Papers

Field

Top tools here

Open problems in Image segmentation

Lack of whole-slide image generation for histopathology1 paper raises it · 1 addresses it
Current generative models only produce small patches, but clinical labels and reports operate at the whole-slide level, limiting alignment with real-world supervision.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Limited longitudinal multimodal reasoning benchmarks1 paper raises it · 1 addresses it
Most medical benchmarks assess reasoning over preselected evidence, not the ability to seek and integrate evidence across longitudinal clinical records and imaging.
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Frozen models cannot learn from deployment experience1 paper raises it · 1 addresses it
Deployed models in medicine do not adapt to new clinical evidence or updated guidelines without retraining, which is often impractical.
- Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIraises · addresses
Benchmark misalignment with real-world clinical use1 paper raises it · 1 addresses it
Public benchmarks often do not reflect the tasks, intents, or constraints of actual clinician queries, reducing their predictive value for deployment performance.
- Clinician use of language models diverges from how the models are evaluatedraises · addresses
Sensitivity to incidental information in clinical reasoning1 paper raises it · 1 addresses it
Models may incorporate or misattribute irrelevant details (e.g., small talk, background noise) in clinical documentation or reasoning, risking contamination.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

image segmentation · volumetric · medical image403 papers59 this week
radiology report generation · medical vision language · vision language models127 papers38 this week
clinical reasoning · question answering · language models205 papers30 this week
patient history · clinical data · health records109 papers26 this week
eeg foundation models · electroencephalography eeg · eeg foundation155 papers24 this week
electrocardiogram ecg · electrocardiogram · ecgs145 papers15 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.LGSep 30
Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis
Tian Xia, Minghao Liu, Yiqing Liang, Laixi Shi, Jiayun Wang
Multimodal large language models (MLLMs) are rapidly advancing clinical diagnosis, yet their adaptation pipelines remain anchored to accuracy-based objectives. Clinical data are heavily class-imbalanced: a constant-majority predictor can score above 90% accuracy while being clinically useless. We therefore evaluate and optimize for AUROC, a threshold-free score that ranks positives above negatives and is invariant to class balance. We focus on prompt optimization in MLLMs. Reflective methods such as GEPA use a binary scores matrix with one row per evaluation instance and one column per candidate prompt; cells record per-instance correctness, so the column average is accuracy and drives candidate selection. We introduce pair-level Pareto prompt evolution (Ranking-PE), which replaces each correctness row with a pairwise-ordering row over (positive, negative) instance pairs: the cell is 1 if the candidate scores the positive higher than the paired negative. The column average then equals empirical AUROC (by the Wilcoxon-Mann-Whitney identity). We apply this swap at all three layers the prompt evolution search reads from - the scores matrix that decides Pareto dominance, the…
PDF arXiv
arXiv cs.LGSep 30
Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text
Dulhan Jayalath, Oiwi Parker Jones
We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the influential work of d'Ascoli et al. (2025), time series of brain activity from subjects perceiving continuous speech are segmented into fixed-length windows starting at each word. A neural network then generates predictions for all of the words in a sentence together. Neighbouring windows partially overlap, implicitly revealing the interval between words. Since these intervals indicate the duration of the words spoken, and different words tend to have different durations - for example, "the" is much shorter than "supercalifragilisticexpialidocious" - the neural network can improve its predictions of words without relying on the underlying brain activity. Consistent with this, the method reaches 22.0% balanced accuracy on synthetic signals containing no brain information, compared with 22.3% on real brain recordings. To prevent the network from learning this shortcut, we make a single, simple change. Instead of jointly encoding all windows in a sentence, we process each independently. As a result, the neural network achieves better…
PDF arXiv
arXiv cs.CLSep 30
Comparison of techniques for fine-tuning open-weight models for entity extraction from radiology reports
Aawez Mansuri, Kush Mehta, Mohammadreza Chavoshi, Jahanzaib Malik, Theodorus Dapamede +8
Converting free-text radiology reports into structured labels supports cohort building, quality assurance, and monitoring of clinical imaging models, but the strongest label extractors are hosted proprietary models whose use raises privacy, cost, and reproducibility concerns. We asked whether a fine-tuned open-weight model (Gemma-3-12B) can match GPT-4o at multi-label intracranial hemorrhage (ICH) acuity extraction from non-contrast head-CT reports, and which ingredients matter. Using a 2x2 design, we crossed two adaptation strategies (a discriminative classification head, CH; generative instruction fine-tuning, IFT) with two training-data sources (distillation of real GPT-4o-labeled reports; synthetic reports generated by GPT-4o from real exemplars), across five training sizes, benchmarked on 100 expert-adjudicated reports against GPT-4o and the un-tuned open-weight base. The distilled instruction-tuned model (DIFT) matched GPT-4o (macro-F1 0.845 vs 0.850; p = 1.000) and exceeded the base model by 0.178. The decisive factor was the training-data source, not the fine-tuning method: both synthetic-data models failed to exceed the un-tuned open-weight base at any training size and…
PDF arXiv
arXiv cs.CLSep 30
OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk Prediction
Mingchen Li, Rohan Pandey, Junhui Qian, Feiyun Ouyang, Sunjae Kwon +1
Opioid overdose remains a major clinical and public health burden, highlighting the need for scalable approaches to identify patients at high risk. Here, we investigate diagnosis-specific adaptation for 180-day opioid overdose risk prediction from patients' preceding one-year longitudinal ICD histories. We develop OODMAMBA and OODQWEN through continued pretraining on longitudinal diagnostic sequences followed by task-specific fine-tuning. Building on the stronger Qwen-based predictors, we further propose OVERDOSEMOE, a multi-expert framework that integrates models of different scales using complementary expert-weighting strategies. Diagnosis-specific adaptation consistently improved predictive performance over general-purpose language-model baselines, with OODQWEN achieving an AUPRC of 24.47 and an AUROC of 68.56. OVERDOSEMOE further improved discrimination and precision, achieving an AUPRC of 25.17 and an AUROC of 69.49 while outperforming the strongest single-model baselines. Among patients ranked in the top 5% of predicted risk, OVERDOSEMOE identified substantially enriched overdose risk, achieving a PPV of 25.38% while retaining meaningful recall. Evaluation on an independent…
PDF arXiv
arXiv cs.CVSep 30
GateSPINE: Gated Cross-View Fusion for Lumbar Spine MRI Report Generation
Hoang Nguyen Van, Cuong Vuong Tuan, Trang Mai Xuan, Bien Tran Van, Nam Tran Van +1
Automated report generation can ease the burden radiolo gists face when interpreting multi-sequence MRI studies. Unlike CT, MRI examinations comprise multiple sequences and imaging planes, each con tributing complementary diagnostic information. Existing methods en code a study as a single volume and combine multiple acquisitions by fixed rules. Findings visible in only one plane are thus diluted and of ten missed, lowering recall on clinical efficacy metrics, where a missed abnormality is most costly. We propose GateSPINE, a vision-language framework that fuses sagittal T1 and T2 volumes with a training-free operator, encodes the fused sagittal and axial volumes with two parallel 3D encoders, and decodes their combined representation into a report. Its core mechanism is a gated cross view fusion module that predicts, per feature channel and token, how much of each view to admit, so the more informative view dominates at each spatial location. We evaluate GateSPINE on three lumbar MRI datasets, comprising two public bench marks and a private cohort collected from Phenikaa University Hospital, using both natural language generation (NLG) and clinical efficacy (CE) metrics.…
PDF arXiv
arXiv eess.IVSep 30
The Effect of Tissue Detection on False Positives of Diffusion-Based Artifact Detection in Histopathology
Konstantinos Moutselos, Ilias Maglogiannis
One-class artifact detectors for whole-slide images learn normal tissue from a clean training pool and flag departures from it. The pool is built by a preprocessing pipeline whose tissue-detection step is usually treated as neutral. We tested whether it is. On 16 annotated slides from The Cancer Genome Atlas, we rebuilt the clean pool of a diffusion-based detector with different tissue detection methods and compared the resulting models in a four-fold cross-validation. Per-slide saturation-Otsu detection excluded normal tissue, chiefly tissue with large clear spaces such as adipose tissue and alveolar parenchyma, and on slides with thick marker ink kept the ink while excluding ordinary tissue. Replacing it with entropy-based detection reduced the false-positive fraction on held-out clean slides from 0.102 to 0.016, in every fold and with a second training seed, without loss of sensitivity; the gain came from the composition of the pool, not its size. Across three tissue detection methods, false positives followed the fraction of such clear-space tissue in the pool, a statistic that needs no labels or training (0.103, 0.016 and 0.009). The effect did not carry over at the same…
PDF arXiv

Papers

Topics in this field

image segmentation · volumetric · medical image403 papers59 this week
radiology report generation · medical vision language · vision language models127 papers38 this week
clinical reasoning · question answering · language models205 papers30 this week
patient history · clinical data · health records109 papers26 this week
eeg foundation models · electroencephalography eeg · eeg foundation155 papers24 this week
electrocardiogram ecg · electrocardiogram · ecgs145 papers15 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.LGSep 30
Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis
Tian Xia, Minghao Liu, Yiqing Liang, Laixi Shi, Jiayun Wang
Multimodal large language models (MLLMs) are rapidly advancing clinical diagnosis, yet their adaptation pipelines remain anchored to accuracy-based objectives. Clinical data are heavily class-imbalanced: a constant-majority predictor can score above 90% accuracy while being clinically useless. We therefore evaluate and optimize for AUROC, a threshold-free score that ranks positives above negatives and is invariant to class balance. We focus on prompt optimization in MLLMs. Reflective methods such as GEPA use a binary scores matrix with one row per evaluation instance and one column per candidate prompt; cells record per-instance correctness, so the column average is accuracy and drives candidate selection. We introduce pair-level Pareto prompt evolution (Ranking-PE), which replaces each correctness row with a pairwise-ordering row over (positive, negative) instance pairs: the cell is 1 if the candidate scores the positive higher than the paired negative. The column average then equals empirical AUROC (by the Wilcoxon-Mann-Whitney identity). We apply this swap at all three layers the prompt evolution search reads from - the scores matrix that decides Pareto dominance, the…
PDF arXiv
arXiv cs.LGSep 30
Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text
Dulhan Jayalath, Oiwi Parker Jones
We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the influential work of d'Ascoli et al. (2025), time series of brain activity from subjects perceiving continuous speech are segmented into fixed-length windows starting at each word. A neural network then generates predictions for all of the words in a sentence together. Neighbouring windows partially overlap, implicitly revealing the interval between words. Since these intervals indicate the duration of the words spoken, and different words tend to have different durations - for example, "the" is much shorter than "supercalifragilisticexpialidocious" - the neural network can improve its predictions of words without relying on the underlying brain activity. Consistent with this, the method reaches 22.0% balanced accuracy on synthetic signals containing no brain information, compared with 22.3% on real brain recordings. To prevent the network from learning this shortcut, we make a single, simple change. Instead of jointly encoding all windows in a sentence, we process each independently. As a result, the neural network achieves better…
PDF arXiv
arXiv cs.CLSep 30
Comparison of techniques for fine-tuning open-weight models for entity extraction from radiology reports
Aawez Mansuri, Kush Mehta, Mohammadreza Chavoshi, Jahanzaib Malik, Theodorus Dapamede +8
Converting free-text radiology reports into structured labels supports cohort building, quality assurance, and monitoring of clinical imaging models, but the strongest label extractors are hosted proprietary models whose use raises privacy, cost, and reproducibility concerns. We asked whether a fine-tuned open-weight model (Gemma-3-12B) can match GPT-4o at multi-label intracranial hemorrhage (ICH) acuity extraction from non-contrast head-CT reports, and which ingredients matter. Using a 2x2 design, we crossed two adaptation strategies (a discriminative classification head, CH; generative instruction fine-tuning, IFT) with two training-data sources (distillation of real GPT-4o-labeled reports; synthetic reports generated by GPT-4o from real exemplars), across five training sizes, benchmarked on 100 expert-adjudicated reports against GPT-4o and the un-tuned open-weight base. The distilled instruction-tuned model (DIFT) matched GPT-4o (macro-F1 0.845 vs 0.850; p = 1.000) and exceeded the base model by 0.178. The decisive factor was the training-data source, not the fine-tuning method: both synthetic-data models failed to exceed the un-tuned open-weight base at any training size and…
PDF arXiv
arXiv cs.CLSep 30
OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk Prediction
Mingchen Li, Rohan Pandey, Junhui Qian, Feiyun Ouyang, Sunjae Kwon +1
Opioid overdose remains a major clinical and public health burden, highlighting the need for scalable approaches to identify patients at high risk. Here, we investigate diagnosis-specific adaptation for 180-day opioid overdose risk prediction from patients' preceding one-year longitudinal ICD histories. We develop OODMAMBA and OODQWEN through continued pretraining on longitudinal diagnostic sequences followed by task-specific fine-tuning. Building on the stronger Qwen-based predictors, we further propose OVERDOSEMOE, a multi-expert framework that integrates models of different scales using complementary expert-weighting strategies. Diagnosis-specific adaptation consistently improved predictive performance over general-purpose language-model baselines, with OODQWEN achieving an AUPRC of 24.47 and an AUROC of 68.56. OVERDOSEMOE further improved discrimination and precision, achieving an AUPRC of 25.17 and an AUROC of 69.49 while outperforming the strongest single-model baselines. Among patients ranked in the top 5% of predicted risk, OVERDOSEMOE identified substantially enriched overdose risk, achieving a PPV of 25.38% while retaining meaningful recall. Evaluation on an independent…
PDF arXiv
arXiv cs.CVSep 30
GateSPINE: Gated Cross-View Fusion for Lumbar Spine MRI Report Generation
Hoang Nguyen Van, Cuong Vuong Tuan, Trang Mai Xuan, Bien Tran Van, Nam Tran Van +1
Automated report generation can ease the burden radiolo gists face when interpreting multi-sequence MRI studies. Unlike CT, MRI examinations comprise multiple sequences and imaging planes, each con tributing complementary diagnostic information. Existing methods en code a study as a single volume and combine multiple acquisitions by fixed rules. Findings visible in only one plane are thus diluted and of ten missed, lowering recall on clinical efficacy metrics, where a missed abnormality is most costly. We propose GateSPINE, a vision-language framework that fuses sagittal T1 and T2 volumes with a training-free operator, encodes the fused sagittal and axial volumes with two parallel 3D encoders, and decodes their combined representation into a report. Its core mechanism is a gated cross view fusion module that predicts, per feature channel and token, how much of each view to admit, so the more informative view dominates at each spatial location. We evaluate GateSPINE on three lumbar MRI datasets, comprising two public bench marks and a private cohort collected from Phenikaa University Hospital, using both natural language generation (NLG) and clinical efficacy (CE) metrics.…
PDF arXiv
arXiv eess.IVSep 30
The Effect of Tissue Detection on False Positives of Diffusion-Based Artifact Detection in Histopathology
Konstantinos Moutselos, Ilias Maglogiannis
One-class artifact detectors for whole-slide images learn normal tissue from a clean training pool and flag departures from it. The pool is built by a preprocessing pipeline whose tissue-detection step is usually treated as neutral. We tested whether it is. On 16 annotated slides from The Cancer Genome Atlas, we rebuilt the clean pool of a diffusion-based detector with different tissue detection methods and compared the resulting models in a four-fold cross-validation. Per-slide saturation-Otsu detection excluded normal tissue, chiefly tissue with large clear spaces such as adipose tissue and alveolar parenchyma, and on slides with thick marker ink kept the ink while excluding ordinary tissue. Replacing it with entropy-based detection reduced the false-positive fraction on held-out clean slides from 0.102 to 0.016, in every fold and with a second training seed, without loss of sensitivity; the gain came from the composition of the pool, not its size. Across three tissue detection methods, false positives followed the fraction of such clear-space tissue in the pool, a statistic that needs no labels or training (0.103, 0.016 and 0.009). The effect did not carry over at the same…
PDF arXiv

Activity · 12 weeks

Fields · AI · updated 38m ago

Image segmentation

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

192papers this week−8.6% vs last week

All papers · 1.1k With code · 4

Newest Most relevant

1k papers this month

Open problems in Image segmentation

Lack of whole-slide image generation for histopathology1 paper raises it · 1 addresses it
Current generative models only produce small patches, but clinical labels and reports operate at the whole-slide level, limiting alignment with real-world supervision.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Limited longitudinal multimodal reasoning benchmarks1 paper raises it · 1 addresses it
Most medical benchmarks assess reasoning over preselected evidence, not the ability to seek and integrate evidence across longitudinal clinical records and imaging.
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Frozen models cannot learn from deployment experience1 paper raises it · 1 addresses it
Deployed models in medicine do not adapt to new clinical evidence or updated guidelines without retraining, which is often impractical.
- Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIraises · addresses
Benchmark misalignment with real-world clinical use1 paper raises it · 1 addresses it
Public benchmarks often do not reflect the tasks, intents, or constraints of actual clinician queries, reducing their predictive value for deployment performance.
- Clinician use of language models diverges from how the models are evaluatedraises · addresses
Sensitivity to incidental information in clinical reasoning1 paper raises it · 1 addresses it
Models may incorporate or misattribute irrelevant details (e.g., small talk, background noise) in clinical documentation or reasoning, risking contamination.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises · addresses

Named by an AI from these papers' abstracts.