RESUMEN

This study aims to apply Mask Regional Convolutional Neural Network (Mask R-CNN) to cervical cancer screening using pap smear histological slides. Based on our current literature review, this is the first attempt of using Mask R-CNN to detect and analyze the nucleus of the cervical cell, screening for normal and abnormal nuclear features. The data set were liquid-based histological slides obtained from Thammasat University (TU) Hospital. The slides contained both cervical cells and various artifacts such as white blood cells, mimicking the slides obtained in actual clinical settings. The proposed algorithm achieved mean average precision (mAP) of 57.8%, accuracy of 91.7%, sensitivity of 91.7%, and specificity of 91.7% per image. As we needed to evaluate the efficiency of our algorithm in comparison to single cell classification algorithm (Zhang et al., IEEE JBHI, vol. 21, no. 6, pp. 1633, 2017), we modified our method to also classify single cells on TU dataset test using Mask R-CNN segmentation. The results obtained had an accuracy of 89.8%, sensitivity of 72.5%, and specificity of 94.3%.

Asunto(s)

RESUMEN

OBJECTIVES: In this study, we compared the pain behaviour and osteoarthritis (OA) progression between anterior cruciate ligament transection (ACLT) and osteochondral injury in surgically-induced OA rat models. METHODS: OA was induced in the knee joints of male Wistar rats using transection of the ACL or induction of osteochondral injury. Changes in the percentage of high limb weight distribution (%HLWD) on the operated hind limb were used to determine the pain behaviour in these models. The development of OA was assessed and compared using a histological evaluation based on the Osteoarthritis Research Society International (OARSI) cartilage OA histopathology score. RESULTS: Both models showed an increase in joint pain as indicated by a significant (p < 0.05) decrease in the values of %HLWD at one week post-surgery. In the osteochondral injury model, the %HLWD returned to normal within three weeks, while in the ACLT model, a significant decrease in the %HLWD was persistent over an eight-week period. In addition, OA progression was more advanced in the ACLT model than in the osteochondral injury model. Furthermore, the ACLT model exhibited a higher mean OA score than that of the osteochondral injury model at 12 weeks. CONCLUSION: The development of pain patterns in the ACLT and osteochondral injury models is different in that the OA progression was significant in the ACLT model. Although both can be used as models for a post-traumatic injury of the knee, the selection of appropriate models for OA in preclinical studies should be specified and relevant to the clinical scenario.Cite this article: T. Tawonsawatruk, O. Sriwatananukulkit, W. Himakhun, W. Hemstapat. Comparison of pain behaviour and osteoarthritis progression between anterior cruciate ligament transection and osteochondral injury in rat models. Bone Joint Res 2018;7:244-251. DOI: 10.1302/2046-3758.73.BJR-2017-0121.R2.