Automatic Identification of Individual Primates with Deep Learning Techniques.
Ontology highlight
ABSTRACT:
SUBMITTER: Guo S
PROVIDER: S-EPMC7415925 | biostudies-literature | 2020 Aug
REPOSITORIES: biostudies-literature
Publications
Automatic Identification of Individual Primates with Deep Learning Techniques.
Guo Songtao S Xu Pengfei P Miao Qiguang Q Shao Guofan G Chapman Colin A CA Chen Xiaojiang X He Gang G Fang Dingyi D Zhang He H Sun Yewen Y Shi Zhihui Z Li Baoguo B
iScience 20200725 8
The difficulty of obtaining reliable individual identification of animals has limited researcher's ability to obtain quantitative data to address important ecological, behavioral, and conservation questions. Traditional marking methods placed animals at undue risk. Machine learning approaches for identifying species through analysis of animal images has been proved to be successful. But for many questions, there needs a tool to identify not only species but also individuals. Here, we introduce a ...[more]
Similar Datasets
Project description:The increasing rates of neurodevelopmental disorders (NDs) are threatening pregnant women, parents, and clinicians caring for healthy infants and children. NDs can initially start through embryonic development due to several reasons. Up to three in 1000 pregnant women have embryos with brain defects; hence, the primitive detection of embryonic neurodevelopmental disorders (ENDs) is necessary. Related work done for embryonic ND classification is very limited and is based on conventional machine learning (ML) methods for feature extraction and classification processes. Feature extraction of these methods is handcrafted and has several drawbacks. Deep learning methods have the ability to deduce an optimum demonstration from the raw images without image enhancement, segmentation, and feature extraction processes, leading to an effective classification process. This article proposes a new framework based on deep learning methods for the detection of END. To the best of our knowledge, this is the first study that uses deep learning techniques for detecting END. The framework consists of four stages which are transfer learning, deep feature extraction, feature reduction, and classification. The framework depends on feature fusion. The results showed that the proposed framework was capable of identifying END from embryonic MRI images of various gestational ages. To verify the efficiency of the proposed framework, the results were compared with related work that used embryonic images. The performance of the proposed framework was competitive. This means that the proposed framework can be successively used for detecting END.
| S-EPMC7169467 | biostudies-literature
Project description:Linear biometric measurements on magnetic resonance images are important for the assessment of fetal brain development, which is expert knowledge dependent and laborious. This study aims to construct a segmentation-based method for automatic two-dimensional biometric measurements of fetal brain on magnetic resonance images that provides a fast and accurate measurement of fetal brain. A total of 268 volumes (5360 images) magnetic resonance images of normal fetuses were included. The automatic method involves two steps. First, the fetal brain was segmented into four parts with a deep segmentation network: cerebrum, cerebellum, and left and right lateral ventricles. Second, the measurement plane was determined, and the corresponding biometric parameters were calculated according to clinical guidelines, including cerebral biparietal diameter (CBPD), transverse cerebellar diameter (TCD), left and right atrial diameter (LAD/RAD). Pearson correlation coefficient and Bland-Altman plots were used to assess the correlation and agreement between computer-predicted values and manual measurements. Mean differences were used to evaluate the errors quantitatively. Analysis of fetal cerebral growth based on the automatic measurements was also displayed. The experiment results show that correlation coefficients for CBPD, TCD, LAD and RAD were as follows: 0.977, 0.990, 0.817, 0.719, mean differences were - 2.405 mm, - 0.008 mm, - 0.33 mm, - 0.213 mm, respectively. The correlation between the errors and gestational age was not statistically significant (p values were 0.2595, 0.0510, 0.1995, and 0.0609, respectively). The proposed automatic method for linear measurements on fetal brain MRI achieves excellent performance, which is expected to be applied in clinical practice and be helpful for prenatal diagnosis and clinical work efficiency improvement.
| S-EPMC10587162 | biostudies-literature
Project description:Cell type classification is an important problem in cancer research, especially with the advent of single cell technologies. Correctly identifying cells within the tumor microenvironment can provide oncologists with a snapshot of how a patient's immune system reacts to the tumor. Wide and deep learning (WDL) is an approach to construct a cell-classification prediction model that can learn patterns within high-dimensional data (deep) and ensure that biologically relevant features (wide) remain in the final model. In this paper, we demonstrate that regularization can prevent overfitting and adding a wide component to a neural network can result in a model with better predictive performance. In particular, we observed that a combination of dropout and ℓ2 regularization can lead to a validation loss function that does not depend on the number of training iterations and does not experience a significant decrease in prediction accuracy compared to models with ℓ1 , dropout, or no regularization. Additionally, we show WDL can have superior classification accuracy when the training and testing of a model are completed data on that arise from the same cancer type but different platforms. More specifically, WDL compared to traditional deep learning models can substantially increase the overall cell type prediction accuracy (36.5 to 86.9%) and T cell subtypes (CD4: 2.4 to 59.1%, and CD8: 19.5 to 96.1%) when the models were trained using melanoma data obtained from the 10X platform and tested on basal cell carcinoma data obtained using SMART-seq. WDL obtains higher accuracy when compared to state-of-the-art cell classification algorithms CHETAH (70.36%) and SingleR (70.59%).
| S-EPMC7878986 | biostudies-literature
Project description:PurposeTo investigate the feasibility of automatic identification and classification of hip fractures using deep learning, which may improve outcomes by reducing diagnostic errors and decreasing time to operation.Materials and methodsHip and pelvic radiographs from 1118 studies were reviewed, and 3026 hips were labeled via bounding boxes and classified as normal, displaced femoral neck fracture, nondisplaced femoral neck fracture, intertrochanteric fracture, previous open reduction and internal fixation, or previous arthroplasty. A deep learning-based object detection model was trained to automate the placement of the bounding boxes. A Densely Connected Convolutional Neural Network (or DenseNet) was trained on a subset of the bounding box images, and its performance was evaluated on a held-out test set and by comparison on a 100-image subset with two groups of human observers: fellowship-trained radiologists and orthopedists; senior residents in emergency medicine, radiology, and orthopedics.ResultsThe binary accuracy for detecting a fracture of this model was 93.7% (95% confidence interval [CI]: 90.8%, 96.5%), with a sensitivity of 93.2% (95% CI: 88.9%, 97.1%) and a specificity of 94.2% (95% CI: 89.7%, 98.4%). Multiclass classification accuracy was 90.8% (95% CI: 87.5%, 94.2%). When compared with the accuracy of human observers, the accuracy of the model achieved an expert-level classification, at the very least, under all conditions. Additionally, when the model was used as an aid, human performance improved, with aided resident performance approximating unaided fellowship-trained expert performance in the multiclass classification.ConclusionA deep learning model identified and classified hip fractures with expert-level performance, at the very least, and when used as an aid, improved human performance, with aided resident performance approximating that of unaided fellowship-trained attending physicians.Supplemental material is available for this article.© RSNA, 2020.
| S-EPMC8017394 | biostudies-literature
Project description:Wearable devices and mobile sensors enable the real-time collection of an abundant source of physiological and behavioural data unobtrusively. Unlike traditional in-person evaluation or ecological momentary assessment (EMA) questionnaire-based approaches, these data sources open many possibilities in remote patient monitoring. However, defining robust models is challenging due to the data's noisy and frequently missing observations. This work proposes an attention-based Long Short-Term Memory (LSTM) neural network-based pipeline for predicting mobility impairment based on WHODAS 2.0 evaluation from such digital biomarkers. Furthermore, we addressed the missing observation problem by utilising hidden Markov models and the possibility of including information from unlabelled samples via transfer learning. We validated our approach using two wearable/mobile sensor data sets collected in the wild and socio-demographic information about the patients. Our results showed that in the WHODAS 2.0 mobility impairment prediction task, the proposed pipeline outperformed a prior baseline while additionally providing interpretability with attention heatmaps. Moreover, using a much smaller cohort via task transfer learning, the same model could learn to predict generalised anxiety severity accurately based on GAD-7 scores.
| S-EPMC10440506 | biostudies-literature
Project description:BackgroundMyopia is the leading cause of visual impairment and affects millions of children worldwide. Timely and annual manual optometric screenings of the entire at-risk population improve outcomes, but screening is challenging due to the lack of availability and training of assessors and the economic burden imposed by the screenings. Recently, deep learning and computer vision have shown powerful potential for disease screening. However, these techniques have not been applied to large-scale myopia screening using ocular appearance images.MethodsWe trained a deep learning system (DLS) for myopia detection using 2,350 ocular appearance images (processed by 7,050 pictures) from children aged 6 to 18. Myopia is defined as a spherical equivalent refraction (SER) [the algebraic sum in diopters (D), sphere + 1/2 cylinder] ≤-0.5 diopters. Saliency maps and gradient class activation maps (grad-CAM) were used to highlight the regions recognized by VGG-Face. In a prospective clinical trial, 100 ocular appearance images were used to assess the performance of the DLS.ResultsThe area under the curve (AUC), sensitivity, and specificity of the DLS were 0.9270 (95% CI, 0.8580-0.9610), 81.13% (95% CI, 76.86-5.39%), and 86.42% (95% CI, 82.30-90.54%), respectively. Based on the saliency maps and grad-CAMs, the DLS mainly focused on eyes, especially the temporal sclera, rather than the background or other parts of the face. In the prospective clinical trial, the DLS achieved better diagnostic performance than the ophthalmologists in terms of sensitivity [DLS: 84.00% (95% CI, 73.50-94.50%) versus ophthalmologists: 64.00% (95% CI, 48.00-72.00%)] and specificity [DLS: 74.00% (95% CI, 61.40-86.60%) versus ophthalmologists: 53.33% (95% CI, 30.00-66.00%)]. We also computed AUC subgroups stratified by sex and age. DLS achieved comparable AUCs for children of different sexes and ages.ConclusionsThis study for the first time applied deep learning to myopia screening using ocular images and achieved high screening accuracy, enabling the remote monitoring of the refractive status in children with myopia. The application of our DLS will directly benefit public health and relieve the substantial burden imposed by myopia-associated visual impairment or blindness.
| S-EPMC7327333 | biostudies-literature
Project description:BackgroundAccurate identification of extrahepatic cholangiocarcinoma (ECC) from an image is challenging because of the small size and complex background structure. Therefore, considering the limitation of manual delineation, it's necessary to develop automated identification and segmentation methods for ECC. The aim of this study was to develop a deep learning approach for automatic identification and segmentation of ECC using MRI.MethodsWe recruited 137 ECC patients from our hospital as the main dataset (C1) and an additional 40 patients from other hospitals as the external validation set (C2). All patients underwent axial T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI). Manual delineations were performed and served as the ground truth. Next, we used 3D VB-Net to establish single-mode automatic identification and segmentation models based on T1WI (model 1), T2WI (model 2), and DWI (model 3) in the training cohort (80% of C1), and compared them with the combined model (model 4). Subsequently, the generalization capability of the best models was evaluated using the testing set (20% of C1) and the external validation set (C2). Finally, the performance of the developed models was further evaluated.ResultsModel 3 showed the best identification performance in the training, testing, and external validation cohorts with success rates of 0.980, 0.786, and 0.725, respectively. Furthermore, model 3 yielded an average Dice similarity coefficient (DSC) of 0.922, 0.495, and 0.466 to segment ECC automatically in the training, testing, and external validation cohorts, respectively.ConclusionThe DWI-based model performed better in automatically identifying and segmenting ECC compared to T1WI and T2WI, which may guide clinical decisions and help determine prognosis.
| S-EPMC10636947 | biostudies-literature
Project description:The coronavirus is considered this century's most disruptive catastrophe and global concern. This disease has prompted extreme social, psychological and economic impacts affecting millions of people around the globe. COVID-19 is transmitted from one infected person's body to another through respiratory droplets. This virus proliferates when people breathe in air-contaminated space with droplets and microscopic airborne particles. This research aims to analyze automatic COVID-19 detection using machine learning techniques to build an intelligent web application. The dataset has been preprocessed by dropping null values, feature engineering, and synthetic oversampling (SMOTE) techniques. Next, we trained and evaluated different classifiers, i.e., logistic regression, random forest, decision tree, k-nearest neighbor, support vector machine (SVM), ensemble models (adaptive boosting and extreme gradient boosting) and deep learning (artificial neural network, convolutional neural network and long short-term memory) techniques. Explainable AI with the LIME framework has been applied to interpret the prediction results. The hybrid CNN-LSTM algorithm with the SMOTE approach performed better than the other models on the employed open-source dataset obtained from the Israeli Ministry of Health website, with 96.34% accuracy and a 0.98 F1 score. Finally, this model was chosen to deploy the proposed prediction system to a website, where users may acquire an instantaneous COVID-19 prognosis based on their symptoms.
| S-EPMC9876019 | biostudies-literature
Project description:The article presents an AI-based fungi species recognition system for a citizen-science community. The system's real-time identification too - FungiVision - with a mobile application front-end, led to increased public interest in fungi, quadrupling the number of citizens collecting data. FungiVision, deployed with a human-in-the-loop, reaches nearly 93% accuracy. Using the collected data, we developed a novel fine-grained classification dataset - Danish Fungi 2020 (DF20) - with several unique characteristics: species-level labels, a small number of errors, and rich observation metadata. The dataset enables the testing of the ability to improve classification using metadata, e.g., time, location, habitat and substrate, facilitates classifier calibration testing and finally allows the study of the impact of the device settings on the classification performance. The continual flow of labelled data supports improvements of the online recognition system. Finally, we present a novel method for the fungi recognition service, based on a Vision Transformer architecture. Trained on DF20 and exploiting available metadata, it achieves a recognition error that is 46.75% lower than the current system. By providing a stream of labeled data in one direction, and an accuracy increase in the other, the collaboration creates a virtuous cycle helping both communities.
| S-EPMC8779018 | biostudies-literature
Project description:BackgroundMedication errors account for a large proportion of all medical errors. In most homes, patients take a variety of medications for a long period. However, medication errors frequently occur because patients often throw away the containers of their medications.ObjectiveWe proposed a deep learning-based system for reducing medication errors by accurately identifying prescription pills. Given the pill images, our system located the pills in the respective pill databases in South Korea and the United States.MethodsWe organized the system into a pill recognition step and pill retrieval step, and we applied deep learning models to train not only images of the pill but also imprinted characters. In the pill recognition step, there are 3 modules that recognize the 3 features of pills and their imprints separately and correct the recognized imprint to fit the actual data. We adopted image classification and text detection models for the feature and imprint recognition modules, respectively. In the imprint correction module, we introduced a language model for the first time in the pill identification system and proposed a novel coordinate encoding technique for effective correction in the language model. We identified pills using similarity scores of pill characteristics with those in the database.ResultsWe collected the open pill database from South Korea and the United States in May 2022. We used a total of 24,404 pill images in our experiments. The experimental results show that the predicted top-1 candidates achieve accuracy levels of 85.6% (South Korea) and 74.5% (United States) for the types of pills not trained on 2 different databases (South Korea and the United States). Furthermore, the predicted top-1 candidate accuracy of our system was 78% with consumer-granted images, which was achieved by training only 1 image per pill. The results demonstrate that our system could identify and retrieve new pills without additional model updates. Finally, we confirmed through an ablation study that the language model that we emphasized significantly improves the pill identification ability of the system.ConclusionsOur study proposes the possibility of reducing medical errors by showing that the introduction of artificial intelligence can identify numerous pills with high precision in real time. Our study suggests that the proposed system can reduce patients' misuse of medications and help medical staff focus on higher-level tasks by simplifying time-consuming lower-level tasks such as pill identification.
| S-EPMC9883737 | biostudies-literature