Abstract
To automate the grading of histological images of engineered cartilage tissues using deep learning. Cartilaginous tissues were engineered from various cell sources. Safranin O and fast green stained histological images of the tissues were graded for chondrogenic quality according to the Modified Bern Score, which ranks images on a scale from zero to six according to the intensity of staining and cell morphology. The whole images were tiled, and the tiles were graded by two experts and grouped into four categories with the following grades: 0, 1-2, 3-4, and 5-6. Deep learning was used to train models to classify images into these histological score groups. Finally, the tile grades per donor were averaged. The root mean square errors (RMSEs) were calculated between each user and the model. Transfer learning using a pretrained DenseNet model was selected. The RMSEs of the model predictions and 95% confidence intervals were 0.49 (0.37, 0.61) and 0.78 (0.57, 0.99) for each user, which was in the same range as the inter-user RMSE of 0.71 (0.51, 0.93). Using supervised deep learning, we could automate the scoring of histological images of engineered cartilage and achieve results with errors comparable to inter-user error. Thus, the model could enable the automation and standardization of assessments currently used for experimental studies as well as release criteria that ensure the quality of manufactured clinical grafts and compliance with regulatory requirements.
Highlights
Large cartilage defects do not have the capacity to regenerate in adults, and currently available treatments have not yet demonstrated predictable long-term efficacy[1]
The model with the best accuracy on the validation dataset was the transfer learning model using DenseNet and the newly trained, fully-connected linear classifier that mapped the output features from the pretrained model to the four classes in our dataset with a validation accuracy was 92.8%, this is the model we chose for analyzing the test data
We showed for the first time that deep learning can be used to automatically grade images of tissue engineered cartilage according to a histological scoring system that is currently used to release grafts in a clinical setting
Summary
Large cartilage defects do not have the capacity to regenerate in adults, and currently available treatments have not yet demonstrated predictable long-term efficacy[1]. New treatment options are required and being investigated2e5. One promising method is the implantation of autologous nasal chondrocytederived engineered tissue, which has been shown to be a safe and feasible method for treating knee-cartilage defects[6]. A phase II clinical trial is currently ongoing to test the efficacy of this treatment (BIO-CHIP: http://biochip-h2020.eu/). Nasal chondrocytes are isolated from the nasal septum, expanded, and seeded onto a collagen I/III scaffold. The resulting constructs are cultured in chondrogenic condition, allowing the cells to produce their own cartilage matrix before implantation in the knee cartilage defect
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.
