Geoffrey Rubin, Joseph Lo, Lavsen Dahal, Yubraj Bhandari
We lifted 12 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| lavsendahal/oracle-ct | — | 8 of 12 |
| Function | Status | Where it lives |
|---|---|---|
| _inflate_tri_to_vol | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("54fb2129472508bb") |
| create_roi_mask | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("a921fb96f6572812") |
| dilate_mask_adaptive | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("ac60d552e4ba0773") |
| inv_sigmoid_temp | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("c16081b0511f7f02") |
| make_trislices | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("57e297dc68e34e85") |
| masked_attention_pool | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("4972a3f1e88d07ba") |
| masks_3d_to_tri | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("b9347bce2263acaa") |
| to_logit | Ran | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("f9668e44eda57a80") |
| OracleCT_DINOv3_MaskedUnaryAttn | Not yet run | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("f197a9d6e3a45f95") |
| get_all_disease_configs | Not yet run | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("6aee030c0668d7ac") |
| get_all_diseases | Not yet run | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("c4f5e947122507dd") |
| get_attention_mask_for_disease | Not yet run | lavsendahal/oracle-ct/models/dinov3_oracle_ct.py code served (permissive licence) · get_code("036217d411ecfdcc") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
There is an urgent need for triage and classification of highvolume medical imaging modalities such as computed tomography (CT), which can improve patient care and mitigate radiologist burnout. Study-level CT triage requires calibrated predictions with localized evidence; however, off-the-shelf Vision-Language Models (VLM) struggle with 3D anatomy, protocol shifts, and noisy report supervision. This study used the two largest publicly available chest CT datasets-CT-RATE and RADCHEST-CT (held-out external test set). Our carefully tuned supervised baseline (instantiated as a simple Global Average Pooling head) establishes a new supervised state of the art, surpassing all reported linear-probe VLMs. Building on this baseline, we present ORACLE-CT, an encoder-agnostic, organ-aware head that pairs Organ-Masked Attention (mask-restricted, per-organ pooling that yields spatial evidence) with Organ-Scalar Fusion (lightweight fusion of normalized volume and mean-HU cues). In the chest setting, ORACLE-CT's masked attention model achieves AUROC 0.86 on CT-RATE; in the abdomen setting, on MERLIN (30 findings), our supervised baseline exceeds a reproduced zero-shot VLM baseline obtained by running publicly released weights through our pipeline, and adding masked attention plus scalar fusion further improves performance to AUROC 0.85. Together, these results deliver state-of-the-art supervised classification performance across both chest and abdomen CT under a unified evaluation protocol. The source code is available at https://github.com/lavsendahal/oracle-ct.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2601.13385")
get_code_for_paper("2601.13385")
have("2601.13385")
Connect an agent — have() is free.