TRV-2026-2901Version 1 · Published

Saved · see the current record

Why this version exists

Certified into the record

The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-2901
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-14T00:02:36.329450Z
status: published
lens: g_space
sector: health
headline: Prostate-Specific Membrane Antigen PET/CT Segmentation Guided by Vision Language Models Embedding Clinical Report Semantics
dek: Whole-body prostate-specific membrane antigen (PSMA) PET/CT segmentation remains challenging: manual contouring is unsustainable, and image-only artificial intelligence models often misclassify physiologic uptake as malignant, causing high false-positive rates. These limitations underscore the need for segmentation strategies that incorporate the nuclear medicine expertise encoded in PET/CT reports but not used by current models. We investigated whether routine PET/CT reports improve automated lesion segmentatio…
gain_title: In a study of 284 prostate cancer patients, an AI model that read PET/CT report text alongside the scans cut false-positive lesions by nearly 4 per patient with BiomedVLP versus an image-only model.
problem_title: (none)
trace_subject: (none)
gain_reading: In a study of 284 prostate cancer patients, an AI model that read PET/CT report text alongside the scans cut false-positive lesions by nearly 4 per patient with BiomedVLP versus an image-only model.
gain_evidence: False-positive lesions were reduced by nearly 4 per patient with BiomedVLP
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built a 3-dimensional segmentation model that combines the text of nuclear medicine reports with 68Ga-PSMA-11 PET/CT images, so that it can better tell cancer from normal physiologic uptake. They tested four ways of encoding report text against an image-only baseline.

With BiomedVLP, false-positive lesions fell by nearly 4 per patient, and by about 3 per patient with RadGraph and GPT-raw. Average symmetric surface distance dropped from 105.4 mm for the image-only model to 23.4 mm with BiomedVLP.

When the authors checked only correctly detected lesions, no language-guided model beat the image-only model on any surface metric. They conclude that the boundary gains came from removing false positives, not from tracing tumours more accurately.
limitation: The test set held only 41 cases from one dataset, and the authors call for external validation, true-positive-only analysis in independent cohorts, and PSMA-specific language pretraining.
tag: Evidence-backed gain
key_points: Of 320 patients scanned with 68Ga-PSMA-11 PET/CT, 284 were analysed: 243 for development and a fixed held-out test set of 41. | Four report-encoding strategies were compared with an image-only baseline: BiomedVLP, RadGraph, GPT-raw and GPT-engineered. | The 95th percentile Hausdorff distance improved from 455.0 mm to 123.8 mm with BiomedVLP. | Precision rose by 0.099 with BiomedVLP and 0.060 with RadGraph, while voxel-level recall dipped by 0.051 with BiomedVLP. | Dice improved by 0.032 but was only borderline significant; lesion-level sensitivity changed by no more than 0.04. | Total lesion PSMA stayed highly correlated with manual measurements (r of 0.85 or higher), but tumour volume correlations varied (r = 0.37-0.70).
rundown: The model is a language-guided SegResNet that fuses report semantics with image features. The text was encoded four ways: BiomedVLP, RadGraph, GPT-raw and GPT-engineered. Of 320 patients, 13 studies were excluded for missing reports or incomplete image-mask pairs, leaving 284 split at the patient level.

Performance was judged on Dice, intersection over union, precision, recall, surface distances and lesion-level false positives under three matching criteria. Significance used paired one-sided Wilcoxon tests with Holm adjustment.

The gains in whole-mask surface metrics vanished once only matched true-positive lesions were analysed (all Holm-adjusted P = 1.0). The authors say this shows false-positive suppression, not better contouring. The trade-off was a modest drop in recall.

The authors say the approach may reduce manual cleanup and support more reliable quantitative workflows, and call for external validation and PSMA-specific language pretraining.
sources:
- peer_reviewed | Journal of Nuclear Medicine | https://doi.org/10.2967/jnumed.126.272702 | 2026-11-12
prev: 0000000000000000000000000000000000000000000000000000000000000000
SHA-256 hash
0f1e0e3b7286d37f8d45b48d28cf8c00329d62155838395df8e7f612a71eeb4b
Previous version’s hash
0000000000000000000000000000000000000000000000000000000000000000
Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2901 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.