Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation
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 segmentatio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/4/685 |
| _version_ | 1827695410903252992 |
|---|---|
| author | Bitewulign Kassa Mekonnen Tung-Han Hsieh Dian-Fu Tsai Shien-Kuei Liaw Fu-Liang Yang Sheng-Lung Huang |
| author_facet | Bitewulign Kassa Mekonnen Tung-Han Hsieh Dian-Fu Tsai Shien-Kuei Liaw Fu-Liang Yang Sheng-Lung Huang |
| author_sort | Bitewulign Kassa Mekonnen |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T12:25:59Z |
| format | Article |
| id | doaj.art-4ba65781ae45482b8148239476d74627 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T12:25:59Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-4ba65781ae45482b8148239476d746272023-11-21T15:01:40ZengMDPI AGDiagnostics2075-44182021-04-0111468510.3390/diagnostics11040685Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary SegmentationBitewulign Kassa Mekonnen0Tung-Han Hsieh1Dian-Fu Tsai2Shien-Kuei Liaw3Fu-Liang Yang4Sheng-Lung Huang5Graduate Institute of Electro-Optical Engineering, National Taiwan University of Science and Technology, No. 43, Keelung Rd., Sec. 4, Da’an Dist., Taipei City 10607, TaiwanResearch Center for Applied Sciences, Academia Sinica, No. 128, Academia Rd., Sec. 2, Nankang, Taipei City 11529, TaiwanResearch Center for Applied Sciences, Academia Sinica, No. 128, Academia Rd., Sec. 2, Nankang, Taipei City 11529, TaiwanGraduate Institute of Electro-Optical Engineering, National Taiwan University of Science and Technology, No. 43, Keelung Rd., Sec. 4, Da’an Dist., Taipei City 10607, TaiwanResearch Center for Applied Sciences, Academia Sinica, No. 128, Academia Rd., Sec. 2, Nankang, Taipei City 11529, TaiwanGraduate Institute of Photonics and Optoelectronics, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei City 10617, TaiwanThe 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.https://www.mdpi.com/2075-4418/11/4/685full-field optical coherence tomographyskin capillary segmentationaugmented dataset generationdeep learningU-Netimage binarization |
| spellingShingle | Bitewulign Kassa Mekonnen Tung-Han Hsieh Dian-Fu Tsai Shien-Kuei Liaw Fu-Liang Yang Sheng-Lung Huang Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation Diagnostics full-field optical coherence tomography skin capillary segmentation augmented dataset generation deep learning U-Net image binarization |
| title | Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation |
| title_full | Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation |
| title_fullStr | Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation |
| title_full_unstemmed | Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation |
| title_short | Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation |
| title_sort | generation of augmented capillary network optical coherence tomography image data of human skin for deep learning and capillary segmentation |
| topic | full-field optical coherence tomography skin capillary segmentation augmented dataset generation deep learning U-Net image binarization |
| url | https://www.mdpi.com/2075-4418/11/4/685 |
| work_keys_str_mv | AT bitewulignkassamekonnen generationofaugmentedcapillarynetworkopticalcoherencetomographyimagedataofhumanskinfordeeplearningandcapillarysegmentation AT tunghanhsieh generationofaugmentedcapillarynetworkopticalcoherencetomographyimagedataofhumanskinfordeeplearningandcapillarysegmentation AT dianfutsai generationofaugmentedcapillarynetworkopticalcoherencetomographyimagedataofhumanskinfordeeplearningandcapillarysegmentation AT shienkueiliaw generationofaugmentedcapillarynetworkopticalcoherencetomographyimagedataofhumanskinfordeeplearningandcapillarysegmentation AT fuliangyang generationofaugmentedcapillarynetworkopticalcoherencetomographyimagedataofhumanskinfordeeplearningandcapillarysegmentation AT shenglunghuang generationofaugmentedcapillarynetworkopticalcoherencetomographyimagedataofhumanskinfordeeplearningandcapillarysegmentation |