Colorectal cancer is the second and the third most common cancer in women and men, respectively. Pathological diagnosis is the “gold standard” for tumor diagnosis. Accurate segmentation of glands from tissue images is a crucial step in assisting pathologists in their diagnosis. The typical methods for gland segmentation form a dense image representation, ignoring its texture and multi-scale attention information. Therefore, we utilize a Gabor-based module to extract texture information at different scales and directions in histopathology images. This paper also designs a Cascade Squeeze Bi-Attention (CSBA) module. Specifically, we add Atrous Cascade Spatial Pyramid (ACSP), Squeeze Position Attention (SPA) module and Squeeze Channel Attention module (SCA) to model semantic correlation and maintain the multi-level aggregation on the spatial pyramid with different dilations. Besides, to solve the imbalance of data distribution and boundary blur, we propose a hybrid loss function to response the object boudary better. The experimental results show that the proposed method achieves state-of-the-art performance on the GlaS challenge dataset and CRAG colorectal adenocarcinoma dataset, respectively.

This paper presents the design and analysis of a novel compact flexure-based rotary micropositioning stage driven by piezoelectric actuator. The developed stage possesses a double four-bar rotary mechanism with rotational symmetric configuration and totally kinematic decoupling, which can convert the linear motion of the piezoelectric actuator into the pure rotational motion, significantly minimizing the parasitic error at the rotation center. Based on the configuration, a single piezoelectric actuator is employed to drive the stage, avoiding actuator redundancy and large configuration size. Meanwhile, we introduce a compliant rotational guiding mechanism to enhance the rotational stiffness and dynamics of the stage. Analytical modeling and finite element analysis are adopted to facilitate the design of dimension. Finally, a prototype of the stage is manufactured and tested, which is capable of a rotational angle of $1.58\text{mrad}$ with the first natural frequency of 430 Hz, whilst the well-constrained maximum center shift along the X- and Y-axis are 0.29 µm and 0.12 µm, respectively, indicating good decoupling capability. Furthermore, the compact size of $70\text{mm}\times 70\text{mm}\times 15\text{mm}$ is beneficial for limited working space.

Multi-modal magnetic resonance imaging (MRI) plays a crucial role in comprehensive disease diagnosis in clinical medicine. However, acquiring certain modalities, such as T2-weighted images (T2WIs), is time-consuming and prone to be with motion artifacts. It negatively impacts subsequent multi-modal image analysis. To address this issue, we propose an end-to-end deep learning framework that utilizes T1-weighted images (T1WIs) as auxiliary modalities to expedite T2WIs’ acquisitions. While image pre-processing is capable of mitigating misalignment, improper parameter selection leads to adverse pre-processing effects, requiring iterative experimentation and adjustment. To overcome this shortage, we employ Optimal Transport (OT) to synthesize T2WIs by aligning T1WIs and performing cross-modal synthesis, effectively mitigating spatial misalignment effects. Furthermore, we adopt an alternating iteration framework between the reconstruction task and the cross-modal synthesis task to optimize the final results. Then, we prove that the reconstructed T2WIs and the synthetic T2WIs become closer on the T2 image manifold with iterations increasing, and further illustrate that the improved reconstruction result enhances the synthesis process, whereas the enhanced synthesis result improves the reconstruction process. Finally, experimental results from FastMRI and internal datasets confirm the effectiveness of our method, demonstrating significant improvements in image reconstruction quality even at low sampling rates.

Purpose: The purpose of this paper is to present a novel method for minor fabric defects detection.Design/methodology/approach: This paper proposes a PETM-CNN algorithm. PETM-CNN is designed based on self-similar estimation algorithm and Convolutional Neural Network. The PE (Patches Extractor) algorithm extracts patches that are possible to be defective patches to preprocess the fabric image. Then a TM-CNN (Triplet Metric CNN) method is designed to predict labels of the patches and the final label of the image. The TM-CNN can perform better than normal CNN.Findings: This algorithm is superior to other algorithms on the data set of fabric images with minor defects. The proposed method achieves accurate classification of fabric images whether it has minor defects or not. The experimental results show that the approach is effective.Originality/value: Traditional fabric defects detection is not effective as minor defects detection, so this paper develops a method of minor fabric images classification based on self-similar estimation and CNN. This paper offers the first investigation of minor fabric defects.