Multi-task contrastive learning for semi-supervised medical image segmentation with multi-scale uncertainty estimation.

. Automated medical image segmentation is vital for the prevention and treatment of disease. However, medical data commonly exhibit class imbalance in practical applications, which may lead to unclear boundaries of specific classes and make it difficult to effectively segment certain tail classes in the results of semi-supervised medical image segmentation.

Microstructurally Tailored Thin β-Ag Se Films toward Commercial Flexible Thermoelectrics.

Aiming to overcome both the structural and commercial limitations of flexible thermoelectric power generators, an efficient room-temperature aqueous selenization reaction that can be completed in air within less than 1 min, to directly fabricate thin β-Ag Se films consisting of perfectly crystalline and large columnar grains with both in-plane randomness and out-of-plane [201] preferred orientation, is designed. A high power factor (PF) of 2590 ± 414 µW m K and a figure-of-merit (zT) of 1.2 ± 0.

Environment-friendly Cu-based thin film solar cells: materials, devices and charge carrier dynamics.

Cu-based thin films are ideal absorbing layer materials for new-generation thin-film solar cells, which have many advantages, such as environment-friendly components, abundant raw materials, low cost, simple manufacturing process, strong anti-interference, radiation resistance, high light absorption coefficient and suitable band gap. Copper indium gallium selenide (CIGS) thin-film solar cells, which have the highest photoelectric conversion efficiency (23.35%) among the various Cu-based materials, have been intensively investigated and exploited.