Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2087
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-21T10:41:21.869298Z
status: published
lens: trace
sector: health
headline: TurkRadLLM: A Compact MedGemma-Based Model for Structuring Turkish Lumbar and Cervical Spine MRI Reports-A Multi-reader Validation Study
dek: To develop and validate a compact, locally deployable MedGemma-based model converting unstructured Turkish spine MRI reports into structured six-field output. In this retrospective single-institution study, 5210 lumbar and 5017 cervical Turkish spine MRI reports were used to fine-tune MedGemma 4B IT with QLoRA. Silver-standard labels from a proprietary large language model served as training targets and as the reference for automated fidelity analyses, but not as the clinical reference standard. Evaluation compr…
gain_title: A fine-tuned compact MedGemma model produced valid structured output from Turkish spine MRI reports that readers accepted, and it ran on a single consumer GPU card.
problem_title: Negative-finding completeness was reader-dependent, with one reader judging negative-finding lists incomplete in 57.8% of reports, and fidelity to the silver-label impression reached only 67.1%.
trace_subject: Structuring Turkish lumbar and cervical spine MRI reports with a fine-tuned compact language model
gain_reading: A fine-tuned compact MedGemma model produced valid structured output from Turkish spine MRI reports that readers accepted, and it ran on a single consumer GPU card.
gain_evidence: Deployment required 14.75 GB of GPU memory on a consumer card.
problem_reading: Negative-finding completeness was reader-dependent, with one reader judging negative-finding lists incomplete in 57.8% of reports, and fidelity to the silver-label impression reached only 67.1%.
problem_evidence: one reader judged negative-finding lists incomplete in 57.8% of reports | negative-finding completeness remained reader-dependent
quick_read: Researchers fine-tuned a small MedGemma 4B model on thousands of Turkish lumbar and cervical spine MRI reports to convert free text into a six-field structured format. Readers reviewed 180 real reports mixed with 20 adversarial cases, and every output was valid JSON that readers accepted as a group.

The result suggests a modest model can run locally on consumer hardware for report structuring, which matters where data privacy or compute is limited. However, training labels came from another language model rather than a clinical reference standard, and one reader found negative-finding lists incomplete often, so clinical reliability is not settled.
limitation: Labels came from a proprietary language model rather than a clinical reference standard, the study was single-institution, and negative-finding completeness varied by reader.
tag: Dual reading
key_points: The model was fine-tuned with QLoRA on 5210 lumbar and 5017 cervical Turkish MRI reports from a single institution. | Agreement with the silver-label impression rose from 17.7% to 67.1% on 1025 held-out reports after fine-tuning. | Urgent-flag sensitivity against the silver reference rose from 18.8% to 62.5%, versus 50.0% for a much larger non-fine-tuned model. | A rule-based baseline reached 99.0% on body region, showing simple methods suffice for some fields. | Deployment needed 14.75 GB of GPU memory on a consumer card.
rundown: The study was retrospective and single-institution. Training targets were silver-standard labels from a proprietary large language model, which were also the reference for automated fidelity analysis but not the clinical reference standard.

Validation combined multi-reader scoring of 180 authentic reports interleaved with 20 adversarial cases, a second round where readers scored the silver labels themselves, and comparison on the full held-out set against a rule-based baseline, the base model, and a much larger model.

When readers scored the silver labels themselves, the fine-tuned model was rated higher on negative findings and lower on the impression. The authors conclude the gain lay in content-level fidelity rather than output validity.
sources:
- peer_reviewed | Journal of Imaging Informatics in Medicine | https://doi.org/10.1007/s10278-026-02427-8 | 2026-10-20
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

017f522217eccd36ed4c87e8f29c7348d73b54aaa99b18a0c10f0f2e03f1ed29

previous

0000000000000000000000000000000000000000000000000000000000000000