Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 55
Filtrar
1.
J Med Syst ; 45(3): 28, 2021 Jan 26.
Artigo em Inglês | MEDLINE | ID: mdl-33496876

RESUMO

Computer Tomography (CT) is currently being adapted for visualization of COVID-19 lung damage. Manual classification and characterization of COVID-19 may be biased depending on the expert's opinion. Artificial Intelligence has recently penetrated COVID-19, especially deep learning paradigms. There are nine kinds of classification systems in this study, namely one deep learning-based CNN, five kinds of transfer learning (TL) systems namely VGG16, DenseNet121, DenseNet169, DenseNet201 and MobileNet, three kinds of machine-learning (ML) systems, namely artificial neural network (ANN), decision tree (DT), and random forest (RF) that have been designed for classification of COVID-19 segmented CT lung against Controls. Three kinds of characterization systems were developed namely (a) Block imaging for COVID-19 severity index (CSI); (b) Bispectrum analysis; and (c) Block Entropy. A cohort of Italian patients with 30 controls (990 slices) and 30 COVID-19 patients (705 slices) was used to test the performance of three types of classifiers. Using K10 protocol (90% training and 10% testing), the best accuracy and AUC was for DCNN and RF pairs were 99.41 ± 5.12%, 0.991 (p < 0.0001), and 99.41 ± 0.62%, 0.988 (p < 0.0001), respectively, followed by other ML and TL classifiers. We show that diagnostics odds ratio (DOR) was higher for DL compared to ML, and both, Bispecturm and Block Entropy shows higher values for COVID-19 patients. CSI shows an association with Ground Glass Opacities (0.9146, p < 0.0001). Our hypothesis holds true that deep learning shows superior performance compared to machine learning models. Block imaging is a powerful novel approach for pinpointing COVID-19 severity and is clinically validated.


Assuntos
Inteligência Artificial/normas , Pulmão/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , Aprendizado Profundo/normas , Feminino , Humanos , Itália , Masculino , Pessoa de Meia-Idade , Reprodutibilidade dos Testes , Índice de Gravidade de Doença
2.
J Med Internet Res ; 23(1): e19689, 2021 01 12.
Artigo em Inglês | MEDLINE | ID: mdl-33433395

RESUMO

BACKGROUND: Liver cancer is a substantial disease burden in China. As one of the primary diagnostic tools for detecting liver cancer, dynamic contrast-enhanced computed tomography provides detailed evidences for diagnosis that are recorded in free-text radiology reports. OBJECTIVE: The aim of our study was to apply a deep learning model and rule-based natural language processing (NLP) method to identify evidences for liver cancer diagnosis automatically. METHODS: We proposed a pretrained, fine-tuned BERT (Bidirectional Encoder Representations from Transformers)-based BiLSTM-CRF (Bidirectional Long Short-Term Memory-Conditional Random Field) model to recognize the phrases of APHE (hyperintense enhancement in the arterial phase) and PDPH (hypointense in the portal and delayed phases). To identify more essential diagnostic evidences, we used the traditional rule-based NLP methods for the extraction of radiological features. APHE, PDPH, and other extracted radiological features were used to design a computer-aided liver cancer diagnosis framework by random forest. RESULTS: The BERT-BiLSTM-CRF predicted the phrases of APHE and PDPH with an F1 score of 98.40% and 90.67%, respectively. The prediction model using combined features had a higher performance (F1 score, 88.55%) than those using APHE and PDPH (84.88%) or other extracted radiological features (83.52%). APHE and PDPH were the top 2 essential features for liver cancer diagnosis. CONCLUSIONS: This work was a comprehensive NLP study, wherein we identified evidences for the diagnosis of liver cancer from Chinese radiology reports, considering both clinical knowledge and radiology findings. The BERT-based deep learning method for the extraction of diagnostic evidence achieved state-of-the-art performance. The high performance proves the feasibility of the BERT-BiLSTM-CRF model in information extraction from Chinese radiology reports. The findings of our study suggest that the deep learning-based method for automatically identifying evidences for diagnosis can be extended to other types of Chinese clinical texts.


Assuntos
Aprendizado Profundo/normas , Diagnóstico por Computador/métodos , Armazenamento e Recuperação da Informação/métodos , Neoplasias Hepáticas/diagnóstico , Processamento de Linguagem Natural , Radiologia/métodos , China , Humanos , Neoplasias Hepáticas/radioterapia
3.
J Med Internet Res ; 22(12): e18418, 2020 12 16.
Artigo em Inglês | MEDLINE | ID: mdl-33325832

RESUMO

BACKGROUND: Despite excellent prediction performance, noninterpretability has undermined the value of applying deep-learning algorithms in clinical practice. To overcome this limitation, attention mechanism has been introduced to clinical research as an explanatory modeling method. However, potential limitations of using this attractive method have not been clarified to clinical researchers. Furthermore, there has been a lack of introductory information explaining attention mechanisms to clinical researchers. OBJECTIVE: The aim of this study was to introduce the basic concepts and design approaches of attention mechanisms. In addition, we aimed to empirically assess the potential limitations of current attention mechanisms in terms of prediction and interpretability performance. METHODS: First, the basic concepts and several key considerations regarding attention mechanisms were identified. Second, four approaches to attention mechanisms were suggested according to a two-dimensional framework based on the degrees of freedom and uncertainty awareness. Third, the prediction performance, probability reliability, concentration of variable importance, consistency of attention results, and generalizability of attention results to conventional statistics were assessed in the diabetic classification modeling setting. Fourth, the potential limitations of attention mechanisms were considered. RESULTS: Prediction performance was very high for all models. Probability reliability was high in models with uncertainty awareness. Variable importance was concentrated in several variables when uncertainty awareness was not considered. The consistency of attention results was high when uncertainty awareness was considered. The generalizability of attention results to conventional statistics was poor regardless of the modeling approach. CONCLUSIONS: The attention mechanism is an attractive technique with potential to be very promising in the future. However, it may not yet be desirable to rely on this method to assess variable importance in clinical settings. Therefore, along with theoretical studies enhancing attention mechanisms, more empirical studies investigating potential limitations should be encouraged.


Assuntos
Aprendizado Profundo/normas , Diabetes Mellitus/epidemiologia , Algoritmos , Pesquisa Empírica , Humanos , Reprodutibilidade dos Testes , República da Coreia , Projetos de Pesquisa
4.
J Med Internet Res ; 22(8): e21173, 2020 08 21.
Artigo em Inglês | MEDLINE | ID: mdl-32763892

RESUMO

BACKGROUND: Compartmental models dominate epidemic modeling. Transmission parameters between compartments are typically estimated through stochastic parameterization processes that depends on detailed statistics of transmission characteristics, which are economically and resource-wise expensive to collect. OBJECTIVE: We aim to apply deep learning techniques as a lower data dependency alternative to estimate transmission parameters of a customized compartmental model, for the purpose of simulating the dynamics of the US coronavirus disease (COVID-19) epidemic and projecting its further development. METHODS: We constructed a compartmental model and developed a multistep deep learning methodology to estimate the model's transmission parameters. We then fed the estimated transmission parameters to the model to predict development of the US COVID-19 epidemic for 35 and 42 days. Epidemics are considered suppressed when the basic reproduction number (R0) is less than 1. RESULTS: The deep learning-enhanced compartmental model predicts that R0 will fall to <1 around August 17-19, 2020, at which point the epidemic will effectively start to die out, and that the US "infected" population will peak around August 16-18, 2020, at 3,228,574 to 3,308,911 individual cases. The model also predicted that the number of accumulative confirmed cases will cross the 5 million mark around August 7, 2020. CONCLUSIONS: Current compartmental models require stochastic parameterization to estimate the transmission parameters. These models' effectiveness depends upon detailed statistics on transmission characteristics. As an alternative, deep learning techniques are effective in estimating these stochastic parameters with greatly reduced dependency on data particularity.


Assuntos
Betacoronavirus/patogenicidade , Infecções por Coronavirus/epidemiologia , Coronavirus/patogenicidade , Aprendizado Profundo/normas , Pneumonia Viral/epidemiologia , Epidemias , Humanos , Pandemias , Projetos de Pesquisa , Estados Unidos
5.
BMC Bioinformatics ; 21(Suppl 4): 259, 2020 Jul 06.
Artigo em Inglês | MEDLINE | ID: mdl-32631221

RESUMO

BACKGROUND: Diabetic retinopathy (DR), the most common cause of vision loss, is caused by damage to the small blood vessels in the retina. If untreated, it may result in varying degrees of vision loss and even blindness. Since DR is a silent disease that may cause no symptoms or only mild vision problems, annual eye exams are crucial for early detection to improve chances of effective treatment where fundus cameras are used to capture retinal image. However, fundus cameras are too big and heavy to be transported easily and too costly to be purchased by every health clinic, so fundus cameras are an inconvenient tool for widespread screening. Recent technological developments have enabled to use of smartphones in designing small-sized, low-power, and affordable retinal imaging systems to perform DR screening and automated DR detection using image processing methods. In this paper, we investigate the smartphone-based portable retinal imaging systems available on the market and compare their image quality and the automatic DR detection accuracy using a deep learning framework. RESULTS: Based on the results, iNview retinal imaging system has the largest field of view and better image quality compared with iExaminer, D-Eye, and Peek Retina systems. The overall classification accuracy of smartphone-based systems are sorted as 61%, 62%, 69%, and 75% for iExaminer, D-Eye, Peek Retina, and iNview images, respectively. We observed that the network DR detection performance decreases as the field of view of the smartphone-based retinal systems get smaller where iNview is the largest and iExaminer is the smallest. CONCLUSIONS: The smartphone-based retina imaging systems can be used as an alternative to the direct ophthalmoscope. However, the field of view of the smartphone-based retina imaging systems plays an important role in determining the automatic DR detection accuracy.


Assuntos
Aprendizado Profundo/normas , Retinopatia Diabética/diagnóstico , Retina/diagnóstico por imagem , Smartphone/normas , Humanos
6.
BMC Bioinformatics ; 21(Suppl 4): 248, 2020 Jul 06.
Artigo em Inglês | MEDLINE | ID: mdl-32631230

RESUMO

BACKGROUND: Identifying drug-target interaction is a key element in drug discovery. In silico prediction of drug-target interaction can speed up the process of identifying unknown interactions between drugs and target proteins. In recent studies, handcrafted features, similarity metrics and machine learning methods have been proposed for predicting drug-target interactions. However, these methods cannot fully learn the underlying relations between drugs and targets. In this paper, we propose anew framework for drug-target interaction prediction that learns latent features from drug-target interaction network. RESULTS: We present a framework to utilize the network topology and identify interacting and non-interacting drug-target pairs. We model the problem as a semi-bipartite graph in which we are able to use drug-drug and protein-protein similarity in a drug-protein network. We have then used a graph labeling method for vertex ordering in our graph embedding process. Finally, we employed deep neural network to learn the complex pattern of interacting pairs from embedded graphs. We show our approach is able to learn sophisticated drug-target topological features and outperforms other state-of-the-art approaches. CONCLUSIONS: The proposed learning model on semi-bipartite graph model, can integrate drug-drug and protein-protein similarities which are semantically different than drug-protein information in a drug-target interaction network. We show our model can determine interaction likelihood for each drug-target pair and outperform other heuristics.


Assuntos
Aprendizado Profundo/normas , Desenvolvimento de Medicamentos/métodos , Algoritmos , Humanos
7.
Neural Netw ; 129: 138-148, 2020 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-32516696

RESUMO

Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications. However, in many applications the data can display structures beyond simply being low-rank or sparse. Fully extracting and exploiting hidden structure information in the data is always desirable and favorable. To reveal more underlying effective manifold structure, in this paper, we explicitly model the data relation. Specifically, we propose a structure learning framework that retains the pairwise similarities between the data points. Rather than just trying to reconstruct the original data based on self-expression, we also manage to reconstruct the kernel matrix, which functions as similarity preserving. Consequently, this technique is particularly suitable for the class of learning problems that are sensitive to sample similarity, e.g., clustering and semisupervised classification. To take advantage of representation power of deep neural network, a deep auto-encoder architecture is further designed to implement our model. Extensive experiments on benchmark data sets demonstrate that our proposed framework can consistently and significantly improve performance on both evaluation tasks. We conclude that the quality of structure learning can be enhanced if similarity information is incorporated.


Assuntos
Aprendizado Profundo/normas , Benchmarking
8.
BMC Bioinformatics ; 21(1): 235, 2020 Jun 09.
Artigo em Inglês | MEDLINE | ID: mdl-32517697

RESUMO

BACKGROUND: The number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction - a process called 'end-to-end learning' - has led to state-of-the-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. RESULTS: By using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. CONCLUSION: Our study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.


Assuntos
Aminoácidos/metabolismo , Biologia Computacional/métodos , Aprendizado Profundo/normas , Humanos
9.
J Med Internet Res ; 22(5): e17252, 2020 05 22.
Artigo em Inglês | MEDLINE | ID: mdl-32441656

RESUMO

BACKGROUND: Sleep apnea is a respiratory disorder characterized by an intermittent reduction (hypopnea) or cessation (apnea) of breathing during sleep. Depending on the presence of a breathing effort, sleep apnea is divided into obstructive sleep apnea (OSA) and central sleep apnea (CSA) based on the different pathologies involved. If the majority of apneas in a person are obstructive, they will be diagnosed as OSA or otherwise as CSA. In addition, as it is challenging and highly controversial to divide hypopneas into central or obstructive, the decision about sleep apnea type (OSA vs CSA) is made based on apneas only. Choosing the appropriate treatment relies on distinguishing between obstructive apnea (OA) and central apnea (CA). OBJECTIVE: The objective of this study was to develop a noncontact method to distinguish between OAs and CAs. METHODS: Five different computer vision-based algorithms were used to process infrared (IR) video data to track and analyze body movements to differentiate different types of apnea (OA vs CA). In the first two methods, supervised classifiers were trained to process optical flow information. In the remaining three methods, a convolutional neural network (CNN) was designed to extract distinctive features from optical flow and to distinguish OA from CA. RESULTS: Overnight sleeping data of 42 participants (mean age 53, SD 15 years; mean BMI 30, SD 7 kg/m2; 27 men and 15 women; mean number of OA 16, SD 30; mean number of CA 3, SD 7; mean apnea-hypopnea index 27, SD 31 events/hour; mean sleep duration 5 hours, SD 1 hour) were collected for this study. The test and train data were recorded in two separate laboratory rooms. The best-performing model (3D-CNN) obtained 95% accuracy and an F1 score of 89% in differentiating OA vs CA. CONCLUSIONS: In this study, the first vision-based method was developed that differentiates apnea types (OA vs CA). The developed algorithm tracks and analyses chest and abdominal movements captured via an IR video camera. Unlike previously developed approaches, this method does not require any attachment to a user that could potentially alter the sleeping condition.


Assuntos
Aprendizado Profundo/normas , Polissonografia/métodos , Apneia do Sono Tipo Central/diagnóstico , Apneia Obstrutiva do Sono/diagnóstico , Espectrofotometria Infravermelho/métodos , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Apneia do Sono Tipo Central/fisiopatologia , Apneia Obstrutiva do Sono/fisiopatologia
10.
Proc Natl Acad Sci U S A ; 117(23): 12592-12594, 2020 06 09.
Artigo em Inglês | MEDLINE | ID: mdl-32457147

RESUMO

Artificial intelligence (AI) systems for computer-aided diagnosis and image-based screening are being adopted worldwide by medical institutions. In such a context, generating fair and unbiased classifiers becomes of paramount importance. The research community of medical image computing is making great efforts in developing more accurate algorithms to assist medical doctors in the difficult task of disease diagnosis. However, little attention is paid to the way databases are collected and how this may influence the performance of AI systems. Our study sheds light on the importance of gender balance in medical imaging datasets used to train AI systems for computer-assisted diagnosis. We provide empirical evidence supported by a large-scale study, based on three deep neural network architectures and two well-known publicly available X-ray image datasets used to diagnose various thoracic diseases under different gender imbalance conditions. We found a consistent decrease in performance for underrepresented genders when a minimum balance is not fulfilled. This raises the alarm for national agencies in charge of regulating and approving computer-assisted diagnosis systems, which should include explicit gender balance and diversity recommendations. We also establish an open problem for the academic medical image computing community which needs to be addressed by novel algorithms endowed with robustness to gender imbalance.


Assuntos
Conjuntos de Dados como Assunto/normas , Aprendizado Profundo/normas , Interpretação de Imagem Radiográfica Assistida por Computador/normas , Radiografia Torácica/normas , Viés , Feminino , Humanos , Masculino , Padrões de Referência , Fatores Sexuais
11.
Int J Neural Syst ; 30(6): 2050034, 2020 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-32466693

RESUMO

As the surveillance devices proliferate, various machine learning approaches for video anomaly detection have been attempted. We propose a hybrid deep learning model composed of a video feature extractor trained by generative adversarial network with deficient anomaly data and an anomaly detector boosted by transferring the extractor. Experiments with UCSD pedestrian dataset show that it achieves 94.4% recall and 86.4% precision, which is the competitive performance in video anomaly detection.


Assuntos
Aprendizado Profundo , Reconhecimento Automatizado de Padrão , Transferência de Experiência , Adulto , Aprendizado Profundo/normas , Humanos , Reconhecimento Automatizado de Padrão/normas , Sensibilidade e Especificidade , Detecção de Sinal Psicológico , Gravação em Vídeo
12.
J Med Internet Res ; 22(4): e17234, 2020 04 29.
Artigo em Inglês | MEDLINE | ID: mdl-32347802

RESUMO

BACKGROUND: Cancer has become the second leading cause of death globally. Most cancer cases are due to genetic mutations, which affect metabolism and result in facial changes. OBJECTIVE: In this study, we aimed to identify the facial features of patients with cancer using the deep learning technique. METHODS: Images of faces of patients with cancer were collected to build the cancer face image data set. A face image data set of people without cancer was built by randomly selecting images from the publicly available MegaAge data set according to the sex and age distribution of the cancer face image data set. Each face image was preprocessed to obtain an upright centered face chip, following which the background was filtered out to exclude the effects of nonrelative factors. A residual neural network was constructed to classify cancer and noncancer cases. Transfer learning, minibatches, few epochs, L2 regulation, and random dropout training strategies were used to prevent overfitting. Moreover, guided gradient-weighted class activation mapping was used to reveal the relevant features. RESULTS: A total of 8124 face images of patients with cancer (men: n=3851, 47.4%; women: n=4273, 52.6%) were collected from January 2018 to January 2019. The ages of the patients ranged from 1 year to 70 years (median age 52 years). The average faces of both male and female patients with cancer displayed more obvious facial adiposity than the average faces of people without cancer, which was supported by a landmark comparison. When testing the data set, the training process was terminated after 5 epochs. The area under the receiver operating characteristic curve was 0.94, and the accuracy rate was 0.82. The main relative feature of cancer cases was facial skin, while the relative features of noncancer cases were extracted from the complementary face region. CONCLUSIONS: In this study, we built a face data set of patients with cancer and constructed a deep learning model to classify the faces of people with and those without cancer. We found that facial skin and adiposity were closely related to the presence of cancer.


Assuntos
Aprendizado Profundo/normas , Expressão Facial , Neoplasias/psicologia , Adolescente , Adulto , Idoso , Criança , Pré-Escolar , Feminino , Humanos , Lactente , Masculino , Pessoa de Meia-Idade , Projetos Piloto , Adulto Jovem
13.
J Med Internet Res ; 22(5): e16443, 2020 05 21.
Artigo em Inglês | MEDLINE | ID: mdl-32348254

RESUMO

BACKGROUND: Continuous photoplethysmography (PPG) monitoring with a wearable device may aid the early detection of atrial fibrillation (AF). OBJECTIVE: We aimed to evaluate the diagnostic performance of a ring-type wearable device (CardioTracker, CART), which can detect AF using deep learning analysis of PPG signals. METHODS: Patients with persistent AF who underwent cardioversion were recruited prospectively. We recorded PPG signals at the finger with CART and a conventional pulse oximeter before and after cardioversion over a period of 15 min (each instrument). Cardiologists validated the PPG rhythms with simultaneous single-lead electrocardiography. The PPG data were transmitted to a smartphone wirelessly and analyzed with a deep learning algorithm. We also validated the deep learning algorithm in 20 healthy subjects with sinus rhythm (SR). RESULTS: In 100 study participants, CART generated a total of 13,038 30-s PPG samples (5850 for SR and 7188 for AF). Using the deep learning algorithm, the diagnostic accuracy, sensitivity, specificity, positive-predictive value, and negative-predictive value were 96.9%, 99.0%, 94.3%, 95.6%, and 98.7%, respectively. Although the diagnostic accuracy decreased with shorter sample lengths, the accuracy was maintained at 94.7% with 10-s measurements. For SR, the specificity decreased with higher variability of peak-to-peak intervals. However, for AF, CART maintained consistent sensitivity regardless of variability. Pulse rates had a lower impact on sensitivity than on specificity. The performance of CART was comparable to that of the conventional device when using a proper threshold. External validation showed that 94.99% (16,529/17,400) of the PPG samples from the control group were correctly identified with SR. CONCLUSIONS: A ring-type wearable device with deep learning analysis of PPG signals could accurately diagnose AF without relying on electrocardiography. With this device, continuous monitoring for AF may be promising in high-risk populations. TRIAL REGISTRATION: ClinicalTrials.gov NCT04023188; https://clinicaltrials.gov/ct2/show/NCT04023188.


Assuntos
Fibrilação Atrial/diagnóstico , Aprendizado Profundo/normas , Fotopletismografia/métodos , Dispositivos Eletrônicos Vestíveis/normas , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estudo de Prova de Conceito , Estudos Prospectivos
14.
Cancer Commun (Lond) ; 40(4): 154-166, 2020 04.
Artigo em Inglês | MEDLINE | ID: mdl-32277744

RESUMO

The development of digital pathology and progression of state-of-the-art algorithms for computer vision have led to increasing interest in the use of artificial intelligence (AI), especially deep learning (DL)-based AI, in tumor pathology. The DL-based algorithms have been developed to conduct all kinds of work involved in tumor pathology, including tumor diagnosis, subtyping, grading, staging, and prognostic prediction, as well as the identification of pathological features, biomarkers and genetic changes. The applications of AI in pathology not only contribute to improve diagnostic accuracy and objectivity but also reduce the workload of pathologists and subsequently enable them to spend additional time on high-level decision-making tasks. In addition, AI is useful for pathologists to meet the requirements of precision oncology. However, there are still some challenges relating to the implementation of AI, including the issues of algorithm validation and interpretability, computing systems, the unbelieving attitude of pathologists, clinicians and patients, as well as regulators and reimbursements. Herein, we present an overview on how AI-based approaches could be integrated into the workflow of pathologists and discuss the challenges and perspectives of the implementation of AI in tumor pathology.


Assuntos
Inteligência Artificial/normas , Aprendizado Profundo/normas , Neoplasias/patologia , Medicina de Precisão/métodos , Humanos
15.
Neural Netw ; 125: 303-312, 2020 May.
Artigo em Inglês | MEDLINE | ID: mdl-32172140

RESUMO

Increasing phishing sites today have posed great threats due to their terribly imperceptible hazard. They expect users to mistake them as legitimate ones so as to steal user information and properties without notice. The conventional way to mitigate such threats is to set up blacklists. However, it cannot detect one-time Uniform Resource Locators (URL) that have not appeared in the list. As an improvement, deep learning methods are applied to increase detection accuracy and reduce the misjudgment ratio. However, some of them only focus on the characters in URLs but ignore the relationships between characters, which results in that the detection accuracy still needs to be improved. Considering the multi-head self-attention (MHSA) can learn the inner structures of URLs, in this paper, we propose CNN-MHSA, a Convolutional Neural Network (CNN) and the MHSA combined approach for highly-precise. To achieve this goal, CNN-MHSA first takes a URL string as the input data and feeds it into a mature CNN model so as to extract its features. In the meanwhile, MHSA is applied to exploit characters' relationships in the URL so as to calculate the corresponding weights for the CNN learned features. Finally, CNN-MHSA can produce highly-precise detection result for a URL object by integrating its features and their weights. The thorough experiments on a dataset collected in real environment demonstrate that our method achieves 99.84% accuracy, which outperforms the classical method CNN-LSTM and at least 6.25% higher than other similar methods on average.


Assuntos
Segurança Computacional , Aprendizado Profundo/normas , Internet
16.
JCO Clin Cancer Inform ; 4: 221-233, 2020 03.
Artigo em Inglês | MEDLINE | ID: mdl-32155093

RESUMO

PURPOSE: Deep learning (DL), a class of approaches involving self-learned discriminative features, is increasingly being applied to digital pathology (DP) images for tasks such as disease identification and segmentation of tissue primitives (eg, nuclei, glands, lymphocytes). One application of DP is in telepathology, which involves digitally transmitting DP slides over the Internet for secondary diagnosis by an expert at a remote location. Unfortunately, the places benefiting most from telepathology often have poor Internet quality, resulting in prohibitive transmission times of DP images. Image compression may help, but the degree to which image compression affects performance of DL algorithms has been largely unexplored. METHODS: We investigated the effects of image compression on the performance of DL strategies in the context of 3 representative use cases involving segmentation of nuclei (n = 137), segmentation of lymph node metastasis (n = 380), and lymphocyte detection (n = 100). For each use case, test images at various levels of compression (JPEG compression quality score ranging from 1-100 and JPEG2000 compression peak signal-to-noise ratio ranging from 18-100 dB) were evaluated by a DL classifier. Performance metrics including F1 score and area under the receiver operating characteristic curve were computed at the various compression levels. RESULTS: Our results suggest that DP images can be compressed by 85% while still maintaining the performance of the DL algorithms at 95% of what is achievable without any compression. Interestingly, the maximum compression level sustainable by DL algorithms is similar to where pathologists also reported difficulties in providing accurate interpretations. CONCLUSION: Our findings seem to suggest that in low-resource settings, DP images can be significantly compressed before transmission for DL-based telepathology applications.


Assuntos
Compressão de Dados/métodos , Aprendizado Profundo/normas , Interpretação de Imagem Assistida por Computador/métodos , Neoplasias/patologia , Patologia Clínica/normas , Processamento de Sinais Assistido por Computador/instrumentação , Telepatologia/normas , Algoritmos , Benchmarking/normas , Humanos , Neoplasias/terapia , Variações Dependentes do Observador , Controle de Qualidade , Curva ROC
17.
Neural Netw ; 125: 281-289, 2020 May.
Artigo em Inglês | MEDLINE | ID: mdl-32151915

RESUMO

Rectified activation units make an important contribution to the success of deep neural networks in many computer vision tasks. In this paper, we propose a Parametric Deformable Exponential Linear Unit (PDELU) and theoretically verify its effectiveness for improving the convergence speed of learning procedure. By means of flexible map shape, the proposed PDELU could push the mean value of activation responses closer to zero, which ensures the steepest descent in training a deep neural network. We verify the effectiveness of the proposed method in the image classification task. Extensive experiments on three classical databases (i.e., CIFAR-10, CIFAR-100, and ImageNet-2015) indicate that the proposed method leads to higher convergence speed and better accuracy when it is embedded into different CNN architectures (i.e., NIN, ResNet, WRN, and DenseNet). Meanwhile, the proposed PDELU outperforms many existing shape-specific activation functions (i.e., Maxout, ReLU, LeakyReLU, ELU, SELU, SoftPlus, Swish) and the shape-adaptive activation functions (i.e., APL, PReLU, MPELU, FReLU).


Assuntos
Aprendizado Profundo/normas , Bases de Dados Factuais , Reconhecimento Automatizado de Padrão/métodos
18.
Neural Netw ; 125: 290-302, 2020 May.
Artigo em Inglês | MEDLINE | ID: mdl-32151916

RESUMO

With the rapid development and wide application of computer, camera device, network and hardware technology, 3D object (or model) retrieval has attracted widespread attention and it has become a hot research topic in the computer vision domain. Deep learning features already available in 3D object retrieval have been proven to be better than the retrieval performance of hand-crafted features. However, most existing networks do not take into account the impact of multi-view image selection on network training, and the use of contrastive loss alone only forcing the same-class samples to be as close as possible. In this work, a novel solution named Multi-view Discrimination and Pairwise CNN (MDPCNN) for 3D object retrieval is proposed to tackle these issues. It can simultaneously input multiple batches and multiple views by adding the Slice layer and the Concat layer. Furthermore, a highly discriminative network is obtained by training samples that are not easy to be classified by clustering. Lastly, we deploy the contrastive-center loss and contrastive loss as the optimization objective that has better intra-class compactness and inter-class separability. Large-scale experiments show that the proposed MDPCNN can achieve a significant performance over the state-of-the-art algorithms in 3D object retrieval.


Assuntos
Aprendizado Profundo/normas , Análise por Conglomerados , Reconhecimento Automatizado de Padrão/métodos
19.
Medicine (Baltimore) ; 99(7): e19114, 2020 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-32049826

RESUMO

INTRODUCTION: Thoracic diseases include a variety of common human primary malignant tumors, among which lung cancer and esophageal cancer are among the top 10 in cancer incidence and mortality. Early diagnosis is an important part of cancer treatment, so artificial intelligence (AI) systems have been developed for the accurate and automated detection and diagnosis of thoracic tumors. However, the complicated AI structure and image processing made the diagnosis result of AI-based system unstable. The purpose of this study is to systematically review published evidence to explore the accuracy of AI systems in diagnosing thoracic cancers. METHODS AND ANALYSIS: We will conduct a systematic review and meta-analysis of the diagnostic accuracy of AI systems for the prediction of thoracic diseases. The primary objective is to assess the diagnostic accuracy of thoracic cancers, including assessing potential biases and calculating combined estimates of sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). The secondary objective is to evaluate the factors associated with different models, classifiers, and radiomics information. We will search databases such as PubMed/MEDLINE, Embase (via OVID), and the Cochrane Library. Two reviewers will independently screen titles and abstracts, perform full article reviews and extract study data. We will report study characteristics and assess methodological quality using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. RevMan 5.3 and Meta-disc 1.4 software will be used for data synthesis. If pooling is appropriate, we will produce summary receiver operating characteristic (SROC) curves, summary operating points (pooled sensitivity and specificity), and 95% confidence intervals around the summary operating points. Methodological subgroup and sensitivity analyses will be performed to explore heterogeneity. PROSPERO REGISTRATION NUMBER: CRD42019135247.


Assuntos
Aprendizado Profundo/normas , Neoplasias Torácicas/diagnóstico , Humanos , Metanálise como Assunto , Revisões Sistemáticas como Assunto
20.
Neural Netw ; 125: 70-82, 2020 May.
Artigo em Inglês | MEDLINE | ID: mdl-32070857

RESUMO

Deep neural network (DNN) quantization converting floating-point (FP) data in the network to integers (INT) is an effective way to shrink the model size for memory saving and simplify the operations for compute acceleration. Recently, researches on DNN quantization develop from inference to training, laying a foundation for the online training on accelerators. However, existing schemes leaving batch normalization (BN) untouched during training are mostly incomplete quantization that still adopts high precision FP in some parts of the data paths. Currently, there is no solution that can use only low bit-width INT data during the whole training process of large-scale DNNs with acceptable accuracy. In this work, through decomposing all the computation steps in DNNs and fusing three special quantization functions to satisfy the different precision requirements, we propose a unified complete quantization framework termed as "WAGEUBN" to quantize DNNs involving all data paths including W (Weights), A (Activation), G (Gradient), E (Error), U (Update), and BN. Moreover, the Momentum optimizer is also quantized to realize a completely quantized framework. Experiments on ResNet18/34/50 models demonstrate that WAGEUBN can achieve competitive accuracy on the ImageNet dataset. For the first time, the study of quantization in large-scale DNNs is advanced to the full 8-bit INT level. In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency. Our throughout quantization framework has great potential for future efficient portable devices with online learning ability.


Assuntos
Aprendizado Profundo/normas
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...