Papers

Field

Top tools here

Open problems in Image segmentation

Lack of benchmarks for real-world clinical deployment1 paper raises it · 0 address it
Current benchmarks do not reflect how clinicians actually use AI systems, limiting their predictive value for real-world performance.
- Clinician use of language models diverges from how the models are evaluatedraises
Handling incidental or irrelevant information in clinical data1 paper raises it · 0 address it
Models may misattribute or be distracted by non-clinical content, leading to errors in documentation and reasoning.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises
Scaling generative models to gigapixel whole-slide images1 paper raises it · 1 addresses it
Existing models generate only small patches, while clinical supervision operates at the whole-slide level.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Temporal modeling of longitudinal clinical data2 papers raise it · 2 address it
Accurate risk prediction requires modeling irregular, multimodal clinical trajectories over time.
- TRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Predictionraises · addresses
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Parameter-efficient fine-tuning for large medical models2 papers raise it · 2 address it
Training or fine-tuning large models on limited medical data is computationally expensive and impractical.
- Scaling Parameter-Efficient Fine-Tuning for Brain Encodingraises · addresses
- Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

image segmentation · volumetric · medical image409 papers39 this week
radiology report generation · medical vision language · vision language models133 papers34 this week
clinical reasoning · question answering · language models210 papers20 this week
eeg foundation models · electroencephalography eeg · eeg foundation158 papers19 this week
patient history · clinical data · health records112 papers17 this week
electrocardiogram ecg · electrocardiogram · ecgs147 papers13 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.CVSep 22
Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer
Yuan Liang, Fangyijie Wang, Kathleen M. Curran, Guénolé Silvestre, Sourav Bhattacharjee +1
Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced CT remains clinically challenging because clear cell RCC (ccRCC) and non-clear cell RCC often show overlapping imaging appearances. This study evaluates whether foundation representations reduce reliance on handcrafted radiomics, or whether radiomics remains complementary for interpretable tumour characterisation. We compared radiomics, conventional CNN features, MedicalNet-pretrained features, MedVAE representations, and fusion variants for binary ccRCC classification on KiTS23, reporting area under the receiver operating characteristic curve (AUC) with bootstrap confidence intervals and average precision (AP) as a complementary class-imbalance-sensitive metric. We further assessed branch-removal ablation, TCGA/AIMI external transfer, and interpretability using radiomics permutation importance and gate-level analysis. Internally, 3D MedVAE gated fusion achieved the best performance, with an AUC of 82.7% and AP of 92.2%. On the external TCGA cohort, the same model achieved an AUC of 79.5% and AP of 98.9%, although specificity remains uncertain because only two external non-ccRCC…
PDF arXiv
arXiv cs.CVSep 22
When Retrieval Hurts: Measuring and Explaining Retrieval-Induced Hallucination in Chest X-ray Report Generation
Emmanuel Idoko, Abdusshakur Olabisi, Shiloh Oni, Adesola Josiah
Retrieval-augmented generation is an attractive way to improve chest X-ray reporting, because reports from similar prior studies supply clinical context a general vision-language model lacks. We show the same mechanism is a reliable source of clinical error. Over 100 MIMIC-CXR studies with a frozen LLaVA-1.5 generator and BioMedCLIP retrieval, CheXbert clinical F1 doubles under relevant retrieval (0.201 to 0.402) and collapses to 0.043 under clinically mismatched retrieval, a fifth of the image-only score; the retrieval-induced hallucination rate, counting only unsupported findings traceable to retrieved evidence, rises from 0.00 to 0.76 and 0.98. To show this is not an artefact of evidence-set coverage, we introduce a coincidental-overlap control that scores image-only generations against evidence they never saw, placing the chance base rate at 0.18, four to five times below the observed rates. The generator does not merely acquire findings, it transcribes text: 95% of reports produced under relevant retrieval contain an eight-word span occurring verbatim in the retrieved evidence but absent from the reference, against 0% without retrieval. We then explain the mechanism: a…
PDF arXiv
arXiv cs.CVSep 22
Radiomics-Conditioned Modulation of RenalCLIP Features for Clear Cell Renal Cell Carcinoma Classification
Yuan Liang, Sourav Bhattacharjee, Abraham Campbell
Radiomics provides quantitative descriptions of tumour appearance that may complement disease-specific foundation models in small labelled cohorts. We investigate this complementarity for computed tomography-based classification of clear cell renal cell carcinoma. Our framework uses radiomics to modulate RenalCLIP features through feature-wise linear modulation (FiLM), while retaining a direct radiomics contribution. Internal testing and external validation compare it with conventional fusion strategies and reference classifiers. The FiLM model achieves an area under the receiver operating characteristic curve (AUC) of 0.804 internally and 0.854 externally, with the highest mean AUC among the evaluated RenalCLIP fusion strategies in both cohorts. Pathway ablations examine the contributions of conditional modulation and the direct radiomics residual, while feature permutation highlights the role of tumour texture. These findings support radiomics as a useful complement to RenalCLIP in a small labelled cohort and identify FiLM as an effective approach to integrating their representations for robust renal tumour classification.
PDF arXiv
arXiv cs.CVSep 22
Complementary Roles of Radiomics and Foundation Representations in Renal Cell Carcinoma Classification: A Comparative Study of 2D and 3D CT Encodings
Yuan Liang, Sourav Bhattacharjee, Abraham Campbell
Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides structured tumour descriptors, whereas foundation representations offer transferable image features. However, it remains unclear whether radiomics still adds value beyond pretrained representations, and how 2D and 3D MedVAE encoders compare in this setting. We compared handcrafted radiomics, 2D MedVAE, 3D MedVAE, and their fusion for binary clear-cell RCC versus non-clear-cell RCC classification on KiTS23 under a unified preprocessing pipeline. Concatenation, cross-attention, and gated fusion were evaluated as representative integration strategies, and radiomics feature importance was analysed to support decision-centric interpretability. Fusion consistently improved discrimination over image-only MedVAE branches. The best overall performance was achieved by 3D gated fusion, with an AUC of 82.7\%, outperforming the best 2D fusion model (79.6%), the radiomics baseline (74.4%), and the single-modality MedVAE branches. Ablation analysis further showed clear gains of the full fusion model over both image-only and…
PDF arXiv
arXiv cs.CVSep 22
Mammo-LIFE: Longitudinal Mammographic Imaging and Clinical Feature Enrichment for Post-Radiotherapy Outcome Prediction
Farnoush Bayatmakou, Maryam Hosseini, Reza Taleei, Arash Mohammadi
Recent advances in Artificial Intelligence (AI)-powered Computer-Aided Diagnosis (CAD) systems have substantially improved breast cancer screening, diagnosis, and prognosis. Comparatively, postradiotherapy outcome prediction using paired longitudinal mammograms has received considerably less attention. This is largely due to the limited availability of well-annotated longitudinal datasets. Longitudinal mammograms, coupled with paired pre- and post-treatment information, provide a unique opportunity to characterize treatment-induced breast tissue changes following radiotherapy. The resulting learned representations can serve as a valuable asset for advancing personalized radiotherapy planning and post-treatment management. In this context, we propose Mammo-LIFE, a patient-level multimodal framework for post-radiotherapy outcome prediction that combines longitudinal mammographic features with patient-level clinical variables. The imaging branch processes paired pre- and post-treatment mammograms acquired from the four standard views using a mammography-specific encoder adapted via Low-Rank Adaptation (LoRA). Within each view, preand post-treatment representations are explicitly…
PDF arXiv
arXiv cs.LGSep 22
Learning to Defer with Guidance on Real World Medical Data
Emma Sun, Joshua Strong, Alison Noble
Medical image interpretation is high-volume and time-consuming, and while AI interpretation can reduce workload, fully autonomous deployment carries potential safety concerns and low specificity may in practice lead to increased clinician workload. Learning to Defer (L2D) addresses this by selectively routing cases between autonomous prediction and human experts by learning from input features and AI model and human performance. While theoretical guarantees have been proven for L2D, its performance has not been validated on real-world medical datasets with human reader annotations. We evaluate the predictor-rejector formulation of two-stage L2D, where the AI predictor model is fixed and separate from the trainable routing or rejector model, on Collab-CXR, a multilabel chest X-ray dataset with multiple human annotations per case. This is the first work to look at L2D in the context of real-world medical imaging data with human annotations. We further introduce a new setup, L2D with Guidance, where the decision space is extended to three choices: predict autonomously, defer to a human expert, or defer to a human expert and provide AI guidance. We compare multiple rejector…
PDF arXiv

Papers

Topics in this field

image segmentation · volumetric · medical image409 papers39 this week
radiology report generation · medical vision language · vision language models133 papers34 this week
clinical reasoning · question answering · language models210 papers20 this week
eeg foundation models · electroencephalography eeg · eeg foundation158 papers19 this week
patient history · clinical data · health records112 papers17 this week
electrocardiogram ecg · electrocardiogram · ecgs147 papers13 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.CVSep 22
Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer
Yuan Liang, Fangyijie Wang, Kathleen M. Curran, Guénolé Silvestre, Sourav Bhattacharjee +1
Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced CT remains clinically challenging because clear cell RCC (ccRCC) and non-clear cell RCC often show overlapping imaging appearances. This study evaluates whether foundation representations reduce reliance on handcrafted radiomics, or whether radiomics remains complementary for interpretable tumour characterisation. We compared radiomics, conventional CNN features, MedicalNet-pretrained features, MedVAE representations, and fusion variants for binary ccRCC classification on KiTS23, reporting area under the receiver operating characteristic curve (AUC) with bootstrap confidence intervals and average precision (AP) as a complementary class-imbalance-sensitive metric. We further assessed branch-removal ablation, TCGA/AIMI external transfer, and interpretability using radiomics permutation importance and gate-level analysis. Internally, 3D MedVAE gated fusion achieved the best performance, with an AUC of 82.7% and AP of 92.2%. On the external TCGA cohort, the same model achieved an AUC of 79.5% and AP of 98.9%, although specificity remains uncertain because only two external non-ccRCC…
PDF arXiv
arXiv cs.CVSep 22
When Retrieval Hurts: Measuring and Explaining Retrieval-Induced Hallucination in Chest X-ray Report Generation
Emmanuel Idoko, Abdusshakur Olabisi, Shiloh Oni, Adesola Josiah
Retrieval-augmented generation is an attractive way to improve chest X-ray reporting, because reports from similar prior studies supply clinical context a general vision-language model lacks. We show the same mechanism is a reliable source of clinical error. Over 100 MIMIC-CXR studies with a frozen LLaVA-1.5 generator and BioMedCLIP retrieval, CheXbert clinical F1 doubles under relevant retrieval (0.201 to 0.402) and collapses to 0.043 under clinically mismatched retrieval, a fifth of the image-only score; the retrieval-induced hallucination rate, counting only unsupported findings traceable to retrieved evidence, rises from 0.00 to 0.76 and 0.98. To show this is not an artefact of evidence-set coverage, we introduce a coincidental-overlap control that scores image-only generations against evidence they never saw, placing the chance base rate at 0.18, four to five times below the observed rates. The generator does not merely acquire findings, it transcribes text: 95% of reports produced under relevant retrieval contain an eight-word span occurring verbatim in the retrieved evidence but absent from the reference, against 0% without retrieval. We then explain the mechanism: a…
PDF arXiv
arXiv cs.CVSep 22
Radiomics-Conditioned Modulation of RenalCLIP Features for Clear Cell Renal Cell Carcinoma Classification
Yuan Liang, Sourav Bhattacharjee, Abraham Campbell
Radiomics provides quantitative descriptions of tumour appearance that may complement disease-specific foundation models in small labelled cohorts. We investigate this complementarity for computed tomography-based classification of clear cell renal cell carcinoma. Our framework uses radiomics to modulate RenalCLIP features through feature-wise linear modulation (FiLM), while retaining a direct radiomics contribution. Internal testing and external validation compare it with conventional fusion strategies and reference classifiers. The FiLM model achieves an area under the receiver operating characteristic curve (AUC) of 0.804 internally and 0.854 externally, with the highest mean AUC among the evaluated RenalCLIP fusion strategies in both cohorts. Pathway ablations examine the contributions of conditional modulation and the direct radiomics residual, while feature permutation highlights the role of tumour texture. These findings support radiomics as a useful complement to RenalCLIP in a small labelled cohort and identify FiLM as an effective approach to integrating their representations for robust renal tumour classification.
PDF arXiv
arXiv cs.CVSep 22
Complementary Roles of Radiomics and Foundation Representations in Renal Cell Carcinoma Classification: A Comparative Study of 2D and 3D CT Encodings
Yuan Liang, Sourav Bhattacharjee, Abraham Campbell
Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides structured tumour descriptors, whereas foundation representations offer transferable image features. However, it remains unclear whether radiomics still adds value beyond pretrained representations, and how 2D and 3D MedVAE encoders compare in this setting. We compared handcrafted radiomics, 2D MedVAE, 3D MedVAE, and their fusion for binary clear-cell RCC versus non-clear-cell RCC classification on KiTS23 under a unified preprocessing pipeline. Concatenation, cross-attention, and gated fusion were evaluated as representative integration strategies, and radiomics feature importance was analysed to support decision-centric interpretability. Fusion consistently improved discrimination over image-only MedVAE branches. The best overall performance was achieved by 3D gated fusion, with an AUC of 82.7\%, outperforming the best 2D fusion model (79.6%), the radiomics baseline (74.4%), and the single-modality MedVAE branches. Ablation analysis further showed clear gains of the full fusion model over both image-only and…
PDF arXiv
arXiv cs.CVSep 22
Mammo-LIFE: Longitudinal Mammographic Imaging and Clinical Feature Enrichment for Post-Radiotherapy Outcome Prediction
Farnoush Bayatmakou, Maryam Hosseini, Reza Taleei, Arash Mohammadi
Recent advances in Artificial Intelligence (AI)-powered Computer-Aided Diagnosis (CAD) systems have substantially improved breast cancer screening, diagnosis, and prognosis. Comparatively, postradiotherapy outcome prediction using paired longitudinal mammograms has received considerably less attention. This is largely due to the limited availability of well-annotated longitudinal datasets. Longitudinal mammograms, coupled with paired pre- and post-treatment information, provide a unique opportunity to characterize treatment-induced breast tissue changes following radiotherapy. The resulting learned representations can serve as a valuable asset for advancing personalized radiotherapy planning and post-treatment management. In this context, we propose Mammo-LIFE, a patient-level multimodal framework for post-radiotherapy outcome prediction that combines longitudinal mammographic features with patient-level clinical variables. The imaging branch processes paired pre- and post-treatment mammograms acquired from the four standard views using a mammography-specific encoder adapted via Low-Rank Adaptation (LoRA). Within each view, preand post-treatment representations are explicitly…
PDF arXiv
arXiv cs.LGSep 22
Learning to Defer with Guidance on Real World Medical Data
Emma Sun, Joshua Strong, Alison Noble
Medical image interpretation is high-volume and time-consuming, and while AI interpretation can reduce workload, fully autonomous deployment carries potential safety concerns and low specificity may in practice lead to increased clinician workload. Learning to Defer (L2D) addresses this by selectively routing cases between autonomous prediction and human experts by learning from input features and AI model and human performance. While theoretical guarantees have been proven for L2D, its performance has not been validated on real-world medical datasets with human reader annotations. We evaluate the predictor-rejector formulation of two-stage L2D, where the AI predictor model is fixed and separate from the trainable routing or rejector model, on Collab-CXR, a multilabel chest X-ray dataset with multiple human annotations per case. This is the first work to look at L2D in the context of real-world medical imaging data with human annotations. We further introduce a new setup, L2D with Guidance, where the decision space is extended to three choices: predict autonomously, defer to a human expert, or defer to a human expert and provide AI guidance. We compare multiple rejector…
PDF arXiv

Activity · 12 weeks

Open problems in Image segmentation

Lack of benchmarks for real-world clinical deployment1 paper raises it · 0 address it
Current benchmarks do not reflect how clinicians actually use AI systems, limiting their predictive value for real-world performance.
- Clinician use of language models diverges from how the models are evaluatedraises
Handling incidental or irrelevant information in clinical data1 paper raises it · 0 address it
Models may misattribute or be distracted by non-clinical content, leading to errors in documentation and reasoning.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises
Scaling generative models to gigapixel whole-slide images1 paper raises it · 1 addresses it
Existing models generate only small patches, while clinical supervision operates at the whole-slide level.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Temporal modeling of longitudinal clinical data2 papers raise it · 2 address it
Accurate risk prediction requires modeling irregular, multimodal clinical trajectories over time.
- TRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Predictionraises · addresses
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Parameter-efficient fine-tuning for large medical models2 papers raise it · 2 address it
Training or fine-tuning large models on limited medical data is computationally expensive and impractical.
- Scaling Parameter-Efficient Fine-Tuning for Brain Encodingraises · addresses
- Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIraises · addresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 11m ago

Image segmentation

Found by the topic model: image segmentation, clinical reasoning, eeg foundation models.

142papers this week−31.1% vs last week

All papers · 1.2k With code · 4

Newest Most relevant

939 papers this month