Purpose The surgical stress of total knee arthroplasty (TKA) procedure and the application of intra‐operative pneumatic thigh tourniquet increases local fibrinolytic activity, which contributes significantly to post‐operative blood loss. Tranexamic acid, an antifibrinolytic drug, is commonly used to control post‐operative blood loss. The recommended mode of administration of tranexamic acid is either oral or intravenous. However, the mechanism of action of the tranexamic acid points towards the possible effectiveness it may have following local/intra‐articular application. This prospective, double‐blinded, randomized preliminary study evaluated the efficacy of intra‐articular tranexamic acid in reducing TKA‐associated post‐operative blood loss. Methods Fifty consenting patients with osteoarthritis of the knee scheduled for primary unilateral cemented‐TKA were randomly allocated to one of the two groups: Tranexamic Acid (TA) group (n = 25, 500 mg/5 ml tranexamic acid) and the control group (n = 25, 5 ml 0.9% saline). The drug and control solution were administered intra‐articularly through the drain tube immediately after the wound closure. Parameters related to blood loss (drop in haemoglobin, haematocrit differential) and the drain output [volume (ml)] were compared between the two groups. Results On a comparative basis, TA‐group obtained significant reduction in the drain output [95% CI: 360.41–539.59, p < 0.001] at 48 h post‐operatively. Even though the control group received sixfold more blood transfusion than TA‐group, it showed a greater drop in haemoglobin and haematocrit (p < 0.05). Conclusions Local application of tranexamic acid seems to be effective in reducing post‐TKA blood loss as well as blood transfusion requirements. Level of evidence Therapeutic study, Level II.

Human facial emotion recognition (FER) has attracted the attention of the research community for its promising applications. Mapping different facial expressions to the respective emotional states are the main task in FER. The classical FER consists of two major steps: feature extraction and emotion recognition. Currently, the Deep Neural Networks, especially the Convolutional Neural Network (CNN), is widely used in FER by virtue of its inherent feature extraction mechanism from images. Several works have been reported on CNN with only a few layers to resolve FER problems. However, standard shallow CNNs with straightforward learning schemes have limited feature extraction capability to capture emotion information from high-resolution images. A notable drawback of the most existing methods is that they consider only the frontal images (i.e., ignore profile views for convenience), although the profile views taken from different angles are important for a practical FER system. For developing a highly accurate FER system, this study proposes a very Deep CNN (DCNN) modeling through Transfer Learning (TL) technique where a pre-trained DCNN model is adopted by replacing its dense upper layer(s) compatible with FER, and the model is fine-tuned with facial emotion data. A novel pipeline strategy is introduced, where the training of the dense layer(s) is followed by tuning each of the pre-trained DCNN blocks successively that has led to gradual improvement of the accuracy of FER to a higher level. The proposed FER system is verified on eight different pre-trained DCNN models (VGG-16, VGG-19, ResNet-18, ResNet-34, ResNet-50, ResNet-152, Inception-v3 and DenseNet-161) and well-known KDEF and JAFFE facial image datasets. FER is very challenging even for frontal views alone. FER on the KDEF dataset poses further challenges due to the diversity of images with different profile views together with frontal views. The proposed method achieved remarkable accuracy on both datasets with pre-trained models. On a 10-fold cross-validation way, the best achieved FER accuracies with DenseNet-161 on test sets of KDEF and JAFFE are 96.51% and 99.52%, respectively. The evaluation results reveal the superiority of the proposed FER system over the existing ones regarding emotion detection accuracy. Moreover, the achieved performance on the KDEF dataset with profile views is promising as it clearly demonstrates the required proficiency for real-life applications.

Level II, retrospective case series.

No abstract