Neural architecture search (NAS) adopts a search strategy to explore the predefined search space to find superior architecture with the minimum searching costs. Bayesian optimization (BO) and evolutionary algorithms (EA) are two commonly used search strategies, but they suffer from being computationally expensive, challenging to implement, and exhibiting inefficient exploration ability. In this article, we propose a neural predictor guided EA to enhance the exploration ability of EA for NAS (NPENAS) and design two kinds of neural predictors. The first predictor is a BO acquisition function for which we design a graph-based uncertainty estimation network as the surrogate model. The second predictor is a graph-based neural network that directly predicts the performance of the input neural architecture. The NPENAS using the two neural predictors are denoted as NPENAS-BO and NPENAS-NP, respectively. In addition, we introduce a new random architecture sampling method to overcome the drawbacks of the existing sampling method. Experimental results on five NAS search spaces indicate that NPENAS-BO and NPENAS-NP outperform most existing NAS algorithms, with NPENAS-NP achieving state-of-the-art performance on four of the five search spaces.

Cancer is a common cause of death worldwide. Despite significant advances in cancer treatments, the morbidity and mortality are still enormous. Tumor heterogeneity, especially intratumoral heterogeneity, is a significant reason underlying difficulties in tumor treatment and failure of a number of current therapeutic modalities, even of molecularly targeted therapies. The development of a virtually noninvasive “liquid biopsy” from the blood has been attempted to characterize tumor heterogeneity. This review focuses on cell-free circulating tumor DNA (ctDNA) in the bloodstream as a versatile biomarker. ctDNA analysis is an evolving field with many new methods being developed and optimized to be able to successfully extract and analyze ctDNA, which has vast clinical applications. ctDNA has the potential to accurately genotype the tumor and identify personalized genetic and epigenetic alterations of the entire tumor. In addition, ctDNA has the potential to accurately monitor tumor burden and treatment response, while also being able to monitor minimal residual disease, reducing the need for harmful adjuvant chemotherapy and allowing more rapid detection of relapse. There are still many challenges that need to be overcome prior to this biomarker getting wide adoption in the clinical world, including optimization, standardization, and large multicenter trials.

The resolution of feature maps is a critical factor for accurate medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation adopt a U-Net-like architecture, which contains an encoder that converts the high-resolution input image into low-resolution feature maps using a sequence of Transformer blocks and a decoder that gradually generates high-resolution representations from low-resolution feature maps. However, the procedure of recovering high-resolution representations from low-resolution representations may harm the spatial precision of the generated segmentation masks. Unlike previous studies, in this study, we utilized the high-resolution network (HRNet) design style by replacing the convolutional layers with Transformer blocks, continuously exchanging feature map information with different resolutions generated by the Transformer blocks. The proposed Transformer-based network is named the high-resolution Swin Transformer network (HRSTNet). Extensive experiments demonstrated that the HRSTNet can achieve performance comparable with that of the state-of-the-art Transformer-based U-Net-like architecture on the 2021 Brain Tumor Segmentation dataset, the Medical Segmentation Decathlon’s liver dataset, and the BTCV multi-organ segmentation dataset.

Hypoxia is one of the marked features of malignant tumors, which is associated with several adaptation changes in the microenvironment of tumor cells. Therefore, targeting tumor hypoxia is a research hotspot for cancer therapy. In this review, we summarize the developing chemotherapeutic drugs for targeting hypoxia, including quinones, nitroaromatic/nitroimidazole, N-oxides, and transition metal complexes. In addition, redox-responsive bonds, such as nitroimidazole groups, azo-groups, and disulfide bonds, are frequently used in drug delivery systems for targeting the redox environment of tumors. Both hypoxia-activated prodrugs and redox-responsive drug delivery nanocarriers have significant effects on targeting tumor hypoxia for cancer therapy. Hypoxia-activated prodrugs are commonly used in clinical trials with favorable prospects, while redox-responsive nanocarriers are currently at the experimental stage.