A Convolutional Neural Network for Search Term Detection

Salehinejad, Hojjat; Barfett, Joseph; Aarabi, Parham; Valaee, Shahrokh; Colak, Errol; Gray, Bruce H.; Dowdell, Tim

doi:10.48550/arxiv.1708.02238

Search citation statements

Order By: Relevance

Paper Sections

Select...

B Bi-cnn Model Architecture2

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2017

Publication Types

Select...

Other1

Relationship

Self Cite1

Independent0

Authors

Journals

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An input report with N words can be represented as a sequence X = [x 1 , ..., x N ], where each word is a vector x n ∈ R D , [32]. As Figure 3 shows, the proposed architecture has two input channels followed by two independent convolution layers.…”

Section: B Bi-cnn Model Architecturementioning

confidence: 99%

See 1 more Smart Citation

Interpretation of Mammogram and Chest X-Ray Reports Using Deep Neural Networks - Preliminary Results

Salehinejad¹,

Valaee²,

Mnatzakanian³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

Radiology reports are an important means of communication between radiologists and other physicians. These reports express a radiologist's interpretation of a medical imaging examination and are critical in establishing a diagnosis and formulating a treatment plan. In this paper, we propose a Bidirectional convolutional neural network (Bi-CNN) model for the interpretation and classification of mammograms based on breast density and chest radiographic radiology reports based on the basis of chest pathology. The proposed approach is a part of an auditing system that evaluates radiology reports to decrease incorrect diagnoses. Our study revealed that the proposed Bi-CNN outperforms convolutional neural network, random forest and support vector machine methods.

show abstract

Section: B Bi-cnn Model Architecturementioning

confidence: 99%

“…Each channel in the proposed model in Figure 3 has three filters with varying window sizes K ∈ {3, 4, 5} that slide across the input layer [24], [32]. The filters extract features from the input layer to construct feature maps of size (N − K + 1) × F , where F is the number of feature maps for each filter.…”

Section: B Bi-cnn Model Architecturementioning

confidence: 99%