Programmed cell death-ligand 2: new insights in cancer.

Immunotherapy has revolutionized cancer treatment, with the anti-PD-1/PD-L1 axis therapy demonstrating significant clinical efficacy across various tumor types. However, it should be noted that this therapy is not universally effective for all PD-L1-positive patients, highlighting the need to expedite research on the second ligand of PD-1, known as Programmed Cell Death Receptor Ligand 2 (PD-L2). As an immune checkpoint molecule, PD-L2 was reported to be associated with patient's prognosis and plays a pivotal role in cancer cell immune escape. An in-depth understanding of the regulatory process of PD-L2 expression may stratify patients to benefit from anti-PD-1 immunotherapy. Our review focuses on exploring PD-L2 expression in different tumors, its correlation with prognosis, regulatory factors, and the interplay between PD-L2 and tumor treatment, which may provide a notable avenue in developing immune combination therapy and improving the clinical efficacy of anti-PD-1 therapies.

A multi-scale keypoint estimation network with self-supervision for spinal curvature assessment of idiopathic scoliosis from the imperfect dataset.

Idiopathic scoliosis (IS) is a common lifetime disease, which exhibits an obvious deformity of spinal curvature to seriously affect heart and lung function. Accurate radiographic assessment of spinal curvature is vitally important for the clinical diagnosis and treatment planning of idiopathic scoliosis. Deep learning algorithms have been widely adopted to the medical image analysis with the remarkable advancement in computer vision. The automated methods can improve the efficiency of clinical diagnosis to relieve the burden of doctors, which have advantage in dealing with the tedious and repetitive tasks. However, existing methods usually require sufficiently large training datasets with strict annotation, which are costly and laborious especially for medical images. Moreover, the medical images of serious IS always contain the blurry and occlusive parts, which would make the accurate and robust estimation of the spinal curvature more difficult. In this paper, a dot annotation approach is presented to train the spinal curvature assessment model, rather than using strict annotation of IS X-ray images. We develop a multi-scale keypoint estimation network to reduce the requirement for large training datasets, in which the Squeeze-and-Excitation (SE) blocks are incorporated to improve the representational capacity of the model. Then, a self-supervision module is designed to alleviate the blurry and occlusive problem, and we use the two-view radiographic assessments of IS to generate a 3D spinal curvature. Finally, extensive experiments are conducted on a collected clinical dataset, in which we obtain 81.5 AP and the average Ed between the predicted keypoints and the ground truths is 0.43, making an improvement over the mainstream approaches.