Learning Site-specific Styles for Multi-institutional Unsupervised Cross-modality Domain Adaptation

Unsupervised cross-modality domain adaptation is a challenging task in medical image analysis, and it becomes more challenging when source and target domain data are collected from multiple institutions. In this paper, we present our solution to tackle the multi-institutional unsupervised domain adaptation for the crossMoDA 2023 challenge. First, we perform unpaired image translation to translate the source domain images to the target domain, where we design a dynamic network to generate synthetic target domain images with controllable, site-specific styles. Afterwards, we train a segmentation model using the synthetic images and further reduce the domain gap by self-training. Our solution achieved the 1st place during both the validation and testing phases of the challenge. The code repository is publicly available at https://github.com/MedICL-VU/crossmoda2023.

Evaluation of Synthetically Generated CT for use in Transcranial Focused Ultrasound Procedures

Transcranial focused ultrasound (tFUS) is a therapeutic ultrasound method that focuses sound through the skull to a small region noninvasively and often under MRI guidance. CT imaging is used to estimate the acoustic properties that vary between individual skulls to enable effective focusing during tFUS procedures, exposing patients to potentially harmful radiation. A method to estimate acoustic parameters in the skull without the need for CT would be desirable. Here, we synthesized CT images from routinely acquired T1-weighted MRI by using a 3D patch-based conditional generative adversarial network (cGAN) and evaluated the performance of synthesized CT (sCT) images for treatment planning with tFUS. We compared the performance of sCT to real CT (rCT) images for tFUS planning using Kranion and simulations using the acoustic toolbox, k-Wave. Simulations were performed for 3 tFUS scenarios: 1) no aberration correction, 2) correction with phases calculated from Kranion, and 3) phase shifts calculated from time-reversal. From Kranion, skull density ratio, skull thickness, and number of active elements between rCT and sCT had Pearson's Correlation Coefficients of 0.94, 0.92, and 0.98, respectively. Among 20 targets, differences in simulated peak pressure between rCT and sCT were largest without phase correction (12.4$\pm$8.1%) and smallest with Kranion phases (7.3$\pm$6.0%). The distance between peak focal locations between rCT and sCT was less than 1.3 mm for all simulation cases. Real and synthetically generated skulls had comparable image similarity, skull measurements, and acoustic simulation metrics. Our work demonstrates the feasibility of replacing real CTs with the MR-synthesized CT for tFUS planning. Source code and a docker image with the trained model are available at https://github.com/han-liu/SynCT_TcMRgFUS

Enhancing Data Diversity for Self-training Based Unsupervised Cross-modality Vestibular Schwannoma and Cochlea Segmentation

Automatic segmentation of vestibular schwannoma (VS) and the cochlea from magnetic resonance imaging (MRI) can facilitate VS treatment planning. Unsupervised segmentation methods have shown promising results without requiring the time-consuming and laborious manual labeling process. In this paper, we present an approach for VS and cochlea segmentation in an unsupervised domain adaptation setting. Specifically, we first develop a cross-site cross-modality unpaired image translation strategy to enrich the diversity of the synthesized data. Then, we devise a rule-based offline augmentation technique to further minimize the domain gap. Lastly, we adopt a self-configuring segmentation framework empowered by self-training to obtain the final results. On the CrossMoDA 2022 validation leaderboard, our method has achieved competitive VS and cochlea segmentation performance with mean dice scores of 0.8178 $\pm$ 0.0803 and 0.8433 $\pm$ 0.0293, respectively.

Synthetic CT Skull Generation for Transcranial MR Imaging-Guided Focused Ultrasound Interventions with Conditional Adversarial Networks

Transcranial MRI-guided focused ultrasound (TcMRgFUS) is a therapeutic ultrasound method that focuses sound through the skull to a small region noninvasively under MRI guidance. It is clinically approved to thermally ablate regions of the thalamus and is being explored for other therapies, such as blood brain barrier opening and neuromodulation. To accurately target ultrasound through the skull, the transmitted waves must constructively interfere at the target region. However, heterogeneity of the sound speed, density, and ultrasound attenuation in different individuals' skulls requires patient-specific estimates of these parameters for optimal treatment planning. CT imaging is currently the gold standard for estimating acoustic properties of an individual skull during clinical procedures, but CT imaging exposes patients to radiation and increases the overall number of imaging procedures required for therapy. A method to estimate acoustic parameters in the skull without the need for CT would be desirable. Here, we synthesized CT images from routinely acquired T1-weighted MRI by using a 3D patch-based conditional generative adversarial network and evaluated the performance of synthesized CT images for treatment planning with transcranial focused ultrasound. We compared the performance of synthetic CT to real CT images using Kranion and k-Wave acoustic simulation. Our work demonstrates the feasibility of replacing real CT with the MR-synthesized CT for TcMRgFUS planning.

A Multi-rater Comparative Study of Automatic Target Localization Methods for Epilepsy Deep Brain Stimulation Procedures

Epilepsy is the fourth most common neurological disorder and affects people of all ages worldwide. Deep Brain Stimulation (DBS) has emerged as an alternative treatment option when anti-epileptic drugs or resective surgery cannot lead to satisfactory outcomes. To facilitate the planning of the procedure and for its standardization, it is desirable to develop an algorithm to automatically localize the DBS stimulation target, i.e., Anterior Nucleus of Thalamus (ANT), which is a challenging target to plan. In this work, we perform an extensive comparative study by benchmarking various localization methods for ANT-DBS. Specifically, the methods involved in this study include traditional registration method and deep-learning-based methods including heatmap matching and differentiable spatial to numerical transform (DSNT). Our experimental results show that the deep-learning (DL)-based localization methods that are trained with pseudo labels can achieve a performance that is comparable to the inter-rater and intra-rater variability and that they are orders of magnitude faster than traditional methods.

Unsupervised Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation via Semi-supervised Learning and Label Fusion

Automatic methods to segment the vestibular schwannoma (VS) tumors and the cochlea from magnetic resonance imaging (MRI) are critical to VS treatment planning. Although supervised methods have achieved satisfactory performance in VS segmentation, they require full annotations by experts, which is laborious and time-consuming. In this work, we aim to tackle the VS and cochlea segmentation problem in an unsupervised domain adaptation setting. Our proposed method leverages both the image-level domain alignment to minimize the domain divergence and semi-supervised training to further boost the performance. Furthermore, we propose to fuse the labels predicted from multiple models via noisy label correction. In the MICCAI 2021 crossMoDA challenge, our results on the final evaluation leaderboard showed that our proposed method has achieved promising segmentation performance with mean dice score of 79.9% and 82.5% and ASSD of 1.29 mm and 0.18 mm for VS tumor and cochlea, respectively. The cochlea ASSD achieved by our method has outperformed all other competing methods as well as the supervised nnU-Net.

CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwnannoma and Cochlea Segmentation

Domain Adaptation (DA) has recently raised strong interests in the medical imaging community. While a large variety of DA techniques has been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality DA. The challenge's goal is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are performed using contrast-enhanced T1 (ceT1) MRI. However, there is growing interest in using non-contrast sequences such as high-resolution T2 (hrT2) MRI. Therefore, we created an unsupervised cross-modality segmentation benchmark. The training set provides annotated ceT1 (N=105) and unpaired non-annotated hrT2 (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137). A total of 16 teams submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice - VS:88.4%; Cochleas:85.7%) and close to full supervision (median Dice - VS:92.5%; Cochleas:87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.

Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation

Automatic methods to segment the vestibular schwannoma (VS) tumors and the cochlea from magnetic resonance imaging (MRI) are critical to VS treatment planning. Although supervised methods have achieved satisfactory performance in VS segmentation, they require full annotations by experts, which is laborious and time-consuming. In this work, we aim to tackle the VS and cochlea segmentation problem in an unsupervised domain adaptation setting. Our proposed method leverages both the image-level domain alignment to minimize the domain divergence and semi-supervised training to further boost the performance. Furthermore, we propose to fuse the labels predicted from multiple models via noisy label correction. Our results on the challenge validation leaderboard showed that our unsupervised method has achieved promising VS and cochlea segmentation performance with mean dice score of 0.8261 $\pm$ 0.0416; The mean dice value for the tumor is 0.8302 $\pm$ 0.0772. This is comparable to the weakly-supervised based method.

Atlas-Based Segmentation of Intracochlear Anatomy in Metal Artifact Affected CT Images of the Ear with Co-trained Deep Neural Networks

We propose an atlas-based method to segment the intracochlear anatomy (ICA) in the post-implantation CT (Post-CT) images of cochlear implant (CI) recipients that preserves the point-to-point correspondence between the meshes in the atlas and the segmented volumes. To solve this problem, which is challenging because of the strong artifacts produced by the implant, we use a pair of co-trained deep networks that generate dense deformation fields (DDFs) in opposite directions. One network is tasked with registering an atlas image to the Post-CT images and the other network is tasked with registering the Post-CT images to the atlas image. The networks are trained using loss functions based on voxel-wise labels, image content, fiducial registration error, and cycle-consistency constraint. The segmentation of the ICA in the Post-CT images is subsequently obtained by transferring the predefined segmentation meshes of the ICA in the atlas image to the Post-CT images using the corresponding DDFs generated by the trained registration networks. Our model can learn the underlying geometric features of the ICA even though they are obscured by the metal artifacts. We show that our end-to-end network produces results that are comparable to the current state of the art (SOTA) that relies on a two-steps approach that first uses conditional generative adversarial networks to synthesize artifact-free images from the Post-CT images and then uses an active shape model-based method to segment the ICA in the synthetic images. Our method requires a fraction of the time needed by the SOTA, which is important for end-user acceptance.