From Simple Labels to Descriptive Sentences in Leukemia Image Classification
Published in Bioengineering & Biotechnology, Computational Sciences, and Immunology
The idea of this paper was very simple. In traditional leukemia classification, each cell image is usually assigned to only one class such as AML, CML, ALL, or CLL. I thought this method is limited because a single label cannot describe the full meaning of a medical image.
So, we tried a different idea. Instead of assigning only one class label, we connected each image to a short descriptive sentence.
For instance:
AML → “Large immature blood cells with abnormal structure.”
CML → “High number of abnormal white blood cells in blood cells.”
ALL → “Fast-growing immature lymphocyte cells in the blood.”
CLL → “Small abnormal lymphocyte cells with slow progression.”
And other similar sentence like that.
In this work, we used both text-to-image and image-to-text learning. The model tried to understand the relation between medical images and written descriptions at the same time. We also used GAN-based methods to help balance the dataset because some classes had fewer images than others.
One challenge in this project was creating meaningful text descriptions that were simple but still useful for the model. Another challenge was the limited and unbalanced medical dataset. Training vision-language models also needed careful tuning and many experiments.
The model performance was evaluated using the metrics discussed in the paper. The final results were around the 70% range. This is not considered perfect or extremely high accuracy. However, the method is more practical and informative than traditional classification systems that only assign simple labels like 0, 1, 2, or 3.
I think the interesting part of this project was trying to make AI understand medical images in a more human-like way using language. This project showed that combining text and image understanding can open new directions in medical AI research.
In the future, this idea can be improved using larger datasets, better text descriptions, and stronger multimodal models. It may also help doctors better understand AI decisions instead of only seeing simple class outputs.
Link of paper: https://link.springer.com/article/10.1007/s44163-026-01239-7
Also links of other researches I contributed:
1- Advanced deep learning framework for automated hematological malignancy classification: Integrating FCMAE V2-WPAT with ACDB-GAN for enhanced leukemia subtype detection
https://doi.org/10.1007/s11760-025-05096-2
2- Constructive learning: A high-performance framework for fetal head circumference estimation
https://doi.org/10.1007/s11227-026-08293-z
3- Multimodal vision-language framework for text-guided leukemia classification using advanced deep learning architectures
https://doi.org/10.1007/s44163-026-01239-7
4- Advancing WBC classification: A hybrid ConvNeXtV2–Swin Transformer framework with R3GAN data balancing and CLAHE preprocessing
Follow the Topic
-
Signal, Image and Video Processing
-
Discover Artificial Intelligence
This is a transdisciplinary, international journal that publishes papers on all aspects of the theory, the methodology and the applications of artificial intelligence (AI).
-
Journal of Imaging Informatics in Medicine
This journal enhances the exchange of knowledge encompassed by the general topic of Imaging Informatics in Medicine including, but not limited to, research and practice in clinical, engineering, information technologies and techniques in all medical imaging environments.
Related Collections
With Collections, you can get published faster and increase your visibility.
Advanced AI Methods for Personalized Healthcare
The advancement of Artificial Intelligence (AI) technologies, especially Reinforcement Learning (RL) and Deep Learning (DL), is transforming healthcare, enabling innovative solutions for patient monitoring, diagnostics, and personalized treatment. These technologies facilitate the effective use of healthcare data and intelligent analytics, enhancing clinical decision-making and improving patient outcomes. AI is revolutionizing how healthcare is delivered, making it more proactive, efficient, and accessible. This Collection explores new methods and applications of AI for healthcare such as personalized healthcare. Contributions in this Collection showcase novel frameworks, case studies, and interdisciplinary approaches that drive the future of personalized healthcare, fostering innovations that bridge technology and patient care.
In this context, we are inviting original research articles, reviews, and perspective papers addressing (but not limited to) the following themes:
- Personalized medicine
- IRL for dynamic treatment regimes
- Wireless sensor networks for patient monitoring
- Identification and prevention of critical condition
- Monitoring systems within the medical devices contest
- Methodologies and tools for the rapid integration of WSNs, IoT and AI in health monitoring
- Behavior analysis of patients
- Personalized health-promoting interventions
- Ambient assisted living and active assisted living
- AI security and privacy models for healthcare applications
- AI methods for rehabilitation
Publishing Model: Open Access
Deadline: Feb 27, 2027
AI for Cybersecurity: Innovations in Threat Detection, Prevention, and Privacy
As cybersecurity threats continue to grow in both complexity and scale, artificial intelligence (AI) has become a critical tool for detecting, preventing, and mitigating cyberattacks. Techniques such as machine learning, deep learning, and federated learning have demonstrated significant potential in enhancing cybersecurity systems, from intrusion detection and malware analysis to digital forensics.
This collection highlights the latest advancements in AI for cybersecurity, focusing on practical and theoretical innovations that improve threat detection, prevention, and response. We invite contributions that address challenges in deploying AI technologies to defend against modern cyber threats while ensuring data security and confidentiality.
Topics of interest include, but are not limited to:
- Machine learning and deep learning for detecting network intrusions, anomalies, and zero-day attacks.
- AI-powered malware detection using behavioral, dynamic, and static analysis techniques.
- AI-driven real-time cybercrime detection tools for immediate data breach identification, ransomware attacks, and fraud prevention.
- Digital forensics leveraging AI to process large data volumes for incident response and cyberattack attribution.
- Hybrid AI-traditional security approaches to improve detection accuracy and reduce false positives.
- AI models for actionable threat intelligence, including predictive models for attack surface analysis and risk assessment.
- Ethical challenges in AI for cybersecurity, including issues of privacy, bias, transparency, and accountability.
This Collection supports and amplifies research related to SDG 9.
Keywords: AI for Cybersecurity; Threat Detection; Machine Learning for Security; Deep Learning for Cyber Defense; Intrusion Detection Systems; Malware Detection; Digital Forensics; Cybercrime Detection; Ransomware Detection; Threat Intelligence
Publishing Model: Open Access
Deadline: Mar 20, 2027
