Medical imaging and diagnosis of subpatellar vertebrae based on improved Laplacian image enhancement algorithm

https://doi.org/10.1016/j.cmpb.2019.105082Get rights and content

Highlights

  • Release and removal of symptomatic infrapatellar patella during arthroscopic surgery can significantly reduce knee pain and improve function.

  • Medical imaging is a necessary and effective advanced method for the diagnosis and treatment of infrapatellar wrinkles.

  • Magnetic resonance imaging can effectively retain the image details, which is conducive to diagnosis and improve the accuracy of diagnosis.

  • The processed image is compared with the original image, and the advantages and disadvantages of the improved Laplacian image enhancement algorithm are analyzed.

Abstract

Objective

Nowadays, arthroscopy is widely applied to the treatment of joint diseases. The experimental trials were designed to determine whether the infrapatellar plica was symptomatic or not, and to appraise the medical effects of these patients who underwent arthroscopic treatment. An improved Laplacian image enhancement algorithm is added to the experiment. The medical image of the Subpatellar vertebral body under arthroscope is processed by the algorithm. The processed image is compared with the original image, and the advantages and disadvantages of the improved Laplacian image enhancement algorithm are analyzed.

Methods

Retrospective Medical trial design was executed in our study. In addition, X-ray film and magnetic resonance imaging (MRI) were included in the study. Visual Analogue Scale (VAS) and Lysholm Score were carried out. Arthroscopy results, MRI findings, and Medical features were researched and analyzed carefully. Then we use the improved Laplacian image enhancement algorithm to process the image, which makes the image more convenient for analysis and improves the diagnostic accuracy.

Results

Some of the experimental protomedical images are not clear enough, and the details and textures are difficult to judge, which hinders the diagnosis. After the improved Laplacian algorithm processing, the image effect has been significantly improved. From the image we get the result, although the wound healed after surgery, some patients have existence of transient swelling in recovery process but no effusion. The pain of all patients knee was sharply relieved and the function was improved. All patients’ conditions were most satisfactory.

Conclusion

The findings in this study demonstrate a significant reduction in knee pain and improvement in function by releasing and removal of the symptomatic infrapatellar plica under arthroscopic surgery. The image processed by the improved Laplacian image enhancement algorithm can effectively retain the image details, which is conducive to diagnosis and improve the diagnostic accuracy.

Introduction

The synovial membrane of the human knee is considered to be physiological structures that remained during the embryonic growing of the knee [1]. The infrapatellar plica of most people is left behind due to incomplete absorption. According to their different origins, the synovial plicae can be divided into four smaller synovial plica: 1) patella medial synovial plica, 2) suprapatellar, 3) infrapatellar plica, and 4) patella lateral plicae [2].

Infrapatellar plica has a reputation of being a mucous membrane. It comes from its infrapatellar fat pad, which widens as it grows obliquely upward, over the anterior cruciate ligament (ACL), and adheres to the intercondylar notch of femur (Fig. 1). The plica is rarely large and thick [3]. There was obvious poor difference between knees, and it had no significant correlation with age [4].

Many types of synovial plicae are often without symptoms and Medical signs. If synovial plicae failed their original elasticity or softness and turn to be fibrotic for various reasons, they could give rise to internal disorder of the knee joint [2], [5], [6]. The synovial plica may be symptomatic over time in the abnormal condition, and then it form what is called the plica syndrome of the knee [2]. The symptomatic infrapatellar plica becomes a kind of plica syndrome, and it is often obvious to the surgeons particularly in the process of arthrocentesis or arthroscopy. For these patients, large and thickened infrapatellar plica can form a hindrance to the pathway of arthroscope and some medical apparatuses [5], [7].

Many outpatients complained of infrapatellar pain or anterior knee pain in a 30°–0° extension of the knee, with a transient “clicking” sound. Patients with light condition felt discomfort after a long walk, but felt no pain. It is often the early features of infrapatellar plica. It is possible that the infrapatellar plica stimulated and extruded the anterior cruciate ligament as well as the articular cartilage of the femoral condyle with flexion and extension of the knee joint. This leads to a marked infrapatellar plica with proliferation and cell activation due to continuous stimulation and force interaction. Such changes will result in chronic inflammation.

In the process of arthrocentesis, lubricating fluid (such as sodium hyaluronate [21]) which should be injected to the joint, did not actually enter the articular cavity but stayed in the hyperplastic synovial membrane. Therefore, after repeated joint arthrocentesis, some patient's condition did not improve significantly, but experienced knee joint swelling. Moreover, it can induce acute inflammation due to the aggravating condition.

It is suggested that knee degeneracy results due to poor X-ray imaging of soft tissues. Unbelievably, the infrapatellar plica does not show up clearly on MRI. The MRI examination had many false appearances, which suggested injury of anterior or lateral meniscus, discoid meniscus and anterior cruciate ligament tear. All of these are contradictory to the intact medial and lateral meniscus and cruciate ligament under arthroscope. All of these illustrate the limitations of the MRI. Therefore, the patient's symptoms did not improve significantly.

Many medical experts do not recognize the condition as it is not obvious. It is often considered to be a meniscus or anterior cruciate ligament injury. Under arthroscopy, the infrapatellar plica has been observed intuitively [8]. Additionally, it had been widely reported in medical literature [9], [10]. During our study, we observed the results of all the patients under our care. The purpose of this study is to determine whether the infrapatellar plicae was symptomatic or not, and to evaluate the Medical outcomes of all the patients.

Image enhancement has the advantages of improving image quality, improving geometric registration accuracy and overcoming the image data incompleteness in object extraction and recognition. It has become an important information processing technology and has been widely used in remote sensing, medicine, aerospace and other fields. Image fusion refers to the use of various imaging sensors to obtain different images, synthesize complementary and redundant information of each image, and produce a new image to obtain more accurate, reliable and comprehensive image description. Image fusion includes three parts: pixel level fusion, feature level fusion and decision level fusion. In recent years, many image fusion methods have been proposed, among which the multi-resolution image fusion method in pixel level fusion is more common. Laplace pyramid decomposition method is one of the multi-resolution analysis methods.

The classical Laplacian pyramid fusion algorithm can achieve the fusion effect without obvious stitching trace, but it has the defect of blurring the image due to the loss of details. In order to solve the above problems, this paper proposes an adaptive fusion area based on the Laplacian pyramid fusion algorithm of graph cutting, and proposes a weighted fusion method of multiple directions including horizontal direction. Using the complete detail information of source image, the fusion image of source image and Laplacian pyramid is fused according to this fusion method. Rules are fused to compensate the Laplace pyramid reconstruction error. This algorithm can effectively improve the details of the fused image, and the mosaic panorama is more realistic, which is in line with the characteristics of human vision. The improved Laplacian algorithm framework is shown in Fig. 2.

Section snippets

Experimental subjects

We performed a systematic research and analysed of all the patients who underwent diagnosis postoperatively with symptomatic infrapatellar plica at our department from October 2015 to March 2018. One hundred and six patients had knee internal lesions such as anterior cruciate ligament rupture, meniscal tears, chondromalacia patella, articular cartilage injury, infrapatellar plicae and medial plica syndrome at the beginning of our study. Those patients with symptomatic infrapatellar plica only

Injury diagnostics

The vertical septum pattern, separate types, split types, fenestra pattern and absent types were analyzed. These types are described as follows. Vertical septum types: the plica continued with the anterior surface of ACL (Fig. 4). Two parts were subdivided (Fig. 4a). Separate types: the plica was absolutely disassociated from ACL (Fig. 4b). Split types: the plica was different completely from the ACL and was split thoroughly (Fig. 4c). Fenestra types: the plica was complete synovium with a

Discussion

It is generally believed that the normal plica results due to the embryological vestigial remnants of synovial tissue of growing knees. It is an elastic tissue. Injury of the knee may result in inflammation, which lead to denaturation and inelasticity of the tissue. Finally, they result into fibrotic bands. But as is known to all, the suprapatellar plica is an important factor to cause symptoms [7].

The main features of infrapatellar plica concerned the problems caused by the membrane in process

Conclusion

Medical imaging coupled with enhanced image processing is a necessary and effective advanced method to make a diagnosis and give treatment for infrapatellar plica. The findings in this study demonstrate a significant reduction in knee pain and improvement in function by releasing and removal of the symptomatic infrapatellar plica under arthroscopic surgery. The image processed by the improved Laplacian image enhancement algorithm can effectively retain the image details, which is conducive to

Compliance with ethical standards

The study was funded by personal (XDT) research and development fund (303-02-01-06-04). And authors whose names appear on the manuscript have contributed sufficiently to the scientific work and therefore share collective responsibility and accountability for the results. The authors declare that they have no conflict of interest. All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee

CRediT authorship contribution statement

Xiangdong Tian: Conceptualization, Formal analysis, Visualization, Writing - original draft. Jian Wang: Formal analysis, Visualization, Writing - original draft, Resources, Software. Dongfeng Du: Data curation, Project administration, Methodology. Shuwen Li: Data curation. Changxiao Han: Methodology. Guangyu Zhu: Formal analysis, Project administration. Yetong Tan: Formal analysis. Sheng Ma: . Handong Chen: . Ming Lei: Data curation.

Declaration of Competing Interest

The authors declared that there was no conflict of interest in this study.

Acknowledgement

The authors express their appreciation for the Medical support of orthopedics and valuable discussions with surgeons at the Orthopedic Center of The Third Affiliated Hospital of Beijing University of Chinese Medicine. This work was supported in part by Graduate school of Beijing University of Chinese Medicine, Beijing.

References (21)

There are more references available in the full text version of this article.

Cited by (12)

  • Deep learning-based approach for detecting COVID-19 in chest X-rays

    2022, Biomedical Signal Processing and Control
    Citation Excerpt :

    Computer-Aided Diagnosis (CAD) technologies have been enhanced to enable physicians automatically to identify potential disorders of organs on X-ray images, overcoming previous limits [29,30]. These systems are primarily powered by fast and powerful computer technology (such as CPU and GPU) and used to perform medical vision computing algorithms such as image enhancement, classification, segmentation, and tumor detection [31–34]. Artificial intelligence approaches such as deep neural networks and machine learning have become the essence of cutting-edge CAD applications in a variety of medical sectors.

  • Automated detection of COVID-19 cases from chest X-ray images using deep neural network and XGBoost

    2022, Radiography
    Citation Excerpt :

    To compensate for this shortcoming, Computer-Aided Diagnosis (CAD) systems can be employed.15,16 Most CAD systems depend on the development of Graphics Processing Units (GPUs), which are applied to implement medical image processing algorithms, such as image enhancement and limb or tumor segmentation.17,18 The development of artificial intelligence, especially some of its branches, such as Machine Learning and Deep Learning (DL), has contributed to greater intelligence in this process compared to human intelligence.

  • FCOD: Fast COVID-19 Detector based on deep learning techniques

    2021, Informatics in Medicine Unlocked
    Citation Excerpt :

    Computer-Aided Diagnosis (CAD) systems have been extended to overcome this limitation and help physicians to identify suspected diseases of vital organs in X-ray images automatically [11,12]. These systems, which are chiefly supported by the fast and advanced of computer technology (like CPU, GPU, and, TPU) are used to operate the medical vision computing algorithms, containing image enhancement, classification, segmentation, and tumor detection tasks [13–15]. In several medical fields, Artificial intelligence (AI) methods like a deep neural network and machine learning turn to the core of the superior CAD applications.

View all citing articles on Scopus
#

These authors contributed equally to the work and should be considered as co-first authors.

View full text