An Automated In-Depth Feature Learning Algorithm for Breast Abnormality Prognosis and Robust Characterization from Mammography Images Using Deep Transfer Learning

Background: Diagnosing breast cancer masses and calcification clusters have paramount significance in mammography, which aids in mitigating the disease’s complexities and curing it at early stages. However, a wrong mammogram interpretation may lead to an unnecessary biopsy of the false-positive findings, which reduces the patient’s survival chances. Consequently, approaches that learn to discern breast masses can reduce the number of misconceptions and incorrect diagnoses. Conventionally used classification models focus on feature extraction techniques specific to a particular problem based on domain information. Deep learning strategies are becoming promising alternatives to solve the many challenges of feature-based approaches. Methods: This study introduces a convolutional neural network (ConvNet)-based deep learning method to extract features at varying densities and discern mammography’s normal and suspected regions. Two different experiments were carried out to make an accurate diagnosis and classification. The first experiment consisted of five end-to-end pre-trained and fine-tuned deep convolution neural networks (DCNN). The in-depth features extracted from the ConvNet are also used to train the support vector machine algorithm to achieve excellent performance in the second experiment. Additionally, DCNN is the most frequently used image interpretation and classification method, including VGGNet, GoogLeNet, MobileNet, ResNet, and DenseNet. Moreover, this study pertains to data cleaning, preprocessing, and data augmentation, and improving mass recognition accuracy. The efficacy of all models is evaluated by training and testing three mammography datasets and has exhibited remarkable results. Results: Our deep learning ConvNet+SVM model obtained a discriminative training accuracy of 97.7% and validating accuracy of 97.8%, contrary to this, VGGNet16 method yielded 90.2%, 93.5% for VGGNet19, 63.4% for GoogLeNet, 82.9% for MobileNetV2, 75.1% for ResNet50, and 72.9% for DenseNet121. Conclusions: The proposed model’s improvement and validation are appropriated in conventional pathological practices that conceivably reduce the pathologist’s strain in predicting clinical outcomes by analyzing patients’ mammography images.

Download Full-text

Deep learning-based framework for the distinction of membranous nephropathy: a new approach through hyperspectral imagery

BMC Nephrology ◽

10.1186/s12882-021-02421-y ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Tianqi Tu ◽

Xueling Wei ◽

Yue Yang ◽

Nianrong Zhang ◽

Wei Li ◽

...

Keyword(s):

Deep Learning ◽

Renal Biopsy ◽

Membranous Nephropathy ◽

Learning Algorithm ◽

Hyperspectral Imagery ◽

Chinese Patients ◽

Support Vector ◽

Deep Learning Algorithm ◽

The Difference ◽

Complex Deposition

Abstract Background Common subtypes seen in Chinese patients with membranous nephropathy (MN) include idiopathic membranous nephropathy (IMN) and hepatitis B virus-related membranous nephropathy (HBV-MN). However, the morphologic differences are not visible under the light microscope in certain renal biopsy tissues. Methods We propose here a deep learning-based framework for processing hyperspectral images of renal biopsy tissue to define the difference between IMN and HBV-MN based on the component of their immune complex deposition. Results The proposed framework can achieve an overall accuracy of 95.04% in classification, which also leads to better performance than support vector machine (SVM)-based algorithms. Conclusion IMN and HBV-MN can be correctly separated via the deep learning framework using hyperspectral imagery. Our results suggest the potential of the deep learning algorithm as a new method to aid in the diagnosis of MN.

Download Full-text

Data augmentation and transfer learning strategies for reaction prediction in low chemical data regimes

Organic Chemistry Frontiers ◽

10.1039/d0qo01636e ◽

2021 ◽

Author(s):

Yun Zhang ◽

Ling Wang ◽

Xinqiao Wang ◽

Chengyun Zhang ◽

Jiamin Ge ◽

...

Keyword(s):

Organic Chemistry ◽

Deep Learning ◽

Drug Discovery ◽

Research And Development ◽

Learning Strategies ◽

Transfer Learning ◽

Chemical Reactions ◽

Data Augmentation ◽

Learning Method ◽

Reaction Prediction

An effective and rapid deep learning method to predict chemical reactions contributes to the research and development of organic chemistry and drug discovery.

Download Full-text

Fast Recognition System for Tree Images based on Caffe Platform and Deep Learning

10.21203/rs.3.rs-52291/v1 ◽

2020 ◽

Author(s):

Zongchen Li ◽

Wenzhuo Zhang ◽

Guoxiong Zhou

Keyword(s):

Deep Learning ◽

Dual Task ◽

Learning Algorithm ◽

Recognition System ◽

Support Vector ◽

Similar Species ◽

Graphical Interface ◽

Fast Recognition ◽

System Solution ◽

Tree Image

Abstract Aiming at the difficult problem of complex extraction for tree image in the existing complex background, we took tree species as the research object and proposed a fast recognition system solution for tree image based on Caffe platform and deep learning. In the research of deep learning algorithm based on Caffe framework, the improved Dual-Task CNN model (DCNN) is applied to train the image extractor and classifier to accomplish the dual tasks of image cleaning and tree classification. In addition, when compared with the traditional classification methods represented by Support Vector Machine (SVM) and Single-Task CNN model, Dual-Task CNN model demonstrates its superiority in classification performance. Then, in order for further improvement to the recognition accuracy for similar species, Gabor kernel was introduced to extract the features of frequency domain for images in different scales and directions, so as to enhance the texture features of leaf images and improve the recognition effect. The improved model was tested on the data sets of similar species. As demonstrated by the results, the improved deep Gabor convolutional neural network (GCNN) is advantageous in tree recognition and similar tree classification when compared with the Dual-Task CNN classification method. Finally, the recognition results of trees can be displayed on the application graphical interface as well. In the application graphical interface designed based on Ubantu system, it is capable to perform such functions as quick reading of and search for picture files, snapshot, one-key recognition, one-key e

Download Full-text

Deep learning para la clasificación de usos de suelo agrícola con Sentinel-2

Revista de Teledetección ◽

10.4995/raet.2020.13337 ◽

2020 ◽

pp. 35

Author(s):

M. Campos-Taberner ◽

F.J. García-Haro ◽

B. Martínez ◽

M.A. Gilabert

Keyword(s):

Remote Sensing ◽

Deep Learning ◽

Near Infrared ◽

Spatial Information ◽

Learning Algorithm ◽

Support Vector ◽

Sensing Applications ◽

Learning Techniques ◽

Remote Sensing Applications ◽

Sentinel 2

<p class="p1">The use of deep learning techniques for remote sensing applications has recently increased. These algorithms have proven to be successful in estimation of parameters and classification of images. However, little effort has been made to make them understandable, leading to their implementation as “black boxes”. This work aims to evaluate the performance and clarify the operation of a deep learning algorithm, based on a bi-directional recurrent network of long short-term memory (2-BiLSTM). The land use classification in the Valencian Community based on Sentinel-2 image time series in the framework of the common agricultural policy (CAP) is used as an example. It is verified that the accuracy of the deep learning techniques is superior (98.6 % overall success) to that other algorithms such as decision trees (DT), k-nearest neighbors (k-NN), neural networks (NN), support vector machines (SVM) and random forests (RF). The performance of the classifier has been studied as a function of time and of the predictors used. It is concluded that, in the study area, the most relevant information used by the network in the classification are the images corresponding to summer and the spectral and spatial information derived from the red and near infrared bands. These results open the door to new studies in the field of the explainable deep learning in remote sensing applications.</p>

Download Full-text

Using geometric constraints to improve performance of image classifiers for automatic segmentation of traffic signs

GEOMATICA ◽

10.1139/geomat-2020-0010 ◽

2021 ◽

pp. 1-23

Author(s):

Roholah Yazdan ◽

Masood Varshosaz ◽

Saied Pirasteh ◽

Fabio Remondino

Keyword(s):

Deep Learning ◽

Learning Algorithm ◽

Automatic Segmentation ◽

Geometric Constraints ◽

Support Vector ◽

Svm Classifier ◽

Data Set ◽

Traffic Signs ◽

Deep Learning Algorithm ◽

Comparison Results

Automatic detection and recognition of traffic signs from images is an important topic in many applications. At first, we segmented the images using a classification algorithm to delineate the areas where the signs are more likely to be found. In this regard, shadows, objects having similar colours, and extreme illumination changes can significantly affect the segmentation results. We propose a new shape-based algorithm to improve the accuracy of the segmentation. The algorithm works by incorporating the sign geometry to filter out the wrong pixels from the classification results. We performed several tests to compare the performance of our algorithm against those obtained by popular techniques such as Support Vector Machine (SVM), K-Means, and K-Nearest Neighbours. In these tests, to overcome the unwanted illumination effects, the images are transformed into colour spaces Hue, Saturation, and Intensity, YUV, normalized red green blue, and Gaussian. Among the traditional techniques used in this study, the best results were obtained with SVM applied to the images transformed into the Gaussian colour space. The comparison results also suggested that by adding the geometric constraints proposed in this study, the quality of sign image segmentation is improved by 10%–25%. We also comparted the SVM classifier enhanced by incorporating the geometry of signs with a U-Shaped deep learning algorithm. Results suggested the performance of both techniques is very close. Perhaps the deep learning results could be improved if a more comprehensive data set is provided.

Download Full-text

A Comprehensive Evaluation of Approaches for Built-Up Area Extraction from Landsat OLI Images Using Massive Samples

Remote Sensing ◽

10.3390/rs11010002 ◽

2018 ◽

Vol 11 (1) ◽

pp. 2 ◽

Cited By ~ 11

Author(s):

Tao Zhang ◽

Hong Tang

Keyword(s):

Learning Strategies ◽

Classification Accuracy ◽

Feature Learning ◽

Automatic Generation ◽

Experimental Results ◽

Support Vector ◽

Feature Engineering ◽

Classification Algorithms ◽

Sample Points ◽

Better Than

Detailed information about built-up areas is valuable for mapping complex urban environments. Although a large number of classification algorithms for such areas have been developed, they are rarely tested from the perspective of feature engineering and feature learning. Therefore, we launched a unique investigation to provide a full test of the Operational Land Imager (OLI) imagery for 15-m resolution built-up area classification in 2015, in Beijing, China. Training a classifier requires many sample points, and we proposed a method based on the European Space Agency’s (ESA) 38-m global built-up area data of 2014, OpenStreetMap, and MOD13Q1-NDVI to achieve the rapid and automatic generation of a large number of sample points. Our aim was to examine the influence of a single pixel and image patch under traditional feature engineering and modern feature learning strategies. In feature engineering, we consider spectra, shape, and texture as the input features, and support vector machine (SVM), random forest (RF), and AdaBoost as the classification algorithms. In feature learning, the convolutional neural network (CNN) is used as the classification algorithm. In total, 26 built-up land cover maps were produced. The experimental results show the following: (1) The approaches based on feature learning are generally better than those based on feature engineering in terms of classification accuracy, and the performance of ensemble classifiers (e.g., RF) are comparable to that of CNN. Two-dimensional CNN and the 7-neighborhood RF have the highest classification accuracies at nearly 91%; (2) Overall, the classification effect and accuracy based on image patches are better than those based on single pixels. The features that can highlight the information of the target category (e.g., PanTex (texture-derived built-up presence index) and enhanced morphological building index (EMBI)) can help improve classification accuracy. The code and experimental results are available at https://github.com/zhangtao151820/CompareMethod.

Download Full-text

Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm

Journal of Personalized Medicine ◽

10.3390/jpm10040213 ◽

2020 ◽

Vol 10 (4) ◽

pp. 213 ◽

Cited By ~ 1

Author(s):

Ki-Sun Lee ◽

Jae Young Kim ◽

Eun-tae Jeon ◽

Won Suk Choi ◽

Nan Hee Kim ◽

...

Keyword(s):

Deep Learning ◽

Learning Strategies ◽

Transfer Learning ◽

Learning Algorithm ◽

Fine Tuning ◽

Deep Convolutional Neural Networks ◽

X Ray ◽

Backbone Network ◽

Deep Learning Algorithm ◽

Chest X Ray

According to recent studies, patients with COVID-19 have different feature characteristics on chest X-ray (CXR) than those with other lung diseases. This study aimed at evaluating the layer depths and degree of fine-tuning on transfer learning with a deep convolutional neural network (CNN)-based COVID-19 screening in CXR to identify efficient transfer learning strategies. The CXR images used in this study were collected from publicly available repositories, and the collected images were classified into three classes: COVID-19, pneumonia, and normal. To evaluate the effect of layer depths of the same CNN architecture, CNNs called VGG-16 and VGG-19 were used as backbone networks. Then, each backbone network was trained with different degrees of fine-tuning and comparatively evaluated. The experimental results showed the highest AUC value to be 0.950 concerning COVID-19 classification in the experimental group of a fine-tuned with only 2/5 blocks of the VGG16 backbone network. In conclusion, in the classification of medical images with a limited number of data, a deeper layer depth may not guarantee better results. In addition, even if the same pre-trained CNN architecture is used, an appropriate degree of fine-tuning can help to build an efficient deep learning model.

Download Full-text

Vision-Based Classification of Mosquito Species: Comparison of Conventional and Deep Learning Methods

Applied Sciences ◽

10.3390/app9183935 ◽

2019 ◽

Vol 9 (18) ◽

pp. 3935 ◽

Cited By ~ 3

Author(s):

Kazushige Okayasu ◽

Kota Yoshida ◽

Masataka Fuchida ◽

Akio Nakamura

Keyword(s):

Deep Learning ◽

Conventional Method ◽

Data Augmentation ◽

Mosquito Species ◽

Experimental Results ◽

Support Vector ◽

Learning Method ◽

Species Classification ◽

Scale Invariant ◽

Machine Method

This study aims to propose a vision-based method to classify mosquito species. To investigate the efficiency of the method, we compared two different classification methods: The handcraft feature-based conventional method and the convolutional neural network-based deep learning method. For the conventional method, 12 types of features were adopted for handcraft feature extraction, while a support vector machine method was adopted for classification. For the deep learning method, three types of architectures were adopted for classification. We built a mosquito image dataset, which included 14,400 images with three types of mosquito species. The dataset comprised 12,000 images for training, 1500 images for testing, and 900 images for validating. Experimental results revealed that the accuracy of the conventional method using the scale-invariant feature transform algorithm was 82.4% at maximum, whereas the accuracy of the deep learning method was 95.5% in a residual network using data augmentation. From the experimental results, deep learning can be considered to be effective for classifying the mosquito species of the proposed dataset. Furthermore, data augmentation improves the accuracy of mosquito species’ classification.

Download Full-text

Deep learning-based framework for the distinction of membranous nephropathy: A new approach through hyperspectral imagery

10.21203/rs.3.rs-30329/v3 ◽

2021 ◽

Author(s):

Tianqi Tu ◽

Xueling Wei ◽

Yue Yang ◽

Nianrong Zhang ◽

Wei Li ◽

...

Keyword(s):

Deep Learning ◽

Renal Biopsy ◽

Membranous Nephropathy ◽

Learning Algorithm ◽

Hyperspectral Imagery ◽

Chinese Patients ◽

Support Vector ◽

Deep Learning Algorithm ◽

The Difference ◽

Complex Deposition

Abstract Background: Common subtypes seen in Chinese patients with membranous nephropathy (MN) include idiopathic membranous nephropathy (IMN) and hepatitis B virus-related membranous nephropathy (HBV-MN). However, the morphologic differences are not visible under the light microscope in certain renal biopsy tissues. Methods: We propose here a deep learning-based framework for processing hyperspectral images of renal biopsy tissue to define the difference between IMN and HBV-MN based on the component of their immune complex deposition. Results: The proposed framework can achieve an overall accuracy of 95.04% in classification, which also leads to better performance than support vector machine (SVM)-based algorithms. Conclusion: IMN and HBV-MN can be correctly separated via the deep learning framework using hyperspectral imagery. Our results suggest the potential of the deep learning algorithm as a new method to aid in the diagnosis of MN.

Download Full-text

Deep Learning for Identification of Acute Illness and Facial Cues of Illness

Frontiers in Medicine ◽

10.3389/fmed.2021.661309 ◽

2021 ◽

Vol 8 ◽

Author(s):

Castela Forte ◽

Andrei Voinea ◽

Malina Chichirau ◽

Galiya Yeshmagambetova ◽

Lea M. Albrecht ◽

...

Keyword(s):

Deep Learning ◽

Data Augmentation ◽

Learning Algorithm ◽

External Validation ◽

Facial Feature ◽

Acute Illness ◽

Facial Features ◽

Genetic Syndromes ◽

Coronary Syndrome ◽

Deep Learning Algorithm

Background: The inclusion of facial and bodily cues (clinical gestalt) in machine learning (ML) models improves the assessment of patients' health status, as shown in genetic syndromes and acute coronary syndrome. It is unknown if the inclusion of clinical gestalt improves ML-based classification of acutely ill patients. As in previous research in ML analysis of medical images, simulated or augmented data may be used to assess the usability of clinical gestalt.Objective: To assess whether a deep learning algorithm trained on a dataset of simulated and augmented facial photographs reflecting acutely ill patients can distinguish between healthy and LPS-infused, acutely ill individuals.Methods: Photographs from twenty-six volunteers whose facial features were manipulated to resemble a state of acute illness were used to extract features of illness and generate a synthetic dataset of acutely ill photographs, using a neural transfer convolutional neural network (NT-CNN) for data augmentation. Then, four distinct CNNs were trained on different parts of the facial photographs and concatenated into one final, stacked CNN which classified individuals as healthy or acutely ill. Finally, the stacked CNN was validated in an external dataset of volunteers injected with lipopolysaccharide (LPS).Results: In the external validation set, the four individual feature models distinguished acutely ill patients with sensitivities ranging from 10.5% (95% CI, 1.3–33.1% for the skin model) to 89.4% (66.9–98.7%, for the nose model). Specificity ranged from 42.1% (20.3–66.5%) for the nose model and 94.7% (73.9–99.9%) for skin. The stacked model combining all four facial features achieved an area under the receiver characteristic operating curve (AUROC) of 0.67 (0.62–0.71) and distinguished acutely ill patients with a sensitivity of 100% (82.35–100.00%) and specificity of 42.11% (20.25–66.50%).Conclusion: A deep learning algorithm trained on a synthetic, augmented dataset of facial photographs distinguished between healthy and simulated acutely ill individuals, demonstrating that synthetically generated data can be used to develop algorithms for health conditions in which large datasets are difficult to obtain. These results support the potential of facial feature analysis algorithms to support the diagnosis of acute illness.

Download Full-text