A preliminary study on the application of deep learning methods based on convolutional network to the pathological diagnosis of PJI

Abstract

Objective This study aimed to establish a deep learning method based on convolutional networks for the preliminary study of the pathological diagnosis of prosthetic joint infections (PJI). Methods We enrolled 20 revision patients after joint replacement from the Department of Orthopedics, the First Medical Center, General Hospital of the People's Liberation Army, from January 2021 to January 2022 (10 of whom were confirmed to be infected against 2018 ICM criteria, and the remaining 10 were verified to be non-infected), and classified high-power field images according to 2018 ICM criteria. Then, we inputted 576 positive images and 576 negative images into a neural network by employing a resNET model, used to select 461 positive images and 461 negative images as training sets, 57 positive images and 31 negative images as internal verification sets, 115 positive images and 115 negative images as external test sets. Results The resNET model classification was used to analyze the pathological sections of PJI patients under high magnification fields. The results of internal validation set showed a positive accuracy of 96.49%, a negative accuracy of 87.09%, an average accuracy of 93.22%, an average recall rate 96.49%, and an F1 of 0.9482. The accuracy of external test results was 97.39% positive, 93.04% negative, the average accuracy of external test set was 93.33%, the average recall rate was 97.39%, with an F1 of 0.9482. The AUC area of the intelligent image-reading diagnosis system was 0.8136. Conclusions This study used the convolutional neural network deep learning to identify high-magnification images from pathological sections of soft tissues around joints, against the diagnostic criteria for acute infection, and a high precision and a high recall rate were accomplished. The results of this technique confirmed that better results could be achieved by comparing the new method with the standard strategies in terms of diagnostic accuracy. Continuous upgrading of extended training sets is needed to improve the diagnostic accuracy of the convolutional network deep learning before it is applied to clinical practice.

Application of machine learning in the prevention of periprosthetic joint infection following total knee arthroplasty: a systematic review

“…Full texts were obtained and reviewed for the remaining 16 studies. Five studies were removed, with 11 studies included for the final analysis [ 7 , 8 , 13 – 21 ]. The included studies targeted four areas of ML application: PJI prediction, diagnosis, antibiotic application, and prognosis (Fig.…”

“…[ 8 ] Periprosthetic joint infection prediction via machine learning: comprehensible personalized decision support for diagnosis The Journal of Arthroplasty 2021 323 patients Tao, Y. [ 13 ] A preliminary study on the application of deep learning methods based on convolutional network to the pathological diagnosis of periprosthetic joint infection Arthroplasty 2022 20 patients (Training sets: 461 positive images, 461 negative images) Prognosis Shohat, N. [ 20 ] 2020 Frank Stinchfield Award: identifying who will fail following irrigation and debridement for prosthetic joint infection The Bone & Joint Journal 2020 609 patients Klemt, C. [ 21 ] Machine learning models accurately predict recurrent infection following revision total knee arthroplasty for periprosthetic joint infection Knee Surgery, Sports Traumatology, Arthroscopy 2021 618 patients …”

“…[ 8 ] 2021 6/11 (54.5%) Fair Tao, Y. [ 13 ] 2022 6/11 (54.5%) Fair Davis, J.J. [ 14 ] 2016 8/11 (72.7%) Fair Drouin, A. [ 15 ] 2019 7/11 (63.6%) Fair Moradigaravand, D. [ 16 ] 2018 8/11 (72.7%) Fair Nguyen, M. [ 17 ] 2018 7/11 (63.6%) Fair Khaledi, A.…”

Clinically applicable optimized periprosthetic joint infection diagnosis via AI-based pathology

“…Our prior research on intelligent pathological diagnosis of PJI showed that excessively large training patches could lead to imprecise identi cation of minute neutrophils [25]. To achieve better diagnostic results with deep learning networks, we reduced ve or more neutrophils, as speci ed in the current criterion, to two or more neutrophils, with pixel area correspondingly lowered from 1200 × 1800 pixels to 600 × 600 pixels.…”

“…Following the 2018 ICM guidelines, we simpli ed the problem by using "at least 5 neutrophils in high-power elds within pathological slides" as the diagnostic criterion. Patches meeting the PJI diagnostic criteria were selected and utilized to train a supervised learning model based on ResNet34, resulting in an intelligent model for PJI image-level diagnosis [25]. The aforementioned ResNet model has been widely applied for the intelligent recognition of images and pathological pictures [39], yielding high accuracy in the pathological diagnosis of malignancies such as lung cancer, gastric cancer, breast cancer, and bladder cancer [40][41][42][43].…”