Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1005
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-09-07T06:06:37.327037Z
status: published
lens: g_space
sector: health
headline: Ultrasound Habitat Radiomics for Preoperative Prediction of Invasive Breast Cancer With a DCIS Component: A Dual-center Retrospective Study
dek: Purpose To develop and externally validate an ultrasound-based habitat subregional radiomics model for preoperative prediction of invasive breast cancer with concomitant ductal carcinoma in situ (IBC-DCIS). Methods A total of 1063 pathologically confirmed breast cancer patients from two centers were retrospectively enrolled and divided into a training cohort (n = 637) and an external validation cohort (n = 426). Tumor regions of interest were manually delineated on two-dimensional ultrasound images and further p…
gain_title: An ultrasound-based habitat subregional radiomics model using SVM achieved strong external validation for preoperative prediction of invasive breast cancer with concomitant DCIS, supporting preoperative risk stratification.
problem_title: (none)
trace_subject: (none)
gain_reading: An ultrasound-based habitat subregional radiomics model using SVM achieved strong external validation for preoperative prediction of invasive breast cancer with concomitant DCIS, supporting preoperative risk stratification.
gain_evidence: An ultrasound-based habitat subregional radiomics model showed favorable performance for the preoperative prediction of IBC-DCIS
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers developed and externally validated an ultrasound-based habitat subregional radiomics model to predict invasive breast cancer with a DCIS component before surgery. Using 1063 patients across two centers, they delineated tumors on 2D ultrasound, clustered them into three intratumoral habitats, and built machine learning models evaluated by AUC, calibration, and decision curve analysis.

By the September 2026 publication date, the combined SVM model had demonstrated favorable external validation performance and clinical net benefit, suggesting it could supplement preoperative risk stratification. Whether this retrospective performance translates to prospective clinical impact, broader populations, and changes in surgical decision-making remains untested in the supplied text.
limitation: 
tag: Evidence-backed gain
key_points: Retrospective dual-center study enrolled 1063 pathologically confirmed breast cancer patients, 637 training and 426 external validation. | Tumor ROIs were manually delineated on 2D ultrasound and partitioned into three intratumoral habitat subregions using unsupervised clustering. | Radiomics features from whole tumor and subregions were selected via Pearson correlation and LASSO, with models compared by DeLong test, calibration curves, and decision curve analysis.
rundown: The study used two-dimensional ultrasound images from two centers. After manual delineation, tumors were divided into three habitat subregions, and radiomics features were extracted from whole tumor and each subregion for model building.

The support vector machine-based combined model had the highest external validation AUC of 0.910 with 95% CI 0.883-0.936, and DeLong testing indicated it significantly outperformed imaging-based and single-region radiomics models.
sources:
- peer_reviewed | Ultrasound in Medicine & Biology | https://doi.org/10.1016/j.ultrasmedbio.2026.06.006 | 2026-09-05
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

3c3e884b20e6df0a208d66167d1ab13404b9c218bc9171f72975c0f148e4c31b

previous

0000000000000000000000000000000000000000000000000000000000000000