Deep learning (DL) models in breast ultrasound (BUS) image analysis face challenges with data imbalance and limited atypical tumor samples. Generative Adversarial Networks (GAN) address these challenges by providing efficient data augmentation for small datasets. However, current GAN approaches fail to capture the structural features of BUS and generated images lack structural legitimacy and are unrealistic. Furthermore, generated images require manual annotation for different downstream tasks before they can be used. Therefore, we propose a two-stage GAN framework, 2s-BUSGAN, for generating annotated BUS images. It consists of the Mask Generation Stage (MGS) and the Image Generation Stage (IGS), generating benign and malignant BUS images using corresponding tumor contours. Moreover, we employ a Feature-Matching Loss (FML) to enhance the quality of generated images and utilize a Differential Augmentation Module (DAM) to improve GAN performance on small datasets. We conduct experiments on two datasets, BUSI and Collected. Moreover, results indicate that the quality of generated images is improved compared with traditional GAN methods. Additionally, our generated images underwent evaluation by ultrasound experts, demonstrating the possibility of deceiving doctors. A comparative evaluation showed that our method also outperforms traditional GAN methods when applied to training segmentation and classification models. Our method achieved a classification accuracy of 69% and 85.7% on two datasets, respectively, which is about 3% and 2% higher than that of the traditional augmentation model. The segmentation model trained using the 2s-BUSGAN augmented datasets achieved DICE scores of 75% and 73% on the two datasets, respectively, which were higher than the traditional augmentation methods. Our research tackles imbalanced and limited BUS image data challenges. Our 2s-BUSGAN augmentation method holds potential for enhancing deep learning model performance in the field.

The detection of Mycobacterium tuberculosis (Mtb) infection plays an important role in the control of tuberculosis (TB), one of the leading infectious diseases in the world. Recent advances in artificial intelligence-aided cellular image processing and analytical techniques have shown great promises in automated Mtb detection. However, current cell imaging protocols often involve costly and time-consuming fluorescence staining, which has become a major bottleneck for procedural automation. To solve this problem, we have developed a novel automated system (AutoCellANLS) for cell detection and the recognition of morphological features in the phase-contrast micrographs by using unsupervised machine learning (UML) approaches and deep convolutional neural networks (CNNs). The detection algorithm can adaptively and automatically detect single cells in the cell population by the improved level set segmentation model with the circular Hough transform (CHT). Besides, we have designed a Cell-net by using the transfer learning strategies (TLS) to classify the virulence-specific cellular morphological changes that would otherwise be indistinguishable to the naked eye. The novel system can simultaneously classify and segment microscopic images of the cell populations and achieve an average accuracy of 95.13% for cell detection, 95.94% for morphological classification, 94.87% for sensitivity, and 96.61% for specificity. AutoCellANLS is able to detect significant morphological differences between the infected and uninfected mammalian cells throughout the infection period (2 hpi/12 hpi/24 hpi). Besides, it has overcome the drawback of manual intervention and increased the accuracy by more than 11% compared to our previous work, which used AI-aided imaging analysis to detect mycobacterial infection in macrophages. AutoCellANLS is also efficient and versatile when tailored to different cell lines datasets (RAW264.7 and THP-1 cell). This proof-of concept study provides a novel venue to investigate bacterial pathogenesis at a macroscopic level and offers great promise in the diagnosis of bacterial infections.

Due to the heterogeneity of ultrasound (US) images and the indeterminate US texture of liver fibrosis (LF), automatic evaluation of LF based on US images is still challenging. Thus, this study aimed to propose a hierarchical Siamese network that combines the information from liver and spleen US images to improve the accuracy of LF grading. There were two stages in the proposed method. In stage one, a dual-channel Siamese network was trained to extract features from paired liver and spleen patches that were cropped from US images to avoid vascular interferences. Subsequently, the L1 distance was used to quantify the liver–spleen differences (LSDs). In stage two, the pretrained weights from stage one were transferred into the Siamese feature extractor of the LF staging model, and a classifier was trained using the fusion of the liver and LSD features for LF staging. This study was retrospectively conducted on US images of 286 patients with histologically proven liver fibrosis stages. Our method achieved a precision and sensitivity of 93.92% and 91.65%, respectively, for cirrhosis (S4) diagnosis, which is about 8% higher than that of the baseline model. The accuracy of the advanced fibrosis (≥S3) diagnosis and the multi-staging of fibrosis (≤S2 vs. S3 vs. S4) both improved about 5% to reach 90.40% and 83.93%, respectively. This study proposed a novel method that combined hepatic and splenic US images and improved the accuracy of LF staging, which indicates the great potential of liver–spleen texture comparison in noninvasive assessment of LF based on US images.

Fundus diseases are among the leading causes of visual impairment and blindness, many of which could be prevented through early intervention. Ultra-widefield fundus (UWF) imaging, offering a wide field of view and enabling non-mydriatic acquisition, has emerged as an ideal modality for screening; however, the volume of cases far exceeds the diagnostic capacity of ophthalmologists, necessitating an automated diagnostic system. Nevertheless, existing deep learning algorithms often encounter challenges including high computational costs, large data requirements, and performance degradation on out-of-distribution data. Domain-adaptive fine-tuning of existing multimodal large models offers a promising pathway to address these limitations. Here, we developed an anomaly detection framework for UWF images based on CLIP. First, we proposed a dual-pathway detection mechanism for accurate anomaly detection. Second, a lightweight hybrid low-rank adapter is designed for parameter-efficient fine-tuning to bridge the domain gap between natural images and fundus images. Moreover, to address the scarcity and variability of abnormal samples, we developed an anomaly synthesis algorithm based on Poisson-blending to broaden and generalize the anomaly paradigm. With only 32 pairs of training samples, the framework achieved efficient and robust anomaly detection. The framework was evaluated on 8 independent cross-source datasets (29,739 images covering >50 anomaly patterns), yielding an average AUC of 85.93% and a peak AUC of 94.54%. Owing to its low computational and data requirements, this framework provides a practical and scalable solution for fundus disease screening and shows strong potential for clinical translation. Code and details are available through https://github.com/JohnLeo-XJTU/AnomalyUWF.