Introduction

Automated identification of arthroplasty implants could aid in pre-operative planning and is a task which could be facilitated through artificial intelligence (AI) and deep learning. The purpose of this study was to develop and test the performance of a deep learning system (DLS) for automated identification and classification of knee arthroplasty (KA) on radiographs.

Aim: The healing capacity of human articular cartilage is very limited in the adult. Therefore tissue engineering techniques were developed to treat cartilage lesions. To it, autologous chondrocytes are harvested from the affected joint and expanded in vitro. During expansion chondrocytes may dedifferentiate, characterized by an increase in type I collagen and a decrease in type II collagen expression. Since high expression of type II collagen is of central importance for the properties of cartilage after transplantation, we investigated if the human platelet supernatants (hPS) containing PDGF and TGF-b or recombinant human bone morphogenetic protein-2 (BMP-2) may modulate the chondrogenic phenotype in monolayer cell cultures (2D) and in three-dimensional culture (3D) systems.

Methods: Chondrocytes from articular knee cartilage of 14 individuals (mean age 36.5 6.5 years) with no history of inflammatory joint disease were isolated and expanded under GMP conditions suitable for clinical purposes. The hPS was prepared from blood of 3 donors and pooled. Cells were seeded either in 2D cultures or embedded in alginate beads (3D) in presence or absence of hPS or recombinant human BMP-2 (generous gift of Dr. Hortschansky, Jena, FRG). After two weeks in culture, cells were harvested and analysis of the chondrogenic phenotype was performed using quantitative RT-PCR, immunocytochemistry and ELISA methods.

Results: Expansion of chondrocytes in primary culture (P0) did not yield populations of dedifferentiated or hypertrophic cells. Expanding cells in first subculture (P1) resulted in spontaneous reduction of type II collagen expression and increase in type I collagen mRNA amounts. Seeding P1 chondrocytes in 3D culture significantly reduced type I collagen, BMP-4 and IL-18 and maintained high type II collagen and BMP-2 encoding mRNA (p < 0.05). Reduction of IL-1b and elevation of IL-10 mRNA were noted but were statistically not significant. Addition of BMP-2 to 2D chondrocytes had no effect on type II collagen or IL-1b mRNA amounts (p < 0.05). In alginate cultures BMP-2 induced type II collagen and reduced IL-1b mRNA amounts. In contrast, addition of hPS containing PDGF and TGF-b, promoted mitotic activity in 2D and alginate cultures. The hPS reduced in 2D cultures type II and induced type I collagen expression. Even in alginate beads induction of type I collagen was detected.

Conclusions: We conclude that the chondrogenic phenotype is stabilized by BMP-2 more effectively in alginate beads but not in monolayer cultures. The hPS promotes proliferation of chondrocytes in vitro but induces elevated type I expression, an indicator of chondrocyte dedifferentiation.

Introduction: Within the last few years numerous operative procedures have been described aiming a biological repair of damaged articular cartilage. Current techniques are: Microfracture, Osteochondral Autografting (Mosaicplasty) and Autologous Chondrocyte Transplantation (ACT).

Several new studies have shown, that the defect size plays a major role in the clinical outcome of the different procedures. Thus, it makes sense to measure the size of a cartilage defect before indicating a certain method for biological repair.

Material and Methods: We have developed a software (beta-version) for measuring the size of a cartilage defect during a routine arthroscopy in a real-time mode. The programme is based on an Infrared-Navigation tool (Orthopilot, B.Braun-Aesculap, Germany).

In order to proof the reliability and the usefulness of this device, we carried out following study: in each of 6 cadaver-knees we performed 2 full-thickness cartilage defects (MFC and LFC) of different size.

In a first run 3 surgeons had to scope the joint and estimate the defect size with means of a scaled probe-hook. In a second run we performed a measurement of the defect with the Orthopilot™; finally an open measurement after arthrotomy was done to act as reference.

Results: Measurement of the cartilage defect size was clearly superior to an estimation by probehook. Especially the inter-observer difference between the surgeons was widely spread, whereas the max. mismeasurement with the Orthopilot was 2mm.

Discussion: Our study has shown, that navigational-assisted determination of chondral defects is superior to a simple estimation of a defect size by a probehook. Considering that the defect size is a crucial point in choosing the appropriate procedure for the treatment of cartilage defects, navigation devices like the CDM-software is maybe a helpful tool in making the right decision for a suitable method of biological cartilage repair.