Automatic detection and segmentation of multiple brain metastases on magnetic resonance image using asymmetric UNet architecture

Abstract

Detection of brain metastases is a paramount task in cancer management due both to the number of high-risk patients and the difficulty of achieving consistent detection. In this study, we aim to improve the accuracy of automated brain metastasis (BM) detection methods using a novel asymmetric UNet (asym-UNet) architecture. An end-to-end asymmetric 3D-UNet architecture, with two down-sampling arms and one up-sampling arm, was constructed to capture the imaging features. The two down-sampling arms were trained using two different kernels (3 × 3 × 3 and 1 × 1 × 3, respectively) with the kernel (1 × 1 × 3) dominating the learning. As a comparison, vanilla single 3D UNets were trained with different kernels and evaluated using the same datasets. Voxel-based Dice similarity coefficient (DSCv), sensitivity (S v), precision (P v), BM-based sensitivity (S BM), and false detection rate (F BM) were used to evaluate model performance. Contrast-enhanced T1 MR images from 195 patients with a total of 1034 BMs were solicited from our institutional stereotactic radiosurgery database. The patient cohort was split into training (160 patients, 809 lesions), validation (20 patients, 136 lesions), and testing (15 patients, 89 lesions) datasets. The lesions in the testing dataset were further divided into two subgroups based on the diameters (small S = 1–10 mm, large L = 11–26 mm). In the testing dataset, there were 72 and 17 BMs in the S and L sub-groups, respectively. Among all trained networks, asym-UNet achieved the highest DSCv of 0.84 and lowest F BM of 0.24. Although vanilla 3D-UNet with a single 1 × 1 × 3 kernel achieved the highest sensitivities for the S group, it resulted in the lowest precision and highest false detection rate. Asym-UNet was shown to balance sensitivity and false detection rate as well as keep the segmentation accuracy high. The novel asym-UNet segmentation network showed overall competitive segmentation performance and more pronounced improvement in hard-to-detect small BMs comparing to the vanilla single 3D UNet.

Automatic segmentation of high‐risk clinical target volume for tandem‐and‐ovoids brachytherapy patients using an asymmetric dual‐path convolutional neural network

“…To the best of our knowledge, this is the first report of auto HR-CTV segmentation for T&O patients using deep learning imaging features extracted from both postimplant CT and preimplant MR. Motivated by the success of asymmetric learning from two different kernels from one input source, 33 in this study, we employed dual-path for CT and MR inputs, respectively, to allow separate control of the filters, channels, depths, and kernel sizes. Specifically, we studied the asymmetric features learned from CT and MR controlled by the relative number of filters and determined the optimal ratio of 18:6 for CT versus MR.…”

Deep learning as a novel method for endoscopic diagnosis of chronic atrophic gastritis: a prospective nested case–control study

“…With the rapid development of DL technology, the application of DL in the field of medical imaging has attracted extensive research and attention, of which determining how to automatically identify and segment lesions in medical images is one of the most concerning problems. In order to solve this problem, the U-Net network model has been proposed [ 17 , 18 ]. It is based on an FCN (fully convolutional network) and consists of an encoder, bottleneck module and decoder.…”

Advancing Brain Metastases Detection in T1-Weighted Contrast-Enhanced 3D MRI Using Noisy Student-Based Training

“…The automated detection/segmentation of BM in MRI data via machine learning (ML) was investigated in several studies [ 3 , 4 , 5 , 6 , 7 , 8 ]; Cho et al [ 9 ] provided a literature review study on the topic comparing state-of-the-art (SOTA) approaches based on the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) [ 10 ] and Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) criteria [ 11 ]. The authors previously introduced a framework for T1-weighted contrast-enhanced 3D MRI [ 4 ] (analyzed among other SOTA approaches in [ 9 ]) for the detection of BM with diameters less than 15 mm to assist early detection of disease.…”