Deep learning pose estimation for multi-cattle lameness detection.

The objective of this study was to develop a fully automated multiple-cow real-time lameness detection system using a deep learning approach for cattle detection and pose estimation that could be deployed across dairy farms. Utilising computer vision and deep learning, the system can analyse simultaneously both the posture and gait of each cow within a camera field of view to a very high degree of accuracy (94-100%). Twenty-five video sequences containing 250 cows in varying degrees of lameness were recorded and independently scored by three accredited Agriculture and Horticulture Development Board (AHDB) mobility scorers using the AHDB dairy mobility scoring system to provide ground truth lameness data. These observers showed significant inter-observer reliability. Video sequences were broken down into their constituent frames and with a further 500 images downloaded from google, annotated with 15 anatomical points for each animal. A modified Mask-RCNN estimated the pose of each cow to output 5 key-points to determine back arching and 2 key-points to determine head position. Using the SORT (simple, online, and real-time tracking) algorithm, cows were tracked as they move through frames of the video sequence (i.e., in moving animals). All the features were combined using the CatBoost gradient boosting algorithm with accuracy being determined using threefold cross-validation including recursive feature elimination. Precision was assessed using Cohen's kappa coefficient and assessments of precision and recall. This methodology was applied to cows with varying degrees of lameness (according to accredited scoring, n = 3) and demonstrated that some characteristics directly associated with lameness could be monitored simultaneously. By combining the algorithm results over time, more robust evaluation of individual cow lameness was obtained. The model showed high performance for predicting and matching the ground truth lameness data with the outputs of the algorithm. Overall, threefold lameness detection accuracy of 100% and a lameness severity classification accuracy of 94% respectively was achieved with a high degree of precision (Cohen's kappa = 0.8782, precision = 0.8650 and recall = 0.9209).

EVM Loss: A Loss Function for Training Neural Networks in Communication Systems.

Neural networks and their application in communication systems are receiving growing attention from both academia and industry. The authors note that there is a disconnect between the typical objective functions of these neural networks with regards to the context in which the neural network will eventually be deployed and evaluated. To this end, a new loss function is proposed and shown to increase the performance of neural networks when implemented in a communication system compared to previous methods. It is further shown that a 'split complex' approach used by many implementations can be improved via formalisation of the 'concatenated complex' approach described herein. Experimental results using the orthogonal frequency division multiplexing (OFDM) and spectrally efficient frequency division multiplexing (SEFDM) modulation formats with varying bandwidth compression factors over a wireless visible light communication (VLC) link validate the efficacy of the proposed method in a real system, achieving the lowest error vector magnitude (EVM), and thus bit error rate (BER), across all experiments, with a 5 dB to 10 dB improvement in the received symbols EVM overall compared to the baseline implementation, with bandwidth compressions down to 40% compared to OFDM, resulting in a spectral efficiency gain of 67%.

Application of Artificial Intelligence-based Technology in Cancer Management: A Commentary on the Deployment of Artificial Neural Networks.

Artificial intelligence was recognised many years ago as a potential and powerful tool to predict disease outcome in many clinical situations. The conventional approaches using statistical methods have provided much information, but are subject to limitations imposed by the complexity of medical data. The structures of the important variants of the machine learning system artificial neural networks (ANN) are discussed and emphasis is given to the powerful analytical support that could be provided by ANN for the prediction of cancer progression and prognosis. The predictive ability of the cellular markers, DNA ploidy and cell-cycle profiles, and molecular markers, such as tumour promoter and suppressor gene, and growth factor and steroid hormone receptors in breast cancer management were also analysed. ANN systems have been successfully deployed to evaluate microRNA profiles of tumours which saliently sway cancer progression and prognosis of the disease, thus counteracting the negative implications of their numerical abundance. Finally, in this setting, the prospective technical improvements in artificial neural networks, as hybrid systems in combination with fuzzy logic and artificial immune networks were also addressed.

Neural Analyses Validate and Emphasize the Role of Progesterone Receptor in Breast Cancer Progression and Prognosis.

Oestrogen receptor (ER) expression is routinely measured in breast cancer management, but the clinical merits of measuring progesterone receptor (PR) expression have remained controversial. Hence the major objective of this study was to assess the potential of PR as a predictor of response to endocrine therapy. We report on analyses of the relative importance of ER and PR for predicting prognosis using robust multilayer perceptron artificial neural networks. Receptor determinations use immunohistochemical (IHC) methods or radioactive ligand binding assays (LBA). In view of the heterogeneity of intratumoral receptor distribution, we examined the relative merits of the IHC and LBA methods. Our analyses reveal a more significant correlation of IHC-determined PR than ER with both nodal status and 5-year disease-free survival (DFS). In LBA, PR displayed higher correlation with survival and ER with nodal status. There was concordance of correlation of PR with DFS by both IHC and LBA. This study suggests a clear distinction between PR and ER, with PR displaying greater correlation than ER with disease progression and prognosis, and emphasizes the marked superiority of the IHC method over LBA. These findings may be valuable in the management of patients with breast cancer.

Prediction of nodal metastasis and prognosis of breast cancer by ANN-based assessment of tumour size and p53, Ki-67 and steroid receptor expression.

BACKGROUND: Tumour stage and the appropriate course of treatment in patients with breast cancer are primarily characterized by the state of metastasis in the axillary lymph nodes. In recent years, substantial research has focused on the prediction of lymph node status based on various pathological and molecular markers in order to obviate the necessity to carry out axillary dissection. In the present study, artificial neural network (ANN) is employed as the analysis platform to examine the prognostic significance of a group of well-established prognostic markers for breast cancer outcome prediction in terms of nodal status. Furthermore, we investigated existing interactions between these markers. PATIENTS AND METHODS: The data set contained 66 patient records, where 5 pathological and molecular markers including tumour size, oestrogen receptor status (ER), progesterone receptor status (PR), Ki-67 and p53 expression had been assessed for each patient. The spread of metastasis to the axillary lymph nodes was clinically diagnosed and patients were accordingly categorized into node-positive and node-negative groups. The aforementioned markers were analyzed using a probabilistic neural network (PNN) for nodal status prediction which was considered as the network output. Furthermore, the interactions between these markers were evaluated using different marker combinations as the network input for finding the best marker arrangement for nodal predication. RESULTS: The best prediction accuracy was obtained by a 3-marker combination including tumour size, PR and p53 with 71% accuracy for nodal prediction. Leaving out ER and PR from the full marker set showed approximately the same variations in the results, which is an indication of the direct correlation of these two markers. Furthermore, tumour size was proved to be the most significant individual marker for predicting nodal metastasis. However, when used in combination with Ki-67 the prediction results drop significantly. CONCLUSION: The results presented here indicate that molecular and pathological markers can provide useful information for early-stage prognosis. However, the interactions between these markers must be considered in order to achieve accurate and reliable prediction.