Search

Automatic differentiation of benign and malignant breast lesions on multiple DCE-MRI series is a challenging task. The performance of the Convolutional Neural Networks (CNNs) based methods is severely affected when the number of DCE-MRI series is inadequate or inconsistent. This paper is motivated by the need of capturing spatial-temporal features from consistent DCE-MRI series for most CNN-based classification methods, and aims at designing an interpolation network that can enlarge the DCE-MRI series. Therefore, our method achieves the objective of breast lesion classification for inconsistent DCE-MRI series with a two-stage method, i.e., DCE-MRI interpolation and classification. Inspired by the learning-based data augmentation, we propose a variable-length multiple DCE-MRI series interpolation method using learned transformations to enlarge DCE-MRI series. Specifically, the forward and backward contrast transformations are learned to estimate the kinetic and spatial variation between different DCE-MRI series. Then, an adaptive warping method is proposed to generate multiple interpolated DCE-MRI series. Finally, the spatial-temporal features are extracted by a new two-stream network from the interpolated DCE-MRI and they are further used to classify breast lesions. We justify the proposed method through extensive experiments using 1223 DCE-MRI slices. Comparing to other methods, it achieves better results on both single series interpolation and multiple series interpolation. The interpolated DCE-MRI greatly improves the classification accuracy nearly by 5% and the best accuracy is 81.9%. [ABSTRACT FROM AUTHOR]

Multi-sequence MRI plays a crucial role in the effective segmentation of breast tumors, contributing to accurate clinical diagnosis and treatment. However, the problem of missing certain sequence images may occur in clinical practice, leading to a potential impact on network performance. In medical imaging tasks, researchers are prone to ignore the correlation between different sequences, resulting in lack of expression of the extracted features. To address these problems, we propose the Feature-enhanced Multi-sequence Feature Fusion Network (FMFF-Net), which fuses information from dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI) sequences to improve the accuracy of breast tumor segmentation. Utilizing an attention mechanism and adversarial learning, FMFF-Net identifies potential mappings and relationships between sequences, generating features for missing sequences and enhancing feature representation. The network incorporates a High-Frequency Edge Attention Block (HFAB) to accentuate tumor edge details, leading to more precise segmentation. Tested on a dataset of 98 high-risk breast cancer MRI images, FMFF-Net demonstrated superior performance, with a Dice Similarity Coefficient (DSC) of 83.6%, Intersection over Union (IoU) of 73.4%, F1 score of 88.1%, and Sensitivity of 74.1%. Comparative analysis against mainstream segmentation methods revealed that our proposed FMFF-Net exhibits a competitive edge in the field of breast tumor segmentation. • Accurately segmenting breast tumors with limited blood supply in the absence of multiple MRI inputs. • The multi-sequence fusion module effectively integrates complementary information to extract detailed features from multi-sequences. • Complementary fusion of multi-sequences improves tumor segmentation accuracy over single-sequence methods. • Experiments show that our network effectively improves the segmentation performance of breast tumors compared to state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

In breast tumor diagnostic tasks, joint analysis of multiple sequences of MRI can improve the accuracy of diagnosis. More and more studies focus on the correlation between sequences and try applying multiple MRI sequences to computer-aided diagnosis. The deep neural network plays a vital role in this process because of its good feature extraction ability. However, the inevitable presence of missing or unavailable sequences in clinical can lead to degraded performance or even failure of multi-input networks. The key problem solved in this paper is to ensure the diagnostic accuracy of the network despite the presence of missing input sequences. A new breast tumor diagnosis deep learning method, ESF-NET, is proposed. First, ESF-NET combines the attention mechanism for adversarial learning to obtain the potential mapping and relationship between sequences and completes the generation of features for the missing sequences. Then the extended sequence fusion module with different fusion strategies is designed, which makes the final fusion results benefit from the feature enhancement resulting from all fusion strategies. These strategies can be adaptively weighted. We apply EST-NET to a dataset of MRI images of 98 women at high risk of breast cancer, including 33 benign and 65 malignant lesions. Each patient data contains several two-dimensional slices with different axial planes, the dataset consists of 2245 slices. In the presence of sequence missing, ESF-NET achieves a diagnostic accuracy of 85.61% at the slice level and 89.66% at the patient level, an improvement of 8.39% compared to using only a single sequence. • A deep learning network for breast tumor diagnosis with missing MR sequence. • An extended sequence fusion block with multiple strategies for feature fusion. • Generation of missing sequence features improves the diagnostic accuracy of network. • State-of-the-art results are obtained on a multi-sequence breast MRI dataset. [ABSTRACT FROM AUTHOR]

Abstract: Objective: To retrospectively evaluate the diagnostic abilities of 2 post-processing methods provided by GE Senographe DS system, tissue equalization (TE) and premium view (PV) in full field digital mammography (FFDM). Materials and methods: In accordance with the ethical standards of the World Medical Association, this study was approved by regional ethics committee and signed informed patient consents were obtained. We retrospectively reviewed digital mammograms from 101 women (mean age, 47 years; range, 23–81 years) in the modes of TE and PV, respectively. Three radiologists, fully blinded to the post-processing methods, all patient clinical information and histologic results, read images by using objective image interpretation criteria for diagnostic information end points such as lesion border delineation, definition of disease extent, visualization of internal and surrounding morphologic features of the lesions. Also, overall diagnostic impression in terms of lesion conspicuity, detectability and diagnostic confidence was assessed. Between-group comparisons were performed with Wilcoxon signed rank test. Results: Readers 1, 2, and 3 demonstrated significant overall better impression of PV in 29, 27, and 24 patients, compared with that for TE in 12, 13, and 11 patients, respectively (p <0.05). Significant (p <0.05) better impression of PV was also demonstrated for diagnostic information end points. Importantly, PV proved to be more sensitive than TE while detecting malignant lesions in dense breast rather than benign lesions and malignancy in non-dense breast (p <0.01). Conclusion: PV compared with TE provides marked better diagnostic information in FFDM, particularly for patients with malignancy in dense breast. [ABSTRACT FROM AUTHOR]

• M2D3D-MC focuses on lesion segmentation with a limited number of DCE-MRI slices. • 2D and 3D operations are deeply integrated in an end-to-end manner. • Multi-scale block is inserted into U-Net to obtain multi-scale information. • The spatial–temporal features of DCE-MRI is learned with the multi-channel image. • The segmentation performance of M2D3D-MC is better than other methods Breast lesion segmentation in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is an essential step for breast cancer analysis. 2D networks have the advantages of low inference time and greater transfer-ability while 3D networks are superior in learning the contextual information in volumetric data. However, the performance of the 3D network is severely affected when MRI has a low-resolution ratio in the third dimension. In order to integrate the advantages of 2D and 3D networks, we propose a mixed 2D and 3D convolutional network with multi-scale context (M2D3D-MC) for lesion segmentation in breast DCE-MRI with a limited number of axial slices in the scans. Through serial 2D and 3D convolution, the mixed 2D and 3D convolution module has the ability to exploit the contexts between adjacent slices. And considering the diversity of shape and size for breast lesions, we introduce a multi-scale context extractor block consisting of atrous convolutions with different sampling rates to extract multi-scale image features. We justify the proposed method through extensive experiments on 90 MRI studies. Compared with both 2D and 3D networks, M2D3D-MC achieves the best performance with DSC, SEN, and PPV of 76.4%, 75.9%, and 82.4% respectively. A new paradigm is provided for breast lesion segmentation by combining 2D and 3D convolutions to exploit the contextual information. It demonstrates stronger performance in mixed 2D and 3D model given the limited number of axial slices. Our investigation also reveals that the multi-scale context block is effective for breast lesion segmentation. [ABSTRACT FROM AUTHOR]

The classification of benign versus malignant breast lesions on multi-sequence Magnetic Resonance Imaging (MRI) is a challenging task since breast lesions are heterogeneous and complex. Recently, deep learning methods have been used for breast lesion diagnosis with raw image input. However, without the guidance of domain knowledge, these data-driven methods cannot ensure that the features extracted from images are comprehensive for breast cancer diagnosis. Specifically, these features are difficult to relate to clinically relevant phenomena. Inspired by the cognition process of radiologists, we propose a Knowledge-driven Feature Learning and Integration (KFLI) framework, to discriminate between benign and malignant breast lesions using Multi-sequences MRI. Starting from sequence division based on characteristics, we use domain knowledge to guide the feature learning process so that the feature vectors of sub-sequence are constrained to lie in characteristic-related semantic space. Then, different deep networks are designed to extract various sub-sequence features. Furthermore, a weighting module is employed for the integration of the features extracted from different sub-sequence images adaptively. The KFLI is a domain knowledge and deep network ensemble, which can extract sufficient and effective features from each sub-sequence for a comprehensive diagnosis of breast cancer. Experiments on 100 MRI studies have demonstrated that the KFLI achieves sensitivity, specificity, and accuracy of 84.6%, 85.7% and 85.0%, respectively, which outperforms other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]