RECORD
Automated Detection of Individual Micro-calcifications from Mammograms using a Multi-stage Cascade Approach
Computer Vision and Pattern Recognition · Submitted 7 Oct 2016
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim These results are significantly more accurate than the current state of the art, which has a TPR of less than 1\% at one FPI and a TPR of 10\% at 10 FPI.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
In mammography, the efficacy of computer-aided detection methods depends, in part, on the robust localisation of micro-calcifications ($\mu$C). Currently, the most effective methods are based on three steps: 1) detection of individual $\mu$C candidates, 2) clustering of individual $\mu$C candidates, and 3) classification of $\mu$C clusters. Where the second step is motivated both to reduce the number of false positive detections from the first step and on the evidence that malignancy depends on a relatively large number of $\mu$C detections within a certain area. In this paper, we propose a novel approach to $\mu$C detection, consisting of the detection \emph{and} classification of individual $\mu$C candidates, using shape and appearance features, using a cascade of boosting classifiers. The final step in our approach then clusters the remaining individual $\mu$C candidates. The main advantage of this approach lies in its ability to reject a significant number of false positive $\mu$C candidates compared to previously proposed methods. Specifically, on the INbreast dataset, we show that our approach has a true positive rate (TPR) for individual $\mu$Cs of 40\% at one false positive per image (FPI) and a TPR of 80\% at 10 FPI. These results are significantly more accurate than the current state of the art, which has a TPR of less than 1\% at one FPI and a TPR of 10\% at 10 FPI. Our results are competitive with the state of the art at the subsequent stage of detecting clusters of $\mu$Cs.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | In mammography, the efficacy of computer-aided detection methods depends, in part, on the robust localisation of micro-calcifications ($\mu$C). | background 1.00 | 0.06 | 0.02 | asserted 0.89 |
| s1 | Currently, the most effective methods are based on three steps: 1) detection of individual $\mu$C candidates, 2) clustering of individual $\mu$C candidates, and 3) classification of $\mu$C clusters. | background 1.00 | 0.04 | 0.03 | asserted 1.00 |
| s2 | Where the second step is motivated both to reduce the number of false positive detections from the first step and on the evidence that malignancy depends on a relatively large number of $\mu$C detections within a certain area. | background 0.99 | 0.06 | 0.03 | asserted 0.99 |
| s3 | In this paper, we propose a novel approach to $\mu$C detection, consisting of the detection \emph{and} classification of individual $\mu$C candidates, using shape and appearance features, using a cascade of boosting classifiers. | contribution 0.73 | 0.83 | 0.10 | asserted 0.98 |
| s4 | The final step in our approach then clusters the remaining individual $\mu$C candidates. | method 0.98 | 0.64 | 0.04 | asserted 0.99 |
| s5 | The main advantage of this approach lies in its ability to reject a significant number of false positive $\mu$C candidates compared to previously proposed methods. | interpretation 0.66 | 0.58 | 0.55 | asserted 0.98 |
| s6 | Specifically, on the INbreast dataset, we show that our approach has a true positive rate (TPR) for individual $\mu$Cs of 40\% at one false positive per image (FPI) and a TPR of 80\% at 10 FPI. | result 1.00 | 0.97 | 0.15 | asserted 1.00 |
| s7 | These results are significantly more accurate than the current state of the art, which has a TPR of less than 1\% at one FPI and a TPR of 10\% at 10 FPI. | result 0.80 | 0.30 | 0.28 | asserted 1.00 |
| s8 | Our results are competitive with the state of the art at the subsequent stage of detecting clusters of $\mu$Cs. | result 0.82 | 0.84 | 0.11 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
In mammography, the efficacy of computer-aided detection methods depends, in part, on the robust localisation of micro-calcifications ($\mu$C). Currently, the most effective methods are based on three steps: 1) detection of individual $\mu$C candidates, 2) clustering of individual $\mu$C candidates, and 3) classification of $\mu$C clusters. Where the second step is motivated both to reduce the number of false positive detections from the first step and on the evidence that malignancy depends on a relatively large number of $\mu$C detections within a certain area. In this paper, we propose a novel approach to $\mu$C detection, consisting of the detection \emph{and} classification of individual $\mu$C candidates, using shape and appearance features, using a cascade of boosting classifiers. The final step in our approach then clusters the remaining individual $\mu$C candidates. The main advantage of this approach lies in its ability to reject a significant number of false positive $\mu$C candidates compared to previously proposed methods. Specifically, on the INbreast dataset, we show that our approach has a true positive rate (TPR) for individual $\mu$Cs of 40\% at one false positive per image (FPI) and a TPR of 80\% at 10 FPI. These results are significantly more accurate than the current state of the art, which has a TPR of less than 1\% at one FPI and a TPR of 10\% at 10 FPI. Our results are competitive with the state of the art at the subsequent stage of detecting clusters of $\mu$Cs.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.