- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Using Deep Learning with Large Dataset of Microscope Images to Develop an Automated Embryo Grading System
摘要： The assessment of embryo viability for in vitro fertilization (IVF) is mainly based on subjective visual analysis, with the limitation of intra- and inter-observer variation and a time-consuming task. In this study, we used deep learning with large dataset of microscopic embryo images to develop an automated grading system for embryo assessment. This study included a total of 171,239 images from 16,201 embryos of 4,146 IVF cycles at Stork Fertility Center (https://www.e-stork.com.tw) from March 6, 2014 to April 13, 2018. The images were captured by inverted microscope (Zeiss Axio Observer Z1) at 112 to 116 hours (Day 5) or 136 to 140 hours (Day 6) after fertilization. Using a pre-trained network trained on the ImageNet dataset as convolution base, we applied Convolutional Neural Network (CNN) on embryo images, using ResNet50 architecture to fine-tune ImageNet parameters. The predicted grading results was compared with the grading results from trained embryologists to evaluate the model performance. The images were labeled by trained embryologists, based on Gardner’s grading system: blastocyst development ranking from 3–6, ICM quality as A, B, or C; and TE quality as a, b, or c. After pre-processing, the images were divided into training, validation, and test groups, in which 60% were allocated to the training group, 20% to the validation group, and 20% to the test group. The ResNet50 algorithm was trained on the 60% images allocated to the training group, and the algorithm’s performance was evaluated using the 20% images allocated to the test group. The results showed an average predictive accuracy of 75.36% for the all three grading categories: 96.24% for blastocyst development, 91.07% for ICM quality, and 84.42% for TE quality. To the best of our knowledge, this is the first study of an automatic embryo grading system using large dataset from Asian population. Combing the promising results obtained in this study with time-lapse microscope system integrated with IVF Electronic Medical Record platform, a fully automated and non-invasive pipeline for embryo assessment will be achieved.
关键词： Embryo Grading,Machine Learning,Embryo Image,Artificial Intelligence
更新于2025-11-21 11:24:58
-
Indoor Navigation With Virtual Graph Representation: Exploiting Peak Intensities of Unmodulated Luminaries
摘要： The ubiquitous luminaries provide a new dimension for indoor navigation, as they are often well-structured and the visible light is reliable for its multipath-free nature. However, existing visible light-based technologies, which are generally frequency-based, require the modulation on light sources, modification to the device, or mounting extra devices. The combination of the cost-extensive floor map and the localization system with constraints on customized hardwares for capturing the flashing frequencies, no doubt, hinders the deployment of indoor navigation systems at scale in, nowadays, smart cities. In this paper, we provide a new perspective of indoor navigation on top of the virtual graph representation. The main idea of our proposed navigation system, named PILOT, stems from exploiting the peak intensities of ubiquitous unmodulated luminaries. In PILOT, the pedestrian paths with enriched sensory data are organically integrated to derive a meaningful graph, where each vertex corresponds to a light source and pairwise adjacent vertices (or light sources) form an edge with a computed length and direction. The graph, then, serves as a global reference frame for indoor navigation while avoiding the usage of pre-deployed floor maps, localization systems, or additional hardwares. We have implemented a prototype of PILOT on the Android platform, and extensive experiments in typical indoor environments demonstrate its effectiveness and efficiency.
关键词： pervasive computing,Human computer interaction,ubiquitous computing,computational and artificial intelligence
更新于2025-09-23 15:23:52
-
[ACM Press the 2nd International Conference - Las Vegas, NV, USA (2018.08.27-2018.08.29)] Proceedings of the 2nd International Conference on Vision, Image and Signal Processing - ICVISP 2018 - Artificial Intelligence in Simple Command
摘要： Artificial intelligence is not far method from our everyday lives. In Indonesia, artificial intelligence is still used from complex until simple command and for this paper we would like to give analytical review for Miposaur robot product in Indonesia. To analyze its artificial intelligence, this paper is using the basic definition of artificial intelligence from Leon [7], Banerjee, and Allen [2]. In Indonesia, we have Sistem Pertahanan Republik Indonesia (Sishanneg/ Indonesian National Defense System) that clearly puts artificial intelligence as one of tools to gain fully Indonesian purpose, mandated in 1945 Indonesian Constutional Law. Hereby the government has budget and satuan kerja/ work unit to support the using of artificial intelligence, both in military or non-military and we are still ongoing to gain the perfect regulation to manage the existence of AI.
关键词： robot,Miposaur,Indonesia,Artificial intelligence,Modernism,Sishanneg,Human,AI
更新于2025-09-23 15:23:52
-
Deep learning-based digital in-line holographic microscopy for high resolution with extended field of view
摘要： A digital in-line holographic microscopy (DIHM) with deep learning-based upscaling method is proposed to overcome the trade-off between high resolving power and large field-of-view (FOV). To enhance the spatial resolution of a hologram, a deep neural network was trained with hologram images, which are defocused images with diffraction patterns. The performance of the artificial intelligence-based DIHM method was verified using hologram images obtained by computer simulation and experiments. Upscaled holograms with enhanced image contrast and clear diffraction pattern provided high quality of reconstructed holograms. In addition to the enhancement of reconstructed image at the sample position, details of light scattering pattern could be revealed with the proposed method. The proposed deep learning-based DIHM method is promising for accurate monitoring of many samples and analyzing dynamics of particles or cells in large FOV with detailed 3D information reconstructed from the upscaled holograms.
关键词： 3D measurement,Digital in-line holographic microscopy,Artificial intelligence
更新于2025-09-23 15:22:29
-
Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images
摘要： Purpose: To develop a new intelligent system based on deep learning for automatically optical coherence tomography (OCT) images categorization. Methods: A total of 60,407 OCT images were labeled by 17 licensed retinal experts and 25,134 images were included. One hundred one-layer convolutional neural networks (ResNet) were trained for the categorization. We applied 10-fold cross-validation method to train and optimize our algorithms. The area under the receiver operating characteristic curve (AUC), accuracy and kappa value were calculated to evaluate the performance of the intelligent system in categorizing OCT images. We also compared the performance of the system with results obtained by two experts. Results: The intelligent system achieved an AUC of 0.984 with an accuracy of 0.959 in detecting macular hole, cystoid macular edema, epiretinal membrane, and serous macular detachment. Specifically, the accuracies in discriminating normal images, cystoid macular edema, serous macular detachment, epiretinal membrane, and macular hole were 0.973, 0.848, 0.947, 0.957, and 0.978, respectively. The system had a kappa value of 0.929, while the two physicians’ kappa values were 0.882 and 0.889 independently. Conclusions: This deep learning-based system is able to automatically detect and differentiate various OCT images with excellent accuracy. Moreover, the performance of the system is at a level comparable to or better than that of human experts. This study is a promising step in revolutionizing current disease diagnostic pattern and has the potential to generate a significant clinical impact.
关键词： artificial intelligence,deep learning,optical coherence tomography,ResNet
更新于2025-09-23 15:22:29
-
Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network
摘要： Background: In this study, images of 2450 benign thyroid nodules and 2557 malignant thyroid nodules were collected and labeled, and an automatic image recognition and diagnosis system was established by deep learning using the YOLOv2 neural network. The performance of the system in the diagnosis of thyroid nodules was evaluated, and the application value of artificial intelligence in clinical practice was investigated. Methods: The ultrasound images of 276 patients were retrospectively selected. The diagnoses of the radiologists were determined according to the Thyroid Imaging Reporting and Data System; the images were automatically recognized and diagnosed by the established artificial intelligence system. Pathological diagnosis was the gold standard for the final diagnosis. The performances of the established system and the radiologists in diagnosing the benign and malignant thyroid nodules were compared. Results: The artificial intelligence diagnosis system correctly identified the lesion area, with an area under the receiver operating characteristic (ROC) curve of 0.902, which is higher than that of the radiologists (0.859). This finding indicates a higher diagnostic accuracy (p = 0.0434). The sensitivity, positive predictive value, negative predictive value, and accuracy of the artificial intelligence diagnosis system for the diagnosis of malignant thyroid nodules were 90.5%, 95.22%, 80.99%, and 90.31%, respectively, and the performance did not significantly differ from that of the radiologists (p > 0.05). The artificial intelligence diagnosis system had a higher specificity (89.91% vs 77.98%, p = 0.026). Conclusions: Compared with the performance of experienced radiologists, the artificial intelligence system has comparable sensitivity and accuracy for the diagnosis of malignant thyroid nodules and better diagnostic ability for benign thyroid nodules. As an auxiliary tool, this artificial intelligence diagnosis system can provide radiologists with sufficient assistance in the diagnosis of benign and malignant thyroid nodules.
关键词： Thyroid nodules,Ultrasound,Artificial intelligence,Computer-aided diagnosis systems,YOLOv2 neural network
更新于2025-09-23 15:22:29
-
Benefits, problems and challenges of plant factories with artificial lighting (PFALs): a short review
摘要： The benefits and problems to be solved and challenges for plant factories with artificial lighting (PFALs) are discussed. The benefits include high resource-use efficiency, high annual productivity per unit land area, and production of high-quality plants without using pesticides, regardless of weather. A major problem to be solved is high initial investment and operation costs. Challenges for the next-generation smart PFALs include the introduction of advanced technologies such as artificial intelligence with the use of big data, genomics and phenomics (or methodologies and protocols for noninvasive measurement of plant-specific traits related to plant structure and function).
关键词： resource-use efficiency (RUE),cultivation system module (CSM),standardization,smart LED lighting system,annual productivity,artificial intelligence,phenotyping
更新于2025-09-23 15:22:29
-
Integrating Handcrafted and Deep Features for Optical Coherence Tomography Based Retinal Disease Classification
摘要： Deep Neural Networks (DNNs) have been widely applied to automatic analysis of medical images for disease diagnosis, and to help human experts by efficiently processing immense amounts of images. While handcrafted feature has been used for eye disease detection or classification since the 1990s, DNN was recently adopted in this area and showed very promising performance. Since handcrafted and deep feature can extract complementary information, we propose in this paper three different integration frameworks to combine handcrafted and deep feature for optical coherence tomography (OCT) image based eye disease classification. In addition, to integrate the handcrafted feature at Input and Fully Connection (FC) layers using existing networks like VGG, DenseNet and Xception, a novel ribcage network (RC Net) is also proposed for feature integration at middle layers. For RC Net, two “rib” channels are designed to independently process deep and handcrafted features, and another so called “spine” channel is designed for the integration. While dense blocks are the main components of the three channels, sum operation is proposed for the feature map integration. Our experimental results showed that the deep networks achieved better classification accuracy after integration of the handcrafted features e.g. SIFT and Gabor. The RC Net showed the best performance among all proposed feature integration methods.
关键词： feature integration,deep learning,Artificial intelligence,optical coherence tomography
更新于2025-09-23 15:22:29
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - NIEL Dose Analysis on triple and single junction InGaP/GaAs/Ge solar cells irradiated with electrons, protons and neutrons
摘要： Quantitative grading of opals is a challenging task even for skilled opal assessors. Current opal evaluation practices are highly subjective due to the complexities of opal assessment and the limitations of human visual observation. In this paper, we present a novel machine vision system for the automated grading of opals—the gemological digital analyzer (GDA). The grading is based on statistical machine learning with multiple characteristics extracted from opal images. The assessment work-flow includes calibration, opal image capture, image analysis, and opal classification and grading. Experimental results show that the GDA-based grading is more consistent and objective compared with the manual evaluations conducted by the skilled opal assessors.
关键词： feature extraction,image analysis,machine vision,learning systems,Artificial intelligence
更新于2025-09-23 15:21:01
-
Fault detection of photovoltaic array based on Grubbs criterion and local outlier factor
摘要： Quantitative grading of opals is a challenging task even for skilled opal assessors. Current opal evaluation practices are highly subjective due to the complexities of opal assessment and the limitations of human visual observation. In this paper, we present a novel machine vision system for the automated grading of opals—the gemological digital analyzer (GDA). The grading is based on statistical machine learning with multiple characteristics extracted from opal images. The assessment workflow includes calibration, opal image capture, image analysis, and opal classification and grading. Experimental results show that the GDA-based grading is more consistent and objective compared with the manual evaluations conducted by the skilled opal assessors.
关键词： feature extraction,image analysis,machine vision,learning systems,Artificial intelligence
更新于2025-09-23 15:21:01