2019
DOI: 10.1007/s12530-019-09310-8
|View full text |Cite
|
Sign up to set email alerts
|

Automatic pectoral muscle removal in mammograms

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
22
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
6
2

Relationship

3
5

Authors

Journals

citations
Cited by 28 publications
(22 citation statements)
references
References 5 publications
0
22
0
Order By: Relevance
“…Rahimeto et. al proposed an automatic pectoral muscle removal technique for breast mammograms 10 . They used wiener filtering for noise removal and Otsu's algorithm for extraction of the biggest blob.…”
Section: Related Workmentioning
confidence: 99%
“…Rahimeto et. al proposed an automatic pectoral muscle removal technique for breast mammograms 10 . They used wiener filtering for noise removal and Otsu's algorithm for extraction of the biggest blob.…”
Section: Related Workmentioning
confidence: 99%
“…Most of the performance metrics encountered in the review include area under curve (AUC), sensitivity (Sn), specificity (Sp), accuracy (Acc), precision (P), recall (R), positive predictive values (PPV), Matthews correlation coefficient (MCC), geometric mean (G-Mean), which are usually successful in describing the classification performance [ 8 , 9 ]. Performance measures including Dice similarity coefficient (DSC) or Zijdenbos similarity index (ZSI) or F1-score, Hausdorff distance (H) and intersection over union (IoU) are the most effective metrics for measuring system’s segmentation performance [ 10 ]. Here, the true positives for the segmentation are the correctly labeled pixel while it is correctly labeled class for classification case.…”
Section: Methodsmentioning
confidence: 99%
“…The total computational time of our method is shorter than most of that of other methods [64] [69] [70] [71], as shown in Table 20.…”
Section: Figure 32 Time Complexity Graph (Pectoral Muscle Removal Prmentioning
confidence: 96%
“…We believe that rather than focusing on curved boundaries in the processing stage itself, which increases the computation time, this can be tackled using the LUTs to extract the ROIs and regions within the ROIs. Rahimeto, S. et al, [64] in their research proposed an automatic pectoral muscle removal method based on the connected component labeling method. The muscle region was extracted using Otsu's multithresholding method.…”
Section: 06%mentioning
confidence: 99%