A context-sensitive deep learning approach for microcalcification detection in mammograms

Wang, Juan; Yang, Yongyi

doi:10.1016/j.patcog.2018.01.009

Cited by 82 publications

(55 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, most deep convolutional neural networks suffer from the detection of small and occluded objects, which has not been well solved even with much more complicated models [10]. In our study, we claim that the detection of small and occluded objects depends not only on detail features but also on semantic features and the contextual information [17]. Deep features have better expression towards the main characteristics of objects and more accurate semantic description of the objects in the scenes [13,15].…”

Section: Introductionmentioning

confidence: 74%

MDFN: Multi-scale deep feature learning network for object detection

Cen

et al. 2020

Pattern Recognition

113

View full text Add to dashboard Cite

This paper proposes an innovative object detector by leveraging deep features learned in high-level layers. Compared with features produced in earlier layers, the deep features are better at expressing semantic and contextual information.The proposed deep feature learning scheme shifts the focus from concrete features with details to abstract ones with semantic information. It considers not only individual objects and local contexts but also their relationships by building a multi-scale deep feature learning network (MDFN). MDFN efficiently detects the objects by introducing information square and cubic inception modules into the high-level layers, which employs parameter-sharing to enhance the computational efficiency. MDFN provides a multi-scale object detector by integrating multi-box, multi-scale and multi-level technologies. Although MDFN employs a simple framework with a relatively small base network (VGG-16), it achieves better or competitive detection results than those with a macro hierarchical structure that is either very deep or very wide for stronger ability of feature extraction. The proposed technique is evaluated extensively on KITTI, PAS-CAL VOC, and COCO datasets, which achieves the best results on KITTI and leading performance on PASCAL VOC and COCO. This study reveals that deep features provide prominent semantic information and a variety of contex-tual contents, which contribute to its superior performance in detecting small or occluded objects. In addition, the MDFN model is computationally efficient, making a good trade-off between the accuracy and speed.Keywords: deep feature learning, multi-scale, semantic and contextual information, small and occluded objects.

show abstract

Section: Introductionmentioning

confidence: 74%

MDFN: Multi-scale deep feature learning network for object detection

Cen

et al. 2020

Pattern Recognition

113

View full text Add to dashboard Cite

show abstract

“…Since we use the whole image as input to our CNN model and to avoid producing unrealistic images, we avoid rotating images in the data augmentation as used in the literature [9][10][11][12]17].…”

Section: Augmented Databasementioning

confidence: 99%

“…Wang et al developed context-sensitive deep neural networks (DNN) where a simplified version of AlexNet based on deep CNN with five convolutional layers and two FC layers is used in the classification of the segmented masses as benign or malignant [10].…”

Section: Introductionmentioning

confidence: 99%

A New Triplet Convolutional Neural Network for Classification of Lesions on Mammograms

Medjeded¹,

Mahmoudi²,

Chenine³

et al. 2019

RIA

View full text Add to dashboard Cite

Mammography provides a useful tool for breast cancer detection. However, many doctors have difficulty in making the right decision based on mammograms. This paper aims to set up a deep learning (DL) architecture that can effectively differentiate between benign and malignant tumors. Specifically, a new triplet convolutional neural network (CNN) was established with three subnetworks, each of which contains a succession of layer blocks. Each block consists of two convolutional layers, a dropout layer and a max-pooling layer. During operation, the region of interest (ROI) extracted from the mammogram is imputed to the first subnetwork, and processed by the Canny filter. The filtered results become the input of the second subnetwork, while the third subnetwork takes the whole image as input. To verify the effectiveness of our architecture, a set of 500 images from 301 patients was extracted from the DDSM database and augmented to 4,000 images, and divided into a training set (80 %) and a testing set (20 %). The results show that our architecture achieved an accuracy of 93.13 %, a sensitivity of 96 % and a specificity of 90.25 %. This research provides a desirable way to identify breast cancer based on mammography.

show abstract

“…Similarly, multiscale texture features have been extracted using variants of wavelets with various scaling functions [21,34,35,36] and fractal methods [37,38]. Recently, deep learning techniques have been developed for detection and for classifying the lesions in mammograms [39,40,41,42].…”

Section: Introductionmentioning

confidence: 99%

Multiscale connected chain topological modelling for microcalcification classification

George

Chen

Zwiggelaar

2019

Computers in Biology and Medicine

View full text Add to dashboard Cite

Computer-aided diagnosis (CAD) systems can be employed to help classify mammographic microcalcification clusters. In this paper, a novel method for the classification of the microcalcification clusters based on topology/connectivity has been introduced. The proposed method is distinct from existing techniques which concentrate on morphology and texture of microcalcifications and surrounding tissue. The proposed approach used multiscale morphological relationship of connectivity between microcalcifications where connected chains between nearest microcalcifications were generated at each scale. Subsequently, graph connectivity features at each scale were extracted to estimate the topological connectivity structure of microcalcification clusters for benign versus malignant classification. The proposed approach was evaluated using publicly available digitized datasets: MIAS and DDSM, in addition to the digital OPTIMAM dataset. The classification of features using KNN obtained a classification accuracy of 86.47 ± 1.30%, 90.0 ± 0.00%, 82.5 ± 2.63%, 76.75 ± 0.66% for the DDSM, MIAS-manual, MIAS-auto and OPTIMAM datasets respectively. The study showed that topological/connectivity modelling using a multiscale approach was appropriate for microcalcification cluster analysis and classification; topological connectivity and distribution can be linked to clinical understanding of microcalcification spatial distribution.

show abstract

A context-sensitive deep learning approach for microcalcification detection in mammograms

Cited by 82 publications

References 43 publications

MDFN: Multi-scale deep feature learning network for object detection

MDFN: Multi-scale deep feature learning network for object detection

A New Triplet Convolutional Neural Network for Classification of Lesions on Mammograms

Multiscale connected chain topological modelling for microcalcification classification

Contact Info

Product

Resources

About