A generalized AI method for pathology cancer diagnosis and prognosis prediction based on transfer learning and hierarchical split.

Objective.This study aims to propose a generalized AI method for pathology cancer diagnosis and prognosis prediction based on transfer learning and hierarchical split.Approach.We present a neural network framework for cancer diagnosis and prognosis prediction in pathological images. To enhance the network's depth and width, we employ a hierarchical split block (HS-Block) to create an AI-aided diagnosis system suitable for semi-supervised clinical settings with limited labeled samples and cross-domain tasks. By incorporating a lightweight convolution unit based on the HS-Block, we improve the feature information extraction capabilities of a regular network (RegNet). Additionally, we integrate a Convolutional Block Attention Module into the first and last convolutions to optimize the extraction of global features and local details. To address limited sample labels, we employ a dual-transfer learning (DTL) mechanism named DTL-HS-Regnet, enabling semi-supervised learning in clinical settings.Main results.Our proposed DTL-HS-Regnet model outperforms other advanced deep-learning models in three different types of cancer diagnosis tasks. It demonstrates superior feature extraction ability, achieving an average sensitivity, specificity, accuracy, and F1 score of 0.9987, 1.0000, 1.0000 and 0.9992, respectively. Furthermore, we evaluate the model's capability to directly extract prognosis prediction information from pathological images by constructing patient cohorts. The results show that the correlation between DTL-HS-Regnet predictions and the presence of cancer-associated fibroblasts is comparable to that of pathologists.Significance.Our proposed AI method offers a generalized approach for cancer diagnosis and prognosis prediction in pathology. The outstanding performance of the DTL-HS-Regnet model demonstrates its potential for improving current practices in image digital pathology, expanding the boundaries of cancer treatment in two critical areas.

Dictionary Learning Based Scheme for Adversarial Defense in Continuous-Variable Quantum Key Distribution.

There exist various attack strategies in continuous-variable quantum key distribution (CVQKD) system in practice. Due to the powerful information processing ability of neural networks, they are applied to the detection and classification of attack strategies in CVQKD systems. However, neural networks are vulnerable to adversarial attacks, resulting in the CVQKD system using neural networks also having security risks. To solve this problem, we propose a defense scheme for the CVQKD system. We first perform low-rank dimensionality reduction on the CVQKD system data through regularized self-representation-locality preserving projects (RSR-LPP) to filter out some adversarial disturbances, and then perform sparse coding reconstruction through dictionary learning to add data details and filter residual adversarial disturbances. We test the proposed defense algorithm in the CVQKD system. The results indicate that our proposed scheme has a good monitoring and alarm effect on CVQKD adversarial disturbances and has a better effect than other compared defense algorithms.