2012
DOI: 10.1002/jmri.23540
|View full text |Cite
|
Sign up to set email alerts
|

Multiparametric MRI maps for detection and grading of dominant prostate tumors

Abstract: -4,7 Purpose: To develop an image-based technique capable of detection and grading of prostate cancer, which combines features extracted from multiparametric MRI into a single parameter map of cancer probability. Materials and Methods:A combination of features extracted from diffusion tensor MRI and dynamic contrast enhanced MRI was used to characterize biopsy samples from 29 patients. Support vector machines were used to separate the cancerous samples from normal biopsy samples and to compute a measure of … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
40
0

Year Published

2014
2014
2021
2021

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 53 publications
(40 citation statements)
references
References 37 publications
0
40
0
Order By: Relevance
“…Our work also incorporated sample augmentation methods to tackle the problem of highly unbalanced data and achieved a much higher accuracy of 0.93 for cancers in the PZ and TZ and 0.92 for cancers occurring only in the PZ following reduction by the hyperparameter selection bias. The majority of the prior works have been focused on classifying cancerous regions from benign structures (24,25,43,44). Our results for classifying noncancerous prostate from malignant cancers ADC mean has been shown to be a viable biomarker for differentiating cancers by their aggressiveness with reasonable accuracy of 0.75 (22).…”
Section: Discussion and Future Workmentioning
confidence: 72%
See 2 more Smart Citations
“…Our work also incorporated sample augmentation methods to tackle the problem of highly unbalanced data and achieved a much higher accuracy of 0.93 for cancers in the PZ and TZ and 0.92 for cancers occurring only in the PZ following reduction by the hyperparameter selection bias. The majority of the prior works have been focused on classifying cancerous regions from benign structures (24,25,43,44). Our results for classifying noncancerous prostate from malignant cancers ADC mean has been shown to be a viable biomarker for differentiating cancers by their aggressiveness with reasonable accuracy of 0.75 (22).…”
Section: Discussion and Future Workmentioning
confidence: 72%
“…We analyzed the efficacy of classifying GS 6ð3 + 3Þ (n = 34) vs. GS ≥7 (n = 159) cancers and GS 7ð3 + 4Þ (n = 114) vs. 7ð4 + 3Þ (n = 26) cancers using (i) t test SVM, (ii) RFE-SVM, and (iii) AdaBoost trained without and with sample augmentation using (i) Gibbs oversampling and (ii) synthetic minority oversampling technique (SMOTE) oversampling. To compare our results with those of previous works (23)(24)(25), we also applied the same methods for distinguishing between noncancerous structures and prostate cancers. The number of samples for noncancerous structures (n = 158) and cancer (n = 198, the GS for five tumors were not provided) were balanced, and hence, did not require sample augmentation.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…It should be emphasized that the most accurate methods of MRI-based prostate cancer detection are typically multiparametric and include diffusion imaging, which is a very effective modality in prostate cancer detection [2,40]. In our previous work we have shown that diffusion imaging outperforms DCE in detection of cancer from biopsy cases and that the combination of the two methods is the most effective solution [16]. Therefore, we expect a significantly improved performance resulting from adding the diffusion parameters to our feature vector in the current wholemount prostatectomy study as well.…”
Section: Discussionmentioning
confidence: 99%
“…The pharmacokinetic parameters extracted from DCE MR images provide physiological information about tissue microvasculature and may be linked to active cancer growth [13,14]. These parameters, when used in a supervised machine learning framework with diffusion tensor features [15,16], or with T2-weighted and diffusion weighted features [17], have shown great potential in prostate cancer detection.…”
Section: Introductionmentioning
confidence: 99%