Adolescent Idiopathic Scoliosis (AIS) is a complex three-dimensional spinal deformity, and accurate morphological assessment requires evaluating both coronal and sagittal alignment. While previous research has made significant progress in developing radiation-free methods for coronal plane assessment, reliable and accurate evaluation of sagittal alignment without ionizing radiation remains largely underexplored. To address this gap, we propose LatXGen, a novel generative framework that synthesizes realistic lateral spinal radiographs from posterior Red-Green-Blue and Depth (RGBD) images of unclothed backs. This enables accurate, radiation-free estimation of sagittal spinal alignment. LatXGen tackles two core challenges: (1) inferring sagittal spinal morphology changes from a lateral perspective based on posterior surface geometry, and (2) performing cross-modality translation from RGBD input to the radiographic domain. The framework adopts a dual-stage architecture that progressively estimates lateral spinal structure and synthesizes corresponding radiographs. To enhance anatomical consistency, we introduce an attention-based Fast Fourier Convolution (FFC) module for integrating anatomical features from RGBD images and 3D landmarks, and a Spatial Deformation Network (SDN) to model morphological variations in the lateral view. Additionally, we construct the first large-scale paired dataset for this task, comprising 3,264 RGBD and lateral radiograph pairs. Experimental results demonstrate that LatXGen produces anatomically accurate radiographs and outperforms existing GAN-based methods in both visual fidelity and quantitative metrics. This study offers a promising, radiation-free solution for sagittal spine assessment and advances comprehensive AIS evaluation.

Density interface inversion directly reveals the density distribution of underground structures, playing a significant role in the field of geophysics. Deep learning, due to its ability to extract complex and nonlinear density structures, has been widely applied to density interface inversion. Current convolution-based neural network methods for inverting density interfaces are limited by the finite receptive field of the convolution paradigm, neglecting long-range dependencies and posing challenges for high-precision inversion of density interfaces. Additionally, when using deep learning for density interface inversion, different channels contain different information, necessitating the effective utilization of this information variation in the channel dimension. To address these issues, this letter proposes a novel dual-path Transformer network for density interface inversion, named Inverseformer. The Local-Global branch introduces Transformer to establish long-range density dependencies and, combined with the U-net network, jointly captures multiscale underground density interface features. The Channel branch introduces a channel attention mechanism for the model to operate attentively between channels, effectively capturing density interface structural changes in the channels. Synthetic model experiments show that the proposed dual-branch network for inverting density interfaces has smaller model errors and better data fitting, resulting in higher inversion accuracy and more stable inversion results. Subsequently, its effectiveness and value were validated in actual data from the Brittany region of France.

Three-dimensional gravity inversion is an effective method for restoring underground density distribution from gravity anomaly data. Conventional regularization inversion has good data fitting, but its inversion model has insufficient model fitting capabilities due to its low-depth resolution. Although data-driven deep learning-based gravity inversion results significantly improve depth resolution and physical property distribution, it is difficult to ensure the data fitting of the inversion results. Accordingly, this study proposes a three-dimensional gravity data inversion based on enhanced dual U-Net framework (EdU-Net) to solve the above problems, making the inversion results have good model and data fitting performance. The proposed EdU-Net consists of two parts: first, training a large generalization pre-trained network Net I, and then quickly generating an enhanced Net II for the target data through fine-tuning. Additionally, this study adds forward-fitting constraints in the framework’s loss function to reduce the problem of large data-fitting errors in traditional data-driven deep learning inversion. The trained Net II inversion result has better model and data fitting accuracy than Net I. Moreover, by comparing the inversion results of synthetic models, this study demonstrates that the EdU-Net method performs better than traditional deep learning. Finally, this method is applied to the measured data of the Gonghe Basin in Qinghai Province, China, and provides a reasonable explanation for the distribution of hot dry rocks.

Dimensionality reduction (DR) is important for feature extraction and classification of hyperspectral images (HSIs). Recently proposed superpixel-based DR models have shown promising performance, where superpixel segmentation techniques were applied to segment an HSI and then DR models like principal component analysis (PCA) or linear discriminant analysis (LDA) were employed to extract the local and/or global features. However, superpixelwise PCA based local features are unsatisfactory because PCA aims to extract features with high variance, which could be inefficient in superpixels with mixed objects or strong noise/outliers. In addition, superpixelwise unsupervised LDA based global features may neglect local (spatial-contextual) information. To address these issues, we propose a new spectral-spatial and superpixelwise unsupervised LDA (S3-ULDA) model for unsupervised feature extraction from HSIs. Specifically, the HSI is first segmented into various superpixels with pseudo labels. Then, superpixel based local reconstruction for HSI denoising is conducted. Next, superpixelwise unsupervised LDA (SuperULDA) is performed on both the original HSI and locally reconstructed data to extract global features. Then, superpixelwise unsupervised local Fisher discriminant analysis (SuperULFDA) is developed for local feature extraction, where each superpixel and its adjacent superpixels (along with their pseudo-labels) are fed into local Fisher discriminant analysis (LFDA) to extract local features. The superpixel-level local manifold structures can be effectively modeled by the proposed SuperULFDA. Finally, by fusing the extracted global and local features, novel global-local and spectral-spatial features can be obtained. Our experimental results on several benchmark HSIs demonstrate the superiority of the proposed method over state-of-the-art methods. The code of the proposed model is available at https://github.com/XinweiJiang/S3-ULDA.