Segmentation of whole breast and fibroglandular tissue using nnU-Net in dynamic contrast enhanced MR images

Huo, Lu; Hu, Xiaoxin; Xiao, Qin; Gu, Yajia; Chu, Xu; Jiang, Luan

doi:10.1016/j.mri.2021.06.017

Cited by 35 publications

(22 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to Huo et al [ 11 ], we are using a one-stage approach with three classes: background, breast and FGT. The advantage of this approach compared to a two-stage approach is the faster inference and the fine-tuning of a single network if re-training is needed.…”

Section: Discussionmentioning

confidence: 99%

“…Zhang et al [ 10 ] proved the robustness of the U-Net architecture over a test set composed of WOFS breast DCE-MRI acquired from different scanners. More recently, Huo et al [ 11 ] made use of the popular open-source framework nnUNet [ 12 ] to confirm the great potential of deep learning approaches for the task of breast and FGT segmentation in breast DCE-MRI acquisitions with fat suppression (FS).…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we present a simple yet efficient means of exploiting the datasets available in order to make the segmentation network robust to different breast MRI T1 sequences, without the need of additional annotations or re-training. We follow the approach of Huo et al [ 11 ], employing the nnUNet framework, and by using a dataset of breast DCE-MRI acquired via the Dixon method, we train a 3D U-Net on both FS and WOFS acquisitions with the same ground truth annotations. We found that this approach allows the network to robustly handle both FS and WOFS acquisitions at inference time, without explicit information about the type of image, while needing only half the amount of manual annotation for training.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI

et al. 2022

View full text Add to dashboard Cite

Automatic breast and fibro-glandular tissue (FGT) segmentation in breast MRI allows for the efficient and accurate calculation of breast density. The U-Net architecture, either 2D or 3D, has already been shown to be effective at addressing the segmentation problem in breast MRI. However, the lack of publicly available datasets for this task has forced several authors to rely on internal datasets composed of either acquisitions without fat suppression (WOFS) or with fat suppression (FS), limiting the generalization of the approach. To solve this problem, we propose a data-centric approach, efficiently using the data available. By collecting a dataset of T1-weighted breast MRI acquisitions acquired with the use of the Dixon method, we train a network on both T1 WOFS and FS acquisitions while utilizing the same ground truth segmentation. Using the “plug-and-play” framework nnUNet, we achieve, on our internal test set, a Dice Similarity Coefficient (DSC) of 0.96 and 0.91 for WOFS breast and FGT segmentation and 0.95 and 0.86 for FS breast and FGT segmentation, respectively. On an external, publicly available dataset, a panel of breast radiologists rated the quality of our automatic segmentation with an average of 3.73 on a four-point scale, with an average percentage agreement of 67.5%.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The size of the augmented dataset is 10 times larger than the original training dataset. The U-Net loss function L total was determined as the sum of the dice loss L Dice and the cross-entropy loss L CE ( 32 ). The hyperparameter learning rate of the optimizer was set to 0.01.…”

Section: Methodsmentioning

confidence: 99%

Contrast-Enhanced Spectral Mammography-Based Prediction of Non-Sentinel Lymph Node Metastasis and Axillary Tumor Burden in Patients With Breast Cancer

Guo

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

PurposeTo establish and evaluate non-invasive models for estimating the risk of non-sentinel lymph node (NSLN) metastasis and axillary tumor burden among breast cancer patients with 1–2 positive sentinel lymph nodes (SLNs).Materials and MethodsBreast cancer patients with 1–2 positive SLNs who underwent axillary lymph node dissection (ALND) and contrast-enhanced spectral mammography (CESM) examination were enrolled between 2018 and 2021. CESM-based radiomics and deep learning features of tumors were extracted. The correlation analysis, least absolute shrinkage and selection operator (LASSO), and analysis of variance (ANOVA) were used for further feature selection. Models based on the selected features and clinical risk factors were constructed with multivariate logistic regression. Finally, two radiomics nomograms were proposed for predicting NSLN metastasis and the probability of high axillary tumor burden.ResultsA total of 182 patients [53.13 years ± 10.03 (standard deviation)] were included. For predicting the NSLN metastasis status, the radiomics nomogram built by 5 selected radiomics features and 3 clinical risk factors including the number of positive SLNs, ratio of positive SLNs, and lymphovascular invasion (LVI), achieved the area under the receiver operating characteristic curve (AUC) of 0.85 [95% confidence interval (CI): 0.71–0.99] in the testing set and 0.82 (95% CI: 0.67–0.97) in the temporal validation cohort. For predicting the high axillary tumor burden, the AUC values of the developed radiomics nomogram are 0.82 (95% CI: 0.66–0.97) in the testing set and 0.77 (95% CI: 0.62–0.93) in the temporal validation cohort.DiscussionCESM images contain useful information for predicting NSLN metastasis and axillary tumor burden of breast cancer patients. Radiomics can inspire the potential of CESM images to identify lymph node metastasis and improve predictive performance.

show abstract

“…nnU-Net is a newly proposed model for medical segmentation tasks [18], and its core design idea is to obtain more reliable segmentation results for various datasets through adaptive preprocessing and model training strategies, rather than manual parameter tuning [18,19]. Owing to its unique advantages, it has been broadly utilized in medical image segmentation, such as coronavirus disease 2019 segmentation [20], kidney and kidney tumor segmentation [21], and breast and fibroglandular tissue segmentation [22]. Until now, no relevant research has been conducted to apply nnU-Net for the segmentation of basal cisterns.…”

Section: Introductionmentioning

confidence: 99%

MRI-based radiomics signature for identification of invisible basal cisterns changes in tuberculous meningitis: a preliminary multicenter study

Liu

et al. 2022

Eur Radiol

View full text Add to dashboard Cite

Objective To develop and evaluate a radiomics signature based on magnetic resonance imaging (MRI) from multicenter datasets for identification of invisible basal cisterns changes in tuberculous meningitis (TBM) patients. Methods Our retrospective study enrolled 184 TBM patients and 187 non-TBM controls from 3 Chinese hospitals (training dataset, 158 TBM patients and 159 non-TBM controls; testing dataset, 26 TBM patients and 28 non-TBM controls). nnU-Net was used to segment basal cisterns in fluid-attenuated inversion recovery (FLAIR) images. Subsequently, radiomics features were extracted from segmented basal cisterns in FLAIR and T2-weighted (T2W) images. Feature selection was carried out in three steps. Support vector machine (SVM) and logistic regression (LR) classifiers were applied to construct the radiomics signature to directly identify basal cisterns changes in TBM patients. Finally, the diagnostic performance was evaluated by the receiver operating characteristic (ROC) curve analysis, calibration curve, and decision curve analysis (DCA). ResultsThe segmentation model achieved the mean Dice coefficients of 0.920 and 0.727 in the training and testing datasets, respectively. The SVM model with 7 T2WI-based radiomics features achieved best discrimination capability for basal cisterns changes with an AUC of 0.796 (95% CI, 0.744-0.847) in the training dataset, and an AUC of 0.751 (95% CI, 0.617-0.886) with good calibration in the testing dataset. DCA confirmed its clinical usefulness. Conclusion The T2WI-based radiomics signature combined with deep learning segmentation could provide a fully automatic, non-invasive tool to identify invisible changes of basal cisterns, which has the potential to assist in the diagnosis of TBM. Key Points• The T2WI-based radiomics signature was useful for identifying invisible basal cistern changes in TBM.• The nnU-Net model achieved acceptable results for the auto-segmentation of basal cisterns.• Combining radiomics and deep learning segmentation provided an automatic, non-invasive approach to assist in the diagnosis of TBM.

show abstract

Segmentation of whole breast and fibroglandular tissue using nnU-Net in dynamic contrast enhanced MR images

Cited by 35 publications

References 26 publications

Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI

Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI

Contrast-Enhanced Spectral Mammography-Based Prediction of Non-Sentinel Lymph Node Metastasis and Axillary Tumor Burden in Patients With Breast Cancer

MRI-based radiomics signature for identification of invisible basal cisterns changes in tuberculous meningitis: a preliminary multicenter study

Contact Info

Product

Resources

About