CrossMoDA 2021 challenge: Benchmark of cross-modality domain adaptation techniques for vestibular schwannoma and cochlea segmentation.

Domain Adaptation (DA) has recently been of strong interest in the medical imaging community. While a large variety of DA techniques have 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 Domain Adaptation. The goal of the challenge 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 commonly performed using contrast-enhanced T1 (ceT1) MR imaging. However, there is growing interest in using non-contrast imaging sequences such as high-resolution T2 (hrT2) imaging. For this reason, we established an unsupervised cross-modality segmentation benchmark. The training dataset provides annotated ceT1 scans (N=105) and unpaired non-annotated hrT2 scans (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 scans as provided in the testing set (N=137). This problem is particularly challenging given the large intensity distribution gap across the modalities and the small volume of the structures. A total of 55 teams from 16 countries submitted predictions to the validation leaderboard. Among them, 16 teams from 9 different countries submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice score - VS: 88.4%; Cochleas: 85.7%) and close to full supervision (median Dice score - 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.

Simulation-based roadmap for the integration of poly-silicon on oxide contacts into screen-printed crystalline silicon solar cells.

We present a simulation-based study for identifying promising cell structures, which integrate poly-Si on oxide junctions into industrial crystalline silicon solar cells. The simulations use best-case measured input parameters to determine efficiency potentials. We also discuss the main challenges of industrially processing these structures. We find that structures based on p-type wafers in which the phosphorus diffusion is replaced by an n-type poly-Si on oxide junction (POLO) in combination with the conventional screen-printed and fired Al contacts show a high efficiency potential. The efficiency gains in comparsion to the 23.7% efficiency simulated for the PERC reference case are 1.0% for the POLO BJ (back junction) structure and 1.8% for the POLO IBC (interdigitated back contact) structure. The POLO BJ and the POLO IBC cells can be processed with lean process flows, which are built on major steps of the PERC process such as the screen-printed Al contacts and the [Formula: see text] passivation. Cell concepts with contacts using poly-Si for both polarities ([Formula: see text]-concepts) show an even higher efficiency gain potential of 1.3% for a [Formula: see text] BJ cell and 2.2% for a [Formula: see text] IBC cell in comparison to PERC. For these structures further research on poly-Si structuring and screen-printing on p-type poly-Si is necessary.