Application of a deep-learning technique to non-linear images from human tissue biopsies for shedding new light on breast cancer diagnosis

Self-Supervised Image Denoising of Third Harmonic Generation Microscopic Images of Human Glioma Tissue by Transformer-Based Blind Spot (TBS) Network

Third harmonic generation (THG) microscopy shows great potential for instant pathology of brain tumor tissue during surgery. However, due to the maximal permitted exposure of laser intensity and inherent noise of the imaging system, the noise level of THG images is relatively high, which affects subsequent feature extraction analysis. Denoising THG images is challenging for modern deep-learning based methods because of the rich morphologies contained and the difficulty in obtaining the noise-free counterparts. To address this, in this work, we propose an unsupervised deep-learning network for denoising of THG images which combines a self-supervised blind spot method and a U-shape Transformer using a dynamic sparse attention mechanism. The experimental results on THG images of human glioma tissue show that our approach exhibits superior denoising performance qualitatively and quantitatively compared with previous methods. Our model achieves an improvement of 2.47-9.50 dB in SNR and 0.37-7.40 dB in CNR, compared to six recent state-of-the-art unsupervised learning models including Neighbor2Neighbor, Blind2Unblind, Self2Self+, ZS-N2N, Noise2Info and SDAP. To achieve an objective evaluation of our model, we also validate our model on public datasets including natural and microscopic images, and our model shows a better denoising performance than several recent unsupervised models such as Neighbor2Neighbor, Blind2Unblind and ZS-N2N. In addition, our model is nearly instant in denoising a THG image, which has the potential for real-time applications of THG microscopy.

Extraction of collagen morphological features from second-harmonic generation microscopy images via GLCM and CT analyses: A cross-laboratory study

Second-harmonic generation (SHG) microscopy provides a high-resolution label-free approach for noninvasively detecting collagen organization and its pathological alterations. Up to date, several imaging analysis algorithms for extracting collagen morphological features from SHG images-such as fiber size and length, order and anisotropy-have been developed. However, the dependence of extracted features on experimental setting represents a significant obstacle for translating the methodology in the clinical practice. We tackled this problem by acquiring SHG images of the same kind of collagenous sample in various laboratories using different experimental setups and imaging conditions. The acquired images were analyzed by commonly used algorithms, such as gray-level co-occurrence matrix or curvelet transform; the extracted morphological features were compared, finding that they strongly depend on some experimental parameters, whereas they are almost independent from others. We conclude with useful suggestions for comparing results obtained in different labs using different experimental setups and conditions.

Exosomal miRNAs and breast cancer: a complex theranostics interlink with clinical significance

Breast cancer (BC) remains the most challenging global health crisis of the current decade, impacting a large population of females annually. In the field of cancer research, the discovery of extracellular vesicles (EVs), specifically exosomes (a subpopulation of EVs), has marked a significant milestone. In general, exosomes are released from all active cells but tumour cell-derived exosomes (TDXs) have a great impact (TDXs miRNAs, proteins, lipid molecules) on cancer development and progression. TDXs regulate multiple events in breast cancer such as tumour microenvironment remodelling, immune cell suppression, angiogenesis, metastasis (EMT-epithelial mesenchymal transition, organ-specific metastasis), and therapeutic resistance. In BC, early detection is the most challenging event, exosome-based BC screening solved the problem. Exosome-based BC treatment is a sign of the transforming era of liquid biopsy, it is also a promising therapeutic tool for breast cancer. Exosome research goes to closer precision oncology via a single exosome profiling approach. Our hope is that this review will serve as motivation for researchers to explore the field of exosomes and develop an efficient, and affordable theranostics approach for breast cancer.

Advances of Exosomal miRNAs in Breast Cancer Progression and Diagnosis

Breast cancer is one of the most commonly diagnosed malignancies and the leading cause of cancer death in women worldwide. Although many factors associated with breast cancer have been identified, the definite etiology of breast cancer is still unclear. In addition, early diagnosis of breast cancer remains challenging. Exosomes are membrane-bound nanovesicles secreted by most types of cells and contain a series of biologically important molecules, such as lipids, proteins, and miRNAs, etc. Emerging evidence shows that exosomes can affect the status of cells by transmitting substances and messages among cells and are involved in various physiological and pathological processes. In breast cancer, exosomes play a significant role in breast tumorigenesis and progression through transfer miRNAs which can be potential biomarkers for early diagnosis of breast cancer. This review discusses the potential utility of exosomal miRNAs in breast cancer progression such as tumorigenesis, metastasis, immune regulation and drug resistance, and further in breast cancer diagnosis.