Automatic Breast Lesion Detection in Ultrafast DCE-MRI Using Deep Learning

  title={Automatic Breast Lesion Detection in Ultrafast DCE-MRI Using Deep Learning},
  author={Fazael Ayatollahi and Shahriar Baradaran Shokouhi and Ritse M. Mann and Jonas Teuwen},
  journal={Medical physics},
PURPOSE We propose a deep learning-based computer-aided detection (CADe) method to detect breast lesions in ultrafast DCE-MRI sequences. This method uses both the three-dimensional spatial information and temporal information obtained from the early-phase of the dynamic acquisition. METHODS The proposed CADe method, based on a modified 3D RetinaNet model, operates on ultrafast T1 weighted sequences, which are preprocessed for motion compensation, temporal normalization, and are cropped before… 

Figures and Tables from this paper

Semi-supervised Breast Lesion Segmentation using Local Cross Triplet Loss for Ultrafast Dynamic Contrast-Enhanced MRI

This work proposes a semi-supervised segmentation approach that can be trained with small amounts of annotations for ultrafast DCE-MRI, and presents a novel loss function that distinguishes breast lesions from non-lesions based on triple loss.

The Role of Deep Learning in Advancing Breast Cancer Detection Using Different Imaging Modalities: A Systematic Review

This review focuses first on the introduction of various breast cancer imaging modalities and their available public datasets, then on proposing the most recent studies considering deep-learning-based models for breast cancer analysis, and systemically summarizes various Imaging modalities, relevant public datasets), deep learning architectures used for different imaging modality, model performances for different tasks such as classification and segmentation, and research directions.

Application of Deep Learning in Breast Cancer Imaging.

An overview of the current state of deep learning research in breast cancer imaging is given, showing similar and even better performances of DL algorithms compared to radiologists, although it is clear that large trials are needed, especially for ultrasound and magnetic resonance imaging, to exactly determine the added value of DL in breast Cancer imaging.

A Survey of Deep Learning Models for Medical Image Analysis

This study provides an overview of various technologies used in Deep Learning in medical imagery and gives a brief idea about their performance.

Validation of Combined Deep Learning Triaging and Computer-Aided Diagnosis in 2901 Breast MRI Examinations From the Second Screening Round of the Dense Tissue and Early Breast Neoplasm Screening Trial.

The combined application of CAT and CAD showed potential to reduce workload of radiologists and to reduce number of biopsies on benign lesions in the second screening round of the DENSE trial, without missing cancer.

Past, Present, and Future of Machine Learning and Artificial Intelligence for Breast Cancer Screening

Before AI is used as an independent, autonomous reader, various challenges need to be addressed, including explainability and interpretability, in addition to repeatability and generalizability, to ensure that AI will provide a significant clinical benefit to breast cancer screening across all populations.

Development and validation of a deep learning model for breast lesion segmentation and characterization in multiparametric MRI

The deep learning computer-aided diagnosis (CADx) model developed significantly improved specificity and achieved comparable accuracy to the radiologists with promise for clinical application to provide preliminary diagnoses.



Fully automated detection of breast cancer in screening MRI using convolutional neural networks

A CADe system that is able to exploit the spatial information obtained from the early-phase scans and can be used in screening programs where abbreviated MRI protocols are used is developed.

Deep Reinforcement Learning for Active Breast Lesion Detection from DCE-MRI

The deep Q-network approach is extended, previously demonstrated on simpler problems such as anatomical landmark detection, in order to detect lesions that have a significant variation in shape, appearance, location and size.

Automated Characterization of Breast Lesions Imaged With an Ultrafast DCE-MR Protocol

Novel features extracted from the kinetics of contrast agent uptake imaged by a short (100 s) view-sharing MRI protocol are introduced, and how these features measure up to commonly used features for regular DCE-MRI of the breast is investigated.

Automated localization of breast cancer in DCE-MRI

Hybrid Mass Detection in Breast MRI Combining Unsupervised Saliency Analysis and Deep Learning

A hybrid mass-detection algorithm that combines unsupervised candidate detection with deep learning-based classification and a novel multi-channel image representation is described, which achieved higher classification performance compared to single-channel images.

Hierarchical Convolutional Neural Networks for Segmentation of Breast Tumors in MRI With Application to Radiogenomics

This work proposes a mask-guided hierarchical learning (MHL) framework for breast tumor segmentation via fully convolutional networks (FCN), and develops an FCN model to generate a 3D breast mask as the region of interest (ROI) for each image, to remove confounding information from input DCE-MR images.

A computer-aided diagnosis system for breast DCE-MRI at high spatiotemporal resolution.

A computer-aided diagnosis system for characterization of breast lesions imaged with high spatiotemporal resolution DCE-MRI of the breast which outperforms a previously proposed system in classifying benign and malignant lesions, while it requires less user interactions.

Artificial Intelligence–Based Classification of Breast Lesions Imaged With a Multiparametric Breast MRI Protocol With Ultrafast DCE-MRI, T2, and DWI

Use of adjunct imaging and PI has a significant contribution in diagnostic performance of ultrafast breast MRI and the developed AI system for interpretation of multiparametric ultra fast breast MRI may improve specificity.

Differentiating benign and malignant mass and non-mass lesions in breast DCE-MRI using normalized frequency-based features

A new computer-aided diagnosis (CADx) to distinguish between malign and benign mass and non-mass lesions in breast DCE-MRI is proposed and the combination of normalized frequency-based features and three-dimensional shape descriptors improves the CADx performance.