Deep learning enables the automation of grading histological tissue engineered cartilage images for quality control standardization. Issue 3 (March 2021)

• Record Type: Journal Article
• Authors: Power, L.; Acevedo, L.; Yamashita, R.; Rubin, D.; Martin, I.; Barbero, A.
• Is Part Of: Osteoarthritis and cartilage. Volume 29:Issue 3(2021)
• Page Start: 433
• Page End: 443
• Publication Date: 2021-03
• Subjects: Machine learning -- Transfer learning -- Convolutional neural networks -- Quality controls -- Regenerative medicine -- Histological score; Osteoarthritis -- Periodicals; Cartilage -- Periodicals; Osteoarthritis -- Periodicals; Cartilage -- Periodicals; Arthrose -- Périodiques; Articulations -- Maladies -- Périodiques; 616.7223005
• DOI: 10.1016/j.joca.2020.12.018
• Languages: English
• ISSNs: 1063-4584

Abstract

Summary: Objective: To automate the grading of histological images of engineered cartilage tissues using deep learning. Methods: 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. Results: 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). Conclusion: 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.