To develop a deep-learning system for the automatic identification of triple-negative breast cancer (TNBC) solely from ultrasound images. A total of 145 patients and 831 images were retrospectively enrolled at Peking Union College Hospital from April 2018 to March 2019. Ultrasound images and clinical information were collected accordingly. Molecular subtypes were determined from immunohistochemical (IHC) results. A CNN with VGG-based architecture was then used to predict TNBC. The model’s performance was evaluated using randomized k-fold stratified cross-validation. A t-SNE analysis and saliency maps were used for model visualization. TNBC was identified in 16 of 145 (11.03%) patients. One hundred fifteen (80%) patients, 15 (10%) patients, and 15 (10%) patients formed the train, validation, and test set respectively. The deep learning system exhibits good efficacy, with an AUC of 0.86 (95% CI: 0.64, 0.95), an accuracy of 85%, a sensitivity of 86%, a specificity of 86%, and an F1-score of 0.74. In addition, the internal representation features learned by the model showed clear differentiation across molecular subtype groups. Such a deep learning system can automatically predict triple-negative breast cancer preoperatively and accurately. It may help to get to more precise and comprehensive management. Graphical Abstract

Thickened synovium with a hypoxic oxygenation status as measured with photoacoustic imaging was associated with fewer Doppler US signals and higher disease activity in study participants with rheum... Background Synovial hypoxia is a hallmark of rheumatoid arthritis (RA). Photoacoustic (PA) imaging, based on the use of laser-generated US, can detect the oxygenation status of tissue in individual...

Objective: To investigate the feasibility of a CAD system S-detect on a database from a single Chinese medical center. Materials and methods: An experienced radiologist performed breast US examinations and made assessments of 266 consecutive breast lesions in 227 patients. S-detect classified the lesions automatically in a dichotomous form. An in-training resident who was blind to both the US diagnostic results and histological results reviewed the images afterward. The final histological results were considered as the diagnostic gold standard. The diagnostic performances and interrater agreements were analyzed. Results: A total of 266 focal breast lesions (161 benign lesions and 105 malignant lesions) were assessed in this study. S-detect had a lower sensitivity (87.07%) and a higher specificity (72.27%) compared with the experienced radiologist (sensitivity 98.1% and specificity 65.43%). The sensitivity and specificity of S-detect were better than that of the resident (sensitivity 82.86% and specificity 68.94%). The AUC value of S-detect (0.807) showed no significant difference with the experienced radiologist (0.817) and was higher than that of the resident (0.758). S-detect had moderate agreement with the experienced radiologist. Conclusion: In this single-center study, a high level of diagnostic performance of S-detect on 266 breast lesions of Chinese women was observed. S-detect had almost equal diagnostic capacity with an experienced radiologist and performed better than a novice reader. S-detect was also distinguished for its high specificity. These results supported the feasibility of S-detect in aiding the diagnosis of breast lesions on an independent database.

Pyroptosis is a newly recognized type of programmed cell death mediated by the gasdermin family and caspase. It is characterized by the formation of inflammasomes and the following inflammatory responses. Recent studies have elucidated the value of pyroptosis induction in cancer treatment. The inflammatory cytokines produced during pyroptosis can trigger immune responses to suppress malignancy. Physical approaches for cancer treatment, including radiotherapy, light-based techniques (photodynamic and photothermal therapy), ultrasound-based techniques (sonodynamic therapy and focused ultrasound), and electricity-based techniques (irreversible electroporation and radiofrequency ablation), are effective in clinical application. Recent studies have reported that pyroptosis is involved in the treatment process of physical approaches. Manipulating pyroptosis using physical approaches can be utilized in combating cancer, according to recent studies. Pyroptosis-triggered immunotherapy can be combined with the original anti-tumor methods to achieve a synergistic therapy and improve the therapeutic effect. Studies have also revealed that enhancing pyroptosis may increase the sensitivity of cancer cells to some physical approaches. Herein, we present a comprehensive review of the literature focusing on the associations between pyroptosis and various physical approaches for cancer and its underlying mechanisms. We also discussed the role of pyroptosis-triggered immunotherapy in the treatment process of physical manipulation.

NF‐κB, a critical cytokine of inflammatory bowel diseases (IBD), is a viable marker to reflect the inflammatory activity of the intestine. We aimed to develop NF‐κB‐targeted microbubbles (MBs) and perform molecular contrast‐enhanced ultrasound (CEUS) to quantify NF‐κB expressions on the intestinal wall in IBD mice in vivo. In this study, NF‐κB‐targeted MBs were fabricated by connecting biotin‐loaded NF‐κB antibodies and avidin‐loaded MBs. NF‐κB‐targeted MBs presented as transparent and round bubbles with an average diameter of 1.03/μm±0.01. The specific binding of targeted MBs and inflammatory cells was validated by in vitro experiments, including flow cytometry, Western blot and immunofluorescence, which revealed the specific binding of targeted MBs and inflammatory cells. Subsequently, NF‐κB‐targeted CEUS imaging was performed on mice with chemical‐induced colitis, and the peak intensity (PI) and time‐to‐peak (TTP) were quantified. Pathological and immunohistochemical (IHC) examinations were further implemented. For the target CEUS group, fast enhancement followed by slow subsiding was observed. The PI of target CEUS of the IBD mice was significantly higher than that of non‐target CEUS of the IBD mice, healthy controls and target CEUS of the treated IBD mice (34835%[13379–73492%] VS 437%[236–901%], 130%[79–231%], 528%[274–779%], p<0.0001), in accordance with the IHC results of NF‐κB expressions. The TTP of target CEUS of the treated mice was significantly higher than that of untreated mice (35.7s [18.1–49.5s] VS 8.3s [4.2–12.5s], p<0.0001). Therefore, we suggested that NF‐κB‐targeted CEUS could accurately detect and quantify NF‐κB expressions on the intestinal walls of IBD, enabling the evaluation of intestinal inflammation.

To make comprehensive assessments of some rheumatoid diseases, a more reliable imaging method for evaluating joint lesions is required. Photoacoustic imaging (PAI) is a state-of-the-art imaging technique, providing new options for diagnosing joint disease. In light of the recent preclinical studies, detailed morphological structures and micro-vessels of small joints, especially the finger joints, could be visualized by PAI with high spatial resolution and optical contrast using different PA implementations. By measuring the signals of oxygenated and deoxygenated hemoglobin through dual-wavelength PAI, oxygenation of local tissues can be identified, thus enabling functional PA imaging. Notably, among various PA systems, the co-registration of PAI into high-end commercial US units with a special-designed handheld PA/US probe can be of great value in further clinical application. Molecular PAI of small joints can also be performed using exogenous PA chromophores. In this article, we aim to inform readers of this new technique in joint imaging and its potential use, to impart a deeper understanding of medical imaging in this field.