EUVIMEDEUVIMED entdecken
Crossref

Disentangling weak spatial priors from generic local context in radiographic abnormality detection: a controlled mechanism audit

Hetal M Bhatt iD, Sunil Bajeja

Biomedical Physics & Engineering Express · 01.12.2026 · 12 (6) · 065018

DOI: 10.1088/2057-1976/aebbbf ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, online erschienen am 12.11.2026. Verfasst von Hetal M Bhatt und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computer Applications, Marwadi University, Rajkot, India. Hauptthemen laut MEDLINE: Radiographic Image Interpretation, Computer-Assisted, Image Processing, Computer-Assisted. Die Arbeit nennt 33 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Improvements from spatially guided crops may reflect generic local context, optimization or operating-point selection rather than informative spatial guidance.

Purpose

To assess whether a coarse foreground guidance map improves radiographic abnormality discrimination beyond non-prior local controls.

Methods

We audited original frozen DenseNet121 pipelines and conducted a revision-stage matched experiment using five seeds, patient-disjoint development partitions, and prior-guided, centered and random-position crops. Crops retained 90% of image width and height. The primary revised comparison used a common eight-epoch local budget and study ROC-AUC. Validation-selected checkpoints and fixed 50:50 global–local fusions were secondary. Evaluation used 1199 studies from 783 patients, with paired patient-cluster bootstrap intervals. This cohort had already been evaluated in the original study.

Results

At the common final epoch, mean ROC-AUC was 0.892 269 for prior-guided, 0.891 573 for centered and 0.892 221 for random-position crops. Mean paired AUC differences were +0.000 696 (seed SD 0.002 757) versus centered and +0.000 048 (SD 0.002 693) versus random. All ten primary per-seed 95% intervals included zero. Fallback exclusion and alternative aggregation yielded small descriptive differences. Original fusion pipelines had similar AUC but different operating profiles at their independently frozen thresholds.

Conclusion

Within MURA and this conservative DenseNet121 crop procedure, spatial guidance showed no consistent ranking advantage over the tested controls. The findings do not establish equivalence or exclude benefits from stronger or different priors. Matching training exposure and reporting discrimination, calibration and operating-point behavior separately strengthen the audit without establishing clinical trustworthiness.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radiographic Image Interpretation, Computer-AssistedImage Processing, Computer-AssistedHumansROC CurveAlgorithmsArea Under Curve

Stichwörter der Autor:innen

MURAglobal–local learningmatched crop controlspatient-cluster inferenceradiographic abnormality detectionweak spatial prior

Autor:innen und Institutionen

  • Faculty of Computer Applications, Marwadi University, Rajkot, India.

ORCID-Profile: Hetal M Bhatt

Zitieren

APA

Bhatt, H. M., & Bajeja, S. (2026). Disentangling weak spatial priors from generic local context in radiographic abnormality detection: a controlled mechanism audit. Biomedical Physics & Engineering Express, 12(6), 065018. https://doi.org/10.1088/2057-1976/aebbbf

Vancouver

Bhatt HM, Bajeja S. Disentangling weak spatial priors from generic local context in radiographic abnormality detection: a controlled mechanism audit. Biomedical Physics & Engineering Express. 2026;12(6):065018. doi:10.1088/2057-1976/aebbbf

BibTeX
@article{Bhatt2026,
  author = {Bhatt, Hetal M and Bajeja, Sunil},
  title = {Disentangling weak spatial priors from generic local context in radiographic abnormality detection: a controlled mechanism audit},
  journal = {Biomedical Physics & Engineering Express},
  year = {2026},
  volume = {12},
  number = {6},
  pages = {065018},
  doi = {10.1088/2057-1976/aebbbf}
}
Kostenlos starten →