Aims and scope

The last quarter century has witnessed major advancements that have brought biomedical imaging to a paramount status in life sciences. As a prominent example, the National Institute of Biomedical Imaging and Bioengineering (NIBIB) was established in 2000 as the newest institute in the National Institutes of Health (NIH), USA. Generally speaking, the scope of biomedical imaging covers data acquisition, image reconstruction, and image analysis, involving theories, methods, systems, and applications. While tomographic and post-processing techniques become increasingly sophisticated, traditional and emerging modalities play more and more critical roles in anatomical, functional, cellular, and molecular imaging. The overall goal of the International Journal of Biomedical Imaging is to promote research and development of biomedical imaging by publishing high-quality research articles and reviews in this rapidly growing interdisciplinary field.

International Journal of Biomedical Imaging is operated by a board of editors consisting of internationally known active researchers. The journal is made available online for free and can also be purchased in print. It utilizes a web-based review process for speedy turnaround up to high standards. In addition to regular issues, special issues will be organized by guest editors. Subject areas include (but are not limited to):

    Digital radiography and tomosynthesis
    X-ray computed tomography (CT)
    Magnetic resonance imaging (MRI)
    Single photon emission computed tomography (SPECT)
    Positron emission tomography (PET)
    Ultrasound imaging
    Diffuse optical tomography, coherence, fluorescence, bioluminescence tomography, impedance tomography
    Neutron imaging for biomedical applications
    Magnetic and optical spectroscopy, and optical biopsy
    Optical, electron, scanning tunneling/atomic force microscopy
    Small animal imaging
    Functional, cellular, and molecular imaging
    Imaging assays for screening and molecular analysis
    Microarray image analysis and bioinformatics
    Emerging biomedical imaging techniques
    Imaging modality fusion
    Biomedical imaging instrumentation
    Biomedical image processing, pattern recognition, and analysis
    Biomedical image visualization, compression, transmission, and storage
    Imaging and modeling related to systems biology and systems biomedicine
    Applied mathematics, applied physics, and chemistry related to biomedical imaging
    Grid-enabling technology for biomedical imaging and informatics

Special Issue on Transforming Healthcare with AI: Automated Interpretation of Medical Scans
Submission Date: 2026-03-20

Description

Artificial intelligence (AI) is rapidly changing the landscape of healthcare, especially in how medical scans are interpreted. AI-powered tools, such as deep learning algorithms, are revolutionizing radiology, pathology, neuroimaging, and other imaging-intensive fields by enhancing diagnostic accuracy, benchmarking performance, and reducing interpretation times. These technologies are increasingly central to clinical decision-making, with applications such as AI in lung cancer screening demonstrating improved early detection and workflow efficiency. Decentralized AI models and privacy-preserving techniques are also gaining traction, enabling secure data sharing and analysis across institutions.

Despite its promise, the widespread adoption of AI in medical scan interpretation faces significant challenges. Key issues include the need for large, diverse, and well-annotated datasets to develop robust models and to address concerns about algorithmic bias, transparency, and generalizability across diverse populations and imaging modalities. Interpretability and reliability of AI models remain critical for clinician trust and regulatory approval, while integration into existing workflows continues to be a barrier. The “black-box” nature of many systems raises ethical and legal questions, particularly around accountability in diagnostic errors. Addressing these issues requires interdisciplinary collaboration among researchers, clinicians, policymakers, and industry stakeholders to ensure effective and long-standing solutions

This special issue aims to highlight innovative research and practical advancements in automated interpretation of medical images and scans, including validation studies, real-world implementations, and ethical frameworks. We invite original research as well as reviews on novel algorithms, clinical adoption strategies, decentralized architectures, and reliability assessments that advance the field. By bringing together diverse perspectives, this issue seeks to highlight ways in which AI can be responsibly integrated in healthcare and improve diagnostic precision, accessibility, and patient outcomes globally.

Potential topics include but are not limited to the following:

    AI in lung cancer screening and neuroimaging
    AI performance benchmarking
    Data privacy in medical imaging
    Machine Learning and Neural Networks in the automated interpretation of biomedical scans
    Reliability of AI-interpreted scans
    Challenges in Clinical adoption of AI in healthcare

Editors

Lead Guest Editor

Abhishek Gupta1
1Central Scientific Instruments Organisation, India

Guest Editors

shailendra rana1 | Nitin Kumar2
1AIIMS Bathinda, India
2Punjab Engineering College Chandigarh, India

Special Issue on Foundations, Frameworks, and Evidence for Translational AI in Breast Cancer Care
Submission Date: 2026-05-25

Description

Translational AI refers to the process of turning artificial intelligence innovations into practical, reliable, effective, and user-friendly tools that deliver sustained impact in real-world clinical settings. In breast imaging, this means bridging the gap between promising algorithmic developments and their safe, trusted, and meaningful integration into daily clinical workflows. While AI systems have demonstrated promising performance in breast cancer detection, risk prediction, density classification, and workflow optimization, these advances only become valuable when they translate into improved outcomes, enhanced efficiency, and better experiences for patients, clinicians, and health systems. As the field matures, the focus must shift from controlled evaluations to human-centered co-development and toward scalable, sustainable, and continuously monitored implementation.

Despite growing evidence and regulatory approvals, the real-world integration and adoption of breast imaging AI tools remain limited. Clinical environments are dynamic—data distributions shift, local workflows vary, and AI-integrated performance can drift or degrade over time with such changes. These realities necessitate localized validation prior to deployment, intentional workflow integration supported by change management, and robust post-deployment monitoring. Usability, explainability, and clinician trust are often underprioritized in development and remain inadequate, creating persistent barriers to acceptance and sustained use—even when tools are supported by rigorous evidence. Moreover, most current systems lack the ability to adapt to changing conditions, posing additional challenges related to safety and reliability and prompting regulatory and ethical considerations. Without intentional co-development between technology developers and clinical service providers–and continued collaboration with clinical, operational, technical, health economic, and patient stakeholders–even the highest-performing AI systems risk falling short of delivering meaningful real-world value and impact.

This Special Issue will focus on advancing the science and practice of Translational AI in breast imaging by addressing a critical gap between innovation and implementation that drives adoption and impact. We welcome contributions on self-correcting and adaptive learning systems, algorithmic bias and fairness analysis of AI systems, stress testing model robustness and reliability, explainability and interpretability of AI systems, real-world deployment strategies, and clinical safety monitoring. Submissions exploring clinician trust-building, human-AI collaboration, and effective change management are especially encouraged. By bringing together research, perspectives, and case studies around these themes, this issue aims to spotlight the multidisciplinary efforts needed to ensure that breast imaging AI systems are not only high-performing but also usable, accepted, and integrated for long-term success in routine patient care.

Potential topics include but are not limited to the following:

    Self-correcting and adaptive learning systems in breast imaging AI
    Algorithmic bias and fairness analysis of AI systems
    Stress testing model robustness and reliability
    Explainability and interpretability of breast imaging AI systems
    Real world implementation and change management for deploying breast imaging AI systems
    Monitoring breast imaging AI in clinical practice
    Strategies and approaches for fostering trust in breast imaging AI

Special Issue on Explainable and Trustworthy AI for Multimodal Biomedical Imaging in Early Cancer Detection
Submission Date: 2026-06-30

Description

The early detection of cancer remains one of the most effective strategies for improving survival rates and reducing treatment costs. Biomedical imaging modalities: such as mammography, magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), ultrasound, and dermoscopy; play a pivotal role in cancer screening, diagnosis, and monitoring. To broaden the applicability and societal impact of this research, this Special Issue expands its scope to include diverse cancer types such as breast, lung, brain, colon, liver, pancreatic, and skin cancers. These inclusions ensure that the findings and methodologies presented are representative of the wide spectrum of cancers encountered in clinical practice. Artificial intelligence (AI) and machine learning (ML) techniques have significantly advanced cancer imaging by improving image interpretation, pattern recognition, and predictive analysis, ultimately contributing to precision oncology.

Despite these advances, major challenges persist in deploying AI-driven solutions in clinical environments. Many powerful AI systems operate as “black boxes,” generating predictions without explaining the rationale behind their decisions. This lack of interpretability can lead to reduced clinician trust and hesitancy in adoption. Moreover, AI models often suffer from issues related to data imbalance, limited generalizability across imaging modalities, and potential biases that may compromise fairness and robustness. Addressing these issues requires frameworks that emphasize not only high accuracy but also transparency, accountability, and clinical reliability.

This Special Issue focuses on the development and integration of Explainable AI (XAI) and Trustworthy AI (TAI) methodologies for multimodal biomedical imaging in early cancer detection. Explainable AI (XAI) refers to computational techniques that make AI model decisions interpretable to humans, allowing clinicians to understand and validate model reasoning. Trustworthy AI (TAI) encompasses systems that ensure fairness, robustness, privacy, and accountability, fostering confidence in real-world clinical deployment. The issue will welcome contributions leveraging deep learning, fuzzy logic, neural networks, and hybrid AI approaches for interpretable and dependable cancer diagnosis. By bridging computational innovation and medical application, this Special Issue aims to promote multidisciplinary collaboration and advance AI-driven diagnostic frameworks that are transparent, fair, and clinically applicable.

Common XAI techniques include:

• SHAP (SHapley Additive exPlanations): Quantifies the contribution of each input feature (e.g., pixel intensity, region of interest) to the model’s output, enabling local and global interpretability.
• LIME (Local Interpretable Model-Agnostic Explanations): Provides simple, interpretable models (e.g., linear approximations) around individual predictions to show which factors most influenced a decision.
• Grad-CAM (Gradient-weighted Class Activation Mapping): Generates heatmaps highlighting critical regions in medical images that contributed to the model’s prediction.
• Integrated Gradients and Attention Mechanisms: Offer gradient-based and model-intrinsic interpretability to enhance clinical trust and visual transparency.

By applying these techniques, XAI ensures that clinicians can validate model reasoning, detect potential biases, and understand the diagnostic rationale—facilitating greater confidence in AI-assisted decision-making.

Key aspects of Trustworthy AI (TAI) include:

• Robustness and Reliability: The model performs consistently across different imaging modalities, scanners, and demographic groups.
• Fairness and Bias Mitigation: Techniques are employed to prevent discrimination based on gender, race, or socioeconomic factors.
• Data Security and Privacy Preservation: Federated learning and differential privacy methods protect patient information during AI training and deployment.
• Ethical Accountability: Compliance with healthcare regulations and ethical AI frameworks ensures responsible use of data and algorithms.

Together, XAI and TAI create a comprehensive foundation for developing interpretable, fair, and clinically dependable AI systems. Their integration into biomedical imaging research aligns technical innovation with ethical and regulatory standards, accelerating the safe translation of AI into clinical oncology practice.

Potential topics include but are not limited to the following:

    Explainable AI frameworks for multimodal cancer imaging (e.g., MRI, CT, PET, ultrasound, dermoscopy)
    Trustworthy and robust AI systems for early detection across diverse cancer types (brain, lung, breast, colon, liver, pancreatic, skin, etc.)
    Methodological advancements using deep learning, fuzzy logic, neural networks, and hybrid AI models
    Integration of imaging data with genomic, pathological, and clinical metadata for predictive and personalized cancer modeling
    Quantitative evaluation of explainability, fairness, robustness, and generalizability of AI models in clinical settings
    Emerging imaging technologies and their AI-enhanced capabilities for early diagnosis
    Real-world deployment strategies and clinical translation of interpretable AI systems
    Ethical, regulatory, and privacy considerations in the development and adoption of AI-driven cancer diagnostics

Special Issue on Machine Learning Approaches in Brain Tumor Segmentation
Submission Date: 2026-08-31

Description

Biomedical imaging has emerged as an indispensable pillar of modern healthcare, enabling non-invasive visualization, diagnosis, and monitoring of a wide range of medical conditions. With the rapid evolution of imaging modalities such as MRI, CT, PET, ultrasound, and optical imaging, there is an unprecedented ability to capture high-resolution anatomical, functional, and molecular information. These advances, coupled with the integration of artificial intelligence (AI), machine learning (ML), and computational modeling, are revolutionizing the way clinicians interpret images, detect abnormalities, and tailor patient-specific treatment plans. Brain tumour segmentation plays a vital role in accurate diagnosis, treatment planning, and prognosis in neuro-oncology. With the rapid advancement of artificial intelligence, machine learning and deep learning techniques have emerged as powerful tools for automating the segmentation process from medical imaging data, particularly Magnetic Resonance Imaging (MRI).

Despite these advancements, several challenges continue to hinder the full realization of biomedical imaging’s potential. High data complexity, variability in acquisition protocols, and the presence of noise and artifacts often limit the reproducibility and accuracy of image interpretation. Moreover, the integration of heterogeneous imaging data from multiple modalities requires sophisticated algorithms capable of handling large-scale, multidimensional datasets while ensuring interpretability and clinical relevance. Regulatory, ethical, and data privacy concerns also present barriers to the widespread adoption of AI-driven imaging solutions in clinical practice. Additionally, real-time processing demands in critical care, intraoperative guidance, and point-of-care diagnostics remain largely unmet, necessitating the development of more efficient and robust computational approaches.

This Special Issue aims to bring together advanced research and innovative methodologies that address the challenges and opportunities in brain tumour segmentation using machine learning. We welcome contributions that explore novel algorithms, deep learning architectures, image preprocessing strategies, and feature extraction techniques for accurate and efficient segmentation of brain tumours from medical imaging modalities, particularly Magnetic Resonance Imaging (MRI). Topics of interest include AI-driven diagnostic frameworks, including convolutional neural networks (CNNs) and hybrid deep learning architectures, multimodal imaging fusion, automated tumour classification, and the integration of quantitative imaging biomarkers for clinical decision support. Special emphasis will be placed on approaches that enhance segmentation accuracy, improve robustness across diverse datasets, reduce computational complexity, and enable real-time analysis in clinical environments. By fostering collaboration between computer scientists, radiologists, and biomedical engineers, this Special Issue seeks to bridge the gap between algorithmic innovation and clinical applicability, ultimately contributing to early detection, precise treatment planning, and improved outcomes for patients with brain tumours.

Potential topics include but are not limited to the following:

    Advanced image (particularly MRI) reconstruction and enhancement techniques
    CNN and deep learning architectures for precise delineation of tumor regions such as gliomas, meningiomas, and pituitary tumors
    Integrating automated brain tumor segmentation into clinical workflows
    Computational models for precision diagnostics and therapeutics