Medical Image De-Identification Benchmark Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916873668395008 |
|---|---|
| author | Pei, Linmin Sutton, Granger Rutherford, Michael Wagner, Ulrike Nolan, Tracy Smith, Kirk Farmer, Phillip Gu, Peter Rana, Ambar Chen, Kailing Ferleman, Thomas Park, Brian Wu, Ye Kojouharov, Jordan Singh, Gargi Lemon, Jon Willis, Tyler Vukadinovic, Milos Duffy, Grant He, Bryan Ouyang, David Pereanez, Marco Samber, Daniel Smith, Derek A. Cannistraci, Christopher Fayad, Zahi Mendelson, David S. Bufano, Michele Kotter, Elmar Haghiri, Hamideh Baidya, Rajesh Dvoretskii, Stefan Maier-Hein, Klaus H. Nolden, Marco Ablett, Christopher Siggillino, Silvia Kaushik, Sandeep Jiang, Hongzhu Xie, Sihan Wan, Zhiyu Michie, Alex Doran, Simon J Waly, Angeline Aurelia Liang, Felix A. Nathaniel Mustagfirin, Humam Arshad Felicia, Michelle Grace Chih, Kuo Po Krish, Rahul Rasool, Ghulam Bouaynaya, Nidhal Koutsoubis, Nikolas Naddeo, Kyle Pandit, Kartik O'Sullivan, Tony Krish, Raj Pan, Qinyan Gustafson, Scott Kopchick, Benjamin Opsahl-Ong, Laura Olvera-Morales, Andrea Pinney, Jonathan Johnson, Kathryn Do, Theresa Klenk, Juergen Diaz, Maria Singh, Arti Chai, Rong Clunie, David A. Prior, Fred Farahani, Keyvan |
| author_facet | Pei, Linmin Sutton, Granger Rutherford, Michael Wagner, Ulrike Nolan, Tracy Smith, Kirk Farmer, Phillip Gu, Peter Rana, Ambar Chen, Kailing Ferleman, Thomas Park, Brian Wu, Ye Kojouharov, Jordan Singh, Gargi Lemon, Jon Willis, Tyler Vukadinovic, Milos Duffy, Grant He, Bryan Ouyang, David Pereanez, Marco Samber, Daniel Smith, Derek A. Cannistraci, Christopher Fayad, Zahi Mendelson, David S. Bufano, Michele Kotter, Elmar Haghiri, Hamideh Baidya, Rajesh Dvoretskii, Stefan Maier-Hein, Klaus H. Nolden, Marco Ablett, Christopher Siggillino, Silvia Kaushik, Sandeep Jiang, Hongzhu Xie, Sihan Wan, Zhiyu Michie, Alex Doran, Simon J Waly, Angeline Aurelia Liang, Felix A. Nathaniel Mustagfirin, Humam Arshad Felicia, Michelle Grace Chih, Kuo Po Krish, Rahul Rasool, Ghulam Bouaynaya, Nidhal Koutsoubis, Nikolas Naddeo, Kyle Pandit, Kartik O'Sullivan, Tony Krish, Raj Pan, Qinyan Gustafson, Scott Kopchick, Benjamin Opsahl-Ong, Laura Olvera-Morales, Andrea Pinney, Jonathan Johnson, Kathryn Do, Theresa Klenk, Juergen Diaz, Maria Singh, Arti Chai, Rong Clunie, David A. Prior, Fred Farahani, Keyvan |
| contents | The de-identification (deID) of protected health information (PHI) and personally identifiable information (PII) is a fundamental requirement for sharing medical images, particularly through public repositories, to ensure compliance with patient privacy laws. In addition, preservation of non-PHI metadata to inform and enable downstream development of imaging artificial intelligence (AI) is an important consideration in biomedical research. The goal of MIDI-B was to provide a standardized platform for benchmarking of DICOM image deID tools based on a set of rules conformant to the HIPAA Safe Harbor regulation, the DICOM Attribute Confidentiality Profiles, and best practices in preservation of research-critical metadata, as defined by The Cancer Imaging Archive (TCIA). The challenge employed a large, diverse, multi-center, and multi-modality set of real de-identified radiology images with synthetic PHI/PII inserted.
The MIDI-B Challenge consisted of three phases: training, validation, and test. Eighty individuals registered for the challenge. In the training phase, we encouraged participants to tune their algorithms using their in-house or public data. The validation and test phases utilized the DICOM images containing synthetic identifiers (of 216 and 322 subjects, respectively). Ten teams successfully completed the test phase of the challenge. To measure success of a rule-based approach to image deID, scores were computed as the percentage of correct actions from the total number of required actions. The scores ranged from 97.91% to 99.93%. Participants employed a variety of open-source and proprietary tools with customized configurations, large language models, and optical character recognition (OCR). In this paper we provide a comprehensive report on the MIDI-B Challenge's design, implementation, results, and lessons learned. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23608 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Medical Image De-Identification Benchmark Challenge Pei, Linmin Sutton, Granger Rutherford, Michael Wagner, Ulrike Nolan, Tracy Smith, Kirk Farmer, Phillip Gu, Peter Rana, Ambar Chen, Kailing Ferleman, Thomas Park, Brian Wu, Ye Kojouharov, Jordan Singh, Gargi Lemon, Jon Willis, Tyler Vukadinovic, Milos Duffy, Grant He, Bryan Ouyang, David Pereanez, Marco Samber, Daniel Smith, Derek A. Cannistraci, Christopher Fayad, Zahi Mendelson, David S. Bufano, Michele Kotter, Elmar Haghiri, Hamideh Baidya, Rajesh Dvoretskii, Stefan Maier-Hein, Klaus H. Nolden, Marco Ablett, Christopher Siggillino, Silvia Kaushik, Sandeep Jiang, Hongzhu Xie, Sihan Wan, Zhiyu Michie, Alex Doran, Simon J Waly, Angeline Aurelia Liang, Felix A. Nathaniel Mustagfirin, Humam Arshad Felicia, Michelle Grace Chih, Kuo Po Krish, Rahul Rasool, Ghulam Bouaynaya, Nidhal Koutsoubis, Nikolas Naddeo, Kyle Pandit, Kartik O'Sullivan, Tony Krish, Raj Pan, Qinyan Gustafson, Scott Kopchick, Benjamin Opsahl-Ong, Laura Olvera-Morales, Andrea Pinney, Jonathan Johnson, Kathryn Do, Theresa Klenk, Juergen Diaz, Maria Singh, Arti Chai, Rong Clunie, David A. Prior, Fred Farahani, Keyvan Computer Vision and Pattern Recognition Cryptography and Security The de-identification (deID) of protected health information (PHI) and personally identifiable information (PII) is a fundamental requirement for sharing medical images, particularly through public repositories, to ensure compliance with patient privacy laws. In addition, preservation of non-PHI metadata to inform and enable downstream development of imaging artificial intelligence (AI) is an important consideration in biomedical research. The goal of MIDI-B was to provide a standardized platform for benchmarking of DICOM image deID tools based on a set of rules conformant to the HIPAA Safe Harbor regulation, the DICOM Attribute Confidentiality Profiles, and best practices in preservation of research-critical metadata, as defined by The Cancer Imaging Archive (TCIA). The challenge employed a large, diverse, multi-center, and multi-modality set of real de-identified radiology images with synthetic PHI/PII inserted. The MIDI-B Challenge consisted of three phases: training, validation, and test. Eighty individuals registered for the challenge. In the training phase, we encouraged participants to tune their algorithms using their in-house or public data. The validation and test phases utilized the DICOM images containing synthetic identifiers (of 216 and 322 subjects, respectively). Ten teams successfully completed the test phase of the challenge. To measure success of a rule-based approach to image deID, scores were computed as the percentage of correct actions from the total number of required actions. The scores ranged from 97.91% to 99.93%. Participants employed a variety of open-source and proprietary tools with customized configurations, large language models, and optical character recognition (OCR). In this paper we provide a comprehensive report on the MIDI-B Challenge's design, implementation, results, and lessons learned. |
| title | Medical Image De-Identification Benchmark Challenge |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2507.23608 |