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 301–400 of 429
Artificial Intelligence Across the Radiology Workflow: A Nine-Stage Narrative Review
Rai, M. C. E., Far, A. B., Darweesh, M., Dhou, S., Aburaed, N., El, S., Elkhazendar, M., & Ellahham, S. (2026) · Diagnostics · doi:10.3390/diagnostics16101485 · Cited by 1
“Multimodal strategies combined imaging and clinical information through image plus history models [141], multimodal attention RNNs [142], retrieval generation agents [143], and CNN RNN systems [144].”
EviRAG: Evidence-Guided Retrieval-Augmented Generation for Medical Vision-Language Models
Gu, Y., Fan, J., Liu, K., Wu, B., Chen, B., Liu, Z., Xiao, Z., Tu, R.-C., Luo, X., & Zhang, M. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809930 · Cited by 1
“Automatic radiology report generation aims to produce clinically faithful textual descriptions grounded in medical images [4, 13].”
Deep Learning for Lung Disease Detection from Chest X-Rays Images
Jangam, E., Annavarapu, C. S. R., & Elloumi, M. (2021) · Springer eBooks · doi:10.1007/978-3-030-71676-9_10 · Cited by 1
Automatic Report Generation based on Multi-modal and Multi-view Model for Fundus Images
Lan, S., Zhou, C., Chen, L., Fan, H., Yan, N., & Huang, Y. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669471 · Cited by 3
“According to [3], we set λ tag = 1 .”
BackgroundMethodInfluentialEvolution of AI in Medical Imaging
Schaefferkoetter, J. D. (2022) · Springer eBooks · doi:10.1007/978-3-031-00119-2_4 · Cited by 1
Generating Lymphoma Ultrasound Image Description with Transformer Model
Chen, D., Zhang, C., & Dong, Y. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-5096-4_17 · Cited by 1
Automatic Report Generation Method based on Multiscale Feature Extraction and Word Attention Network
Du, X., Pan, H., Zhang, K., He, S., Bian, X., & Chen, W. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25198-6_40 · Cited by 3
Tang, Y., He, Z., Wu, Q., et al. (2023) · Applied Sciences · doi:10.3390/app13137981 · Cited by 1
Si, J., Zhao, H., Huang, L., & Tu, Z. (2023) · International Conference on Intelligent Medicine and Image Processing (IMIP) · doi:10.1109/imip57114.2023.00022 · Cited by 1
“On both datasets, we compare our proposed method with several state-of-the-art image captioning models [32, 33, 28, 34, 5, 35].”
BackgroundMethodDeep understanding of radiology reports: leveraging dynamic convolution in chest X-ray images
Jaiswal, T., Pandey, M., & Tripathi, P. (2023) · Data Technologies and Applications · doi:10.1108/dta-07-2023-0307 · Cited by 3
Tang, W., Pei, C., Yu, P., Zhang, H., Min, X., Chen, C., Han, K., Xu, W., & Zhang, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47401-9_8 · Cited by 1
Enhancing Medical Report Generation in Multi-Slice Fusion Scenarios
Bu, S., Li, T., & Dai, Z. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385537 · Cited by 1
Prior tissue knowledge-driven contrastive learning for brain CT report generation
Shi, Y., Ji, J., Zhang, X., Liu, Y., Wang, Z., & Xu, H. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01289-w · Cited by 2
TinyCheXReport: Compressed deep neural network for Chest X-ray report generation
Alotaibi, F. S., Alyoubi, K. H., Mittal, A., Gupta, V., & Kaur, N. (2024) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3676166 · Cited by 1
“In addition to visual features, Jing et al. [10] used semantic features as well.”
Automatic Radiology Report Generation: A Comprehensive Review and Innovative Framework
Hamma, M. B., Merrouni, Z. A., Frikh, B., & Ouhbi, B. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10821974 · Cited by 1
“There are two modified branches of CNN-RNN architectures which are CNN-HRNN 1 [13], [21] and CNN-SRNN 2 [14].”
Ma, X., Kuang, Y., Yuan, L., Cheng, T., Zeng, Y., & Liu, S. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10832064 · Cited by 1
A Novel Transformer-Based Framework for Chest X-Ray Captioning with Clinical Sign Detection
Tran, T. T., Nguyen, D. V. M., & Huynh, H. T. (2025) · SN Computer Science · doi:10.1007/s42979-025-04032-y · Cited by 2
Automatic Radiology Report Generation Based on State-Space Model
Zhang, D., Tan, Y., Qin, J., & Xiang, X. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3579888 · Cited by 3
“The proposed method is compared with previous state-of-the-art (SOTA) models, such as COATT [35], R2Gen [8], PPKED [18], R2GenCMN [20], KEMMRG [36], AS-GMD [9], DEKG [26], MAMRG [21], MiniGPT-4-RRG [22], MDAKF [37] and SERPENT-VLM [38].”
Izhar, A., Idris, N. B., & Japar, N. B. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105603 · Cited by 1
Yang, H., Tang, H., Song, S., & Li, X. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3589103 · Cited by 4
“Consequently, numerous deep learning-based approaches have been developed in recent years to address the challenges associated with RRG. Previous works in RRG [2], [3], [4] have typically adopted the image captioning paradigm [5], [6], [7] due to the similarities between the tasks.”
Extractive Radiology Reporting With Memory-Based Cross-Modal Representations
Tian, Y., Yan, Z., Lyu, N., & Song, Y. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3636868 · Cited by 1
“Typically, in practice, each sentence in a radiology report independently describes a specific observation [2], [3], [4], resulting in low inter-sentence dependency where the overall meaning of the report remains the same even when the order of the sentences changes.”
A Hierarchical Approach for Joint Extraction of Entities and Relations
Xiao, S., Zhang, Q., Sun, J., Wang, Y., & Zhang, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72113-8_47 · Cited by 1
Machine Interpretation of Medical Images Using Deep Learning
Chhatbar, V., Gondhalekar, M., Pimple, S., & Pawar, R. (2021) · IEEE Global Conference for Advancement in Technology (GCAT) · doi:10.1109/gcat52182.2021.9587518 · Cited by 1
Artificial Intelligence in Gastroenterology
Strümke, I., Hicks, S. A., Thambawita, V. L., et al. (2022) · Artificial Intelligence in Medicine · doi:10.1007/978-3-030-64573-1_163 · Cited by 1
Abela, B., Abu-Khalaf, J., Yang, C.-W. R., Mašek, M., & Gupta, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-22695-3_37 · Cited by 2
Feng, W., Yazdani, A., Bornet, A., et al. (2025) · medRxiv · doi:10.1101/2025.03.17.25324103 · Cited by 1
Extending Chest X-Ray with Multi Label Disease Sequence
Zheng, A., Bai, C., & Liu, N. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-1194-0_19
Artificial Intelligence in Gastroenterology
Strümke, I., Hicks, S. A., Thambawita, V. L., Jha, D., Parasa, S., Riegler, M. A., & Halvorsen, P. (2021) · Springer eBooks · doi:10.1007/978-3-030-58080-3_163-2
Medical Scene Graphs and Reasoning
Cao, C., He, Y., Chen, Y., et al. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669882
“Automatic medical report generation is of great value in the medical field [1], [2].”
BackgroundBaselines for Automatic Medical Image Reporting
Cardillo, F. A. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-29717-5_4
MedNet: A Dual-Copy Mechanism for Medical Report Generation from Images
Nie, P. C., & Liu, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44210-0_38
MeFormer: Generating Radiology Reports via Memory Enhanced Pretraining Transformer
Li, F., Wang, P., Lin, K., & Wang, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35415-1_6 · Cited by 1
Enriching Semantic Features for Medical Report Generation
Luan, Q., Pan, H., Zhang, K., Shi, K., & Jia, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44696-2_37 · Cited by 1
Adaptively Multi-Objective Adversarial Training for Medical Image Report Generation
Zhang, X., & Liu, J. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10386004
“It requires the model to use longer text to more fully describe the rich content of the image, and focus on describing local anomalies in the visual image [1], [2], [5], [7]–[10].”
MethodInfluentialAutomatic Detection of Disorder and Report Generation from MRI Scans
Kodmurgi, P. S., Bonthala, S., Supreeth, N. P., et al. (2024) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi60426.2024.10502739
“A novel method for automated report production utilizing a combination of CNN and LSTM networks is presented by Jing et al. [4].”
MethodChai, L., Qi, L., Sun, H., & Li, J. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00032
“As a representative multimodal task, image captioning [4] has become a core research topic for various applications in high-stake domains, such as medical report generation [5], visually impaired assistance [6], and anomaly detection [7].”
BackgroundSimilarity Retrieval and Medical Cross-Modal Attention Based Medical Report Generation
Dong, X., Pan, H., Lan, H., Zhang, K., & Chen, C. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7232-2_12
Visual Presentation Learning with Contrastive Learning for Radiology Report Generation
Yu, L., Wang, X., Ma, C., & Deng, B. (2024) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3669754.3669760
“Jing et al. [8] employed a joint attention model that simultaneously focuses on visual and semantic features.”
DMR$$^2$$G: diffusion model for radiology report generation
Ouyang, H., Chang, Z., Tang, B., & Li, S. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20206-x · Cited by 1
“Notably, [7] leveraged CNNs for feature extraction and HRNNs [8] for report generation, while CMAS [4] employed dual RNNs to enhance sentence accuracy in reports.”
Multi-granularity Semantic Guided Transformer for Radiology Report Generation
Song, Y., Hua, X., Zhang, K., Zan, H., & Li, R. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9437-9_36
Tubaishat, A., Zia, T., Windridge, D., Nawaz, M., & Razzaq, S. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10640-1
“Third, while these systems perform well on descriptive accuracy metrics, they may lack completeness, consistency, and clinical accuracy [5, 8].”
Fan, Y., & Wang, S. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-5181-5_9
TGMT: A Terminology-Guided Multi-Task Approach for Lung Cancer CT Report Generation
Su, H. F., Liu, B., Zhu, X., Lü, X., Wu, N., & Hu, D. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10781518
“Some studies also the adopted attention mechanism to gain better connections between image features and report descriptions to improve the report generation performance [8]–[10].”
Li, R., Yue, M., Jin, X., & Wang, Y. (2024) · IEEE International Conference on Medical Artificial Intelligence (MedAI) · doi:10.1109/medai62885.2024.00056 · Cited by 1
GIT-CXR: End-to-End Transformer for Chest X-Ray Report GenerationPreprint
Sîrbu, I., Sîrbu, I.-R., Bogojeska, J., & Rebedea, T. E. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.02598 · Cited by 2
“While recent advances in image captioning, such as CNN encoders paired with RNN decoders (Jing et al., 2017; Li et al., 2018) and transformers integrated with complex modules (Cao et al., 2023), have shown promise, generating accurate medical reports from images remains an unresolved challenge,…”
Radiographic Reports Generation via Retrieval Enhanced Cross-modal Fusion
Hou, X., Luo, Y., Song, W., Guo, Y., You, W., & Li, S. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10821990
“To overcome this limitation, Co-Att [8] introduced a co-attention mechanism to localize abnormal regions, coupled with a hierarchical LSTM model designed to generate long, coherent paragraphs.”
Reinforcement Learning for Improved Alignment in Radiology Reports Generation
Shao, Y., Xu, R., Tan, C., Liu, G., Fang, T., & Huo, H. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10864815
“Most existing models adopt the standard image captioning methods [4] [5] and utilize an encoder-decoder framework [6] [7].”
InfluentialRadiology Report Generation Based on Multi-Scale Feature Fusion and Enhancement
Cao, Y., Ding, H., Li, B., Sun, X., She, Q., & Rahman, M. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_3
A Review of Automated Report Generation Technologies for Ophthalmic Medical Imaging
Zheng, Y., & Su, P. (2025) · Scientific Journal of Technology · doi:10.54691/0xcw7739
“Recent research in automatic radiology report generation models has made significant strides [1][2][3][4][5].”
A Label-focused Transformer for Generating Illness-aware Medical Reports
Zhou, S., & Bie, H. (2024) · IEEE Smart World Congress (SWC) · doi:10.1109/swc62898.2024.00228
“Works by Jing et al., 2018 [6] ; Wang et al., 2018 [7] ; Li et al., 2018 [8] ; Liu et al., 2019 [9] have suggested utilizing a hierarchical co-attention CNN-RNN model enhanced with multitask learning for the generation of radiology narratives and the classification of disease labels.”
CTGLM: A Vision-Language Model for Automated Chinese Chest CT Report Generation
Zhang, K., Li, Y., Gao, Q., Huang, X., Hua, X., & Li, R. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-3755-3_11
A Benchmark for Multi-Task Evaluation of Pretrained Models in Medical Report Generation
Lin, R., Li, C., & Wang, R. (2025) · BIO Web of Conferences · doi:10.1051/bioconf/202517403010
“Designed to automatically produce accurate and coherent reports that detail the impressions and observations derived from medical images [2-4], effective MRG can significantly alleviate the diagnostic workload for physicians, decrease patient waiting time, and enhance the practical application of…”
Hybrid Attention-Based Stacked Bi-LSTM Model for Automated MultiImage Captioning
Ravinder, P., & Srinivasan, S. (2025) · Journal of Computer Science · doi:10.3844/jcssp.2025.883.904
“(Singh et al ., 2023) Open-i chest X-ray dataset 57.70 95.20 CNN-RNN (Singh et al ., 2023) Open-i chest X-ray dataset 51.10 81.20 DenseNet-201 (Singh et al ., 2023) Open-i chest X-ray dataset 57.40 93.80 HLSTM (Jing et al ., 2017) IU X-Ray 51.70 - HLSTM (Jing et al ., 2017) PEIR 30 - Language model (Approach 1) (Seliv…”
InfluentialUtilizing Transformer-Based Image Descriptors for Improving Chest X-Ray Analysis
Agarwal, L., & Verma, B. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-2647-2_40
Leveraging an Image-Enhanced Cross-Modal Fusion Network for Radiology Report Generation
Guo, Y., Hou, X., Liu, Z., & Zhang, Y. (2025) · Journal of Computational Biology · doi:10.1177/15578666251365959
“Many recent works have followed the encoder – decoder paradigm similar to image captioning tasks (Jing et al., 2018).”
Zhao, H., Xu, Z., & Ren, T. (2025) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai65741.2025.11108454
“For instance, the work by Jing et al. [10] introduced a multi-task learning paradigm designed to concurrently produce medical image reports and identify relevant medical tags, employing a co-attention mechanism to aid in localizing abnormalities within the images.”
Zhao, H., Ai, X., Li, W., et al. (2025) · International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML) · doi:10.1145/3748382.3748390
Soliman, A., Yaacoub, E. E., Mohamed, A. M. S., & Erbad, A. (2025) · International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets65254.2025.11106784
“This technology can reduce this labor-intensive report generation process for radiologists and help facilitate automation in healthcare [6].”
Shen, T., Teng, Z., & Zhang, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04555-3_13
Xu, H., Sowmya, A., Katz, I. A., & Wang, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04971-1_60
KECAN: knowledge-enhanced cross-modal alignment network for ophthalmic report generation
Wang, J., Shi, M., Fan, J., Zhang, Y., & Wang, R. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01956-6 · Cited by 1
Optimizing Efficiency and Visual-Textual Alignment for LLM-Based Radiology Report Generation
Chen, Z., Gao, P., Lee, Y., Barthélemy, J., Zhou, L., & Wang, L. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210172
“Early work in this domain used CNNs and LSTMs [5]–[7], followed by transformer-based models that significantly improved report quality [1], [2], [9], [12].”
Ju, S., Chen, Z., Xiao, Y., Shen, Y., Su, Y., Chen, K., & Liao, X. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209540
“To address these limitations, subsequent research by Jing et al. [13] introduced cascaded LSTM models that incorporated medical topic vectors.”
MFDP: Multi-View Feature Integration and Enhanced Disease Prompting for Radiology Report Generation
Zhao, Y., Yang, K., Wu, Y., & Li, X. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3632356 · Cited by 1
“Moreover, multi-view approaches also show great potential in RRG [33], [22], which emphasize that image tokens from different views provide multiple information of the patient’s anatomy and lesions during text decoding, compensating for the limitations of single-view images.”
Chen, H., Pei, M., & Nie, Z. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4100-3_10
Label Auxiliary and Cross-modal Auxiliary Memory Network for Medical Report Generation
Yang, R., & Li, F. (2025) · International Symposium on Computer and Information Processing Technology (ISCIPT) · doi:10.1109/iscipt67144.2025.11265610
Reference-guided state-aware framework for chest X-ray report generation
Shi, K., Yu, Z., Qi, Z., Li, L., & Cai, X. (2025) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece65727.2025.11257108
“Early work like Jing et al.[11] added co-attention to enhance visual-textual interaction.”
InfluentialTabatabaee, S., & Khasawneh, M. T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5864720
Bayrakdar, S., & Yücedağ, İ. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02311-y
“This system is based on an encoder-decoder model pre - sented by Jing et al. for generating reports from medical images [ 25 ].”
Divya, P., Chakraborty, P. S., Chalavadi, K. M., & Chen, Y. (2025) · Applied Intelligence · doi:10.1007/s10489-025-07031-x
“The gate utilizes current input and the previous memory state, applying a sigmoid function to control how much of the new memory state is exposed as output.”
ViT-driven Visual Extraction in R2GenCMN for medical report generation
Ling, C., Wang, J., Fan, J., & Zhou, M. (2025) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess67117.2025.11268093 · Cited by 1
“Recent studies have explored hybrid models combining retrieval and generation strategies, as well as attention-based frameworks, to enhance the precision and clinical value of the reports produced [1]–[3].”
InfluentialA Comparative Study of Deep Learning Applications in Medical Report Generation Using Chest X-Rays
Likitha, P., Shah, K., Agarwal, K., Gowda, M., & Vishwanath, S. (2025) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc66258.2025.11280289
“This architecture was inspired by previous work on natural language generation tasks, where the CNN was used to extract features from images and the LSTM provided temporal dependencies between words [32].”
Medical Concept Guided Frequency Representation for Chest X-ray Report Generation
Huang, L., Zhao, X., Liu, X., & Li, C. (2025) · Cognitive Computation · doi:10.1007/s12559-025-10537-8
“Jing et al. [25] take a two-level decoder to generate long text paragraphs instead of single sentences.”
Hentati, R., Hentati, M., & Abid, A. (2025) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ae2e01
Mwcl: Memory-driven and mapping alignment with weighted contrastive learning for radiology reports
Usman, M., Ma, Z., & Yijia, Z. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02040-9
Wholistic report generation for Breast ultrasound using LangChain
Huh, J., Ahn, H. S., Park, H. J., & YE, J. C. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102697 · Cited by 1
X-Gen: Enhancing Radiology Report Generation via LLM-Driven Data Augmentation and Decoupled Training
Wang, C., Chen, Q., To, M., Kutaiba, N., Yoo, J.-G., Xie, Y., & Wu, Q. (2025) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta68720.2025.11302459
“Some earlier notable works, such as [35, 13], all employ LSTM [9] as the generation decoder.”
Generating Clinically Relevant Reports from Chest X-Rays for Cardiomegaly Diagnosis
Mondal, C., Kai, C. K., Pham, D.-S., et al. (2025) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta68720.2025.11302462
“However, interpreting these images and producing detailed diagnostic reports is a time-consuming task, even for experienced radiologists [9].”
Filling in the Missing Piece: Advancing Automated Radiology Report Generation with Clinical Insights
Wang, C., Chen, Q., Xie, Y., & Wu, Q. (2025) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta68720.2025.11302443
“Some works [7, 2, 20] combine the findings and impression sections as the training target and take images as the sole input.”
Shi, Y., & Kimura, M. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-0887-7_32
Medical Image Captioning in Radiology Reporting Using Artificial Intelligence
Abed, E. A., & Aguili, T. (2025) · International Conference on Communications and Networking (ComNet) · doi:10.1109/comnet68251.2025.11325450
“Work in adjacent fields such as remote sensing [29], [30], [31] has also inspired medical applications [32], contributing techniques for fine-grained visual analysis, dataset construction, and evaluation frameworks [33], [34], [35].”
Zeng, Y., Zhang, Z., Jiang, W., & Liu, S. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343253
“Several studies [1], [2] have used the encoder-decoder framework that relies only on image features to generate reports and have made some progress, using a visual encoder to extract visual features from radiology images and then feeding the visual features into a decoder to generate the text…”
Multi-scale based cross-modal semantic alignment network for radiology report generation
Zhang, Z., Zhao, L., Lan, D., Wang, Y., Jiang, L., & Dong, X. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343384
“For cross-modal alignment, CoATT [13] constructs a co-attention mechanism to align visual features with disease labels.”
InfluentialTang, M., Ding, W., Wei, C. A. I., & Jiang, Y. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00475-2
CyclicAligner: Knowledge-Enhanced Cyclical Alignment for Chest X-Ray Report Generation
Sun, J., Wang, P., Zhang, K., Tan, X., Fu, Z., & Yang, Y. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356622 · Cited by 1
“[4] proposed a multi-task learning framework to predict medical tags and generate reports.”
Yu, C., You, J., Huang, S., Yan, Z., Xu, W., & Lin, Z. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356157
“In addition to incorporating prior knowledge, recent studies [17]–[23] have optimized feature representations through joint training of auxiliary tasks.”
Hou, X., Li, Y., & Wang, S. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00133
“The experimental results, summarized in Table 3, reveal several key findings.”
Ye, C., Lv, J., Li, G., Wu, R., Zeng, S., Jiang, N., Liu, B., Wu, J., Ji, D., & Zhang, H. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00672-z
“In the early research, Recurrent Neural Networks (RNNs) (Pham et al. 2014) and Long Short-Term Memory networks (LSTMs) (Vinyals et al. 2015; Chen et al. 2018; Jing et al. 2018) were prevalent in this domain.”
Breaking Barriers in Bone Disease Detection Advancements and Challenges in Medical Image Captioning
Umamaheswari, K., & Nagira, R. (2026) · International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS) · doi:10.1109/iciscois62701.2026.11447802
“To identify pseudo-reports using unlabeled medical images, Jing et al. [24] proposed to use unsupervised natural language models.”
InfluentialAutomated Medical Report Generation with Transformers and Spatio-Semantic Analysis
Aryalakshmi, P., & Salim, A. (2025) · International Conference on Data Science and Intelligent Network Computing (ICDSINC) · doi:10.1109/icdsinc66221.2025.11448202
Sun, Y., Jiang, J., & Chen, Y. (2026) · doi:10.2196/preprints.95888
Hierarchical Anatomically-Aligned Radiology Report Generation
Zeng, J., Liang, J., Wang, Y., & Xiao, Y. H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460775
Zhao, L., & Liu, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460330
Hamma, M. B., Merrouni, Z. A., Frikh, B., & Ouhbi, B. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11556-z · Cited by 1
“Attention mechanisms partially mitigated this issue by providing coarse visual grounding (Jing et al. 2018b ), although such explanations reflected correlation rather”
Park, J., Won, H., Kim, J., Hwang, J. S., Han, J. M., Park, J. I., Hwang, D. D.-J., & Han, J. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00504 · Cited by 1
Advancing In-Context Learning for Efficient and Stable Medical Report Generation
Li, M., Liu, R., Shi, Z., Han, M., Yao, L., Li, Z., Chang, X., Pohl, K. M., Islam, M. T., & Xing, L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3689780
“Early MRG models employed dual-layer LSTM-based decoders [15], [38], which were later replaced by transformer-based architectures [39], [40], [41] for improved contextual modeling.”
Automated Radiology Report Generation from Chest X-rays using DenseNet-121 and LSTM
Patil, K., Inamdar, M. M., Kudalagi, R., Gadad, A., Kulkarni, U., & Gani, P. (2026) · IEEE International Conference for Convergence in Computing Technology (I3CTCON) · doi:10.1109/i3ctcon68242.2026.11507993 · Cited by 1
“Compared with general image captioning [13] [14], radiology text tends to be more structured and conservative, with domain-specific terminology and a strong emphasis on clinical accuracy.”
Bouridane, A., Hezil, N., Hamoudi, R., Al-Maadeed, S. A., & Rogov, O. Y. (2026) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi61048.2026.11515574
“Existing approaches suffer from limited attention to relevant anatomical regions, insufficient interpretability, and suboptimal multi-scale feature utilization [1, 2].”
LACFNet: Locality Aware Cross Modal Fusion Network for Automatic Medical Image Report Generation
Li, Y., Peng, K., Liu, T., & Xiao, H. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522656
“…Quantitative analysis: IU-Xray dataset: We compare our model with classical and state-of-the-art (SOTA) models in medical image report generation, including COATT [4], CMAS [5], M2Transformer [21], PPKED [12], R2Gen [7], MSAT [27], JPG [8], CvT-212DistilGPT2 [28], METrans-former [1], and MGRG [29].”
Raja, S., Dhayanithi, K., Kotte, K., et al. (2026) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla67915.2026.11522480
“Jing et al. [12] coupled image-level feature vectors with hierarchical LSTM decoders to generate multi-sentence radiology reports, providing an early blueprint for vision-language integration in diagnostic AI.”
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
