In this study, a ResNet approach based on multipolarization SHG imaging is proposed for the categorization and regression of collagen type I and II blend hydrogels at 0%, 25%, 50%, 75%, and 100% type II, without the need for
prior time-consuming model fitting. A ResNet model, pretrained on 18 progressive polarization SHG images at 10° intervals for each percentage, categorizes the five blended collagen hydrogels with a mean absolute error (MAE) of 0.021, while the model pretrained on nonpolarization images exhibited 0.083 MAE. Moreover, the pretrained models can also generally regress the blend hydrogels at 20%, 40%, 60%, and 80% type II. In conclusion, the multipolarization SHG image-based ResNet analysis demonstrates the potential for an automated approach using deep learning to extract valuable information from the collagen matrix.
Collagen is ubiquitously found inside the human body and is the main structural protein in the Extracellular Matrix (ECM) of various tissues. In this work, we focus on the improvement instrumentation and methods used for obtaining collagen structural information in the SHG microscopy. We proposed dual liquid crystals based polarization-resolved SHG approach to address the deadlock, which breaks limitation of only working for modulating excitation angle of linear polarization but not directionality for all polarization state control. We assessed the SHG polarization excited responses of the isolated collagen type I and type II gels with quantitative analysis methods at different scale levels using our system and the results showed the potential of Dual-LC PSHG microscopy to differentiate the type of collagen based on the macroscopic SHG responses.
Discriminating type I and type II collagen is important owing to its dominating presence in cartilage and connective tissues where an alteration of collagen matrix is observed in several diseases including osteogenesis imperfecta and osteoarthritis. For non-destructive investigation of the molecular level properties of collagen, a non-invasive Dual-liquid crystal based polarization-resolved second harmonic (SHG) microscopy is utilized to facilitate the quantitative characterization of collagen types I and II in fracture healing tissues. In this study, we extend an existing approach allowing the quick generation of any desired linear polarization states without any mechanical parts to quantify the characteristics of collagen types using pitch angle and anisotropy parameter. Furthermore, data reliability is ensured by using right and left-hand circular polarization imaging centered circular dichroism analysis. Our findings indicate that the effective pitch angle for the collagen at fracture healing tissue is 48.4° and 49.9° at two weeks and four weeks of repair respectively where type II collagen dominates in the former and type I in the latter. The mean SHG-CD response of the articular cartilage is 0.271 and 0.183 at the rich zone of collagen types II and I, respectively. These findings are correlated to the values obtained from the non-fractured control bone tissue. The measurements obtained reflect the different types of collagen in the molecular fibril assembly. Therefore, these methods demonstrate a powerful tool to provide new insights on understanding the role of collagen in ECM structure and on the development of cartilage repair.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.