Open research questions in Radiomics and Machine Learning in Medical Imaging
688 gap statements mined from Radiomics and Machine Learning in Medical Imaging papers in our 7.9M-paper local library, which holds 4,305 papers on the topic — drawn mostly from each paper's own stated research gap, future-work, challenge and limitation notes, and its abstract. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one.
Choosing where to publish on Radiomics and Machine Learning in Medical Imaging? See the ranked Medicine journals.
What the literature leaves open
The lack of intelligent computational systems to integrate complex and continuously evolving datasets. The need for improved diagnosis, treatment response prediction, and clinical decision support in cancer management. The limitations of conventional analytical approaches in cancer management.
Limited normative data available on baseline metabolic profile of the spinal cord. Lack of defined physiological benchmarks for FDG uptake in the spinal cord. Difficulty in differentiating between physiological and pathological uptake in the spinal cord.
Lack of a reliable predictive model for ASDeg following ACDF. Need for a multimodal approach integrating clinical, conventional radiomics, and deep learning features. Limited understanding of the independent significant predictors of ASDeg.
Development and validation of a deep learning radiomics model for predicting adjacent segment degeneration following anterior cervical discectomy and fusion · 2026 · DOICurrent secondary prevention measures for stroke patients have limitations. There is a need for a more accurate recurrence risk prediction model for intracranial atherosclerotic stroke.
Development of a recurrence risk prediction model for intracranial atherosclerotic stroke using HR-VWI combined with radiomics · 2026 · DOILimited sample size due to the rarity of the diseases. Potential for selection bias due to retrospective design. Difficulty in grading myxoid lesions on restricted tissue specimens.
Externally validated MRI radiomics machine learning models for differentiating between myxoid liposarcoma and myxoma · 2026 · DOILimited ability to differentiate between myxoid liposarcoma and myxoma using imaging and pathology. Substantial radiologic overlap between the two conditions. Need for reliable preoperative differentiation to guide treatment strategies and prognostic implications.
Externally validated MRI radiomics machine learning models for differentiating between myxoid liposarcoma and myxoma · 2026 · DOIIt highlights the need for personalized strategies to address the complex heterogeneity of gastric cancer. The paper identifies the gap in the current understanding of gastric cancer's molecular mechanisms and clinically actionable biomarker discovery.
Beyond Biomarkers: Machine Learning-Driven Multiomics for Personalized Medicine in Gastric Cancer · 2025 · DOIThe paper also notes the need for more comprehensive and predictive diagnostic models that integrate imaging and genomic data.
Deep Learning-Driven Multimodal Integration of miRNA and Radiomic for Lung Cancer Diagnosis · 2025 · DOICurrent CAD systems are limited by their dependence on singular deep learning architectures. The ineffectiveness of current systems in utilising multiscale features. Elevated computational complexity of current CAD systems.
Lung and Colon Cancer Classification Using Multiscale Deep Features Integration of Compact Convolutional Neural Networks and Feature Selection · 2025 · DOIOvercoming the limitations of prior CAD systems, including limited feature scope and inadequate fusion methodologies. Achieving optimal computational efficiency and high diagnostic accuracy. Integrating deep features from multiple CNNs with distinct handcrafted features.
Multi-Domain Feature Incorporation of Lightweight Convolutional Neural Networks and Handcrafted Features for Lung and Colon Cancer Diagnosis · 2025 · DOIThe integration of these features may contribute to more comprehensive toxicity risk assessment and warrants further investigation in clinical decision-making contexts.
A Multimodal Machine Learning Model Combining Dosimetric and Radiomic Shape Features for Predicting Moderate‑to‑Severe Xerostomia After Radiation Therapy for Nasopharyngeal Carcinoma · 2026 · DOIWhile muscle radiomics have been associated with strength and mobility in older adults, longitudinal applications remain understudied.
Longitudinal changes in radiomic features of skeletal muscle on CT images with changes in muscle strength and physical performance in older adults · 2026 · DOIIn addition, issues such as standardization, reproducibility, interpretability and data heterogeneity remain to be resolved.
Empowering Breast Cancer Precision Diagnosis with Advanced Ultrasound: From Radiomics to Radio-multiomics · 2026 · DOIHowever, the impact of peritumoral region size on predictive performance has not been systematically studied.
Machine-learning models for differentiating benign and malignant breast masses: Integrating automated breast volume scanning intra-tumoral, peri-tumoral features, and clinical information · 2025 · DOIExtensive qualitative and quantitative analyses, cross-dataset testing, and radiologist blind tests are carried out to demonstrate that TI-GAN can realistically model the tumor invasion under practical challenges of medical datasets such as limited data and high intra-class heterogeneity.
While the tumor mass is the most significant feature, the impacted tissue surrounding the tumor is also a significant biomarker contributing to the visual manifestation of mutations — which has not been studied as extensively.
Accurate and timely identification of ALK rearrangements remains essential but can be limited by tissue availability, cost, and turnaround time of molecular testing. Heterogeneity in treatment response and the development of both primary and acquired resistance complicate long-term disease control. External validation and clinical implementation of AI models remain limited across studies.
A limitation of this study is that all experiments were conducted on a single publicly available dataset.
Multimodal Deep Learning Radiomics Nomogram for Preoperative Breast Cancer Prediction Using Ultrasound Imaging and Clinical Data · 2026 · DOIFurther research is needed to develop and validate AI-based methods for improving PET and SPECT imaging in AD. The use of deep learning and classical machine learning techniques should be explored further. The development of new radiotracers and imaging protocols should be continued.
SPECT and PET imaging of Alzheimer’s disease revisited: from biomarkers to artificial intelligence-based prediction · 2026 · DOILimited feature scope in prior CAD systems for lung and colon cancer diagnosis. Inadequate fusion methodologies in prior CAD systems. Dependence on resource-intensive preprocessing in prior CAD systems.
Multi-Domain Feature Incorporation of Lightweight Convolutional Neural Networks and Handcrafted Features for Lung and Colon Cancer Diagnosis · 2025 · DOIRadiomic survival studies in glioblastoma report heterogeneous prognostic features, but how much of this stems from the methodology itself is rarely examined.
How Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma Cohorts · 2026Investigating the application of AI in cancer research - Developing more robust and generalizable deep learning models - Addressing ethical concerns related to AI-based decision…
The study had a limited sample size of 76 healthy adult participants, - The study did not account for partial volume effect (PVE) correction, - The study used a retrospective cross-sectional…
Further investigation of multiomics integration for GC - Development of more robust ML models for GC diagnosis and prognosis - Exploration of clinical utility of proteomic…
Beyond Biomarkers: Machine Learning-Driven Multiomics for Personalized Medicine in Gastric Cancer · 2025 · DOIClinical translation of multimodal diagnostic models for lung cancer, - Development of precise and noninvasive techniques for early diagnosis and staging, - Investigation of predictive capacity of radiomic for genetic…
Deep Learning-Driven Multimodal Integration of miRNA and Radiomic for Lung Cancer Diagnosis · 2025 · DOI
Most-cited papers in Radiomics and Machine Learning in Medical Imaging
- The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping · Radiology · 2020 · 3,931 citations
- Medical Image Segmentation Review: The Success of U-Net · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024 · 924 citations
- A Review of Deep-Learning-Based Medical Image Segmentation Methods · Sustainability · 2021 · 793 citations
- Artificial Intelligence in Cancer Research and Precision Medicine · Cancer Discovery · 2021 · 750 citations
- Modern Diagnostic Imaging Technique Applications and Risk Factors in the Medical Field: A Review · BioMed Research International · 2022 · 698 citations
- AI applications to medical images: From machine learning to deep learning · Physica Medica · 2021 · 675 citations
- The TRIPOD-LLM reporting guideline for studies using large language models · Nature Medicine · 2025 · 556 citations
- The Biological Meaning of Radiomic Features · Radiology · 2021 · 525 citations
- Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer · Nature Communications · 2020 · 508 citations
- The ANTsX ecosystem for quantitative biological and medical imaging · Scientific Reports · 2021 · 485 citations
Most recent work
- A Comprehensive Review of Multimodal Large Language Models for Medical Imaging and Omics Data · Archives of Computational Methods in Engineering · 2026
- From classical machine learning to emerging foundation models: review on multimodal data integration for cancer research · Artificial Intelligence Review · 2026
- Treg-driven magnetic resonance radiomics in glioblastoma: a multicenter and cross-species model for prognostic biomarker discovery · Cancer Letters · 2026
- MRI-Based Radiomics for Non-Invasive Prediction of Molecular Biomarkers in Gliomas · Cancers · 2026
- Topologically distinct 2D and 3D intratumoral heterogeneity scores for preoperatively predicting invasiveness in stage I lung adenocarcinoma: A multicenter study · PLOS Digital Health · 2026
- Handcrafted vs. Deep Radiomics vs. Fusion vs. Deep Learning: A Comprehensive Review of Machine Learning -Based Cancer Outcome Prediction in PET and SPECT Imaging · Journal of Imaging Informatics in Medicine · 2026
- Preoperative CT-based topologically distinct intratumoral heterogeneity scores for predicting intratumoral tertiary lymphoid structures and outcomes in hepatocellular carcinoma: A multicenter study · European Journal of Surgical Oncology · 2026
- Hybrid 2D/3D CNN and radiomics model for brain tumor classification using EfficientNetb0 and ResNet-18 · BMC Medical Imaging · 2026
- Multi-omics deep learning improves FDG PET-CT-based long-term prognostication of breast cancer · npj Precision Oncology · 2026
- AI-Driven Advances in Precision Oncology: Toward Optimizing Cancer Diagnostics and Personalized Treatment · AI · 2026
Find a gap in your own Radiomics and Machine Learning in Medical Imaging sub-topic
This page shows what the Radiomics and Machine Learning in Medical Imaging literature already flags as unresolved. To narrow it to your specific question, search the Research Gap Finder: the search is free with a free account and lists the papers closest to your topic first. Unlocking that topic (50 credits, charged once) fills the comparison table from our 7.9M-paper local library and writes the gaps from its rows.
Open the Research Gap Finder →