Model‐based image restoration targeting higher‐dose digital mammography: Impact on radiologists' detection of clustered microcalcifications
8 affiliations
- 1Department of Electrical and Computer Engineering, São Carlos School of Engineering University of São Paulo São Carlos Brazil
- 2Real Time Tomography, LLC Villanova USA
- 3Barretos Cancer Hospital Pio XII Foundation Barretos Brazil
- 4Signal Processing Research Centre Tampere University Tampere Finland
- 5Department of Radiology University of Pennsylvania Philadelphia USA
- 6Department of Translational Medicine, Faculty of Medicine, Diagnostic Radiology Lund University Malmö Sweden
- 7Department of Translational Medicine, Faculty of Medicine, Medical Radiation Physics Lund University Malmö Sweden
- 8Department of Hematology, Oncology and Radiation Physics, Radiation Physics Skåne University Hospital Malmö Sweden
Abstract
Background: Image noise in digital mammography (DM) can obscure image details and reduce the detectability of clinically relevant findings such as microcalcifications.
Purpose: To present and evaluate an extended model‐based (MB) image restoration pipeline for DM that incorporates quantum, electronic, and structural noise components, as well as spatial noise correlation, and to assess its effect on breast radiologists' detection of simulated microcalcification clusters in clinical mammograms.
Methods: A total of 120 clinical DM images acquired using a GE Senographe Pristina system were used. Simulated microcalcification clusters were inserted into locally dense fibroglandular regions at controlled contrast levels. The restoration pipeline was configured to target the signal and noise characteristics predicted by the model for an acquisition at approximately twice the original radiation dose. Six breast radiologists with different levels of experience, classified as Junior or Senior, participated in two human observer experiments: (i) a pilot study using original clinical images with simulated clusters and a four‐alternative forced‐choice (4AFC) protocol combined with a three‐down‐one‐up (3D1U) staircase to estimate reader‐specific contrast detection thresholds and achieve comparable baseline task difficulty across readers; and (ii) a main 4AFC observer study using individualized datasets generated according to each reader's estimated contrast threshold, in which microcalcification detection performance was compared between the original and restored image conditions based on the percentage of correct responses (PC). Two generalized linear mixed models (GLMMs) were used: the first evaluated the effect of image condition as a fixed effect, with reader and case as crossed random intercepts, and the second evaluated the effect of reader experience on detection performance in the original image condition.
Results: At the reader‐specific contrast thresholds estimated in the pilot study, the mean PC for the original images was 78.3%, within the prespecified target performance range. Mean PC increased to 84.3% for the restored images, corresponding to an absolute improvement of 6.0 percentage points. The primary GLMM indicated a significant restoration effect on detection performance (OR = 1.57, 95% CI: 1.15–2.14, p=0.005). Baseline mean PC was 78.7% for Junior readers and 78.0% for Senior readers, and the separate GLMM found no evidence of an experience‐group effect under the original image condition (p=0.858).
Conclusions: The proposed extended MB restoration pipeline improved the detectability of simulated microcalcification clusters by breast radiologists under the controlled 4AFC conditions investigated. By targeting the signal and noise characteristics predicted by the model for an acquisition at approximately twice the original radiation dose without requiring additional radiation exposure, the method represents a promising approach for improving microcalcification detectability in DM.
Related
- Artificial Intelligence-Based Automated Detection of Chest X-ray Abnormalities as Support for Young Radiologists
- iSL-YOLOv11: global–local attention enhanced small lesion detection in mammography images
- Image-Based Breast Implant Detection for Mammography Dataset Curation and Near-Real-Time Deployment: Comparing Foundation Models and Task-Specific Convolutional Models
- Therapy-Persistent Leukemia Is Selectively Vulnerable to SLC23A1 Restoration via Targeting KHSRP
- Mammographic Microcalcifications and Breast Cancer: A Case - Control Study
BibTeX
@article{brandao2026modelbased,
title = {{Model‐based image restoration targeting higher‐dose digital mammography: Impact on radiologists' detection of clustered microcalcifications}},
author = {Renann F. Brandão and Lucas R. Borges and Silvia M. P. S. Sabino and Renato F. Caron and Alessandro Foi and Predrag R. Bakic and Anders Tingberg and Marcelo A. C. Vieira},
journal = {Medical Physics},
year = {2026},
month = oct,
doi = {10.1002/mp.70739},
url = {https://doi.org/10.1002/mp.70739},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Model‐based image restoration targeting higher‐dose digital mammography: Impact on radiologists' detection of clustered microcalcifications
AU - Renann F. Brandão
AU - Lucas R. Borges
AU - Silvia M. P. S. Sabino
AU - Renato F. Caron
AU - Alessandro Foi
AU - Predrag R. Bakic
AU - Anders Tingberg
AU - Marcelo A. C. Vieira
PY - 2026
DA - 2026/10/26
JO - Medical Physics
DO - 10.1002/mp.70739
UR - https://doi.org/10.1002/mp.70739
AB - Background: Image noise in digital mammography (DM) can obscure image details and reduce the detectability of clinically relevant findings such as microcalcifications. Purpose: To present and evaluate an extended model‐based (MB) image restoration pipeline for DM that incorporates quantum, electronic, and structural noise components, as well as spatial noise correlation, and to assess its effect on breast radiologists' detection of simulated microcalcification clusters in clinical mammograms. Methods: A total of 120 clinical DM images acquired using a GE Senographe Pristina system were used. Simulated microcalcification clusters were inserted into locally dense fibroglandular regions at controlled contrast levels. The restoration pipeline was configured to target the signal and noise characteristics predicted by the model for an acquisition at approximately twice the original radiation dose. Six breast radiologists with different levels of experience, classified as Junior or Senior, participated in two human observer experiments: (i) a pilot study using original clinical images with simulated clusters and a four‐alternative forced‐choice (4AFC) protocol combined with a three‐down‐one‐up (3D1U) staircase to estimate reader‐specific contrast detection thresholds and achieve comparable baseline task difficulty across readers; and (ii) a main 4AFC observer study using individualized datasets generated according to each reader's estimated contrast threshold, in which microcalcification detection performance was compared between the original and restored image conditions based on the percentage of correct responses (PC). Two generalized linear mixed models (GLMMs) were used: the first evaluated the effect of image condition as a fixed effect, with reader and case as crossed random intercepts, and the second evaluated the effect of reader experience on detection performance in the original image condition. Results: At the reader‐specific contrast thresholds estimated in the pilot study, the mean PC for the original images was 78.3%, within the prespecified target performance range. Mean PC increased to 84.3% for the restored images, corresponding to an absolute improvement of 6.0 percentage points. The primary GLMM indicated a significant restoration effect on detection performance (OR = 1.57, 95% CI: 1.15–2.14, p=0.005). Baseline mean PC was 78.7% for Junior readers and 78.0% for Senior readers, and the separate GLMM found no evidence of an experience‐group effect under the original image condition (p=0.858). Conclusions: The proposed extended MB restoration pipeline improved the detectability of simulated microcalcification clusters by breast radiologists under the controlled 4AFC conditions investigated. By targeting the signal and noise characteristics predicted by the model for an acquisition at approximately twice the original radiation dose without requiring additional radiation exposure, the method represents a promising approach for improving microcalcification detectability in DM.
SN - 0094-2405
SN - 2473-4209
ER -