Benchmarking PathCLIP for Pathology Image Analysis.

Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pre-training (CLIP) model has shown remarkable proficiency in understanding natural images. Drawing inspiration from CLIP, pathology-dedicated CLIP (PathCLIP) has been developed, utilizing over 200,000 image and text pairs in training. While the performance the PathCLIP is impressive, its robustness under a wide range of image corruptions remains unknown. Therefore, we conduct an extensive evaluation to analyze the performance of PathCLIP on various corrupted images from the datasets of osteosarcoma and WSSS4LUAD. In our experiments, we introduce eleven corruption types including brightness, contrast, defocus, resolution, saturation, hue, markup, deformation, incompleteness, rotation, and flipping at various settings. Through experiments, we find that PathCLIP surpasses OpenAI-CLIP and the pathology language-image pre-training (PLIP) model in zero-shot classification. It is relatively robust to image corruptions including contrast, saturation, incompleteness, and orientation factors. Among the eleven corruptions, hue, markup, deformation, defocus, and resolution can cause relatively severe performance fluctuation of the PathCLIP. This indicates that ensuring the quality of images is crucial before conducting a clinical test. Additionally, we assess the robustness of PathCLIP in the task of image-to-image retrieval, revealing that PathCLIP performs less effectively than PLIP on osteosarcoma but performs better on WSSS4LUAD under diverse corruptions. Overall, PathCLIP presents impressive zero-shot classification and retrieval performance for pathology images, but appropriate care needs to be taken when using it.

Masked Conditional Variational Autoencoders for Chromosome Straightening.

Karyotyping is of importance for detecting chromosomal aberrations in human disease. However, chromosomes easily appear curved in microscopic images, which prevents cytogeneticists from analyzing chromosome types. To address this issue, we propose a framework for chromosome straightening, which comprises a preliminary processing algorithm and a generative model called masked conditional variational autoencoders (MC-VAE). The processing method utilizes patch rearrangement to address the difficulty in erasing low degrees of curvature, providing reasonable preliminary results for the MC-VAE. The MC-VAE further straightens the results by leveraging chromosome patches conditioned on their curvatures to learn the mapping between banding patterns and conditions. During model training, we apply a masking strategy with a high masking ratio to train the MC-VAE with eliminated redundancy. This yields a non-trivial reconstruction task, allowing the model to effectively preserve chromosome banding patterns and structure details in the reconstructed results. Extensive experiments on three public datasets with two stain styles show that our framework surpasses the performance of state-of-the-art methods in retaining banding patterns and structure details. Compared to using real-world bent chromosomes, the use of high-quality straightened chromosomes generated by our proposed method can improve the performance of various deep learning models for chromosome classification by a large margin. Such a straightening approach has the potential to be combined with other karyotyping systems to assist cytogeneticists in chromosome analysis.

Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-Ray Images.

Coronavirus disease 2019 (COVID-19) is one of the most destructive pandemic after millennium, forcing the world to tackle a health crisis. Automated lung infections classification using chest X-ray (CXR) images could strengthen diagnostic capability when handling COVID-19. However, classifying COVID-19 from pneumonia cases using CXR image is a difficult task because of shared spatial characteristics, high feature variation and contrast diversity between cases. Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models. To address these challenges, Multiscale Attention Guided deep network with Soft Distance regularization (MAG-SD) is proposed to automatically classify COVID-19 from pneumonia CXR images. In MAG-SD, MA-Net is used to produce prediction vector and attention from multiscale feature maps. To improve the robustness of trained model and relieve the shortage of training data, attention guided augmentations along with a soft distance regularization are posed, which aims at generating meaningful augmentations and reduce noise. Our multiscale attention model achieves better classification performance on our pneumonia CXR image dataset. Plentiful experiments are proposed for MAG-SD which demonstrates its unique advantage in pneumonia classification over cutting-edge models. The code is available at https://github.com/JasonLeeGHub/MAG-SD.

Overendocytosis of superparamagnetic iron oxide particles increases apoptosis and triggers autophagic cell death in human osteosarcoma cell under a spinning magnetic field.

The toxicity of superparamagnetic iron oxide nanoparticles (SPIONs) is still a vital topic of debate and the mechanisms remain unclear. In the present study, overdose SPIONs could induce osteosarcoma cell death and the effects were exaggerated when combined with spinning magnetic field (SMF). In the combination group, mitochondrial transmembrane potential decrease more obviously and reactive oxygen species (ROS) was found to generate much higher in line with that of the apoptosis ratio. Meantime, amount of autophagy was induced. Inhibiting the autophagy generation by 3-methyladenine (3-MA) increase cell viability but decrease the caspase 3/7 and caspase 8 activities in combination groups, and inhibiting apoptosis took the same effect. In the end, the SPIONs effects on xenograft mice was examed by intratumoral injection. The result showed that the combination group could greatly decrease the tumor volume and prolong the lifespan of mice. In sum, the result indicated that overdose SPIONs induced ROS generation, and excessive ROS induced by combination of SPIONs and SMF contribute to autophagy formation, which play a apoptosis-promoting role that formed as a platform to recruits initiate the caspase activities.

MicroRNA-29b inhibits TGF-ß1-induced fibrosis via regulation of the TGF-ß1/Smad pathway in primary human endometrial stromal cells.

Transforming growth factor (TGF)­ß1 has a key role in the regulation of fibrosis and organ dysfunction. During the pathogenesis and progression of vital organ fibrosis, the microRNA (miR)­29 family is irregularly downregulated and exogenous supplementation of miR­29b has a strong anti­fibrotic capacity. However, whether TGF­ß1 is able to provoke endometrial fibrosis, and the role of miR­29 in endometrial fibrosis remain unclear. In the present study, RT­qPCR, immunocytochemistry, western blot analysis, scanning electron microscopy, immunofluorescence staining, cell proliferation assay and flow cytometric analysis were employed. The results demonstrated that the expression levels of collagen, type 1, alpha 1 (COL1A1), α­smooth muscle actin (α­SMA) and phosphorylated (p)­Smad2/3 were increased, whereas miR­29b and maternally expressed gene 3 (MEG3) were decreased in primary endometrial stromal cells (ESCs) in response to TGF­ß1 stimulation, in a time and dose­dependent manner. Furthermore, overexpression of miR­29b markedly reduced the expression levels of COL1A1 and α­SMA, and decreased the expression and nuclear accumulation of p­Smad2/3. In addition, ectopic overexpression of miR­29b increased the expression levels of MEG3, inhibited myofibroblast­like cell proliferation and induced apoptosis. These findings indicated that miR­29b may have a significant anti­fibrotic role, and may attenuate TGF­ß1­induced fibrosis in ESCs. Therefore, exogenous miR­29b may serve as a potential therapeutic agent for the treatment of endometrial fibrosis.

MicroRNA-29b Inhibits Endometrial Fibrosis by Regulating the Sp1-TGF-ß1/Smad-CTGF Axis in a Rat Model.

Intrauterine adhesions (IUAs), which are characterized by endometrial fibrosis, increase the risk of secondary infertility and recurrent miscarriage. MicroRNA-29 (miR-29) is a potent inhibitor of TGF-ß1/Smad signaling. In this study, we investigated the therapeutic potential of agomir-29b, an miR-29b mimic, in endometrial fibrosis induced by dual injury (uterine curettage and lipopolysaccharide treatment) in a rat model of IUA and explored the underlying mechanism. We found that injured rats developed endometrial fibrosis characterized by increased COL1A1 and α-smooth muscle actin expression and decreased E-cadherin expression, associated with a loss of miR-29b. Overexpression of miR-29b before injury prevented endometrial fibrosis including collagen accumulation and epithelial-mesenchymal transition. Delay of agomir-29b treatment until endometrial fibrosis was established on day 4 also halted the progression of disease. Further experiments indicated that miR-29b inhibited endometrial fibrosis via blockade of the Sp1-TGF-ß1/Smad-CTGF pathway. In conclusion, agomir-29b may act as a novel and effective therapeutic agent against IUAs.