Automated analysis of rabbit knee calcified cartilage morphology using micro‐computed tomography and deep learning

Rytky, Santeri J.O.; Huang, Lingwei; Tanska, Petri; Tiulpin, Aleksei; Panfilov, Egor; Herzog, Walter; Korhonen, Rami K.; Saarakkala, Simo; Finnilä, Mikko A. J.

doi:10.1111/joa.13435

Cited by 16 publications

(18 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12 To detail further changes in the subchondral bone plate, a highresolution µCT is needed to separate the subchondral bone plate porosity and calcified cartilage. 38 The OARSI score in the medial tibial plateau was greater in the CNTRL group compared to the C-L and ACLT groups at the 2-week time point. We can only speculate that this may be ascribed to the presence of spontaneous OA in the CNTRL group at the beginning of the experiments.…”

Section: Discussionmentioning

confidence: 80%

See 1 more Smart Citation

Early changes in osteochondral tissues in a rabbit model of post‐traumatic osteoarthritis

Huang

Riihioja

Tanska

et al. 2021

Journal Orthopaedic Research

Self Cite

View full text Add to dashboard Cite

Concurrent osteoarthritic (OA) manifestations in bone and cartilage are poorly known. To shed light on this issue, this study aims to investigate changes in subchondral bone and articular cartilage at two time points after anterior cruciate ligament transection (ACLT) in a rabbit model. 2 (N = 16) and 8 (N = 10) weeks after ACLT, the subchondral bone structure, cartilage thickness, Osteoarthritis Research Society International (OARSI) score, fixed charged density (FCD), and collagen orientation angle were analyzed. OA related changes were evaluated by comparing the ACLT to the contralateral (C-L) and control knees. Already 2 weeks after ACLT, higher trabecular number in the medial femoral condyle and femoral groove, greater OARSI score in the femoral condyles, and thinner trabeculae in the lateral tibial plateau and femoral groove were observed in ACLT compared to C-L knees. Only minor changes of cartilage collagen orientation in the femoral condyles and femoral groove and smaller FCD in the femoral condyles, medial tibial plateau, femoral groove and patella were observed. 8 weeks post-ACLT, the surgical knees had thinner subchondral plate and trabeculae, and smaller trabecular bone volume fraction in most of the knee locations. OARSI score was greater in the femoral condyle and lateral tibial plateau cartilage. FCD loss was progressive only in the femoral condyle, femoral groove, and patellar cartilage, and minor changes of cartilage collagen orientation angle were present in the femoral condyles, femoral This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Discussionmentioning

confidence: 80%

“…The resolution of the µCT imaging we used was moderate and was selected to allow comparisons to our previous studies 12 . To detail further changes in the subchondral bone plate, a high‐resolution µCT is needed to separate the subchondral bone plate porosity and calcified cartilage 38 …”

Section: Discussionmentioning

confidence: 99%

Early changes in osteochondral tissues in a rabbit model of post‐traumatic osteoarthritis

Huang

Riihioja

Tanska

et al. 2021

Journal Orthopaedic Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…[28][29][30] Recently, emerging studies showed that AI can be used in orthopaedics. [31][32][33] For example, Yeh et al 30 showed that an AI-baed automatic alignment measure system can locate spinal anatomic landmarks with a high accuracy and produce radiographic parameters that correlated well with operator-based measurements. Yabu et al 34 also demonstrated that convolutional neural network could detect new osteoporotic vertebral fractures utilising magnetic resonance images with performance comparable to that of spine surgeons.…”

Section: Discussionmentioning

confidence: 99%

Deep learning approach for guiding three‐dimensional computed tomography reconstruction of lower limbs for robotically‐assisted total knee arthroplasty

Zhang

Ding

et al. 2021

Robotics Computer Surgery

View full text Add to dashboard Cite

Background: Robotic-assisted total knee arthroplasty (TKA) was performed to promote the accuracy of bone resection and mechanical alignment. Among these TKA system procedures, 3D reconstruction of CT data of lower limbs consumes significant manpower. Artificial intelligence (AI) algorithms applying deep learning has been proved efficient in automated identification and visual processing.Methods: CT data of a total of 200 lower limbs scanning were used for AI-based 3D model construction and CT data of 20 lower limbs scanning were utilised for verification. Results:We showed that the performance of an AI-guided 3D reconstruction of CT data of lower limbs for robotic-assisted TKA was similar to that of the operatorbased approach. The time of 3D lower limb model construction using AI was 4.7 min. AI-based 3D models can be used for surgical planning. Conclusion:AI was used for the first time to guide the 3D reconstruction of CT data of lower limbs for facilitating robotic-assisted TKA. Incorporation of AI in 3D model reconstruction before TKA might reduce the workload of radiologists. K E Y W O R D Sartificial intelligence, HURWA robotic-assisted TKA system, robotically TKA assisted system, 3D CT model | INTRODUCTIONTotal knee arthroplasty (TKA) is an effective procedure for cases with end-stage rheumatoid arthritis or osteoarthritis of the knee. 1 The surgery was carried out in over 370,000 and 700,000 patients annually in China and USA, respectively. 2 Despite the development in implant materials and design, thromboembolic prophylaxis, rehabilitation, computer navigation and patient-specific implants, and the use of prophylactic antibiotics, over 20% of patients reported unsatisfaction following TKA. [3][4][5][6] Robotically assisted TKA was thus developed to promote mechanical alignment, accuracy of bone resection, soft tissue protection, and implant survivorship and implant stability. [7][8][9][10] In this connection, our previous studies showed that a novel HURWA robotic-assisted TKA system (BEIJING HURWA-ROBOT Technology Co. Ltd) could enhance the accuracy of bone resection in terms of resection angles and levels in the sawbone and the sheep models. 11,12 The procedures of robotic-assisted TKA system consists of the following steps: preoperative computed tomography (CT) scanning of lower limbs, three-dimensional (3D) reconstruction of CT data of lower limbs, CT-based planning, surgical planning depending on the 3D CT model, and the act of performing robotic-assisted TKA. Among

show abstract

“…Deep learning and speci cally convolutional neural networks (CNNs) have recently seen an enormous increase in popularity for their application in di cult biological micro-CT image segmentation tasks 49 . CNN has been recently used for segmentation of: ant brain 50 , murine mineralised cartilage/bone 51 and rabbit calci ed knee cartilages 52 in micro-CT images. While this segmentation provides us with morphological information about the object of interest, it does not tell us anything about its function in the context of brain anatomy.…”

Section: Introductionmentioning

confidence: 99%

High resolution micro-CT imaging in mice stroke models: from 3D detailed infarct characterization to automatic area segmentation

Gomes

Pinto

Matula

et al. 2022

Preprint

View full text Add to dashboard Cite

Characterization of brain infarct lesion in rodent models of stroke is crucial to assess the outcome of stroke therapies and to study the disease pathophysiology. However, so far it has been mostly performed by: 1) histological methods, a time-consuming process that lead to significant flaws; or 2) via MRI imaging, which is faster, yielding 3D information but at high costs. High-resolution micro-CT imaging became, in the last decade, a simple, fast, and cheaper solution, allowing 3D sample analysis. Here, we describe that high-resolution micro-CT, either using iodine/OsO4 as contrast agents, can be successfully applied for fine quantification and localization of lesion size and edema volume in preclinical stroke models. We successfully correlated this new approach with the standard histological method TTC. In transient MCAO mouse stroke model, we were able to identify/quantify large lesioned areas (segmented in core/penumbra), up to degenerated finer striatal myelinated fibers in a transient-ischemic-attack (TIA) mouse model, at different timepoints post-ischemia, through manual/automatic segmentation approaches (deep learning). Furthermore, whole brain 3D reconstructions allow brain atlas co-registration with specific affected brain areas. Hence, the presented methodology, through iodine/OsO4 micro-CT imaging, constitutes a valuable advance for precise and detailed assessment of stroke outcomes in preclinical animal studies.

show abstract

Automated analysis of rabbit knee calcified cartilage morphology using micro‐computed tomography and deep learning

Abstract: This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 16 publications

References 49 publications

Early changes in osteochondral tissues in a rabbit model of post‐traumatic osteoarthritis

Early changes in osteochondral tissues in a rabbit model of post‐traumatic osteoarthritis

Deep learning approach for guiding three‐dimensional computed tomography reconstruction of lower limbs for robotically‐assisted total knee arthroplasty

High resolution micro-CT imaging in mice stroke models: from 3D detailed infarct characterization to automatic area segmentation

Contact Info

Product

Resources

About