TY - JOUR
T1 - Breast ultrasound lesions recognition:
T2 - end-to-end deep learning approaches
AU - Hoon Yap, Moi
AU - Goyal, Manu
AU - Osman, Fatima
AU - Martí, Robert
AU - Denton, Erika
AU - Juette, Arne
AU - Zwiggelaar, Reyer
PY - 2018/10/10
Y1 - 2018/10/10
N2 - Multistage processing of automated breast ultrasound lesions recognition is dependent on the performance
of prior stages. To improve the current state of the art, we propose the use of end-to-end deep learning
approaches using fully convolutional networks (FCNs), namely FCN-AlexNet, FCN-32s, FCN-16s, and FCN-8s
for semantic segmentation of breast lesions. We use pretrained models based on ImageNet and transfer learning
to overcome the issue of data deficiency. We evaluate our results on two datasets, which consist of a total of
113 malignant and 356 benign lesions. To assess the performance, we conduct fivefold cross validation using
the following split: 70% for training data, 10% for validation data, and 20% testing data. The results showed that
our proposed method performed better on benign lesions, with a top “mean Dice” score of 0.7626 with FCN-16s,
when compared with the malignant lesions with a top mean Dice score of 0.5484 with FCN-8s. When considering
the number of images with Dice score >0.5, 89.6% of the benign lesions were successfully segmented and
correctly recognised, whereas 60.6% of the malignant lesions were successfully segmented and correctly recognized.
We conclude the paper by addressing the future challenges of the work.
AB - Multistage processing of automated breast ultrasound lesions recognition is dependent on the performance
of prior stages. To improve the current state of the art, we propose the use of end-to-end deep learning
approaches using fully convolutional networks (FCNs), namely FCN-AlexNet, FCN-32s, FCN-16s, and FCN-8s
for semantic segmentation of breast lesions. We use pretrained models based on ImageNet and transfer learning
to overcome the issue of data deficiency. We evaluate our results on two datasets, which consist of a total of
113 malignant and 356 benign lesions. To assess the performance, we conduct fivefold cross validation using
the following split: 70% for training data, 10% for validation data, and 20% testing data. The results showed that
our proposed method performed better on benign lesions, with a top “mean Dice” score of 0.7626 with FCN-16s,
when compared with the malignant lesions with a top mean Dice score of 0.5484 with FCN-8s. When considering
the number of images with Dice score >0.5, 89.6% of the benign lesions were successfully segmented and
correctly recognised, whereas 60.6% of the malignant lesions were successfully segmented and correctly recognized.
We conclude the paper by addressing the future challenges of the work.
KW - image segmentation
KW - breast
KW - ultrasonography
KW - data modelling
KW - image classification
KW - tumor growth modelling
KW - RGB color model
U2 - 10.1117/1.JMI.6.1.011007
DO - 10.1117/1.JMI.6.1.011007
M3 - Article
C2 - 30310824
SN - 2329-4310
VL - 6
JO - Journal of Medical Imaging
JF - Journal of Medical Imaging
IS - 1
M1 - 011007
ER -