Michael Majer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Michael Majer has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Astrid Van Camp
Maastricht University, GROW – Research Institute for Oncology and Reproduction, Department of Precision Medicine, Maastricht, The Netherlands
1 shared publication - Corinne Balleyguier
Département d’Imagerie, Institut Gustave Roussy, Université Paris-Saclay, 94800 Villejuif, France
1 shared publication - Henry C. Woodruff
Department of Precision Medicine, GROW - Research Institute for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands
1 shared publication - Hilde Bosmans
Department of Imaging and Pathology, KU Leuven, Leuven, Belgium
1 shared publication - Lesley Cockmartin
UZ Leuven
1 shared publication - Marc B. I. Lobbes
Department of Medical Imaging, Zuyderland Medical Center, Sittard-Geleen, the Netherlands
1 shared publication
Latest Publications
- Open Access
- 28 April 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 12 (S2) , 1-18
Impact of synthetic data on training a deep learning model for lesion detection and classification in contrast-enhanced mammography
PurposePredictive models for contrast-enhanced mammography often perform better at detecting and classifying enhancing masses than (non-enhancing) microcalcification clusters. We aim to investigate whether incorporating synthetic data with simulated microcalcification clusters during training can enhance model performance.ApproachMicrocalcification clusters were simulated in low-energy images of lesion-free breasts from 782 patients, considering local texture features. Enhancement was simulated in the corresponding recombined images. A deep learning (DL) model for lesion detection and classification was trained with varying ratios of synthetic and real (850 patients) data. In addition, a handcrafted radiomics classifier was trained using delineations and class labels from real data, and predictions from both models were ensembled. Validation was performed on internal (212 patients) and external (279 patients) real datasets.ResultsThe DL model trained exclusively with synthetic data detected over 60% of malignant lesions. Adding synthetic data to smaller real training sets improved detection sensitivity for malignant lesions but decreased precision. Performance plateaued at a detection sensitivity of 0.80. The ensembled DL and radiomics models performed worse than the standalone DL model, decreasing the area under this receiver operating characteristic curve from 0.75 to 0.60 on the external validation set, likely due to falsely detected suspicious regions of interest.ConclusionsSynthetic data can enhance DL model performance, provided model setup and data distribution are optimized. The possibility to detect malignant lesions without real data present in the training set confirms the utility of synthetic data. It can serve as a helpful tool, especially when real data are scarce, and it is most effective when complementing real data.
- 28 April 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 12 (S2) , 1-18
Open AccessImpact of synthetic data on training a deep learning model for lesion detection and classification in contrast-enhanced mammography
PurposePredictive models for contrast-enhanced mammography often perform better at detecting and classifying enhancing masses than (non-enhancing) microcalcification clusters. We aim to investigate whether incorporating synthetic data with simulated microcalcification clusters during training can enhance model performance.ApproachMicrocalcification clusters were simulated in low-energy images of lesion-free breasts from 782 patients, considering local texture features. Enhancement was simulated in the corresponding recombined images. A deep learning (DL) model for lesion detection and classification was trained with varying ratios of synthetic and real (850 patients) data. In addition, a handcrafted radiomics classifier was trained using delineations and class labels from real data, and predictions from both models were ensembled. Validation was performed on internal (212 patients) and external (279 patients) real datasets.ResultsThe DL model trained exclusively with synthetic data detected over 60% of malignant lesions. Adding synthetic data to smaller real training sets improved detection sensitivity for malignant lesions but decreased precision. Performance plateaued at a detection sensitivity of 0.80. The ensembled DL and radiomics models performed worse than the standalone DL model, decreasing the area under this receiver operating characteristic curve from 0.75 to 0.60 on the external validation set, likely due to falsely detected suspicious regions of interest.ConclusionsSynthetic data can enhance DL model performance, provided model setup and data distribution are optimized. The possibility to detect malignant lesions without real data present in the training set confirms the utility of synthetic data. It can serve as a helpful tool, especially when real data are scarce, and it is most effective when complementing real data.