Topic Editors

AI Center, Korea University College of Medicine, Seoul 02841, Republic of Korea
Prof. Dr. Hyuntae Park
Department of Obstetrics and Gynecology, Korea University College of Medicine, Seoul 02841, Republic of Korea

Artificial Intelligence and Big Data in Biomedical Engineering

Abstract submission deadline
31 October 2026
Manuscript submission deadline
31 December 2026
Viewed by
22660

Topic Information

Dear Colleagues,

Emerging literature uses artificial intelligence in biomedical engineering (BME) applications. It is free from unrealistic assumptions of “all the other variables staying constant”. It delivers important values and rankings of predictors for BME applications (e.g., SHAP plots). Moreover, the notions of generative artificial intelligence and reinforcement learning are enjoying immense popularity now. Given a sequence of words, artificial intelligence generates a sequence of their probabilities based on BERT or GPT. Its astonishing performance comes from the attention mechanism (in which different input words receive different weights based on their similarity with the output word). Reinforcement learning is a branch of artificial intelligence where the environment gives rewards, an agent takes actions to maximize the cumulative reward, and the environment moves to the next period with given probabilities. In fact, it has been reinforcement learning that has brought the notion of artificial intelligence to worldwide popularity since the publication of a seminal article on Alpha-Go in 2016. However, little examination has been performed, and more investigation is needed on artificial intelligence in BME applications. In this context, this Topic invites original and review articles on artificial intelligence in BME applications. Some potential topics are listed below:

  • Tissue Engineering, Regenerative Medicine and Drug Discovery in Aging;
  • Tissue Engineering, Regenerative Medicine and Drug Discovery in Fertility;
  • Artificial Intelligence Agent in Emergency Medicine;
  • Artificial Intelligence Agent in Mental Health;
  • Biological Materials, Biological Mechanics and Medical Imaging in Neurology.

Prof. Dr. Kwang-Sig Lee
Prof. Dr. Hyuntae Park
Topic Editors

Keywords

  • machine learning
  • deep learning
  • explainable artificial intelligence
  • SHAP
  • generative artificial intelligence
  • BERT
  • GPT
  • reinforcement learning
  • biomedical engineering

Participating Journals

Journal Name Impact Factor CiteScore Launched Year First Decision (median) APC
Applied Sciences
applsci
2.9 6.1 2011 15 Days CHF 2400 Submit
Bioengineering
bioengineering
4.4 7.5 2014 16.9 Days CHF 2700 Submit
BioMedInformatics
biomedinformatics
3.6 7.1 2021 20.8 Days CHF 1200 Submit
Diagnostics
diagnostics
3.8 6.9 2011 20.4 Days CHF 2600 Submit
Journal of Imaging
jimaging
3.8 7.3 2015 21.3 Days CHF 1800 Submit

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

  1. Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
  2. Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
  3. Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
  4. Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
  5. Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (10 papers)

Order results
Result details
Journals
Select all
Export citation of selected articles as:
18 pages, 9841 KB  
Article
DFU-MambaKAN: A Lightweight Hybrid Mamba-KAN Architecture for Diabetic Foot Ulcer Screening and Severity Grading
by Md Nafis Azad Nobel, Sazid Rahman Kazi, Tajul Islam Rafi, Mainuddin Adel Rafi, Umer Aqeel, Md Ranu Hossen, Md Al Ridwan and Roise Uddin
BioMedInformatics 2026, 6(4), 57; https://doi.org/10.3390/biomedinformatics6040057 - 6 Aug 2026
Viewed by 354
Abstract
Diabetic foot ulcers (DFUs) are a major cause of lower-extremity amputation, and image-based decision support may assist screening and preliminary triage where specialist access is limited. We propose DFU-MambaKAN, a hybrid architecture combining a pure-PyTorch selective state-space (Mamba) block with a Gaussian radial-basis-function [...] Read more.
Diabetic foot ulcers (DFUs) are a major cause of lower-extremity amputation, and image-based decision support may assist screening and preliminary triage where specialist access is limited. We propose DFU-MambaKAN, a hybrid architecture combining a pure-PyTorch selective state-space (Mamba) block with a Gaussian radial-basis-function Kolmogorov–Arnold Network (RBF-KAN) feed-forward layer. The study evaluates two distinct tasks: (1) binary normal-versus-ulcer screening and (2) a dataset-specific four-class Wagner-Meggitt severity-grading task. DFU-MambaKAN contains 1.062 million parameters and was compared with ResNet50, EfficientNet-B0, MobileNetV3-Small, and ViT-Tiny under the manuscript’s common downstream training protocol. The reported values are point estimates from one deterministic 70/15/15 split generated with seed 42; no confidence intervals, repeated-seed averages, or inferential significance tests were obtained. On binary screening, DFU-MambaKAN achieved 97.17% accuracy, macro-F1 0.970, and AUC 0.994. On four-class grading, it achieved 67.75% accuracy, macro-F1 0.677, and AUC 0.895, whereas the baselines achieved 98.14–99.00% accuracy. This large gap means that the present evidence does not establish competitiveness for multiclass severity grading. Possible contributors include training duration and convergence, dataset size and class definitions, label or image-quality uncertainty, hyperparameter selection, global token mixing, and architecture–task mismatch; extended learning-curve analysis and multi-seed evaluation are needed to test these explanations. An automated technical audit identified 342 exact duplicates among 1055 class-folder images in Dataset A (32.4%); no deduplicated-versus-nondeduplicated performance comparison was performed, so this finding is reported as a methodological caution rather than proof of accuracy inflation. The model’s 1.062M parameter count supports parameter-efficient storage, but its measured single-image GPU latency was 90.54–93.14 ms, substantially higher than the baselines. Accordingly, the current evidence supports further investigation for batched or queued screening more strongly than immediate real-time mobile deployment. External clinical validation, multi-seed analysis, statistical testing, convergence studies, and component ablations remain necessary. Full article
Show Figures

Figure 1

32 pages, 1700 KB  
Systematic Review
From Explainability to Clinical Actionability in Multi-Modal AI for Cardiovascular Prediction: A Systematic Review
by Hamza Nouri, Rafae Abderrahim and Mohamed Erritali
BioMedInformatics 2026, 6(4), 55; https://doi.org/10.3390/biomedinformatics6040055 - 3 Aug 2026
Viewed by 709
Abstract
Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, driving the need for reliable tools for early risk prediction. Artificial intelligence (AI) applied to electrocardiograms (ECGs) has shown strong predictive performance for future cardiac events, yet its clinical adoption remains limited by [...] Read more.
Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, driving the need for reliable tools for early risk prediction. Artificial intelligence (AI) applied to electrocardiograms (ECGs) has shown strong predictive performance for future cardiac events, yet its clinical adoption remains limited by the lack of transparency and trust associated with black-box models. This systematic review examines recent advances in AI-based cardiovascular prediction, focusing on the combined challenges of multi-modal data fusion and clinically actionable explainability. Following PRISMA 2020 guidelines, we analyzed 65 peer-reviewed studies published between 2018 and 2025, identified through a systematic search of PubMed, IEEE Xplore, Web of Science, Scopus, ACM Digital Library, and Google Scholar. The reviewed literature reveals that while most AI-ECG models achieve high predictive accuracy, typically AUC 0.85–0.95, the majority rely on post hoc explainability techniques that offer limited clinical insight, and 61.5% of included studies implement no explainability method at all. External validation remains critically underutilized, performed by only 12.3% of studies, and multi-modal approaches integrating ECG data with electronic health records, biomarkers, or genomics represent only 27.7% of the reviewed literature. While these multi-modal models demonstrate improved contextualization and predictive performance, they remain insufficiently validated and inconsistently interpretable. Among studies employing XAI techniques, attention mechanisms were the most prevalent approach (28% of XAI studies), followed by saliency maps (20%), SHAP (16%), and LIME (8%). Only 9.2% of studies were prospective or clinical trials, underscoring the gap between algorithmic development and real-world clinical deployment. Applying a pre-specified four-level clinical actionability scoring framework (Level 0–3), we found that the majority of studies (61.5%) scored at Level 0 (no actionability), with only 9.2% reaching Level 3 (demonstrated clinical impact), confirming that the clinical translation gap extends beyond trial design to encompass the broader absence of clinically contextualised evaluation of AI-ECG systems. This review highlights a persistent and critical gap between predictive performance and clinical usability, and outlines four key directions for developing AI-ECG systems that can better support trustworthy clinical decision-making: (1) developing inherently interpretable architectures, (2) advancing unified multi-modal fusion and explanation frameworks, (3) establishing standardized benchmarks for explainability evaluation, and (4) conducting robust prospective validation measuring real-world patient outcomes. Full article
Show Figures

Figure 1

27 pages, 3651 KB  
Article
Artificial Intelligence-Based Prototype for Early Diagnosis of Gingivitis and Periodontitis in Adults
by Sergio David Pintado-Brito, Jeannett Alejandra Izquierdo-Vega, Rocío Ortega-Palacios, Aleli Julieta Izquierdo-Vega, Fredy Santander-Baños, Manuel Sánchez-Gutiérrez, Iriana Yunuen Ángeles-Espinosa and Eduardo Osiris Madrigal-Santillán
BioMedInformatics 2026, 6(4), 43; https://doi.org/10.3390/biomedinformatics6040043 - 10 Jul 2026
Viewed by 851
Abstract
Background: Periodontal diseases continue to be highly prevalent worldwide, and their early detection represents a clinical challenge, especially when based on non-standardized intraoral photographs. The present study develops an artificial intelligence-based prototype for the automatic classification of periodontal health, gingivitis, and periodontitis using [...] Read more.
Background: Periodontal diseases continue to be highly prevalent worldwide, and their early detection represents a clinical challenge, especially when based on non-standardized intraoral photographs. The present study develops an artificial intelligence-based prototype for the automatic classification of periodontal health, gingivitis, and periodontitis using Red, Green, Blue (RGB) images obtained in real conditions. Methods: A dataset comprising 1552 (306 healthy, 1019 with gingivitis, and 227 with periodontitis) was constructed by integrating proprietary clinical photographs with a public repository. A patient-level stratified split was enforced to prevent data leakage, ensuring that all images from the same patient remained within a single partition. This proposal uses EfficientNet-B2, which includes two-phase training, balanced focal loss, weighted sampling, CutMix/MixUp augmentation, and centered anatomical cropping to improve generalization across varied images. Results: The final model achieved an accuracy of 0.833, a macro F1-score (F1) of 0.832 [95% CI: 0.789–0.874], and a macro Area Under the Curve (AUC) of 0.962 [95% CI: 0.946–0.976] on an independent test set. A seven-configuration ablation study showed that each training component contributes to improved performance, and a baseline comparison with ResNet-50 demonstrated the superiority of EfficientNet-B2. Five-fold cross-validation with patient-level grouping yielded consistent results (F1 = 0.832 ± 0.016, AUC = 0.950 ± 0.005). Conclusions: These results demonstrate that EfficientNet-B2 is useful for assessing periodontal health using readily available RGB photographs, with potential for early detection, clinical triage, and remote assessment in modern dentistry. Full article
Show Figures

Figure 1

15 pages, 1206 KB  
Article
Causal Graphical Models for Transition from Healthy Vaginal Microbiota to Bacterial Vaginosis in Pregnant Women
by Maricela García-Avalos, Juana Canul-Reich, Lil María Xibai Rodríguez-Henríquez and Erick Natividad De la Cruz-Hernández
BioMedInformatics 2026, 6(3), 32; https://doi.org/10.3390/biomedinformatics6030032 - 21 May 2026
Viewed by 673
Abstract
This study developed two Causal Graphical Models (CGMs) to analyze the transitions associated with Bacterial Vaginosis (BV) and to identify key bacterial species at each stage. BV results from an imbalance in the vaginal microbiota, whose composition varies among women and across developmental [...] Read more.
This study developed two Causal Graphical Models (CGMs) to analyze the transitions associated with Bacterial Vaginosis (BV) and to identify key bacterial species at each stage. BV results from an imbalance in the vaginal microbiota, whose composition varies among women and across developmental stages. A previous CGM identified influential bacteria but did not address changes between microbiota states. Here, we extend that framework to capture these associations. Path Analysis, a structural equation modeling method based on observed variables that estimates effects through correlations and covariances, was applied to a dataset of 132 pregnant women (4–24 weeks of gestation) from Tabasco, Mexico, previously collected by third parties during healthy pregnancy campaigns and associated with BV diagnosis. Models were validated using statistical metrics and evaluation by a clinical microbiologist. The first model, representing the transition from normal microbiota (BV−) to an indeterminate state (I), identified Megasphaera Type 1 as significant. The second model, from I to bacterial vaginosis-positive (BV+), identified Atopobium vaginae and Bacterial Vaginosis-Associated Bacterium Type 2 as significant contributors. These findings highlight the importance of the intermediate state in dysbiosis progression and support the use of CGMs for studying microbiome dynamics. Full article
Show Figures

Graphical abstract

24 pages, 1980 KB  
Article
Efficient Visual Field Sensitivity Estimation via a Lightweight Global Context-Aware CNN Using Standard 2D OCT Thickness Maps
by Shamsudeen Abdullahi, Yuttapong Jiraraksopakun, Apichai Bhatranand, Anita Manassakorn, Sunee Chansangpetch, Kitiya Ratanawongphaibul and Visanee Tantisevi
BioMedInformatics 2026, 6(3), 26; https://doi.org/10.3390/biomedinformatics6030026 - 8 May 2026
Viewed by 8784
Abstract
Glaucoma is a chronic progressive optic neuropathy causing irreversible blindness globally, underscoring the need for reliable diagnostic tools. While visual field (VF) testing remains the clinical standard, it has significant limitations, including subjective variability and patient cooperation difficulties. Optical coherence tomography (OCT) offers [...] Read more.
Glaucoma is a chronic progressive optic neuropathy causing irreversible blindness globally, underscoring the need for reliable diagnostic tools. While visual field (VF) testing remains the clinical standard, it has significant limitations, including subjective variability and patient cooperation difficulties. Optical coherence tomography (OCT) offers objective structural assessment. Recent deep learning approaches for VF prediction from OCT data can achieve high accuracy, but require raw three-dimensional volumetric data and substantial computational infrastructure that limit their deployment in routine clinical practice. We developed a lightweight convolutional neural network that predicts VF sensitivity from standard two-dimensional OCT thickness maps routinely available in clinical settings. The architecture integrates multiscale depthwise separable convolutions with attention mechanisms and employs an Exponentially Weighted Mean Squared Error loss function to enhance accuracy in clinically critical low-sensitivity regions. Using data from 241 subjects with five-fold cross-validation, our model achieved mean absolute error of 3.32 ± 2.35 dB and correlation of 0.74. This approach addresses the practical deployment limitations of existing methods while maintaining competitive accuracy, enabling implementation in resource-constrained clinical settings for patients who cannot reliably perform standard perimetry. Full article
Show Figures

Graphical abstract

26 pages, 4030 KB  
Article
DuDeM: A Dual-Network Model for Early Gastric Cancer Detection Based on Capsule Endoscopy
by Tianyi Feng, Qian He, Tianqi Chen and Weibing Wang
Bioengineering 2026, 13(3), 356; https://doi.org/10.3390/bioengineering13030356 - 18 Mar 2026
Viewed by 1202
Abstract
Early detection is critical for improving outcomes in gastric cancer, yet lesion recognition in capsule endoscopy is challenged by interference from different gastric anatomical sites, patient posture changes, and gastric peristalsis. This study aims to prompt a robust deep learning model to address [...] Read more.
Early detection is critical for improving outcomes in gastric cancer, yet lesion recognition in capsule endoscopy is challenged by interference from different gastric anatomical sites, patient posture changes, and gastric peristalsis. This study aims to prompt a robust deep learning model to address these challenges. A dual-network model, named DuDeM (DualNet Detection Model), was developed by integrating a ResNet50-based convolutional branch with a CapsuleNet branch incorporating dynamic routing. The convolutional branch extracts local lesion features that are transmitted to primary capsules, while dynamic routing enables adaptive matching between capsule layers to establish local–global feature associations. An attention-weighted strategy is applied for feature fusion. The model was trained using capsule endoscopy images from nine hospitals in China and public datasets, and its performance was compared with eight representative models, with ablation analyses validating key components. Results showed that DuDeM achieved an area under the curve (AUC) of 0.981 and an F1-score of 0.979, with sensitivity, specificity, and precision all exceeding 97%, and performance degradation limited to within 3% under mild image perturbations. These findings suggest that DuDeM enables reliable early gastric cancer (EGC) recognition and may support large-scale capsule endoscopy screening in clinical practice. Full article
Show Figures

Figure 1

31 pages, 1866 KB  
Review
Artificial Intelligence in Corneal Drug Delivery Systems
by Amirhosein Panjipour, Soheil Sojdeh, Zohreh Arabpour and Ali R. Djalilian
BioMedInformatics 2026, 6(2), 11; https://doi.org/10.3390/biomedinformatics6020011 - 27 Feb 2026
Cited by 2 | Viewed by 3160
Abstract
Conventional topical therapy for corneal and anterior segment diseases is limited by rapid tear clearance and multilayer corneal barriers, resulting in low bioavailability and the need for frequent dosing. Artificial intelligence (AI) is emerging as a complementary approach that learns quantitative relationships between [...] Read more.
Conventional topical therapy for corneal and anterior segment diseases is limited by rapid tear clearance and multilayer corneal barriers, resulting in low bioavailability and the need for frequent dosing. Artificial intelligence (AI) is emerging as a complementary approach that learns quantitative relationships between molecular structure, formulation variables, and ocular performance. In corneal drug delivery, machine learning models have been used to optimize multicomponent formulations and processing conditions; predict key quality attributes such as particle size, zeta potential, encapsulation efficiency and release kinetics; and estimate corneal permeability, retention and ocular irritation risk, thereby reducing experimental burden and guiding safer design. AI can also be coupled with mechanistic ocular pharmacokinetic/pharmacodynamic models to translate formulation attributes into predicted tissue exposure. Finally, inverse design approaches enable the discovery of new carriers and devices, illustrated by machine learning-guided peptide carriers and smart contact lens platforms that combine sensing with on-demand drug release. Despite these advances, current datasets remain small and heterogeneous, external validation and benchmarking against conventional workflows are limited, and uncertainty quantification and interpretability must be addressed to enable clinical translation. This review summarizes corneal barriers and delivery platforms, critically evaluates where AI provides measurable value across design, characterization and performance and highlights data and validation priorities needed for trustworthy AI-enabled corneal therapeutics. Full article
Show Figures

Figure 1

27 pages, 1594 KB  
Review
Toward Clinically Dependable AI for Brain Tumors: A Unified Diagnostic–Prognostic Framework and Triadic Evaluation Model
by Mohammed A. Atiea, Mona Gafar, Shahenda Sarhan and Abdullah M. Shaheen
BioMedInformatics 2026, 6(1), 7; https://doi.org/10.3390/biomedinformatics6010007 - 27 Jan 2026
Cited by 1 | Viewed by 2140
Abstract
Artificial intelligence (AI) has shown promising performance in brain tumor diagnosis and prognosis; however, most reported advances remain difficult to translate into clinical practice due to limited interpretability, inconsistent evaluation protocols, and weak generalization across datasets and institutions. In this work, we present [...] Read more.
Artificial intelligence (AI) has shown promising performance in brain tumor diagnosis and prognosis; however, most reported advances remain difficult to translate into clinical practice due to limited interpretability, inconsistent evaluation protocols, and weak generalization across datasets and institutions. In this work, we present a critical synthesis of recent brain tumor AI studies (2020–2025) guided by two novel conceptual tools: a unified diagnostic-prognostic framework and a triadic evaluation model emphasizing interpretability, computational efficiency, and generalizability as core dimensions of clinical readiness. Following PRISMA 2020 guidelines, we screened and analyzed over 100 peer-reviewed studies. A structured analysis of reported metrics reveals systematic trends and trade-offs—for instance, between model accuracy and inference latency—rather than providing a direct performance benchmark. This synthesis exposes critical gaps in current evaluation practices, particularly the under-reporting of interpretability validation, deployment-level efficiency, and external generalization. By integrating conceptual structuring with evidence-driven analysis, this work provides a framework for more clinically grounded development and evaluation of AI systems in neuro-oncology. Full article
Show Figures

Figure 1

27 pages, 1031 KB  
Article
PMR-Q&A: Development of a Bilingual Expert-Evaluated Question–Answer Dataset for Large Language Models in Physical Medicine and Rehabilitation
by Muhammed Zahid Sahin, Fatma Betul Derdiyok, Serhan Ayberk Kilic, Kasim Serbest and Kemal Nas
Bioengineering 2026, 13(1), 125; https://doi.org/10.3390/bioengineering13010125 - 22 Jan 2026
Cited by 4 | Viewed by 1410
Abstract
Objectives: This study presents the development of a bilingual, expert-evaluated question–answer (Q&A) dataset, named PMR-Q&A, designed for training large language models (LLMs) in the field of Physical Medicine and Rehabilitation (PMR). Methods: The dataset was created through a systematic and semi-automated [...] Read more.
Objectives: This study presents the development of a bilingual, expert-evaluated question–answer (Q&A) dataset, named PMR-Q&A, designed for training large language models (LLMs) in the field of Physical Medicine and Rehabilitation (PMR). Methods: The dataset was created through a systematic and semi-automated framework that converts unstructured scientific texts into structured Q&A pairs. Source materials included eight core reference books, 2310 academic publications, and 323 theses covering 15 disease categories commonly encountered in PMR clinical practice. Texts were digitized using layout-aware optical character recognition (OCR), semantically segmented, and distilled through a two-pass LLM strategy employing GPT-4.1 and GPT-4.1-mini models. Results: The resulting dataset consists of 143,712 bilingual Q&A pairs, each annotated with metadata including disease category, reference source, and keywords. A representative subset of 3000 Q&A pairs was extracted for expert validation to evaluate the dataset’s reliability and representativeness. Statistical analyses showed that the validation sample accurately reflected the thematic and linguistic structure of the full dataset, with an average score of 1.90. Conclusions: The PMR-Q&A dataset is a structured and expert-evaluated resource for developing and fine-tuning domain-specific large language models, supporting research and educational efforts in the field of physical medicine and rehabilitation. Full article
Show Figures

Figure 1

20 pages, 7543 KB  
Article
Contrastive Learning with Feature Space Interpolation for Retrieval-Based Chest X-Ray Report Generation
by Zahid Ur Rahman, Gwanghyun Yu, Lee Jin and Jin Young Kim
Appl. Sci. 2026, 16(1), 470; https://doi.org/10.3390/app16010470 - 1 Jan 2026
Cited by 1 | Viewed by 1707
Abstract
Automated radiology report generation from chest X-rays presents a critical challenge in medical imaging. Traditional image-captioning models struggle with clinical specificity and rare pathologies. Recently, contrastive vision language learning has emerged as a robust alternative that learns joint visual–textual representations. However, applying contrastive [...] Read more.
Automated radiology report generation from chest X-rays presents a critical challenge in medical imaging. Traditional image-captioning models struggle with clinical specificity and rare pathologies. Recently, contrastive vision language learning has emerged as a robust alternative that learns joint visual–textual representations. However, applying contrastive learning (CL) to radiology remains challenging due to severe data scarcity. Prior work has employed input space augmentation, but these approaches incur computational overhead and risk distorting diagnostic features. This work presents CL with feature space interpolation for retrieval (CLFIR), a novel CL framework operating on learned embeddings. The method generates interpolated pairs in the feature embedding space by mixing original and shuffled embeddings in batches using a mixing coefficient λU(0.85,0.99). This approach increases batch diversity via synthetic samples, addressing the limitations of CL on medical data while preserving diagnostic integrity. Extensive experiments demonstrate state-of-the-art performance across critical clinical validation tasks. For report generation, CLFIR achieves BLEU-1/ROUGE/METEOR scores of 0.51/0.40/0.26 (Indiana university [IU] X-ray) and 0.45/0.34/0.22 (MIMIC-CXR). Moreover, CLFIR excels at image-to-text retrieval with R@1 scores of 4.14% (IU X-ray) and 24.3% (MIMIC-CXR) and achieves 0.65 accuracy in zero-shot classification on the CheXpert5×200 dataset, surpassing the established vision-language models. Full article
Show Figures

Figure 1

Back to TopTop