Masako Kataoka1, Takuto Fukutome2, Tomohiro Takemura2, Kango Kawase2, Kojiro Yano3, Maya Honda4, Mami Iima4, Akane Ohashi4, Masakazu Toi5, and Kaori Togashi4
1Radiology (Diagnostic Imaging and Nuclear Medicine), Kyoto Univ. Hospital, Kyoto, Japan, 2Faculty of Medicine, Kyoto University, Kyoto, Japan, 3Osaka Institute of Technology, Osaka, Japan, 4Kyoto University Graduate School of Medicine, Kyoto, Japan, 5Kyoto University, Kyoto, Japan
Synopsis
We aimed to develop a
system for automatic segmentation of tumor-related vessels on ultrafast dynamic
contrast (UF-DCE) MRI using U-net. Training set consisted of image dataset of
20 MIP images obtained from -15 to +60 sec after contrast injection from 59
patients. Exclusion
criteria were those with poor image quality. The dice similarity coefficient
was above 0.8 for training set, 0.6 for validation set. Careful analysis of
failed cases revealed that inaccurate segmentation of the vessel were caused by
low-contrast images, noisy-images, artifact, bright skin line due to incomplete
fat suppression, and non-mass enhancement that may mimic vasculature.
INTRODUCTION
Ultrafast dynamic contrast enhanced (UF-DCE)-MRI of
the breast
captures very early phase of contrast enhancement of the lesion at a temporal
resolution of 4 seconds. This state-of-the-art DCE technique allows us to
evaluate vascularity of the lesion through up-slope kinetic information as well
as vessels around the lesion, which are developed in case of aggressive malignant
lesions [1]. The interval between feeding artery enhancement and drainage vein
enhancement is associated with breast cancers. Breast cancer induces angiogenesis
and this leads to tumor progression. Therefore,
it is important to evaluate tumor-related vessels. Visual evaluation failed to
capture quantifiable nature of the vessels. Manual segmentation are
time-consuming and subjective, suggesting the need of quantification [2]. Deep convolutional
neural network is one of the pixel-based machine learning methods. Among
various network, U-Net is a fully convolutional network and has been used for
image segmentation including breast fibrograndular tissues. In order to
establish automatic system to quantify tumor-related
vascularity, we aimed to develop U-Net system to automatically
segment breast tumor-related vessels on UF-DCE MRI separate from the breast tumor itself. METHODS
The study population consisted of female patients who
underwent breast MRI with UF-DCE-MRI from December 2015 to March 2018 due to
known / suspected breast lesions. Images
with poor image quality and without any enhancing lesion were excluded. For
malignant lesions, In total, 46 patients who underwent UF-DCE MRI were included.
MRI
procotol: MR images were obtained with 3T MR unit (Prisma/Skyra,
Siemens). Gadobutrol/Gadoteridol was intravenously infused (2.0ml/sec). UF-DCE MRI
(15sec before -60sec after the contrast injection, 3.7sec×20frames) was
followed by standard DCE-MRI. UF-DCE-MRI was acquired by a prototype based on
the 3D gradient-echo VIBE sequence using a CS reconstruction (TR/TE 5.0/2.5, FA
15, FOV 360×360mm, matrix 384×269, thickness 2.5mm, CS acceleration=16.5), with
30 iterations. Based on these UF-DCE MRI, 19 subtracted MIP images per patient
were computed.
Image
segmentation and training for U-Net:
Out of 19 subtracted MIP
images, the first 5-6 images were excluded from the analysis because no enhancing
lesions were identified. The training data consisted of 364 MIP
images from 32 patients for training and 174 MIP images from 14 patients for
validation.The main lesion(s) and vessels were manually segmented by three readers (supervised by an expert breast radiologist). These segmented
areas were exported as layers, then trimmed (fig.1). Images were trimmed to include tumor
and ipsilateral vessels, and exclude chest wall. For current analysis, original images and
labelled vessel images were used. The trimmed images were 128 x 128 pixel batch
images per lesions. Image augmentation by
horizontal and vertical flips were used for training set (fig.2).
Deep learning segmentation was
performed using the U-Net, consisting of convolution and max-pooling layer at
the descending part, while convolution and up-sampling layer at the ascending
part. The manually segmented images were used as a ground truth. The
performance of segmentation was evaluated using the overall accuracy per pixel
and the Dice Similarity Coefficient (DSC). Visual inspection of the segmented
image created by U-Net were also performed. RESULTS
Initial training using accuracy as
evaluation function resulted in over 0.9 accuracy. However, actual vessel
images were not ideal with over and under estimation of the segmented area. For
more strict training, the further analysis used DSC as evaluation function,
and “1-DCS” as loss function. Final model achieved a DSC of more than 0.8 for
training set, yet DSC of validation set remained approximately 0.6.
Cases of
low DSC with “unsuccessful” segmentation were analyzed for possible reasons. Vessel-related
reasons included small vessels that just started to enhance, small and tortuous
vessels, vessels running over or close to the main lesion, the vessel adjacent
to the non-mass type lesion. Non-vessel-related reasons included severe motion
artifact, incomplete fat suppression, marked background parenchymal enhancement.
Some representative cases comparing original and automatically segmented images of the tumor and
tumor-related vessels were shown in figure 3-5. In general, major thick vessels were successfully identified, while smaller thinner vessels were not detected by the trained automatic segmentation system. DISCUSSION and CONCLUSION
This trial of automatic segmentation
using U-Net demonstrated that automatic segmentation and quantification of
tumor –related vessels is possible, yet challenging. The vessels in the breast are generally small. In addition, experimental
results showed that tumor-related vessels are tortuous and incomplete, that
makes segmentation harder. Further training to improve accuracy include increase the sample size, with more weight to identify thinner vessels. Acknowledgements
Dominik Nickel and Yuta Urushibata from Siemens for their technical support. KAKENHI-JP 15K09922References
1. Onishi, N., et al., Ultrafast dynamic
contrast-enhanced mri of the breast using compressed sensing: breast cancer
diagnosis based on separate visualization of breast arteries and veins. J Magn
Reson Imaging, 2018. 47(1): p. 97-104
2. Wu, C., et al., Quantitative analysis of vascular
properties derived from ultrafast DCE-MRI to discriminate malignant and benign
breast tumors. Magn Reson Med, 2019. 81(3): p. 2147-2160.