Current sellar tumor diagnosis depends on multiple computational pathology tools, which are costly and timeconsuming. Automating tumor subtype classification directly from WSIs is valuable but challenging due to their high data complexity, making standard image classifiers inadequate. This work introduces TG-ViT, a novel text-guided framework that leverages clinical histopathological texts for classifying three sellar tumor subtypes. Unlike typical multi-modal models that deeply fuse text and image features, TG-ViT uses a dualnetwork design: a lightweight multi-head cross-attention text fusion module guides the pretrained image encoder during finetuning, using text as a medical prior at the patch level, rather than for deep alignment. TG-ViT was trained on 659 hospital cases. Results on the HS-dataset and ablation studies show that TG-ViT outperforms state-of-the-art deep learning methods in WSI classification.

Prevalent studies on deep learning-based 3D medical image segmentation capture the continuous variation across 2D slices mainly via convolution, Transformer, inter-slice interaction, and time series models. In this work, via modeling this variation by an ordinary differential equation (ODE), we propose a cross instance query-guided Transformer architecture (CQformer) that leverages features from preceding slices to improve the segmentation performance of subsequent slices. Its key components include a cross-attention mechanism in an ODE formulation, which bridges the features of contiguous 2D slices of the 3D volumetric data. In addition, a regression head is employed to shorten the gap between the bottleneck and the prediction layer. Extensive experiments on 7 datasets with various modalities (CT, MRI) and tasks (organ, tissue, and lesion) demonstrate that CQformer outperforms previous state-of-the-art segmentation algorithms on 6 datasets by 0.44%-2.45%, and achieves the second highest performance of 88.30% on the BTCV dataset. The code is available at https://github.com/qbmizsj/CQformer.

Accurate neonatal brain MRI segmentation is valuable for investigating brain growth patterns and tracking the progression of neurodevelopmental disorders. However, it is a challenging task to use intensity-based methods to segment neonatal brain structures because of small contrast differences between brain regions caused by the inherent myelination process. Although convolutional neural networks offer the potential to segment brain structures in an intensity-independent manner, they suffer from lack of in-plane long-range dependency which is essential for the segmentation. To solve this problem, we propose a novel Transformer-Weighted network (TW-Net) to incorporate in-plane long-range dependency information. TW-Net employs a conventional encoder-decoder architecture with a Transformer module in the middle. The Transformer module uses a rotate-and-flip layer to better calculate the similarity between two patches in a slice to leverage similar patterns of geometrical and texture features within brain structures. In addition, a deep supervision module and squeeze-and-excitation blocks are introduced to incorporate boundary information of brain structures. Compared with state-of-the-art deep learning algorithms, TW-Net outperforms these methods for multiple-label tasks in 2D and 2.5D configurations on two independent public datasets, demonstrating that TW-Net is a promising method for neonatal brain MRI segmentation.

Segmenting the fine structure of the mouse brain on magnetic resonance (MR) images is critical for delineating morphological regions, analyzing brain function, and understanding their relationships. Compared to a single MRI modality, multimodal MRI data provide complementary tissue features that can be exploited by deep learning models, resulting in better segmentation results. However, multimodal mouse brain MRI data is often lacking, making automatic segmentation of mouse brain fine structure a very challenging task. To address this issue, it is necessary to fuse multimodal MRI data to produce distinguished contrasts in different brain structures. Hence, we propose a novel disentangled and contrastive GAN-based framework, named MouseGAN++, to synthesize multiple MR modalities from single ones in a structure-preserving manner, thus improving the segmentation performance by imputing missing modalities and multi-modality fusion. Our results demonstrate that the translation performance of our method outperforms the state-of-the-art methods. Using the subsequently learned modality-invariant information as well as the modality-translated images, MouseGAN++ can segment fine brain structures with averaged dice coefficients of 90.0% (T2w) and 87.9% (T1w), respectively, achieving around +10% performance improvement compared to the state-of-the-art algorithms. Our results demonstrate that MouseGAN++, as a simultaneous image synthesis and segmentation method, can be used to fuse cross-modality information in an unpaired manner and yield more robust performance in the absence of multimodal data. We release our method as a mouse brain structural segmentation tool for free academic usage at https://github.com/yu02019.