by 4
VMEKNet: Visual Memory and External Knowledge Based Network for Medical Report Generation
Chen, W., Pan, H., Zhang, K., Du, X., & Cui, Q. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20862-1_14 · Cited by 7
A Systematic Literature Review on Image Captioning
Ding, Y. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-36004-6_54 · Cited by 4
A Doctors Behavior Aware and Domain Knowledge Driven Model for Medical Report Generation
Wang, H., Niu, J., Liu, X., & Wang, Y. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385596 · Cited by 4
Enhanced Knowledge Injection for Radiology Report Generation
Li, Q., Xu, J., Yuan, R., Chen, M., Zhang, Y., Feng, R., Zhang, X., & Gao, S. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385817 · Cited by 6
“It adopts an encoder-decoder structure, composed of a Weighted Concept Knowledge branch and a Multimodal Retrieval Knowledge branch.”
MethodImproving the Factual Correctness of Radiology Report Generation with Semantic Rewards
Delbrouck, J.-B., Chambon, P., Bluethgen, C., Tsai, E., Almusa, O., & Langlotz, C. P. (2022) · arXiv · doi:10.48550/arxiv.2210.12186 · Cited by 63
Zou, Y., & Yin, Z. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00023 · Cited by 4
“…disease classification and report generation, considering the frontal and lateral images from the same patient as two in-181 dependent instances [27], while some studies like [49, 52] argue that lateral images contain complementary information to frontal images that benefit text report…”
Conditional Latent Diffusion Models for Irregularly Spaced Longitudinal Radiological Data
Mouadden, N., Laousy, O., Marini, R., Ong, V., Revel, M., Chassagnon, G., Christodoulidis, S., & Vakalopoulou, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05182-0_11 · Cited by 3
Ren, G., Hou, M., Yang, X., Huang, Y., Li, D., Zhang, N., Liu, P., Ye, H., Chen, Z., & Chen, H. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02044-9 · Cited by 4
“Early works such as Jing et al. ’ s Show, Attend and Tell 25 and CX-Report 26 applied encoder-decoder architectures to generate radiology reports from chest X-rays.”
Wang, J., Fan, J., Zhou, M., Zhang, Y., & Shi, M. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103317 · Cited by 8
Recent advances in artificial intelligence for radiology report generation: a brief review
Tran, C., Pal, B., Stirrat, T., Shi, V., & Umair, M. (2026) · BJR|Artificial Intelligence · doi:10.1093/bjrai/ubag003 · Cited by 4
Automatic medical report generation: a comprehensive review of methodologies and applications
Yan, T., He, H. W., Chan, I. N., Qin, Y. Y., Li, Z., & Wong, P. K. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3474 · Cited by 3
Semantic Feedback-Based RAG for Radiology Report Generation
Jia, X., Xiong, Y., Pei, S., Zhang, Y., Yan, C., & Fang, Z. (2026) · Big Data Mining and Analytics · doi:10.26599/bdma.2025.9020037 · Cited by 4
Helmy, H., Hosseini, A., Ibrahim, A., Mirza, A. B., Sadek, A., & Serag, A. (2026) · Applied Artificial Intelligence · doi:10.1080/08839514.2026.2626117 · Cited by 4
Pan, Y., Sun, G., Zhu, Y., Jiang, H., Shu, H., & Nguyen, L.-M. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3712240 · Cited by 8
“A key advancement was the integration of the attention mechanism [11], which allowed the decoder to dynamically focus on relevant image regions, enhancing report accuracy and providing a degree of interpretability [12], [13].”
Multi-Modal Fusion with Semantic Supervision for Radiology Report Generation
Jia, X., Xiong, Y., Zhang, Y., & Luo, L. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230389 · Cited by 3
Toward Supporting Breast Cancer Diagnosis Based on Captioning Mammogram and Ultrasound Images
Luong, H. H., Nguyen, H. T., & Thai-Nghe, N. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-9616-8_6 · Cited by 3
Toward an enhanced automatic medical report generator based on large transformer models
Prieto-Ordaz, O., Ramírez-Alonso, G. M. D. J., Montes-y-Gómez, M., & López, R. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10382-0 · Cited by 5
“For example, the study of Jing, Xie, and Xing [27] employed a sequential structure that uses two models to address the task.”
Rethinking Radiology Report Generation via Causal Inspired Counterfactual Augmentation
Song, X., Liu, J., Liu, Y., Li, Y., Lei, W., & Wang, R. (2024) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3698587.3701353 · Cited by 3
“Therefore, the previous works proposed to use HLSTM [16] that hierarchically generate the topics and sentences with two LSTM layers [12, 19, 21, 26, 35], or employed the long-term memory ability of Transformer [29] model to directly produce a long paragraph [6, 10, 11, 18, 28].”
ADCNet: Anomaly-Driven Cross-Modal Contrastive Network for Medical Report Generation
Liu, Y., Zhang, J., Liu, K., & Tan, L. (2025) · Electronics · doi:10.3390/electronics14030532 · Cited by 3
Artificial Intelligence in Oral Health
Binod, H., Shithij, T., Tichý, A., et al. (2025) · Springer eBooks · doi:10.1007/978-3-031-84047-0_1 · Cited by 3
Diagnostic Captioning by Cooperative Task Interactions and Sample-Graph Consistency
Wang, Z., Wang, L., Li, X., & Zhou, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3562866 · Cited by 4
MvKeTR: Chest CT Report Generation With Multi-View Perception and Knowledge Enhancement
Deng, X., He, X., Bao, J., Zhou, Y., Cai, S., Cai, C., & Chen, Z. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3581289 · Cited by 9
“Motivated by the success of encoder-decoder architecture in image captioning, recent SOTA studies [27], [28], [29], [30] have all utilized this framework to produce medical reports combined with a visual extractor.”
APNet: Semantic Segmentation for Pelvic MR Image
Liang, T., Sun, M., Gao, L., Lu, J., & Tsutsui, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03335-4_23 · Cited by 3
“Jing et.al [10] propose an attention mechanism that learns the weights of both visual and semantic features, to define abnormal locations in medical images and generate relevant description sentences.”
BackgroundMethodReview on Automated Report Generation Methods for Enterprises
冯, 灿. (2022) · Computer Science and Application · doi:10.12677/csa.2022.1210236 · Cited by 3
Deep Learning based Automatic Radiology Report Generation
Kumar, M., Panitini, M., Vemulapalli, S., & Sai, M. J. N. V. (2023) · International Conference on Artificial Intelligence and Smart Energy (ICAIS) · doi:10.1109/icais56108.2023.10073691 · Cited by 3
CMT: Cross-modal Memory Transformer for Medical Image Report Generation
Cao, Y., Cui, L., Zhang, L., Yu, F., Cheng, Z., Li, Z., Xu, Y., & Miao, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30675-4_30 · Cited by 7
Enhancing Chest X-ray Analysis using Encoder-Decoder with GRU for Report Generation
Pandey, S., Saha, P., Sharan, G., et al. (2024) · International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) · doi:10.1109/icaect60202.2024.10469644 · Cited by 3
“Liao et al. [1]: The study introduces a recurrent neural network (RNN)-based method for radiology report captioning, showing notable superiority over traditional bag-of-words models.”
MethodTransformer-Based Chest X-ray Report Generation Model
Shaikh, Z. A., & Bharti, J. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-8628-6_20 · Cited by 3
IFNet: An Image-Enhanced Cross-Modal Fusion Network for Radiology Report Generation
Guo, Y., Hou, X., Liu, Z., & Zhang, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5128-0_23 · Cited by 3
Comprehensive Review on Natural Language Generation for Automated Report Writing in Finance
Abbas, S., Pal, B. L., Ajay, S., et al. (2024) · British Journal of Computer Networking and Information Technology · doi:10.52589/bjcnit-elbol7ty · Cited by 3
“Similarly, in 2018, Jing et al. (2018) introduced deep learning methods to help generate medical diagnosis reports and reduce the workload of medical professionals.”
BackgroundA Multi-Modal Feature Fusion-Based Approach for Chest X-Ray Report Generation
Cheddi, F., Habbani, A., & Nait‐Charif, H. (2024) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom62286.2024.10657835 · Cited by 3
“Current methods typically use an encoder-decoder model [5] [6], where the encoder utilizes convolutional neural networks (CNN) to extract visual features from the radiology image, while the decoder employs recurrent neural networks (RNN) to produce text descriptions for the reports.”
MethodMachine Learning Solutions in Smart Healthcare
Patel, V., Chaurasia, V., Siddiqui, E. A., Patole, S. P., & Mahadeva, R. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-4326-5.ch013 · Cited by 3
Optimizing medical image report generation through a discrete diffusion framework
Sun, S., Su, Z., Meizhou, J., Feng, Y., Hu, Q., Luo, J., Hu, K., & Yang, Z. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07111-2 · Cited by 4
“Further advancements, including hierarchical attention mechanisms [6] and Hierarchical Recurrent Neural Networks (HRNNs) [7], improved the quality and structure of generated reports.”
An image selection framework for automatic report generation
Hyun, C., Hur, C., & Park, H. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13120-7 · Cited by 3
“Owing to such demand, methodological studies on extracting core and meaningful information from data [22, 38], and application studies such as automatic report generation using various types of data are being conducted [11].”
BackgroundImproving Radiology Report Generation with Adaptive Attention
Wang, L., & Chen, J. (2022) · Studies in computational intelligence · doi:10.1007/978-3-031-14771-5_21 · Cited by 3
Vision-Language Transformer Framework for Automated Medical Imaging Reporting
Duong, V.-H., Tran, M.-Q., Nguyen, N.-K., Pham, D. H.-H., Bui, M.-Q., & Lai, D.-T. (2025) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr67746.2025.11133782 · Cited by 2
“Early approaches primarily employed Convolutional Neural Networks (CNNs) for visual feature extraction and Recurrent Neural Networks (RNNs), such as Long Short-Term Memory (LSTM), for generating descriptive sentences [1].”
Wang, J., Zhu, L., Bhalerao, A. H., & He, Y. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102644 · Cited by 5
Izhar, A., Japar, N. B., Idris, N. B., & Dang, T. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228227 · Cited by 8
“The PGROSS dataset [27] contains descriptions from the Gross sub-collection of the PEIR digital library, totaling 7,442 image-caption pairs with associated tags.”
Frontier of Smart Healthcare Engineering Management
Ding, S., Wu, D. D., Zhao, L., & Li, X. (2022) · AI for risks · doi:10.1007/978-981-19-2560-3_2 · Cited by 2
A survey of medical image captioning technique： encoding， decoding and latest advance
Zhu, Y., & Li, X. (2023) · Journal of Image and Graphics · doi:10.11834/jig.211021 · Cited by 2
Radiology Report Generation via Visual Recalibration and Context Gating-Aware
Hou, X., Sang, G., Liu, Z., Li, X., & Zhang, Y. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-7074-2_9 · Cited by 4
Automatic Generation of Discharge Summary of EMRs Based on Multi-granularity Information Fusion
Zhao, B., Zan, H., Niu, C., Chang, H., & Zhang, K. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9864-7_17 · Cited by 2
GHCL: Gaussian heuristic curriculum learning for Brain CT report generation
Shen, Q., Shi, Y., Zhang, X., Ji, J., Liu, Y., & Xu, H. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01266-3 · Cited by 2
Automatic Medical Report Generation Based on Detector Attention Module and GPT-Based Word LSTM
Gu, Y., Sun, J., Wang, X., Li, R., & Zhou, Z. (2024) · International Conference on Data-driven Optimization of Complex Systems (DOCS) · doi:10.1109/docs63458.2024.10704337 · Cited by 4
“Jing et al. [3] utilized Convolu-tional Neural Networks (CNN) to extract visual features and lesion semantic features for generating medical reports.”
BackgroundMethodInfluentialDesign as Desired: Utilizing Visual Question Answering for Multimodal Pre-training
Su, T., Li, J., Zhang, X., Jin, H., Chen, H., Wang, Q., Lv, F., Zhao, B., & Hu, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72083-3_56 · Cited by 2
Sequence-Integrated Radiology Report Generation Leveraging Positional Encoding for Text and Images
Pan, Y., Li, K., Wu, J., Shu, H., Shao, F., Xin, J., & Sun, G. (2024) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/cyberscitech64112.2024.00085 · Cited by 2
“A joint attention mechanism has been proposed to explore both text and image information simultaneously through a multitask learning framework [1].”
Denoising Multi-Level Cross-Attention and Contrastive Learning for Chest Radiology Report Generation
Zhu, D., Liu, L., Yang, X., Liu, L., & Peng, W. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01422-9 · Cited by 2
“Existing chest radiology report generation models mostly utilize an encoder-decoder framework [1–3], with CNNs [4] and vision transformers [5] serving as encoders for visual feature extraction.”
Analyzing the Vulnerability of Cyber-Attacks in IoMT Devices Using Generative AI
Yadav, L., & Sharma, V. (2025) · Studies in big data · doi:10.1007/978-3-031-75095-3_24 · Cited by 2
IMGEF: integrated multimodal graph-enhanced framework for radiology report generation
Usman, M., Hou, X., Guo, Y., Liang, Z., & Yijia, Z. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01858-7 · Cited by 2
“• COATT [43]: The co-attentive mechanism detects images and features simultaneously with hierarchical LSTM to model long-term dependencies.”
Coherent Medical Report Generation from Chest Radiographs with Weighted Localized Features
Reddy, P. C., Thota, G., Alupula, P., Nagaraju, K., & Korra, S. B. (2025) · International Conference on Recent Advances in Information Technology · doi:10.1109/rait65068.2025.11089157 · Cited by 2
“One of the earliest studies in this domain laid the groundwork for developing automatic imaging report generation using deep learning [17].”
KdINet: Knowledge-driven Interpretable Network for Medical Imaging Diagnosis
Cao, Y., Cui, L.-Z., Zhang, L., Yu, F., Li, Z., Xu, Y., & Miao, C. (2022) · IEEE International Conference on Bioinformatics and Biomedicine · doi:10.1109/bibm55620.2022.9995345 · Cited by 1
“4) Baselines: To compare with our KdINet, the following methods are used as the main baselines for disease classification tasks: SaT [14], CoAtt [15], RGKG [6], and PPKED [16].”
MethodA Generalized Deep Learning Model for Multi-disease Chest X-Ray Diagnostics
Bajwa, N., Bajwa, K., Shakeel, M. F., Rana, A. I., Haqqi, K., & Khan, S. A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43085-5_43 · Cited by 3
“These works ranged from developing different architectures for single and multiple disease detection 14 , to localizing 15 and even partially writing the radiology reports using recurrent neural networks 16 .”
BackgroundSIG-Former: monocular surgical instruction generation with transformers
Zhang, J., Nie, Y., Chang, J. M., & Zhang, J. (2022) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02718-9 · Cited by 2
Improving Radiology Report Generation via Object Dropout Strategy and MLP-based Captioner
Chen, Z., & Tang, Y. (2022) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec55388.2022.10019809 · Cited by 3
“To solve this problem, Jing et al. [21]proposed a Co-Attention mechanism that cooperated with the hierarchical LSTM structure.”
BackgroundNishino, T. (2023) · Journal of Natural Language Processing · doi:10.5715/jnlp.30.250 · Cited by 2
Attention-based Generative Adversarial Network in Medical Imaging: A Review (Preprint)Preprint
Zhao, J., Hou, X., Pan, M., et al. (2022) · doi:10.2196/preprints.38410 · Cited by 2
Trust it or Not: Confidence-Guided Automatic Radiology Report GenerationPreprint
Wang, Y., Lin, Z., Xu, Z., Dong, H., Luo, J. D., Tian, J., Shi, Z., Zhang, Y., Jianping Fan, B., & He, Z. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4482859 · Cited by 2
Segundo, L. B. D. S., Teixeira, V., Pedrini, H., & Dias, Z. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-65775-8_14 · Cited by 1
Adversarial Training with Comprehensive Objective for Medical Image Report Generation
Zhang, X., & Liu, J. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385588 · Cited by 1
“Current methods [1]–[5], limited by uneven image quality, only detect anomalies based on the image, leading to inconsistent performance.”
BackgroundMethodInfluentialFgKF: Fine-Grained Knowledge Fusion for Radiology Report Generation
Zhang, K., Huang, X., Zan, H., Ma, Y., Gao, Q., & Li, Y. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9864-7_16 · Cited by 2
Enhancement of medical report generation by multi-scale image deblurring strategy
Wang, Y., Du, Y., & Tang, S. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650006 · Cited by 2
Lo, C., & Chen, H.-R. (2024) · Health Informatics Journal · doi:10.1177/14604582241288460 · Cited by 1
Automatic Radiology Report Generation: Approaches and Insights
Khairnar, N. S., & Sane, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-7710-5_28 · Cited by 1
Agarwal, S., Yashwanth, D., Arya, K. V., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-3859-5_7 · Cited by 1
Elgayar, S., Hamad, S. H., & El-Horbaty, E.-S. M. (2024) · International Conference on Computer Theory and Applications (ICCTA) · doi:10.1109/iccta64612.2024.10974869 · Cited by 1
“Writers[5] has proposed filling in text templates for bone fractures that were produced by and recognized in the X-ray bone medical images, while a multi-task framework that combines co-attention to create texts and forecast tags has been proposed by the authors[6].”
RMPT: Reinforced Memory-Driven Pure Transformer for Automatic Chest X-Ray Report Generation
Qin, C., Xiong, Y., Chen, W., & Li, Y. (2025) · Mathematics · doi:10.3390/math13091492 · Cited by 1
Artificial intelligence assisted ultrasound report generation
Zeng, J., Zhao, K.-K., & Zhao, N. (2025) · Artificial Intelligence in Medical Imaging · doi:10.35711/aimi.v6.i1.107069 · Cited by 2
Joint Imbalance Adaptation for Radiology Report Generation
Li, W., Han, G., Wu, Y., Huang, I., & Huang, X. (2025) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-025-00205-9 · Cited by 1
“Radiology report generation is a multimodal and medical image-to-text task that generates text descriptions for radiographs (e.g., X-ray or CT scan), which may reduce the workloads of radiolo-031 gists (Jing et al., 2018, 2019).”
BackgroundAdapting Vision Language Models for Structured Clinical Description Generation in Mammography
Castro, A. C., Rodrigues, D., & Filho, A. R. G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05559-0_24 · Cited by 1
Feng, W., Yazdani, A., Bornet, A., et al. (2025) · BMJ Open · doi:10.1136/bmjopen-2025-104112 · Cited by 1
“15 16 Despite promising advancements in current research, generating clinically readable and interpretable radiology reports with complex, lengthy structures using AI remains a significant challenge.”
Graph-Driven Medical Report Generation with Adaptive Knowledge Distillation
Chen, J., Huang, X., Jiang, M., Li, Y., Zou, Z., & Qian, D. (2025) · Applied Sciences · doi:10.3390/app152010974 · Cited by 1
GlaLSTM: A Concurrent LSTM Stream Framework for Glaucoma Detection via Biomarker Relationship Mining
Huang, C., Xie, W., Lee, T. J., et al. (2025) · doi:10.1109/embc58623.2025.11254836 · Cited by 1
“To further refine this approach, multimodal data fusion is employed to enhance biomarker representation, and an attention mechanism [6], [32] is utilized to dynamically assess the relative importance of different biomarkers in glaucoma detection.”
A hybrid transformer architecture with Mamba for medical image report generation
Yang, R., & Li, F. Q. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02103-x · Cited by 1
Haghighi, T., Gholami, S., Sokol, J. T., Biswas, A., Lim, J. I., Leng, T., Thompson, A. C., Tabkhi, H., & Alam, M. N. (2025) · Communications Medicine · doi:10.1038/s43856-025-01293-9 · Cited by 1
“Natural language summaries render AI outputs more interpretable and actionable 19 – 21 .”
Enhanced Feature Set Integration for Automated Radiology Report Generation
Prasika, L., Subiksha, M. M., & Monica, G. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-10667-4_10 · Cited by 1
Review of generative AI for lesion localization and automatic report generation
Sun, K., Wang, Y., Huang, S., Liu, Y., Chen, H., Lian, Z., Tan, M., Lin, X., Zhou, W., Qiu, Z., et al. (2026) · Med-X · doi:10.1007/s44258-026-00076-8 · Cited by 1
“A fundamental challenge in developing reliable models for lesion-aware report generation is the long-tail distribution of clinical data [254].”
R2GenCSR: Mining Contextual and Residual Information for LLMs-Based Radiology Report Generation
Wang, X., Li, Y., Wang, F., Wang, S., Li, C., & Jiang, B. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2026.3669539 · Cited by 28
“Jing et al. [22] propose to predict the possible diseases using LSTM [17] and then generate medical reports based on those predictions.”
MGK-RAG: Multi-Granularity Knowledge Guided Retrieval-Augmented Generation for Radiology Report
Ma, J., Yue, X., Chen, Y., Shi, J., Wei, Z., & Jia, Z. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792924 · Cited by 1
“Earlyend-to-end generative models, from CNN-RNN [8] and R2Gen [3] to recent LLM-based architecture [17], have improved report fluency but still produce factually inaccurate reports, which are unacceptable in clinical settings [11, 12].”
Metadata
- Authors
- Jing, B., Xie, P., & Xing, E.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2018
- Pages
- 2577-2586
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2770165365
- Cited by
- 657
- References
- 28
- Citations by year
- 2026: 57 · 2025: 123 · 2024: 115 · 2023: 111 · 2022: 80 · 2021: 81 · 2020: 45 · 2019: 34 · 2018: 11
- FWCI
- 12.69
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- multi-task learning, co-attention, hierarchical LSTM, tag prediction, clinical report writing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
