Efficient pyramid channel attention network for pathological myopia recognition with pretraining-and-finetuning.

Pathological myopia (PM) is the leading ocular disease for impaired vision worldwide. Clinically, the characteristics of pathology distribution in PM are global-local on the fundus image, which plays a significant role in assisting clinicians in diagnosing PM. However, most existing deep neural networks focused on designing complex architectures but rarely explored the pathology distribution prior of PM. To tackle this issue, we propose an efficient pyramid channel attention (EPCA) module, which fully leverages the potential of the clinical pathology prior of PM with pyramid pooling and multi-scale context fusion. Then, we construct EPCA-Net for automatic PM recognition based on fundus images by stacking a sequence of EPCA modules. Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters. In addition, we construct a PM recognition benchmark termed PM-fundus by collecting fundus images of PM from publicly available datasets. The comprehensive experiments demonstrate the superiority of EPCA-Net over state-of-the-art methods in the PM recognition task. For example, EPCA-Net achieves 97.56% accuracy and outperforms ViT by 2.85% accuracy on the PM-fundus dataset. The results also show that our method based on the pretraining-and-finetuning paradigm achieves competitive performance through comparisons to part of previous methods based on traditional fine-tuning paradigm with fewer tunable parameters, which has the potential to leverage more natural image foundation models to address the PM recognition task in limited medical data regime.

Pyramid Pixel Context Adaption Network for Medical Image Classification With Supervised Contrastive Learning.

Spatial attention (SA) mechanism has been widely incorporated into deep neural networks (DNNs), significantly lifting the performance in computer vision tasks via long-range dependency modeling. However, it may perform poorly in medical image analysis. Unfortunately, the existing efforts are often unaware that long-range dependency modeling has limitations in highlighting subtle lesion regions. To overcome this limitation, we propose a practical yet lightweight architectural unit, pyramid pixel context adaption (PPCA) module, which exploits multiscale pixel context information to recalibrate pixel position in a pixel-independent manner dynamically. PPCA first applies a well-designed cross-channel pyramid pooling (CCPP) to aggregate multiscale pixel context information, then eliminates the inconsistency among them by the well-designed pixel normalization (PN), and finally estimates per pixel attention weight via a pixel context integration. By embedding PPCA into a DNN with negligible overhead, the PPCA network (PPCANet) is developed for medical image classification. In addition, we introduce supervised contrastive learning to enhance feature representation by exploiting the potential of label information via supervised contrastive loss (CL). The extensive experiments on six medical image datasets show that the PPCANet outperforms state-of-the-art (SOTA) attention-based networks and recent DNNs. We also provide visual analysis and ablation study to explain the behavior of PPCANet in the decision-making process.

General Synthesis of Multiple-Cores@Multiple-Shells Hollow Composites and Their Application to Lithium-Ion Batteries.

Rational nanostructure design has proved fruitful in addressing the bottlenecks of diverse fields. Especially hollow multi-shelled structures (HoMS) have stood out due to their temporal-spatial ordering mass transfer and buffering effect. Localizing multiple cores in a HoMS is highly desired, which could endow it with more fascinating properties. However, such a structure has been barely reported due to the highly challenging fabrication. Here, we develop a controllable synthesis strategy to realize such a structure, which is applicable for diverse cores and shells. Additionally, cores and shells could be tuned to be homogeneous or heterogeneous, with the core and shell number well controlled. In situ TEM analysis verifies that the inner shell confines the expansion orientation of cores, while the outer shell maintains a stable interface. In addition to energy storage, such structure is also promising for multi-drug co-delivery and sequential responsive release as well as tandem catalysis applications.

Hollow Multi-Shelled Structural TiO2-x with Multiple Spatial Confinement for Long-Life Lithium-Sulfur Batteries.

TiO2-x with well-controlled hollow multi-shelled structures (HoMSs) were designed and synthesized, via a sequential templating approach (STA), to act as sulfur carrier materials. They were explored as physico-chemical encapsulation materials. Particularly, the sulfur cathode based on triple-shelled TiO2-x HoMSs delivered a specific capacity of 903 mAh g-1 with a capacity retention of 79 % at 0.5 C and a Coulombic efficiency of 97.5 % over 1000 cycles. The outstanding electrochemical performance is attributed to better spatial confinement and integrated conductivity of the intact triple-shell that combine the features of physico-chemical adsorption, short charge transfer path along with mechanical strength.