Segmentation stability of human head and neck cancer medical images for radiotherapy applications under de-identification conditions: Benchmarking data sharing and artificial intelligence use-cases

Frontiers in Oncology

Oncology

Benjamin H. Kann¹  Kimmo Kaski²  Joel Jaskari²  Jaakko Sahlsten²  Enrico Glerean³  Antti Mäkitie⁴  Kareem A. Wahid⁵  Clifton D. Fuller⁵  Mohamed A. Naser⁵  Renjie He⁵ 

[1] Artificial Intelligence in Medicine Program, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, United States;Department of Computer Science, Aalto University School of Science, Espoo, Finland;Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland;Department of Otorhinolaryngology, Head and Neck Surgery, University of Helsinki and Helsinki University Hospital, Helsinki, Finland;Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States;

关键词: anonymization;    radiotherapy;    head and neck cancer;    MRI;    medical imaging;    artificial intelligence (AI);    autosegmentation;    defacing;   

DOI  :  10.3389/fonc.2023.1120392

 received in 2022-12-09, accepted in 2023-02-13,  发布年份 2023

来源: Frontiers

【 摘 要 】

BackgroundDemand for head and neck cancer (HNC) radiotherapy data in algorithmic development has prompted increased image dataset sharing. Medical images must comply with data protection requirements so that re-use is enabled without disclosing patient identifiers. Defacing, i.e., the removal of facial features from images, is often considered a reasonable compromise between data protection and re-usability for neuroimaging data. While defacing tools have been developed by the neuroimaging community, their acceptability for radiotherapy applications have not been explored. Therefore, this study systematically investigated the impact of available defacing algorithms on HNC organs at risk (OARs).MethodsA publicly available dataset of magnetic resonance imaging scans for 55 HNC patients with eight segmented OARs (bilateral submandibular glands, parotid glands, level II neck lymph nodes, level III neck lymph nodes) was utilized. Eight publicly available defacing algorithms were investigated: afni_refacer, DeepDefacer, defacer, fsl_deface, mask_face, mri_deface, pydeface, and quickshear. Using a subset of scans where defacing succeeded (N=29), a 5-fold cross-validation 3D U-net based OAR auto-segmentation model was utilized to perform two main experiments: 1.) comparing original and defaced data for training when evaluated on original data; 2.) using original data for training and comparing the model evaluation on original and defaced data. Models were primarily assessed using the Dice similarity coefficient (DSC).ResultsMost defacing methods were unable to produce any usable images for evaluation, while mask_face, fsl_deface, and pydeface were unable to remove the face for 29%, 18%, and 24% of subjects, respectively. When using the original data for evaluation, the composite OAR DSC was statistically higher (p ≤ 0.05) for the model trained with the original data with a DSC of 0.760 compared to the mask_face, fsl_deface, and pydeface models with DSCs of 0.742, 0.736, and 0.449, respectively. Moreover, the model trained with original data had decreased performance (p ≤ 0.05) when evaluated on the defaced data with DSCs of 0.673, 0.693, and 0.406 for mask_face, fsl_deface, and pydeface, respectively.ConclusionDefacing algorithms may have a significant impact on HNC OAR auto-segmentation model training and testing. This work highlights the need for further development of HNC-specific image anonymization methods.

【 授权许可】

Unknown   
Copyright © 2023 Sahlsten, Wahid, Glerean, Jaskari, Naser, He, Kann, Mäkitie, Fuller and Kaski