Search

Abstract Background Studies have shown that medial subluxation of the tibia occurs after anterior cruciate ligament (ACL) rupture. However, it is unclear whether anterior cruciate ligament reconstruction (ACLR) can correct tibial coronal subluxation. Purpose To determine whether the tibia is medially subluxated after ACL rupture, and whether ACLR can correct medial subluxation of the tibia. Study design Case series; Level of evidence, 4, Retrospective clinical study. Methods The distance of tibial coronal subluxation before and after ACLR surgery was measured in 48 patients with ACL rupture and meniscus injury. Tibiofemoral subluxation was defined as the perpendicular distance between the long axis of the tibia and a second parallel line originating at the most proximal aspect of the femoral intercondylar notch. To determine the long axis of the tibia, two circles separated by 5 cm were centered on the proximal tibia. The proximal circle is 5 cm from the tibial plateau, and the distal circle is 5 cm from the proximal circle. The line passing through the center of the two circles was considered the long axis of the proximal tibia. Care was taken to ensure that each patient lied on the back with their patellae facing upward, to minimize rotational variation among the radiographs. At the same time, 30 patients with simple meniscus injury who underwent arthroscopy during the same period were selected to determine the degree of tibiofemoral coronal subluxation as the baseline value. The changes before and after operation were compared, as well as the differences with the baseline data. Result The average follow-up period was 21.2 ± 5.8 months. The average distance of tibial coronal subluxation before ACLR was 5.5 ± 2.1 mm, which was significantly different from that of baseline group (7.3 ± 2.1 mm) (P

Abstract Background Studies have shown that the spherical shape of the lateral femoral condyle has a clear relationship with the relative axial movement of tibiofemoral joint and the anterior cruciate ligament (ACL) rupture. The purpose of this study was to describe the distal curvature of the lateral femoral condyle by ratio of height of lateral femoral condyle to anteroposterior diameter (HAPR), and evaluate its correlation with ACL rupture. Methods A retrospective case-control study of 64 patients was conducted. Two age-and sex-matched cohorts (each n = 32) were analyzed: primary ACL ruptures, and a control group consisting of isolated meniscal tears. On the radiograph, the distance from the intersection of the axis of the distal femur and the anteriorly diameter of the lateral femoral condyle to the lower point of the lateral femoral condyle divided by the anteriorly diameter of the lateral femoral condyle is HAPR. The HAPR was measured by digital radiograph imaging systems (DR) to quantify femoral sphericity. Cutoff values were defined; and diagnostic performance of the risk factors was assessed. Meanwhile, we measured the posterior tibial slope (PTS) on radiograph and compared the two methods to evaluate the significance of HAPR in predicting ACL rupture. Results A total of sixty-four patients who met the inclusion criteria were included in the final analysis (32 with primary ACL rupture, 32 controls). The HAPR was smaller in the knees with primary ACL rupture (0.31 ± 0.02) than that of the control group (0.33 ± 0.02) (p

Abstract Background The rapid development of artificial intelligence technology has improved the capability of automatic breast cancer diagnosis, compared to traditional machine learning methods. Convolutional Neural Network (CNN) can automatically select high efficiency features, which helps to improve the level of computer-aided diagnosis (CAD). It can improve the performance of distinguishing benign and malignant breast ultrasound (BUS) tumor images, making rapid breast tumor screening possible. Results The classification model was evaluated with a different dataset of 100 BUS tumor images (50 benign cases and 50 malignant cases), which was not used in network training. Evaluation indicators include accuracy, sensitivity, specificity, and area under curve (AUC) value. The results in the Fus2Net model had an accuracy of 92%, the sensitivity reached 95.65%, the specificity reached 88.89%, and the AUC value reached 0.97 for classifying BUS tumor images. Conclusions The experiment compared the existing CNN-categorized architecture, and the Fus2Net architecture we customed has more advantages in a comprehensive performance. The obtained results demonstrated that the Fus2Net classification method we proposed can better assist radiologists in the diagnosis of benign and malignant BUS tumor images. Methods The existing public datasets are small and the amount of data suffer from the balance issue. In this paper, we provide a relatively larger dataset with a total of 1052 ultrasound images, including 696 benign images and 356 malignant images, which were collected from a local hospital. We proposed a novel CNN named Fus2Net for the benign and malignant classification of BUS tumor images and it contains two self-designed feature extraction modules. To evaluate how the classifier generalizes on the experimental dataset, we employed the training set (646 benign cases and 306 malignant cases) for tenfold cross-validation. Meanwhile, to solve the balance of the dataset, the training data were augmented before being fed into the Fus2Net. In the experiment, we used hyperparameter fine-tuning and regularization technology to make the Fus2Net convergence.

Abstract Background Breast cancer is one of the most serious diseases threatening women’s health. Early screening based on ultrasound can help to detect and treat tumours in the early stage. However, due to the lack of radiologists with professional skills, ultrasound-based breast cancer screening has not been widely used in rural areas. Computer-aided diagnosis (CAD) technology can effectively alleviate this problem. Since breast ultrasound (BUS) images have low resolution and speckle noise, lesion segmentation, which is an important step in CAD systems, is challenging. Results Two datasets were used for evaluation. Dataset A comprises 500 BUS images from local hospitals, while dataset B comprises 205 open-source BUS images. The experimental results show that the proposed method outperformed its related classic segmentation methods and the state-of-the-art deep learning model RDAU-NET. Its accuracy (Acc), Dice similarity coefficient (DSC) and Jaccard index (JI) reached 96.25%, 78.4% and 65.34% on dataset A, and its Acc, DSC and sensitivity reached 97.96%, 86.25% and 88.79% on dataset B, respectively. Conclusions We proposed an adaptive morphological snake based on marked watershed (AMSMW) algorithm for BUS image segmentation. It was proven to be robust, efficient and effective. In addition, it was found to be more sensitive to malignant lesions than benign lesions. Methods The proposed method consists of two steps. In the first step, contrast limited adaptive histogram equalization (CLAHE) and a side window filter (SWF) are used to preprocess BUS images. Lesion contours can be effectively highlighted, and the influence of noise can be eliminated to a great extent. In the second step, we propose adaptive morphological snake (AMS). It can adjust the working parameters adaptively according to the size of the lesion. Its segmentation results are combined with those of the morphological method. Then, we determine the marked area and obtain candidate contours with a marked watershed (MW). Finally, the best lesion contour is chosen by the maximum average radial derivative (ARD).