2015
DOI: 10.1007/978-3-319-24571-3_9
|View full text |Cite
|
Sign up to set email alerts
|

Ultrasound-Based Detection of Prostate Cancer Using Automatic Feature Selection with Deep Belief Networks

Abstract: Abstract.We propose an automatic feature selection framework for analyzing temporal ultrasound signals of prostate tissue. The framework consists of: 1) an unsupervised feature reduction step that uses Deep Belief Network (DBN) on spectral components of the temporal ultrasound data; 2) a supervised fine-tuning step that uses the histopathology of the tissue samples to further optimize the DBN; 3) a Support Vector Machine (SVM) classifier that uses the activation of the DBN as input and outputs a likelihood for… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
15
0

Year Published

2016
2016
2020
2020

Publication Types

Select...
5
1
1

Relationship

2
5

Authors

Journals

citations
Cited by 25 publications
(15 citation statements)
references
References 11 publications
0
15
0
Order By: Relevance
“…To generate our model, we aim to use homogeneous prostate tissue regions with reliable ground-truth labels. Therefore, we select cores for training if they meet all of the following three selection criteria, similar to our previous work [1]: (i) located more than 3 mm distance to the prostate boundary in TRUS images; (ii) have matching histopathology labels between axial and sagittal biopsies; and (iii) have a tumor length larger than 7 mm if cancerous. We select 32 cores from 27 patients, which fulfill the above criteria, and use the temporal US data from them to generate our model.…”
Section: Methodsmentioning
confidence: 99%
See 3 more Smart Citations
“…To generate our model, we aim to use homogeneous prostate tissue regions with reliable ground-truth labels. Therefore, we select cores for training if they meet all of the following three selection criteria, similar to our previous work [1]: (i) located more than 3 mm distance to the prostate boundary in TRUS images; (ii) have matching histopathology labels between axial and sagittal biopsies; and (iii) have a tumor length larger than 7 mm if cancerous. We select 32 cores from 27 patients, which fulfill the above criteria, and use the temporal US data from them to generate our model.…”
Section: Methodsmentioning
confidence: 99%
“…To generate features for each ROI, we take the Fourier transform of the time course signals in the ROI, normalized to the frame rate. For each ROI, we generate 50 positive frequency components by averaging the absolute values of the discrete Fourier transform (DFT) of the zero-mean temporal US data [1,15]. …”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…1 Different feature sets extracted from these signals have been successfully applied to various classification problems for distinguishing cancerous and benign tissue in both ex vivo 1, 2 and in vivo [3][4][5][6] studies. These studies have demonstrated that the tissue classification results with temporal ultrasound outperforms conventional tissue typing approaches, including B-mode texture analysis and spectral methods.…”
Section: Introductionmentioning
confidence: 99%