A Generic Graph-Based Neural Architecture Encoding Scheme With Multifaceted Information.

Neural architecture search (NAS) can automatically discover well-performing architectures in a large search space and has been shown to bring improvements to various applications. However, the computational burden of NAS is huge, since exploring a large search space can need evaluating more than thousands of architecture samples. To improve the sample efficiency of search space exploration, predictor-based NAS methods learn a performance predictor of architectures, and utilize the predictor to sample worth-evaluating architectures. The encoding scheme of NN architectures is crucial to the predictor's generalization ability, and thus crucial to the efficacy of the NAS process. To this end, we have designed a generic Graph-based neural ArchiTecture Encoding Scheme (GATES), a more reasonable modeling of NN architectures that mimics their data processing. Nevertheless, GATES is unaware of the concrete computing semantic of NN operations or architectures. Thus, the learning of operation embeddings and weights in GATES can only exploit the information in architectures-performance pairs. We propose GATES++, which incorporates multifaceted information about NN's operation-level and architecture-level computing semantics into its construction and training, respectively. Experiments on benchmark search spaces show that both the operation-level and architecture-level information can bring improvements alone, and GATES++ can discover better architectures after evaluating the same number of architectures.

Explainable liver tumor delineation in surgical specimens using hyperspectral imaging and deep learning.

Surgical removal is the primary treatment for liver cancer, but frequent recurrence caused by residual malignant tissue remains an important challenge, as recurrence leads to high mortality. It is unreliable to distinguish tumors from normal tissues merely under visual inspection. Hyperspectral imaging (HSI) has been proved to be a promising technology for intra-operative use by capturing the spatial and spectral information of tissue in a fast, non-contact and label-free manner. In this work, we investigated the feasibility of HSI for liver tumor delineation on surgical specimens using a multi-task U-Net framework. Measurements are performed on 19 patients and a dataset of 36 specimens was collected with corresponding pathological results serving as the ground truth. The developed framework can achieve an overall sensitivity of 94.48% and a specificity of 87.22%, outperforming the baseline SVM method by a large margin. In particular, we propose to add explanations on the well-trained model from the spatial and spectral dimensions to show the contribution of pixels and spectral channels explicitly. On that basis, a novel saliency-weighted channel selection method is further proposed to select a small subset of 5 spectral channels which provide essentially as much information as using all 224 channels. According to the dominant channels, the absorption difference of hemoglobin and bile content in the normal and malignant tissues seems to be promising markers that could be further exploited.

Spectrometer-free biological detection method using porous silicon microcavity devices.

This paper proposes a label-free and spectrometer-free method for biological detection with high detecting resolution. Taking advantage of the optical properties of porous silicon microcavity, the refractive index changes caused by biological reaction can be detected by measuring the incident angle of the minimum reflected light intensity. Based on the above method, label-free eight-base pair DNA detection can be realized with a corresponding detection limit is as low as 87 nM. This method provides high detecting resolution at a low equipment cost, and can be further used to develop an advanced instrument for biological detection.