Mai A. Shaaban
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mai A. Shaaban has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Yaqub
Mohamed bin Zayed University of Artificial Intelligence
4 shared publications - Vijay Ram Kumar Papineni
Department of Radiology, Sheikh Shakhbout Medical City, Abu Dhabi, United Arab Emirates
2 shared publications Abbas Akkasi
Carleton University
1 shared publicationAdnan Khan
Carleton University
1 shared publication- Adnan Khan
Carleton University
1 shared publication - Ibrahim Almakky
Mohamed bin Zayed University of Artificial Intelligence
1 shared publication
Latest Publications
- Open Access
- 28 October 2025
- Published by Springer Nature in Research Square
Towards Multimodal Retrieval-Augmented Generation for Medical Visual Question Answering
Medical visual question answering (MedVQA) is a critical AI healthcare task that combines medical image analysis with natural language understanding to assist clinicians in decision-making. While medical vision-language models have shown promise in this domain, they struggle with factual inaccuracies and hallucinations. Retrieval-augmented generation (RAG) improves the factual accuracy by grounding responses in external knowledge, yet text-only or image-only retrieval systems struggle with the inherently multimodal nature of medical data, leading to information loss. This paper proposes a novel multimodal RAG framework tailored for MedVQA, which leverages multimodal data, including medical images, reports, and generated captions, to provide more accurate clinical answers. We introduce a training paradigm that uses captions as auxiliary supervision, enhancing cross-modal alignment via contrastive learning. Comprehensive evaluations on MedVQA benchmarks demonstrate the framework’s effectiveness, achieving a 7% average accuracy improvement over unimodal RAG baselines. Our study has the potential to better support clinicians in delivering accurate, timely, and trustworthy patient care by improving the reliability of MedVQA systems. The code is publicly available at https://github.com/AiMl-hub/MM-RAG-MedVQA.
- 28 October 2025
- Published by Springer Nature in Research Square
Open AccessTowards Multimodal Retrieval-Augmented Generation for Medical Visual Question Answering
Medical visual question answering (MedVQA) is a critical AI healthcare task that combines medical image analysis with natural language understanding to assist clinicians in decision-making. While medical vision-language models have shown promise in this domain, they struggle with factual inaccuracies and hallucinations. Retrieval-augmented generation (RAG) improves the factual accuracy by grounding responses in external knowledge, yet text-only or image-only retrieval systems struggle with the inherently multimodal nature of medical data, leading to information loss. This paper proposes a novel multimodal RAG framework tailored for MedVQA, which leverages multimodal data, including medical images, reports, and generated captions, to provide more accurate clinical answers. We introduce a training paradigm that uses captions as auxiliary supervision, enhancing cross-modal alignment via contrastive learning. Comprehensive evaluations on MedVQA benchmarks demonstrate the framework’s effectiveness, achieving a 7% average accuracy improvement over unimodal RAG baselines. Our study has the potential to better support clinicians in delivering accurate, timely, and trustworthy patient care by improving the reliability of MedVQA systems. The code is publicly available at https://github.com/AiMl-hub/MM-RAG-MedVQA.
- 19 September 2025
- Published by Springer Nature
- p. 459-469
MOTOR: Multimodal Optimal Transport via Grounded Retrieval in Medical Visual Question Answering
- 19 September 2025
- Published by Springer Nature
- p. 459-469
MOTOR: Multimodal Optimal Transport via Grounded Retrieval in Medical Visual Question Answering
- 13 April 2025
- Published by Springer Nature
- p. 211-222
MedPromptX: Grounded Multimodal Prompting for Chest X-Ray Diagnosis
- 13 April 2025
- Published by Springer Nature
- p. 211-222
MedPromptX: Grounded Multimodal Prompting for Chest X-Ray Diagnosis
- 4 October 2024
- Published by Springer Nature
- p. 328-338
HuLP: Human-in-the-Loop for Prognosis
- 15 October 2023
- Published by Springer Nature
- p. 434-443
PECon: Contrastive Pretraining to Enhance Feature Alignment Between CT and EHR Data for Improved Pulmonary Embolism Diagnosis
- 15 October 2023
- Published by Springer Nature
- p. 434-443
PECon: Contrastive Pretraining to Enhance Feature Alignment Between CT and EHR Data for Improved Pulmonary Embolism Diagnosis
- Open Access
- 26 April 2022
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 8 (6) , 4897-4909
Deep convolutional forest: a dynamic deep ensemble approach for spam detection in text
The increase in people’s use of mobile messaging services has led to the spread of social engineering attacks like phishing, considering that spam text is one of the main factors in the dissemination of phishing attacks to steal sensitive data such as credit cards and passwords. In addition, rumors and incorrect medical information regarding the COVID-19 pandemic are widely shared on social media leading to people’s fear and confusion. Thus, filtering spam content is vital to reduce risks and threats. Previous studies relied on machine learning and deep learning approaches for spam classification, but these approaches have two limitations. Machine learning models require manual feature engineering, whereas deep neural networks require a high computational cost. This paper introduces a dynamic deep ensemble model for spam detection that adjusts its complexity and extracts features automatically. The proposed model utilizes convolutional and pooling layers for feature extraction along with base classifiers such as random forests and extremely randomized trees for classifying texts into spam or legitimate ones. Moreover, the model employs ensemble learning procedures like boosting and bagging. As a result, the model achieved high precision, recall, f1-score and accuracy of 98.38%.
- 26 April 2022
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 8 (6) , 4897-4909
Open AccessDeep convolutional forest: a dynamic deep ensemble approach for spam detection in text
The increase in people’s use of mobile messaging services has led to the spread of social engineering attacks like phishing, considering that spam text is one of the main factors in the dissemination of phishing attacks to steal sensitive data such as credit cards and passwords. In addition, rumors and incorrect medical information regarding the COVID-19 pandemic are widely shared on social media leading to people’s fear and confusion. Thus, filtering spam content is vital to reduce risks and threats. Previous studies relied on machine learning and deep learning approaches for spam classification, but these approaches have two limitations. Machine learning models require manual feature engineering, whereas deep neural networks require a high computational cost. This paper introduces a dynamic deep ensemble model for spam detection that adjusts its complexity and extracts features automatically. The proposed model utilizes convolutional and pooling layers for feature extraction along with base classifiers such as random forests and extremely randomized trees for classifying texts into spam or legitimate ones. Moreover, the model employs ensemble learning procedures like boosting and bagging. As a result, the model achieved high precision, recall, f1-score and accuracy of 98.38%.
- 27 August 2003
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 166-169
Identifying junk electronic mail in Microsoft outlook with a support vector machine
In this paper, we utilize a simple support vector machine to identify commercial electronic mail. The use of a personalized dictionary for model training provided a classification accuracy of 96.69%, while a much larger system dictionary achieved 95.26%. The classification system was subsequently implemented as an add-in for Microsoft Outlook XP, providing sorting and grouping capabilities using Outlook's interface to the typical desktop e-mail user.
- 27 August 2003
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 166-169
Identifying junk electronic mail in Microsoft outlook with a support vector machine
In this paper, we utilize a simple support vector machine to identify commercial electronic mail. The use of a personalized dictionary for model training provided a classification accuracy of 96.69%, while a much larger system dictionary achieved 95.26%. The classification system was subsequently implemented as an add-in for Microsoft Outlook XP, providing sorting and grouping capabilities using Outlook's interface to the typical desktop e-mail user.