Science AI Journal
Medicine · Research topic

Open research questions in Medical Imaging Techniques and Applications

58 unresolved questions extracted from the limitations and future-work sections of 230 Medical Imaging Techniques and Applications papers in our library. Each links back to the study that raised it.

What the literature leaves open

  • Accurately assessing all lesions and understanding their spatial distribution remains a significant challenge. The study also identifies the challenge of ignoring physiologically high-uptake regions in PET.

    Anatomy-aware lymphoma lesion detection in whole-body PET/CT · 2026 · DOI

  • Detecting liver metastases from uveal melanoma using standard imaging approaches can be challenging. Dynamic PET imaging has technical complexity and limited clinical implementation. Interindividual differences in hepatic metabolism, tumor perfusion, and systemic tracer clearance can affect imaging results.

    Are liver metastases from uveal melanoma a clinical indication for dynamic PET? A comparison of Patlak parametric imaging with standard and delayed static SUV imaging using long axial field-of-view PET/CT · 2026 · DOI

  • The interpretation of changes in contrast enhancement and tumor necrosis on CT. The high rates of false positive findings on [18F]FDG PET. The need for robust evidence on the use of [18F]FDG PET in immunotherapy.

    [18F]FDG PET during immunotherapy: mind the gap between evidence, imaging guidelines, and oncology practice · 2026 · DOI

  • The dataset size may be relatively limited, which may disadvantage the larger transformer-based models. The framework operates with approximately 50% missing data and 1/3 missing detectors.

    Two-stage deep learning framework for the restoration of incomplete-ring PET images · 2026 · DOI

  • To further improve the performance of the framework using larger datasets. To apply the framework to various clinical applications, such as brain imaging and cancer diagnosis.

    Two-stage deep learning framework for the restoration of incomplete-ring PET images · 2026 · DOI

  • The study used simulated and clinical datasets, but the sample size is limited. The framework was evaluated using a specific set of metrics, but other metrics may be relevant. The study did not investigate the use of other group representations.

    SO(3)-based and structure-guided deformable registration for respiratory motion correction in thoracic PET · 2026 · DOI

  • Investigating the use of other group representations. Evaluating the framework using larger clinical datasets. Investigating the application of the framework to other imaging modalities.

    SO(3)-based and structure-guided deformable registration for respiratory motion correction in thoracic PET · 2026 · DOI

  • Baseline M-stage assessment was limited by the low number of clinically confirmed M1 cases.

    Stage-dependent performance and molecular subtype-specific relapse patterns on same-session [18F]FDG PET/contrast-enhanced CT in breast cancer · 2026 · DOI

  • The released codebase was tested on a workstation equipped with specific high-end hardware (two NVIDIA GeForce RTX 3090 GPUs, Intel Xeon Gold 5218 CPU, 128GB RAM), potentially limiting accessibility and scalability to different computing environments.

    Real-time reconstruction of 3D bone models via very-low-dose protocols · 2026 · DOI

  • The application of transformer-based architectures (referenced in the paper's discussion of recent advances in medical image analysis) versus traditional convolutional neural networks for cross-platform PET harmonization in the context of amyloid and tau quantification has not been empirically compared in neurodegenerative disease imaging.

    A unified deep learning framework for cross-platform harmonization of multi-tracer PET quantification in neurodegenerative disease · 2026 · DOI

  • The framework's generalizability to scanner configurations combining different attenuation correction methods (bone-inclusive vs. bone-exclusive Dixon models, synthetic CT generation variants) across integrated PET/MRI and standalone PET/CT systems in multi-center neurodegenerative disease studies requires systematic evaluation.

    A unified deep learning framework for cross-platform harmonization of multi-tracer PET quantification in neurodegenerative disease · 2026 · DOI

  • In addition, timing analy- ses were limited by the incomplete availability of paired surgery and PET/ceCT dates, which prevented a robust subtype-specific evaluation of time-to-relapse.

    Site-Specific Patterns of Distant Relapse on ^18F-FDG PET/Contrast-Enhanced CT According to Molecular Subtype in Breast Cancer: A Retrospective Cohort Study · 2026 · DOI

  • The study did not include scatter correction, which may reduce image contrast and affect quantitative accuracy. The study used a limited number of phantoms and acquisition modes.

    Implementation of continuous bed motion acquisition on a preclinical digital PET/CT system: Monte Carlo simulation and experimental measurements · 2026 · DOI

  • Further studies are needed to evaluate the performance of the CBM mode in preclinical PET systems. The effect of scatter correction on the CBM mode should be investigated.

    Implementation of continuous bed motion acquisition on a preclinical digital PET/CT system: Monte Carlo simulation and experimental measurements · 2026 · DOI

  • The study identifies a gap in the current lesion detection methods, which do not effectively utilize anatomical information. The study aims to address this gap by investigating the effect of adding anatomical priors.

    Anatomy-aware lymphoma lesion detection in whole-body PET/CT · 2026 · DOI

  • Conventional correction methods have limitations related to accuracy, radiation exposure, and practical applicability. Deep neural networks have shown promise but are limited by instability during training and mode collapse.

    GPDM: generation-prior diffusion model for accelerated direct attenuation and scatter correction of whole-body 18F-FDG PET · 2026 · DOI

  • Bao, Understanding gans: Funda- mentals, variants, training challenges, applications, and open problems, Multimed. Moreover, the trained model is not limited to a specific scanner; it can be applied to different PET scanners, enabling the generation of ASC PET even on PET scanners without CT or MR capabilities.

    GPDM: generation-prior diffusion model for accelerated direct attenuation and scatter correction of whole-body 18F-FDG PET · 2026 · DOI

  • The effect of SUVmax thresholds on FDG-PET/CT segmentation is not well established. There is a need for a comprehensive comparison of SUVmax thresholds for FDG-PET/CT segmentation.

    Optimising FDG-PET/CT Segmentation in Metastatic Breast Cancer: Comparison of SUVmax Thresholds Using syngo.via · 2026 · DOI

  • Moreover, site-specific variations—such as bone versus liver metastases—may affect the optimal threshold, but were not analysed separately in this study. Future research should confirm these results in larger, multicentre cohorts and explore the relationship between threshold-dependent PET metrics and clinical outcomes, including progression-free and overall survival. Additionally, investigating the utility of adaptive or machine learning-based thresholding techniques may further enhance segmentation accuracy and reliability across diverse lesion types and imaging systems. Finally, this study did not include a ground-truth reference (e.g., expert manual contours or phantom-validated thresholds). erefore, the findings primarily describe how threshold choice influences derived metrics rather than absolute delineation accuracy.

    Optimising FDG-PET/CT Segmentation in Metastatic Breast Cancer: Comparison of SUVmax Thresholds Using syngo.via · 2026 · DOI

  • The clinical utility of dynamic PET imaging in detecting liver metastases from uveal melanoma is not well established. Prior work has shown that static SUV imaging may not be optimal for detecting liver metastases from uveal melanoma.

    Are liver metastases from uveal melanoma a clinical indication for dynamic PET? A comparison of Patlak parametric imaging with standard and delayed static SUV imaging using long axial field-of-view PET/CT · 2026 · DOI

  • The need for efficient sparse-view CT reconstruction. The lack of understanding of the importance of global coverage in ray selection for NeRF-based CT reconstruction.

    Analyzing Ray Sampling and Layer Normalization Contributions in NeRF-based CT Reconstruction · 2026 · DOI

  • Wang, "Structure-aware sparse-view X-ray 3D reconstruction," in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, Jun.

    Analyzing Ray Sampling and Layer Normalization Contributions in NeRF-based CT Reconstruction · 2026 · DOI

  • The study is a preliminary study, requiring further investigation. The study only examined one patient's 18F-FDG brain image.

    Impact of Image Reconstruction on Quantitative Analysis of 18F-FDG PET in Epilepsy Evaluation: A Preliminary Study · 2026 · DOI

  • The lack of optimal image reconstruction configurations for reliable clinical decision-making in epilepsy evaluation. The need for further investigation into the influence of image reconstruction configurations on quantitative metrics within cerebral PET images.

    Impact of Image Reconstruction on Quantitative Analysis of 18F-FDG PET in Epilepsy Evaluation: A Preliminary Study · 2026 · DOI

  • Existing methods fail to reconstruct decent images due to ill-defined sampling conditions. There is a need for a method that can effectively suppress artifacts in TCT images.

    ProTCT: projection quantification and fidelity constraint integrated deep reconstruction for Tangential CT · 2026 · DOI

Most-cited papers in Medical Imaging Techniques and Applications

Most recent work

Find a gap in your own Medical Imaging Techniques and Applications sub-topic

This page shows what the Medical Imaging Techniques and Applications literature already flags as unresolved. To narrow it to your specific question, run the guided finder — it searches the gap library on demand and checks candidates against 250M+ OpenAlex works.

Open the Research Gap Finder →

Related topics in Medicine

Substance Abuse Treatment and Outcomes
1,213 open questions
Artificial Intelligence in Healthcare and Education
1,153 open questions
Physical Activity and Health
718 open questions
Dementia and Cognitive Impairment Research
565 open questions
Attention Deficit Hyperactivity Disorder
544 open questions
Smoking Behavior and Cessation
532 open questions
Innovations in Medical Education
480 open questions
HIV/AIDS Research and Interventions
472 open questions
58 open questions have been extracted from the limitations and future-work passages of 230 Medical Imaging Techniques and Applications papers in our library. Each one below links back to the study that raised it, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 120,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? A Tier 1–5 acceptance probability in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck prior-publication & salami-slicing risk across 8 sources.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.