EUVIMEDScopri EUVIMED
Open access · CC BY-NC-ND 4.0

Mixed-source-to-institutional hospital-holdout evaluation of DICOM-aware adaptive harmonization for chest radiograph lesion detection

Abu Salam, Cinantya Paramita, Pulung Nurtantio Andono, Purwanto, Moch Arief Soeleman, Erwin Yudi Hidayat, Defri Kurniawan, Daniel Rizky, Budi Setiawan, Antonius Gunawan Santoso, Sasha-Gay Wright

Array · 2026-12 · 32 · 101225

DOI: 10.1016/j.array.2026.101225 ↗

At a glance

Journal article in Array, 2026-12. Written by Abu Salam and 10 co-authors. 59 references. The full text is freely available (open access, CC BY-NC-ND 4.0).

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Robust cross-hospital generalization remains a major challenge in chest radiograph lesion detection, especially when detectors are trained on mixed public and institutional development sources and then transferred to a previously unseen hospital. This study evaluated whether a Digital Imaging and Communications in Medicine (DICOM)-aware adaptive harmonization branch, Adaptive HyFusion, changes held-out institutional lesion-detection performance under a mixed-source-to-institutional hospital-holdout design compared with standard preprocessing. A fixed Faster R-CNN detector with a ResNet-50-FPN backbone was evaluated under a harmonized five-class lesion ontology using VinDr-CXR, MS-CXR, and two non-public Indonesian hospital cohorts. Scenario 2A used RSUD Dr. Adhyatma, MPH Jawa Tengah for institutional development and RSUD Sunan Kalijaga Kabupaten Demak as the locked held-out test source; Scenario 2B reversed the hospital roles as a sensitivity analysis. The experimental protocol used patient/study-clean institutional development splits while preserving the locked held-out test sets. Performance was assessed using mAP 50 , mAP 50 : 95 , class-wise AP, recall, precision, false positives per image, threshold sensitivity, FROC-oriented summaries, and paired bootstrap uncertainty estimates. In Scenario 2A, Adaptive HyFusion showed numerically higher average held-out mAP 50 (0.127 ± 0.026 vs. 0.110 ± 0.073) and mAP 50 : 95 (0.042 ± 0.014 vs. 0.038 ± 0.023), but the paired bootstrap mAP 50 difference was small and uncertain (+0.017; 95% CI: −0.052 to +0.099). In Scenario 2B, Adaptive HyFusion showed comparable mAP 50 to baseline (0.114 ± 0.011 vs. 0.117 ± 0.015) and lower false positives per image (0.985 ± 0.080 vs. 1.137 ± 0.114), but lower recall. Component ablations showed that isolated spatial, frequency, fixed-fusion, and adaptive-without-QC variants did not consistently improve held-out institutional performance. These findings support Adaptive HyFusion as an auditable DICOM-aware harmonization strategy that can alter held-out operating behavior under source shift, but they do not establish a statistically or operationally convincing generalization benefit on the primary Scenario 2A benchmark.

Cite

APA

Salam, A., Paramita, C., Andono, P. N., Purwanto, Soeleman, M. A., Hidayat, E. Y., Kurniawan, D., Rizky, D., Setiawan, B., Santoso, A. G., & Wright, S. (2026). Mixed-source-to-institutional hospital-holdout evaluation of DICOM-aware adaptive harmonization for chest radiograph lesion detection. Array, 32, 101225. https://doi.org/10.1016/j.array.2026.101225

Vancouver

Salam A, Paramita C, Andono PN, Purwanto, Soeleman MA, Hidayat EY, et al. Mixed-source-to-institutional hospital-holdout evaluation of DICOM-aware adaptive harmonization for chest radiograph lesion detection. Array. 2026;32:101225. doi:10.1016/j.array.2026.101225

BibTeX
@article{Salam2026,
  author = {Salam, Abu and Paramita, Cinantya and Andono, Pulung Nurtantio and Purwanto and Soeleman, Moch Arief and Hidayat, Erwin Yudi and Kurniawan, Defri and Rizky, Daniel and Setiawan, Budi and Santoso, Antonius Gunawan and Wright, Sasha-Gay},
  title = {Mixed-source-to-institutional hospital-holdout evaluation of DICOM-aware adaptive harmonization for chest radiograph lesion detection},
  journal = {Array},
  year = {2026},
  volume = {32},
  pages = {101225},
  doi = {10.1016/j.array.2026.101225}
}
Start for free →