Deep learning achieves radiologist-level performance of tumor segmentation in breast MRI

09/21/2020
by   Lukas Hirsch, et al.
22

Purpose: The goal of this research was to develop a deep network architecture that achieves fully-automated radiologist-level segmentation of breast tumors in MRI. Materials and Methods: We leveraged 38,229 clinical MRI breast exams collected retrospectively from women aged 12-94 (mean age 54) who presented between 2002 and 2014 at a single clinical site. The training set for the network consisted of 2,555 malignant breasts that were segmented in 2D by experienced radiologists, as well as 60,108 benign breasts that served as negative controls. The test set consisted of 250 exams with tumors segmented independently by four radiologists. We selected among several 3D deep convolutional neural network architectures, input modalities and harmonization methods. The outcome measure was the Dice score for 2D segmentation, and was compared between the network and radiologists using the Wilcoxon signed-rank test and the TOST procedure. Results: The best-performing network on the training set was a volumetric U-Net with contrast enhancement dynamic as input and with intensity normalized for each exam. In the test set the median Dice score of this network was 0.77. The performance of the network was equivalent to that of the radiologists (TOST procedure with radiologist performance of 0.69-0.84 as equivalence bounds: p = 5e-10 and p = 2e-5, respectively; N = 250) and compares favorably with published state of the art (0.6-0.77). Conclusion: When trained on a dataset of over 60 thousand breasts, a volumetric U-Net performs as well as expert radiologists at segmenting malignant breast lesions in MRI.

READ FULL TEXT

page 4

page 5

page 6

page 7

page 9

research
04/18/2023

Fibroglandular Tissue Segmentation in Breast MRI using Vision Transformers – A multi-institutional evaluation

Accurate and automatic segmentation of fibroglandular tissue in breast M...
research
01/27/2020

Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net

We propose a novel deep learning based approach to breast mass segmentat...
research
11/24/2022

Non-inferiority of Deep Learning Model to Segment Acute Stroke on Non-contrast CT Compared to Neuroradiologists

Purpose: To develop a deep learning model to segment the acute ischemic ...
research
08/20/2023

Developing a Machine Learning-Based Clinical Decision Support Tool for Uterine Tumor Imaging

Uterine leiomyosarcoma (LMS) is a rare but aggressive malignancy. On ima...
research
12/27/2019

Handling Missing MRI Input Data in Deep Learning Segmentation of Brain Metastases: A Multi-Center Study

The purpose was to assess the clinical value of a novel DropOut model fo...
research
04/18/2016

Pieces-of-parts for supervoxel segmentation with global context: Application to DCE-MRI tumour delineation

Rectal tumour segmentation in dynamic contrast-enhanced MRI (DCE-MRI) is...

Please sign up or login with your details

Forgot password? Click here to reset