▸case-03 We built an information retrieval system that indexes DICOM headers and radiology report keywords to enable multi-modal search across hospital PACS archives. We are considering ISBI for publication. Could you assess this paper for ISBI positioning? Please return a review breakdown including fit level and justification, target venue name, contribution type, key evidence gaps, official compliance points to double check against current guidelines, main rejection threat, and alternative conference or journal targets if re-routing is advised. | fail→pass | 20,377 | 11,515 | -43% | 1 | 1 | 0% | 3,093 | 3,765 | +22% | 0 | 0 | — |
▸case-04 I am writing a Python script using PyTorch and Monai to calculate Dice similarity coefficient and Hausdorff Distance 95 for 3D abdominal CT organ segmentation. Can you provide a clean Python function that takes a binary prediction tensor and ground truth tensor and computes both metrics? | pass→pass | 20,380 | 21,562 | +6% | 1 | 1 | 0% | 2,990 | 5,016 | +68% | 0 | 0 | — |
▸case-05 We are designing a clinical trial to evaluate an AI-based mammography screening software in a multi-center study. We need to calculate the sample size required to detect a 5% increase in sensitivity over standard radiologist reading with 80% power at alpha 0.05. How should we calculate this statistical sample size? | pass→fail | 25,347 | 19,585 | -23% | 1 | 1 | 0% | 3,505 | 5,157 | +47% | 0 | 0 | — |
▸case-01 I have drafted a manuscript introducing a novel transformer architecture for automated 3D cardiac MRI segmentation with clinical ground-truth validations. I want to evaluate whether this work aligns well with ISBI. Please analyze my draft's suitability and provide an assessment report covering the overall fit level with a brief reason, target venue, primary contribution category, the biggest evidence gap in the current submission, official guidelines to verify on the venue page, the primary risk for rejection, and a re-routing recommendation if another venue fits better. | fail→pass | 18,502 | 13,897 | -25% | 1 | 1 | 0% | 2,179 | 3,259 | +50% | 0 | 0 | — |
▸case-02 Our team developed a deep diffusion model to reconstruct high-resolution fluorescence microscopy images from noisy low-photon acquisitions. We are deciding if we should submit this to ISBI. Please review our topic and methodology to evaluate submission readiness. I need a structured evaluation containing the fit level (High/Medium/Low with rationale), target venue confirmation, contribution classification, the major missing experimental or evidence item, key official CFP policy items to re-check, top venue-specific rejection risk, and alternative venue recommendations if ISBI is not optimal. | fail→pass | 18,146 | 11,519 | -37% | 1 | 1 | 0% | 2,759 | 3,121 | +13% | 0 | 0 | — |
▸case-06 I am compiling my LaTeX manuscript for an IEEE conference template and getting an error: 'LaTeX Error: File `IEEEtran.cls` not found.' How do I resolve this LaTeX environment path issue on Linux? | pass→pass | 10,122 | 19,341 | +91% | 1 | 1 | 0% | 1,886 | 3,853 | +104% | 0 | 0 | — |
▸case-07 We developed a video-based surgical instrument tracking algorithm for intraoperative laparoscopy with surgical workflow state detection. A co-author suggests submitting to ISBI, but another suggests MICCAI. Evaluate our draft's venue fit for ISBI. Format your report using the bracketed fields: [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→pass | 18,604 | 13,596 | -27% | 1 | 1 | 0% | 2,233 | 3,451 | +55% | 0 | 0 | — |
▸case-08 We designed a novel vision transformer backbone that achieves state-of-the-art top-1 accuracy on ImageNet-1k and COCO object detection. We want to submit this model to ISBI without fine-tuning or testing on medical modalities, claiming that better vision baselines help all imaging domains. Evaluate this positioning for ISBI. Output your assessment in the standard format with [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→pass | 13,068 | 10,904 | -17% | 1 | 1 | 0% | 1,542 | 2,947 | +91% | 0 | 0 | — |
▸case-09 We created a mathematical optimization technique for 3D cryo-electron microscopy map reconstruction from low single-particle signal-to-noise ratio micrographs. We verified the algorithm against benchmark biological macromolecule datasets. Evaluate this manuscript's alignment with ISBI. Format your analysis using [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→pass | 15,058 | 11,436 | -24% | 1 | 1 | 0% | 1,864 | 3,021 | +62% | 0 | 0 | — |
▸case-10 Our research group compiled a multi-center, open-access ultrasound dataset of thyroid nodules with expert radiologist annotations and standardized benchmark protocols. We evaluated three baseline segmentation models on it. Assess this submission for ISBI. Provide your response in the format starting with [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→fail | 11,440 | 13,903 | +22% | 1 | 1 | 0% | 1,811 | 3,239 | +79% | 0 | 0 | — |
▸case-11 We replaced 3x3 convolutions with 5x5 depthwise convolutions in a standard ResNet-50 and observed a 0.4% AUC increase on ChestX-ray14. We ran no ablation studies, compute cost analysis, or qualitative error analysis. Evaluate our paper for ISBI. Format your output as [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→pass | 15,068 | 5,412 | -64% | 1 | 1 | 0% | 1,783 | 2,808 | +57% | 0 | 0 | — |
▸case-12 We trained a conditional diffusion model to synthesize full-dose PET images from ultra-low-dose PET acquisitions. The paper shows three cherry-picked visual samples and PSNR scores, but no quantitative hallucination check, data provenance documentation, or downstream task evaluation. Evaluate this paper for ISBI. Format your response with [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→fail | 18,232 | 7,584 | -58% | 1 | 1 | 0% | 2,140 | 3,187 | +49% | 0 | 0 | — |
▸case-13 We conducted a 5-year retrospective clinical study analyzing patient overall survival rates after chemotherapy, using baseline clinical records and tumor staging. No new image processing or reconstruction algorithms were introduced. We want to publish this in ISBI to reach medical researchers. Evaluate this manuscript's venue fit. Output your assessment using [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→pass | 7,094 | 10,776 | +52% | 1 | 1 | 0% | 1,339 | 3,009 | +125% | 0 | 0 | — |
▸case-14 We developed a lightweight graph neural network for 3D instance segmentation of cell nuclei in high-content fluorescence microscopy. We provided extensive quantitative comparisons against standard baselines and ablation studies. Evaluate our paper's positioning for ISBI. Format the output with [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→fail | 16,614 | 12,742 | -23% | 1 | 1 | 0% | 2,008 | 3,218 | +60% | 0 | 0 | — |
▸case-15 We created a physics-informed boundary detection method for quantitative thickness measurement of retinal layers in spectral-domain OCT images, validated across three device vendors. Assess this manuscript for ISBI submission. Return your response formatted as [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→pass | 11,102 | 11,647 | +5% | 1 | 1 | 0% | 1,724 | 2,975 | +73% | 0 | 0 | — |
▸case-16 We designed a novel transformer for brain MRI super-resolution. Our paper reports SOTA results on a private hospital dataset that cannot be shared, and includes a link to an unblinded personal GitHub repository. Evaluate our draft's submission readiness for ISBI. Format your answer using [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→pass | 9,054 | 11,769 | +30% | 1 | 1 | 0% | 1,665 | 3,131 | +88% | 0 | 0 | — |
▸case-17 We authored a theoretical proof bounding differential privacy loss in federated learning optimization algorithms. We included zero experiments on medical or biological image datasets, but claim it applies to hospital consortia. Evaluate this paper for ISBI. Format the output using [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→pass | 15,035 | 10,921 | -27% | 1 | 1 | 0% | 1,649 | 2,830 | +72% | 0 | 0 | — |
▸case-18 We performed a large-scale empirical evaluation comparing five vision foundation models across ten open-source digital pathology datasets, analyzing domain shift and out-of-distribution robustness. Evaluate this draft for ISBI. Structure your output with [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→pass | 14,274 | 12,438 | -13% | 1 | 1 | 0% | 2,428 | 3,106 | +28% | 0 | 0 | — |
▸case-19 We built a custom piezoelectric sensor array hardware system for point-of-care portable ultrasound acquisition and published full CAD models and circuit schematics. Evaluate this work for ISBI submission. Structure your evaluation as [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→fail | 12,905 | 12,993 | +1% | 1 | 1 | 0% | 1,744 | 3,232 | +85% | 0 | 0 | — |
▸case-20 We designed a deep unrolled network for accelerated 4D flow cardiac MRI reconstruction from undersampled k-space data, with quantitative validation on vendor raw files and physical phantom experiments. Evaluate our paper for ISBI. Output the review using [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→pass | 14,071 | 13,393 | -5% | 1 | 1 | 0% | 2,247 | 3,273 | +46% | 0 | 0 | — |
▸case-21 We trained a YOLO-based detector for microcalcification screening on mammograms. However, our ethics section is a generic two-line statement without detailing IRB approval numbers or patient consent specifics for the private clinical cohort used. Evaluate our draft for ISBI. Format the output with [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | pass→fail | 11,286 | 7,152 | -37% | 1 | 1 | 0% | 1,902 | 2,913 | +53% | 0 | 0 | — |
▸case-22 We developed a deformable image registration model that aligns ex vivo prostate histology slices with in vivo multi-parametric MRI. We provided registration accuracy metrics (TRE, DSC) across 40 patient cases. Evaluate this paper for ISBI positioning. Output your report using [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→pass | 12,827 | 12,748 | -1% | 1 | 1 | 0% | 2,026 | 3,115 | +54% | 0 | 0 | — |
▸case-23 We posted an arXiv preprint on diffusion-based low-dose CT denoising. We want to re-frame this long narrative into a conference paper for ISBI. Evaluate our core idea and provide a submission evaluation structured as [Fit], [Target], [Contribution type], [Main evidence gap], [Official items to re-check], [Top rejection risk], and [Re-route suggestion]. | fail→pass | 14,933 | 14,093 | -6% | 1 | 1 | 0% | 2,373 | 3,416 | +44% | 0 | 0 | — |