As the most common joint disorder, Osteoarthritis (OA) is problematic for countries with an aging population. In OA, the cartilage degrades which causes bone on bone contact which results in constant pain for those affected. Treatments for OA are centered around symptom relief since there is no drug approved that will slow/stop OA disease progression. The cells that make up the cartilage are called chondrocytes. These chondrocytes must regulate themselves to build and break down the cartilage when necessary through cell signaling. When this signaling isn’t done properly, the chondrocytes may break down too much cartilage and result in OA. To better understand the signaling within the chondrocytes, an Atomic Force Microscope (AFM) was used to measure the movement and forces of mechanical receptor molecules (integrins) on the surface of the cell. However, because the measurements were near the sensitivity limit of the AFM, there was not enough certainty that noise (i.e., thermal, instrument and building) was not a dominant factor within the data. The focus of this project was to subtract model-based noise out of the displacement data to correct the data for further analysis. Instrument noise and building noise was found from the negative control, bare silica. Random thermal noise curves were generated based on theoretical thermal noise RMS values. A Fast Fourier Transform (FFT) was applied to each individual curve and each noise FFT was subtracted from the chondrocyte displacement curve in Python code. Inverse FFTs were applied to the resulting curves, resulting in noise-corrected time domain displacement curves.