Thibault Bogniaho
Research Subjects
Thibault Bogniaho has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Clara Bremond Martin
ETIS Laboratory UMR 8051 (CY Cergy Paris Université, ENSEA, CNRS), 6 Avenue du Ponceau, 95000 Cergy, France
1 shared publication Jérôme Seymour
1 shared publication- Nadjia Kachenoura
Laboratoire d'Imagerie Biomédicale (LIB) Sorbonne Université, INSERM, CNRS Paris France
1 shared publication - Tianrui Huang1 shared publication
Latest Publications
- Open Access
- 24 September 2026
- Published by Elsevier in SSRN Electronic Journal
Transfer Study of Scene Text Removal Models for Multimodality DICOM Image Anonymization using Synthetic Data
The Digital Imaging and Communications in Medicine (DICOM) format is widely used to store medical images along with patient-related Protected Health Information (PHI) within hospital Picture Archiving and Communication System (PACS). However, the compliant anonymization of DICOM objects for PACS-to-PACS transmission remains challenging. Our objective is to identify a lightweight conditioned Generative Adversarial Network (cGAN) adapted from Scene Text Removal (STR) models, capable of effectively removing burned-in text from DICOM images while restoring the underlying tissue structures. To this aim, we generated a synthetic dataset with 620 images from The Cancer Imaging Archive (TCIA) database, containing four modalities with fake PHI. A localized generation strategy is applied to minimize unintended errors outside the burned-in text regions, as they typically occupy only a small portion. Then, five cGAN-based architectures are fine-tuned and compared to evaluate their reconstruction performance, FLOPs and inference time. After fine-tuning, all models are subsequently evaluated on CPU-only inference to assess their real-world transferability, identifying GaRNet model as the best trade-off across different evaluation aspects. Compared with the second-best cGAN, MTRNet++, GaRNet required 23.6 times fewer FLOPs and achieved 11.4 times faster inference while maintaining comparable structural similarity and PSNR score.
- 24 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTransfer Study of Scene Text Removal Models for Multimodality DICOM Image Anonymization using Synthetic Data
The Digital Imaging and Communications in Medicine (DICOM) format is widely used to store medical images along with patient-related Protected Health Information (PHI) within hospital Picture Archiving and Communication System (PACS). However, the compliant anonymization of DICOM objects for PACS-to-PACS transmission remains challenging. Our objective is to identify a lightweight conditioned Generative Adversarial Network (cGAN) adapted from Scene Text Removal (STR) models, capable of effectively removing burned-in text from DICOM images while restoring the underlying tissue structures. To this aim, we generated a synthetic dataset with 620 images from The Cancer Imaging Archive (TCIA) database, containing four modalities with fake PHI. A localized generation strategy is applied to minimize unintended errors outside the burned-in text regions, as they typically occupy only a small portion. Then, five cGAN-based architectures are fine-tuned and compared to evaluate their reconstruction performance, FLOPs and inference time. After fine-tuning, all models are subsequently evaluated on CPU-only inference to assess their real-world transferability, identifying GaRNet model as the best trade-off across different evaluation aspects. Compared with the second-best cGAN, MTRNet++, GaRNet required 23.6 times fewer FLOPs and achieved 11.4 times faster inference while maintaining comparable structural similarity and PSNR score.