Training data enhancements for improving colonic polyp detection using deep convolutional neural networks

2021 ◽  
Vol 111 ◽  
pp. 101988
Author(s):  
Victor de Almeida Thomaz ◽  
Cesar A. Sierra-Franco ◽  
Alberto B. Raposo
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Colonic Polyp ◽  
Training Data ◽  
Polyp Detection ◽  
Deep Convolutional Neural Networks ◽  
Colonic Polyp Detection

scholarly journals Dealing with Lack of Training Data for Convolutional Neural Networks: The Case of Digital Pathology

Electronics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 256
Author(s):  
Francesco Ponzio ◽  
Gianvito Urgese ◽  
Elisa Ficarra ◽  
Santa Di Cataldo
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Digital Pathology ◽  
Training Data ◽  
Automated Classification ◽  
Computationally Efficient ◽  
Deep Convolutional Neural Networks ◽  
Cad Systems ◽  
Tissue Characteristics

Thanks to their capability to learn generalizable descriptors directly from images, deep Convolutional Neural Networks (CNNs) seem the ideal solution to most pattern recognition problems. On the other hand, to learn the image representation, CNNs need huge sets of annotated samples that are unfeasible in many every-day scenarios. This is the case, for example, of Computer-Aided Diagnosis (CAD) systems for digital pathology, where additional challenges are posed by the high variability of the cancerous tissue characteristics. In our experiments, state-of-the-art CNNs trained from scratch on histological images were less accurate and less robust to variability than a traditional machine learning framework, highlighting all the issues of fully training deep networks with limited data from real patients. To solve this problem, we designed and compared three transfer learning frameworks, leveraging CNNs pre-trained on non-medical images. This approach obtained very high accuracy, requiring much less computational resource for the training. Our findings demonstrate that transfer learning is a solution to the automated classification of histological samples and solves the problem of designing accurate and computationally-efficient CAD systems with limited training data.

scholarly journals Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks

2018 ◽  
Vol 38 (3) ◽  
Author(s):  
Miao Wu ◽  
Chuanbo Yan ◽  
Huiqiang Liu ◽  
Qian Liu
Keyword(s):  
Neural Networks ◽  
Ovarian Cancer ◽  
Convolutional Neural Networks ◽  
Image Data ◽  
Training Data ◽  
Serous Carcinoma ◽  
Deep Convolutional Neural Networks ◽  
Ovarian Cancers ◽  
Cancer Types

Ovarian cancer is one of the most common gynecologic malignancies. Accurate classification of ovarian cancer types (serous carcinoma, mucous carcinoma, endometrioid carcinoma, transparent cell carcinoma) is an essential part in the different diagnosis. Computer-aided diagnosis (CADx) can provide useful advice for pathologists to determine the diagnosis correctly. In our study, we employed a Deep Convolutional Neural Networks (DCNN) based on AlexNet to automatically classify the different types of ovarian cancers from cytological images. The DCNN consists of five convolutional layers, three max pooling layers, and two full reconnect layers. Then we trained the model by two group input data separately, one was original image data and the other one was augmented image data including image enhancement and image rotation. The testing results are obtained by the method of 10-fold cross-validation, showing that the accuracy of classification models has been improved from 72.76 to 78.20% by using augmented images as training data. The developed scheme was useful for classifying ovarian cancers from cytological images.

scholarly journals ADVERSARIAL DOMAIN ADAPTATION FOR THE CLASSIFICATION OF AERIAL IMAGES AND HEIGHT DATA USING CONVOLUTIONAL NEURAL NETWORKS

2019 ◽  
Vol IV-2/W7 ◽  
pp. 197-204 ◽  
Author(s):  
D. Wittich ◽  
F. Rottensteiner
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Domain Adaptation ◽  
Feature Representation ◽  
Training Data ◽  
Aerial Images ◽  
Remotely Sensed Data ◽  
Target Domain ◽  
Deep Convolutional Neural Networks

<p><strong>Abstract.</strong> Domain adaptation (DA) can drastically decrease the amount of training data needed to obtain good classification models by leveraging available data from a source domain for the classification of a new (target) domains. In this paper, we address deep DA, i.e. DA with deep convolutional neural networks (CNN), a problem that has not been addressed frequently in remote sensing. We present a new method for semi-supervised DA for the task of pixel-based classification by a CNN. After proposing an encoder-decoder-based fully convolutional neural network (FCN), we adapt a method for adversarial discriminative DA to be applicable to the pixel-based classification of remotely sensed data based on this network. It tries to learn a feature representation that is domain invariant; domain-invariance is measured by a classifier’s incapability of predicting from which domain a sample was generated. We evaluate our FCN on the ISPRS labelling challenge, showing that it is close to the best-performing models. DA is evaluated on the basis of three domains. We compare different network configurations and perform the representation transfer at different layers of the network. We show that when using a proper layer for adaptation, our method achieves a positive transfer and thus an improved classification accuracy in the target domain for all evaluated combinations of source and target domains.</p>

Seismic stratigraphy interpretation by deep convolutional neural networks: A semisupervised workflow

Geophysics ◽  
2020 ◽  
Vol 85 (4) ◽  
pp. WA77-WA86 ◽  
Author(s):  
Haibin Di ◽  
Zhun Li ◽  
Hiren Maniar ◽  
Aria Abubakar
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Seismic Data ◽  
Network Architecture ◽  
Domain Knowledge ◽  
Model Building ◽  
Seismic Stratigraphy ◽  
Training Data ◽  
Data Sets ◽  
Deep Convolutional Neural Networks

Depicting geologic sequences from 3D seismic surveying is of significant value to subsurface reservoir exploration, but it is usually time- and labor-intensive for manual interpretation by experienced seismic interpreters. We have developed a semisupervised workflow for efficient seismic stratigraphy interpretation by using the state-of-the-art deep convolutional neural networks (CNNs). Specifically, the workflow consists of two components: (1) seismic feature self-learning (SFSL) and (2) stratigraphy model building (SMB), each of which is formulated as a deep CNN. Whereas the SMB is supervised by knowledge from domain experts and the associated CNN uses a similar network architecture typically used in image segmentation, the SFSL is designed as an unsupervised process and thus can be performed backstage while an expert prepares the training labels for the SMB CNN. Compared with conventional approaches, the our workflow is superior in two aspects. First, the SMB CNN, initialized by the SFSL CNN, successfully inherits the prior knowledge of the seismic features in the target seismic data. Therefore, it becomes feasible for completing the supervised training of the SMB CNN more efficiently using only a small amount of training data, for example, less than 0.1% of the available seismic data as demonstrated in this paper. Second, for the convenience of seismic experts in translating their domain knowledge into training labels, our workflow is designed to be applicable to three scenarios, trace-wise, paintbrushing, and full-sectional annotation. The performance of the new workflow is well-verified through application to three real seismic data sets. We conclude that the new workflow is not only capable of providing robust stratigraphy interpretation for a given seismic volume, but it also holds great potential for other problems in seismic data analysis.

scholarly journals Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kazutoshi Ukai ◽  
Rashedur Rahman ◽  
Naomi Yagi ◽  
Keigo Hayashi ◽  
Akihiro Maruo ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Pelvic Fracture ◽  
Bone Fractures ◽  
Lesion Detection ◽  
Training Data ◽  
3D Ct ◽  
Deep Convolutional Neural Networks ◽  
Risk Of Death ◽  
Automated Method

AbstractPelvic fracture is one of the leading causes of death in the elderly, carrying a high risk of death within 1 year of fracture. This study proposes an automated method to detect pelvic fractures on 3-dimensional computed tomography (3D-CT). Deep convolutional neural networks (DCNNs) have been used for lesion detection on 2D and 3D medical images. However, training a DCNN directly using 3D images is complicated, computationally costly, and requires large amounts of training data. We propose a method that evaluates multiple, 2D, real-time object detection systems (YOLOv3 models) in parallel, in which each YOLOv3 model is trained using differently orientated 2D slab images reconstructed from 3D-CT. We assume that an appropriate reconstruction orientation would exist to optimally characterize image features of bone fractures on 3D-CT. Multiple YOLOv3 models in parallel detect 2D fracture candidates in different orientations simultaneously. The 3D fracture region is then obtained by integrating the 2D fracture candidates. The proposed method was validated in 93 subjects with bone fractures. Area under the curve (AUC) was 0.824, with 0.805 recall and 0.907 precision. The AUC with a single orientation was 0.652. This method was then applied to 112 subjects without bone fractures to evaluate over-detection. The proposed method successfully detected no bone fractures in all except 4 non-fracture subjects (96.4%).

scholarly journals Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Wenyi Lin ◽  
Kyle Hasenstab ◽  
Guilherme Moura Cunha ◽  
Armin Schwartzman
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Training Sample ◽  
Training Data ◽  
Added Value ◽  
Relative Role ◽  
Deep Convolutional Neural Networks ◽  
Training Sample Size

AbstractWe propose a random forest classifier for identifying adequacy of liver MR images using handcrafted (HC) features and deep convolutional neural networks (CNNs), and analyze the relative role of these two components in relation to the training sample size. The HC features, specifically developed for this application, include Gaussian mixture models, Euler characteristic curves and texture analysis. Using HC features outperforms the CNN for smaller sample sizes and with increased interpretability. On the other hand, with enough training data, the combined classifier outperforms the models trained with HC features or CNN features alone. These results illustrate the added value of HC features with respect to CNNs, especially when insufficient data is available, as is often found in clinical studies.

scholarly journals CLASSIFICATION OF URBAN AERIAL DATA BASED ON PIXEL LABELLING WITH DEEP CONVOLUTIONAL NEURAL NETWORKS AND LOGISTIC REGRESSION

2016 ◽  
Vol XLI-B7 ◽  
pp. 405-410 ◽  
Author(s):  
W. Yao ◽  
P. Poleswki ◽  
P. Krzystek
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Urban Areas ◽  
Evidence Theory ◽  
Infrared Camera ◽  
Training Data ◽  
Data Sources ◽  
Remotely Sensed Data ◽  
Deep Convolutional Neural Networks ◽  
Recent Success

The recent success of deep convolutional neural networks (CNN) on a large number of applications can be attributed to large amounts of available training data and increasing computing power. In this paper, a semantic pixel labelling scheme for urban areas using multi-resolution CNN and hand-crafted spatial-spectral features of airborne remotely sensed data is presented. Both CNN and hand-crafted features are applied to image/DSM patches to produce per-pixel class probabilities with a &lt;i&gt;L&lt;/i&gt;&lt;sub&gt;1&lt;/sub&gt;-norm regularized logistical regression classifier. The evidence theory infers a degree of belief for pixel labelling from different sources to smooth regions by handling the conflicts present in the both classifiers while reducing the uncertainty. The aerial data used in this study were provided by ISPRS as benchmark datasets for 2D semantic labelling tasks in urban areas, which consists of two data sources from LiDAR and color infrared camera. The test sites are parts of a city in Germany which is assumed to consist of typical object classes including impervious surfaces, trees, buildings, low vegetation, vehicles and clutter. The evaluation is based on the computation of pixel-based confusion matrices by random sampling. The performance of the strategy with respect to scene characteristics and method combination strategies is analyzed and discussed. The competitive classification accuracy could be not only explained by the nature of input data sources: e.g. the above-ground height of nDSM highlight the vertical dimension of houses, trees even cars and the nearinfrared spectrum indicates vegetation, but also attributed to decision-level fusion of CNN’s texture-based approach with multichannel spatial-spectral hand-crafted features based on the evidence combination theory.

scholarly journals Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

2018 ◽  
Author(s):  
Yang He ◽  
Guoliang Kang ◽  
Xuanyi Dong ◽  
Yanwei Fu ◽  
Yi Yang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
The State ◽  
Training Data ◽  
Deep Convolutional Neural Networks ◽  
Inference Procedure ◽  
Accuracy Improvement ◽  
Large Capacity ◽  
Pruning Methods

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pretrained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0.2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/softfilter-pruning

scholarly journals CLASSIFICATION OF URBAN AERIAL DATA BASED ON PIXEL LABELLING WITH DEEP CONVOLUTIONAL NEURAL NETWORKS AND LOGISTIC REGRESSION

2016 ◽  
Vol XLI-B7 ◽  
pp. 405-410
Author(s):  
W. Yao ◽  
P. Poleswki ◽  
P. Krzystek
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Urban Areas ◽  
Evidence Theory ◽  
Infrared Camera ◽  
Training Data ◽  
Data Sources ◽  
Remotely Sensed Data ◽  
Deep Convolutional Neural Networks ◽  
Recent Success

The recent success of deep convolutional neural networks (CNN) on a large number of applications can be attributed to large amounts of available training data and increasing computing power. In this paper, a semantic pixel labelling scheme for urban areas using multi-resolution CNN and hand-crafted spatial-spectral features of airborne remotely sensed data is presented. Both CNN and hand-crafted features are applied to image/DSM patches to produce per-pixel class probabilities with a <i>L</i><sub>1</sub>-norm regularized logistical regression classifier. The evidence theory infers a degree of belief for pixel labelling from different sources to smooth regions by handling the conflicts present in the both classifiers while reducing the uncertainty. The aerial data used in this study were provided by ISPRS as benchmark datasets for 2D semantic labelling tasks in urban areas, which consists of two data sources from LiDAR and color infrared camera. The test sites are parts of a city in Germany which is assumed to consist of typical object classes including impervious surfaces, trees, buildings, low vegetation, vehicles and clutter. The evaluation is based on the computation of pixel-based confusion matrices by random sampling. The performance of the strategy with respect to scene characteristics and method combination strategies is analyzed and discussed. The competitive classification accuracy could be not only explained by the nature of input data sources: e.g. the above-ground height of nDSM highlight the vertical dimension of houses, trees even cars and the nearinfrared spectrum indicates vegetation, but also attributed to decision-level fusion of CNN’s texture-based approach with multichannel spatial-spectral hand-crafted features based on the evidence combination theory.

Sign in / Sign up

Export Citation Format

Share Document