Medical Manifestation-Aware De-Identification

• URL: http://arxiv.org/abs/2412.10804v1
• Date: Sat, 14 Dec 2024 12:09:41 GMT
• Title: Medical Manifestation-Aware De-Identification
• Authors: Yuan Tian, Shuo Wang, Guangtao Zhai,
• Abstract summary: We release MeMa, consisting of over 40,000 photo-realistic patient faces. MeMa avoids breaching real patient privacy, while ensuring rich and plausible medical manifestations. We recruit expert clinicians to annotate MeMa with both coarse- and fine-grained labels.
• Score: 45.48447211223584
• License:
• Abstract: Face de-identification (DeID) has been widely studied for common scenes, but remains under-researched for medical scenes, mostly due to the lack of large-scale patient face datasets. In this paper, we release MeMa, consisting of over 40,000 photo-realistic patient faces. MeMa is re-generated from massive real patient photos. By carefully modulating the generation and data-filtering procedures, MeMa avoids breaching real patient privacy, while ensuring rich and plausible medical manifestations. We recruit expert clinicians to annotate MeMa with both coarse- and fine-grained labels, building the first medical-scene DeID benchmark. Additionally, we propose a baseline approach for this new medical-aware DeID task, by integrating data-driven medical semantic priors into the DeID procedure. Despite its conciseness and simplicity, our approach substantially outperforms previous ones. Dataset is available at https://github.com/tianyuan168326/MeMa-Pytorch.

Related papers

• De-Identification of Medical Imaging Data: A Comprehensive Tool for Ensuring Patient Privacy [4.376648893167674]
  Open-source tool can be used to de-identify DICOM magnetic resonance images, computer images, whole slide images and magnetic resonance twix raw data. Proposal comprises an elaborate anonymization pipeline for multiple types of inputs, reducing the need for additional tools used for de-identification of imaging data.
  arXiv  Detail & Related papers  (2024-10-16T09:31:24Z)
• OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition [66.91236298878383]
  Depression Recognition (DR) poses a considerable challenge, especially in the context of privacy concerns. We design a new imaging system to erase the identity information of captured facial images while retain disease-relevant features. It is irreversible for identity information recovery while preserving essential disease-related characteristics necessary for accurate DR.
  arXiv  Detail & Related papers  (2024-02-29T01:20:29Z)
• End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks [3.1133049660590615]
  We present an end-to-end architecture based on the Hamiltonian Variational Autoencoder (HVAE) This approach yields an improved posterior distribution approximation compared to traditional Variational Autoencoders (VAE) Our method outperforms generative adversarial conditions, showcasing enhancements in image quality synthesis.
  arXiv  Detail & Related papers  (2023-11-17T11:56:53Z)
• Privacy Protection in MRI Scans Using 3D Masked Autoencoders [2.463789441707266]
  Data anonymization and de-identification is concerned with ensuring the privacy and confidentiality of individuals' personal information. We propose CP-MAE, a model that de-identifies the face by remodeling it. With our method we are able to synthesize high-fidelity scans of resolution up to $2563$ -- compared to $1283$ with previous approaches.
  arXiv  Detail & Related papers  (2023-10-24T12:25:37Z)
• MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation [58.53672866662472]
  We introduce a modality-agnostic SAM adaptation framework, named as MA-SAM. Our method roots in the parameter-efficient fine-tuning strategy to update only a small portion of weight increments. By injecting a series of 3D adapters into the transformer blocks of the image encoder, our method enables the pre-trained 2D backbone to extract third-dimensional information from input data.
  arXiv  Detail & Related papers  (2023-09-16T02:41:53Z)
• FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders [81.21440457805932]
  We propose a novel framework FaceMAE, where the face privacy and recognition performance are considered simultaneously. randomly masked face images are used to train the reconstruction module in FaceMAE. We also perform sufficient privacy-preserving face recognition on several public face datasets.
  arXiv  Detail & Related papers  (2022-05-23T07:19:42Z)
• Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask [66.63753229115983]
  We adapt the object proposal generation system AttentionMask and propose a dedicated post-processing to select promising proposals. The results on the ROBUST-MIS Challenge 2019 show that our adapted AttentionMask system is a strong foundation for generating state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-21T21:37:56Z)
• Conditional De-Identification of 3D Magnetic Resonance Images [29.075173293529947]
  We propose a new class of de-identification techniques that, instead of removing facial features, remodels them. We demonstrate that our approach preserves privacy far better than existing techniques, without compromising downstream medical analyses.
  arXiv  Detail & Related papers  (2021-10-18T15:19:35Z)
• Towards Face Encryption by Generating Adversarial Identity Masks [53.82211571716117]
  We propose a targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks. TIP-IM provides 95%+ protection success rate against various state-of-the-art face recognition models.
  arXiv  Detail & Related papers  (2020-03-15T12:45:10Z)
• Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation [12.10092482860325]
  Face-swapping as a de-identification approach is reliable, and it keeps the keypoints almost invariant, significantly better than traditional methods. This study proposes a pipeline for video de-identification and keypoint preservation, clearing up some ethical restrictions for medical data sharing.
  arXiv  Detail & Related papers  (2020-02-07T22:36:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.