Deep learning approaches to automatic radiology report generation: A systematic review

Liao, Yuxiang; Liu, Hantao; Spasić, Irena

doi:10.1016/j.imu.2023.101273

Cited by 9 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the model comparison is hindered by dataset diversity, although incorporating radiology reports is expected to grow [20]. Radiology reports, diverse in style and influenced by biases, pose challenges in training robust models, with few datasets meeting scalability and accessibility criteria [25]. Most RRG systems concentrate on X-ray tests, with emerging applications for CT scans and MRI datasets, each encountering unique challenges [25].…”

Section: Related Workmentioning

confidence: 99%

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

Parres,

Albiol,

Paredes

2024

Bioengineering

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

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

Parres,

Albiol,

Paredes

2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…In this work, a simple but effective design of CNN architecture was carried out to identify the CT images of COVID-19 patients. In computer vision and medical imaging, X-ray and CT images are used for diagnosis or prognosis [23]. Diagnosis is the actual recognition of the disease being suffered.…”

Section: Introductionmentioning

confidence: 99%

SCOV-CNN: A Simple CNN Architecture for COVID-19 Identification Based on the CT Images

Haryanto,

Suhartanto,

Murni

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Since the coronavirus was first discovered in Wuhan, it has widely spread and was finally declared a global pandemic by the WHO. Image processing plays an essential role in examining the lungs of affected patients. Computed Tomography (CT) and X-ray images have been popularly used to examine the lungs of COVID-19 patients. This research aims to design a simple Convolution Neural Network (CNN) architecture called SCOV-CNN for the classification of the virus based on CT images and implementation on the web-based application. The data used in this work were CT images of 120 patients from hospitals in Brazil. SCOV-CNN was inspired by the LeNet architecture, but it has a deeper convolution and pooling layer structure. Combining seven and five kernel sizes for convolution and padding schemes can preserve the feature information from the images. Furthermore, it has three fully connected (FC) layers with a dropout of 0.3 on each. In addition, the model was evaluated using the sensitivity, specificity, precision, F1 score, and ROC curve values. The results showed that the architecture we proposed was comparable to some prominent deep learning techniques in terms of accuracy (0.96), precision (0.98), and F1 score (0.95). The best model was integrated into a website-based system to help and facilitate the users' activities. We use Python Flask Pam tools as a web server on the server side and JavaScript for the User Interface (UI) Design

show abstract

Future Trends and Challenges

Seeram,

Kanade

2024

Artificial Intelligence in Medical Imaging Technology

View full text Add to dashboard Cite

Deep learning approaches to automatic radiology report generation: A systematic review

Cited by 9 publications

References 49 publications

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

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

SCOV-CNN: A Simple CNN Architecture for COVID-19 Identification Based on the CT Images

Future Trends and Challenges

Contact Info

Product

Resources

About