Mixed-source-to-institutional hospital-holdout evaluation of DICOM-aware adaptive harmonization for chest radiograph lesion detection
Authors:
- Abu SalamASAbu Salam
- Cinantya ParamitaCPCinantya Paramita
- Pulung Nurtantio AndonoPAPulung Nurtantio Andono
- PurwantoPUPurwanto
- Moch Arief SoelemanMSMoch Arief Soeleman
- Erwin Yudi HidayatEHErwin Yudi Hidayat
- Defri KurniawanDKDefri Kurniawan
- Daniel RizkyDRDaniel Rizky
- Budi SetiawanBSBudi Setiawan
- Antonius Gunawan SantosoASAntonius Gunawan Santoso
- Sasha-Gay WrightSWSasha-Gay Wright
Open Access
Abstract
No abstract availableThis publication has 45 references indexed in Scilit:
- Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging2025
- Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging2024
- Class imbalance on medical image classification: towards better evaluation practices for discrimination and calibration performanceEuropean Radiology, 2024
- CheXstray: A Real-Time Multi-Modal Monitoring Workflow for Medical Imaging AI2023
- CXR Segmentation by AdaIN-Based Domain Adaptation and Knowledge Distillation2022
- Histogram-Based Unsupervised Domain Adaptation for Medical Image Classification2022
- Automated quality assessment of chest radiographs based on deep learning and linear regression cascade algorithmsEuropean Radiology, 2022
- Continual Domain Incremental Learning for Chest X-Ray Classification in Low-Resource Clinical Settings2021
- Can We Trust Deep Learning Based Diagnosis? The Impact of Domain Shift in Chest Radiograph Classification2020
- Automated identification of chest radiographs with referable abnormality with deep learning: need for recalibrationEuropean Radiology, 2020