Rongguo Zhang

Navodini Wijethilake, Reuben Dorent, Marina Ivory et al.

The cross-Modality Domain Adaptation (crossMoDA) challenge series, initiated in 2021 in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), focuses on unsupervised cross-modality segmentation, learning from contrast-enhanced T1 (ceT1) and transferring to T2 MRI. The task is an extreme example of domain shift chosen to serve as a meaningful and illustrative benchmark. From a clinical application perspective, it aims to automate Vestibular Schwannoma (VS) and cochlea segmentation on T2 scans for more cost-effective VS management. Over time, the challenge objectives have evolved to enhance its clinical relevance. The challenge evolved from using single-institutional data and basic segmentation in 2021 to incorporating multi-institutional data and Koos grading in 2022, and by 2023, it included heterogeneous routine data and sub-segmentation of intra- and extra-meatal tumour components. In this work, we report the findings of the 2022 and 2023 editions and perform a retrospective analysis of the challenge progression over the years. The observations from the successive challenge contributions indicate that the number of outliers decreases with an expanding dataset. This is notable since the diversity of scanning protocols of the datasets concurrently increased. The winning approach of the 2023 edition reduced the number of outliers on the 2021 and 2022 testing data, demonstrating how increased data heterogeneity can enhance segmentation performance even on homogeneous data. However, the cochlea Dice score declined in 2023, likely due to the added complexity from tumour sub-annotations affecting overall segmentation performance. While progress is still needed for clinically acceptable VS segmentation, the plateauing performance suggests that a more challenging cross-modal task may better serve future benchmarking.

Jiechao Ma, Rongguo Zhang

Cardiovascular disease (CVD) is a common and strong threat to human beings, featuring high prevalence, disability and mortality. The amount of coronary artery calcification (CAC) is an effective factor for CVD risk evaluation. Conventionally, CAC is quantified using ECG-synchronized cardiac CT but rarely from general chest CT scans. However, compared with ECG-synchronized cardiac CT, chest CT is more prevalent and economical in clinical practice. To address this, we propose an automatic method based on Dense U-Net to segment coronary calcium pixels on both types of CT scans. Our contribution is two-fold. First, we propose a novel network called DenseRAUnet, which takes advantage of Dense U-net, ResNet and atrous convolutions. We prove the robustness and generalizability of our model by training it exclusively on chest CT while test on both types of CT scans. Second, we design a loss function combining bootstrap with IoU function to balance foreground and background classes. DenseRAUnet is trained in a 2.5D fashion and tested on a private dataset consisting of 144 scans. Results show an F1-score of 0.75, with 0.83 accuracy of predicting cardiovascular disease risk.

Jiechao Ma, Xiang Li, Hongwei Li et al.

Early diagnosis of pulmonary nodules (PNs) can improve the survival rate of patients and yet is a challenging task for radiologists due to the image noise and artifacts in computed tomography (CT) images. In this paper, we propose a novel and effective abnormality detector implementing the attention mechanism and group convolution on 3D single-shot detector (SSD) called group-attention SSD (GA-SSD). We find that group convolution is effective in extracting rich context information between continuous slices, and attention network can learn the target features automatically. We collected a large-scale dataset that contained 4146 CT scans with annotations of varying types and sizes of PNs (even PNs smaller than 3mm were annotated). To the best of our knowledge, this dataset is the largest cohort with relatively complete annotations for PNs detection. Our experimental results show that the proposed group-attention SSD outperforms the classic SSD framework as well as the state-of-the-art 3DCNN, especially on some challenging lesion types.