A deep learning system to obtain the optimal parameters for a threshold-based breast and dense tissue segmentation

Pérez‐Benito, Francisco Javier; Signol, François; Pérez-Cortés, Juan-Carlos; Fuster-Baggetto, Alejandro; Pollán, Marina; Pérez‐Gómez, Beatriz; Salas-Trejo, Dolores; Casals, María Rosa; Failde, Inmaculada; Llobet, Rafael

doi:10.1016/j.cmpb.2020.105668

Cited by 23 publications

(16 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The different mammogram acquisition devices show huge variability in the quality of mammograms. As demonstrated previously in [ 16 ], this variability was found to be significant and negatively impacted the training of a machine learning model. Therefore, normalization among acquisition devices was performed by applying the following steps: Normalize the pixel values of the image between

.…”

Section: Methodsmentioning

confidence: 54%

See 1 more Smart Citation

Breast Dense Tissue Segmentation with Noisy Labels: A Hybrid Threshold-Based and Mask-Based Approach

et al. 2022

Self Cite

View full text Add to dashboard Cite

Breast density assessed from digital mammograms is a known biomarker related to a higher risk of developing breast cancer. Supervised learning algorithms have been implemented to determine this. However, the performance of these algorithms depends on the quality of the ground-truth information, which expert readers usually provide. These expert labels are noisy approximations to the ground truth, as there is both intra- and inter-observer variability among them. Thus, it is crucial to provide a reliable method to measure breast density from mammograms. This paper presents a fully automated method based on deep learning to estimate breast density, including breast detection, pectoral muscle exclusion, and dense tissue segmentation. We propose a novel confusion matrix (CM)—YNet model for the segmentation step. This architecture includes networks to model each radiologist’s noisy label and gives the estimated ground-truth segmentation as well as two parameters that allow interaction with a threshold-based labeling tool. A multi-center study involving 1785 women whose “for presentation” mammograms were obtained from 11 different medical facilities was performed. A total of 2496 mammograms were used as the training corpus, and 844 formed the testing corpus. Additionally, we included a totally independent dataset from a different center, composed of 381 women with one image per patient. Each mammogram was labeled independently by two expert radiologists using a threshold-based tool. The implemented CM-Ynet model achieved the highest DICE score averaged over both test datasets (0.82±0.14) when compared to the closest dense-tissue segmentation assessment from both radiologists. The level of concordance between the two radiologists showed a DICE score of 0.76±0.17. An automatic breast density estimator based on deep learning exhibited higher performance when compared with two experienced radiologists. This suggests that modeling each radiologist’s label allows for better estimation of the unknown ground-truth segmentation. The advantage of the proposed model is that it also provides the threshold parameters that enable user interaction with a threshold-based tool.

show abstract

.…”

Section: Methodsmentioning

confidence: 54%

“…In a previous study [ 16 ], we introduced a fully automated framework for dense-tissue segmentation. It included breast detection, pectoral muscle exclusion, and dense-tissue segmentation.…”

Section: Introductionmentioning

confidence: 99%

Breast Dense Tissue Segmentation with Noisy Labels: A Hybrid Threshold-Based and Mask-Based Approach

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The histograms of the images may be considered as Probability Density Functions (PDFs) and may serve to measure the variability among gray-level distributions using a methodology based on information geometry [18] . This methodology has been successfully applied to characterize EHR (Electronic Health Record) data [19] , [20] , to assess the variability among patients with different headache pain intensity [21] , or to detect pixel distribution differences among images acquired from different mammographs [22] .…”

Section: Methodsmentioning

confidence: 99%

“…Recent literature has demonstrated the emergence of methodologies useful to reduce the impact of such a bias. Image preprocessing methods [22] or deep learning architectures designed to deal with biased datasets [37] may be a good starting point.…”

Section: Limitations Of the Studymentioning

confidence: 99%

Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients

et al. 2021

Self Cite

View full text Add to dashboard Cite

Chest X-ray images are useful for early COVID-19 diagnosis with the advantage that X-ray devices are already available in health centers and images are obtained immediately. Some datasets containing X-ray images with cases (pneumonia or COVID-19) and controls have been made available to develop machine-learning-based methods to aid in diagnosing the disease. However, these datasets are mainly composed of different sources coming from pre-COVID-19 datasets and COVID-19 datasets. Particularly, we have detected a significant bias in some of the released datasets used to train and test diagnostic systems, which might imply that the results published are optimistic and may overestimate the actual predictive capacity of the techniques proposed. In this paper, we analyze the existing bias in some commonly used datasets and propose a series of preliminary steps to carry out before the classic machine learning pipeline in order to detect possible biases, to avoid them if possible and to report results that are more representative of the actual predictive power of the methods under analysis.

show abstract

“…However, it had a high requirement for system operation performance. Mask R-CNN was also used to detect key points of tick marks and pointers, then used the intersection of circle and straight line to calculate the reading [11], but the algorithm was complex, and computationally intensive.…”

Section: Introductionmentioning

confidence: 99%

A Pointer Type Instrument Intelligent Reading System Design Based on Convolutional Neural Networks

2020

View full text Add to dashboard Cite

The pointer instrument has the advantages of being simple, reliable, stable, easy to maintain, having strong anti-interference properties, and so on, which has long occupied the main position of electrical and electric instruments. Though the pointer instrument structure is simple, it is not convenient for real-time reading of measurements. In this paper, a RK3399 microcomputer was used for real-time intelligent reading of a pointer instrument using a camera. Firstly, a histogram normalization transform algorithm was used to optimize the brightness and enhance the contrast of images; then, the feature recognition algorithm You Only Look Once 3rd (YOLOv3) was used to detect and capture the panel area in images; and Convolutional Neural Networks were used to read and predict the characteristic images. Finally, predicted results were uploaded to a server. The system realized automatic identification, numerical reading, an intelligent online reading of pointer data, which has high feasibility and practical value. The experimental results show that the recognition rate of this system was 98.71% and the reading accuracy was 97.42%. What is more, the system can accurately locate the pointer-type instrument area and read corresponding values with simple operating conditions. This achievement meets the demand of real-time readings for analog instruments.

show abstract

A deep learning system to obtain the optimal parameters for a threshold-based breast and dense tissue segmentation

Abstract: Background and Objective: Breast cancer is the most frequent cancer in women. The Spanish healthcare network established population-based screening programs in all Autonomous Communities, where mammograms of asymptomatic women are taken with early diagnosis purposes. Breast density

Cited by 23 publications

References 46 publications

Breast Dense Tissue Segmentation with Noisy Labels: A Hybrid Threshold-Based and Mask-Based Approach

Breast Dense Tissue Segmentation with Noisy Labels: A Hybrid Threshold-Based and Mask-Based Approach

Bias Analysis on Public X-Ray Image Datasets of Pneumonia and COVID-19 Patients

A Pointer Type Instrument Intelligent Reading System Design Based on Convolutional Neural Networks

Contact Info

Product

Resources

About