Multi-modal Magnetic Resonance Imaging (MRI) can provide complementary information for automatic brain tumor segmentation, which is crucial for diagnosis and prognosis. While missing modality data is common in clinical practice and it can result in the collapse of most previous methods relying on complete modality data. Current state-of-the-art approaches cope with the situations of missing modalities by fusing multi-modal images and features to learn shared representations of tumor regions, which often ignore explicitly capturing the correlations among modalities and tumor regions. Inspired by the fact that modality information plays distinct roles to segment different tumor regions, we aim to explicitly exploit the correlations among various modality-specific information and tumor-specific knowledge for segmentation. To this end, we propose a Dual Disentanglement Network (D ² -Net) for brain tumor segmentation with missing modalities, which consists of a modality disentanglement stage (MD-Stage) and a tumor-region disentanglement stage (TD-Stage). In the MD-Stage, a spatial-frequency joint modality contrastive learning scheme is designed to directly decouple the modality-specific information from MRI data. To decompose tumor-specific representations and extract discriminative holistic features, we propose an affinity-guided dense tumor-region knowledge distillation mechanism in the TD-Stage through aligning the features of a disentangled binary teacher network with a holistic student network. By explicitly discovering relations among modalities and tumor regions, our model can learn sufficient information for segmentation even if some modalities are missing. Extensive experiments on the public BraTS-2018 database demonstrate the superiority of our framework over state-of-the-art methods in missing modalities situations. Codes are available at https://github.com/CityU-AIM-Group/D2Net .

The degradation in image resolution harms the performance of medical image diagnosis. By inferring high-frequency details from low-resolution (LR) images, super-resolution (SR) techniques can introduce additional knowledge and assist high-level tasks. In this paper, we propose a SR enhanced diagnosis framework, consisting of an efficient SR network and a diagnosis network. Specifically, a Multi-scale Refined Context Network (MRC-Net) with Refined Context Fusion (RCF) is devised to leverage global and local features for SR tasks. Instead of learning from scratch, we first develop a recursive MRC-Net with temporal context, and then propose a recursion distillation scheme to enhance the performance of MRC-Net from the knowledge of the recursive one and reduce the computational cost. The diagnosis network jointly utilizes the reliable original images and more informative SR images by two branches, with the proposed Sample Affinity Interaction (SAI) blocks at different stages to effectively extract and integrate discriminative features towards diagnosis. Moreover, two novel constraints, sample affinity consistency and sample affinity regularization, are devised to refine the features and achieve the mutual promotion of these two branches. Extensive experiments of synthetic and real LR cases are conducted on wireless capsule endoscopy and histopathology images, verifying that our proposed method is significantly effective for medical image diagnosis.

Antiangiogenic therapies are considered promising for the treatment of glioblastoma (GB). The non-collagenous C-terminal globular NC1 domain of type VIII collagen a1 chain, Vastatin, is an endogenous antiangiogenic polypeptide. Sustained enhanced expression of Vastatin was shown to inhibit tumour growth and metastasis in murine hepatocellular carcinoma models. In this study, we further explored the efficacy of Vastatin in the treatment of GB xenografts. Treatment of Vastatin was carried out using a nanopolymer gene vector PEI600-CyD-Folate (H1). Antiangiogenic effect of Vastatin was tested in vitro by using co-culture system and conditioned medium. An orthotopic GB murine model was established to examine the in vivo therapeutic effect of Vastatin alone treatment and its combination with temozolomide. Vastatin gene transfection mediated by H1 could target tumour cells specifically and suppress the proliferation of microvessel endothelial cells (MECs) through a paracrine inhibition manner. Enhancing Vastatin expression by intracerebral injection of H1-Vastatin significantly prolonged animal survival from 48 to 75 days in GB murine model, which was comparable to the effect of Endostatin, the most studied endogenous antiangiogenic polypeptide. The diminished presence of CD34 positive cells in the GB xenografts suggested that Vastatin induced significant antiangiogenesis. Moreover, a synergistic effect in extending survival was detected when H1-Vastatin was administered with temozolomide (TMZ) in GB chemoresistant murine models. Our results suggest, for the first time, that Vastatin is an antiangiogenic polypeptide with significant potential therapeutic benefit for GB. H1-Vastatin gene therapy may have important implications in re-sensitizing recurrent GB to standard chemotherapeutic agents.