Abstract
The segmentation of capillaries in human skin in full-field optical coherence tomography (FF-OCT) images plays a vital role in clinical applications. Recent advances in deep learning techniques have demonstrated a state-of-the-art level of accuracy for the task of automatic medical image segmentation. However, a gigantic amount of annotated data is required for the successful training of deep learning models, which demands a great deal of effort and is costly. To overcome this fundamental problem, an automatic simulation algorithm to generate OCT-like skin image data with augmented capillary networks (ACNs) in a three-dimensional volume (which we called the ACN data) is presented. This algorithm simultaneously acquires augmented FF-OCT and corresponding ground truth images of capillary structures, in which potential functions are introduced to conduct the capillary pathways, and the two-dimensional Gaussian function is utilized to mimic the brightness reflected by capillary blood flow seen in real OCT data. To assess the quality of the ACN data, a U-Net deep learning model was trained by the ACN data and then tested on real in vivo FF-OCT human skin images for capillary segmentation. With properly designed data binarization for predicted image frames, the testing result of real FF-OCT data with respect to the ground truth achieved high scores in performance metrics. This demonstrates that the proposed algorithm is capable of generating ACN data that can imitate real FF-OCT skin images of capillary networks for use in research and deep learning, and that the model for capillary segmentation could be of wide benefit in clinical and biomedical applications.
Highlights
To evaluate the quality of our augmented capillary networks (ACNs) images to represent in vivo full-field optical coherence tomography (FF-optical coherence tomography (OCT)) data of capillary networks in human skin, we investigated two scenarios to assess the performance: (1) The trained model was first tested by the ACN volumetric testing datasets, which were not seen by the model during the model building stage
(2) After reaching the required accuracy level with the testing ACN datasets, the model was tested by real FF-OCT images of human skin in vivo with capillaries annotated by experts [14]
We demonstrated that our algorithm for generating ACN data to simulate real FF-OCT images with in vivo skin capillary networks can be effectively and efficiently used to train our model
Summary
Blood vessels make up a complex system that plays a prominent role in homogenization processes, such as angiogenesis, fluid and solute balance, thrombosis, perfusion/oxygenation, and blood pressure [1,2]. The blood vessel system is an important prognostic indicator of many clinical outcomes in various areas of medicine, such as neurosurgery [3], laryngology, oncology [4], and ophthalmology. The system comprises arteries, capillaries, and venous networks [2,5]. Capillary networks are microvascular networks (the smallest vessels), only 7–10 μm in diameter; they are present in all human body tissues and are of a size sufficient to transport red blood cells [6,7]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
