Arteriovenous malformations (AVMs) are vascular anomalies where arteries and veins are directly connected through a complex, tangled web of abnormal arteries and veins instead of a normal capillary network. AVMs in the brain, lung, and visceral organs, including the liver and gastrointestinal tract, result in considerable morbidity and mortality. AVMs are the underlying cause of three major clinical symptoms of a genetic vascular dysplasia termed hereditary hemorrhagic telangiectasia (HHT), which is characterized by recurrent nosebleeds, mucocutaneous telangiectases, and visceral AVMs and caused by mutations in one of several genes, including activin receptor–like kinase 1 (ALK1). It remains unknown why and how selective blood vessels form AVMs, and there have been technical limitations to observing the initial stages of AVM formation. Here we present in vivo evidence that physiological or environmental factors such as wounds in addition to the genetic ablation are required for Alk1-deficient vessels to develop to AVMs in adult mice. Using the dorsal skinfold window chamber system, we have demonstrated for what we believe to be the first time the entire course of AVM formation in subdermal blood vessels by using intravital bright-field images, hyperspectral imaging, fluorescence recordings of direct arterial flow through the AV shunts, and vascular casting techniques. We believe our data provide novel insights into the pathogenetic mechanisms of HHT and potential therapeutic approaches.

Transfer learning is a machine learning approach that reuses a learning method developed for a task as the starting point for a model on a target task. The goal of transfer learning is to improve performance of target learners by transferring the knowledge contained in other (but related) source domains. As a result, the need for large numbers of target-domain data is lowered for constructing target learners. Due to this immense property, transfer learning techniques are frequently used in ultrasound breast cancer image analyses. In this review, we focus on transfer learning methods applied on ultrasound breast image classification and detection from the perspective of transfer learning approaches, pre-processing, pre-training models, and convolutional neural network (CNN) models. Finally, comparison of different works is carried out, and challenges—as well as outlooks—are discussed.

3D in vivo optical imaging on a mouse has been obtained using a 2D MEMS mirror for lateral scanning in a time-domain optical coherence tomography (OCT) system. The MEMS mirror aperture size is 1 × 1 mm², and the device footprint is 2 × 2 mm². The MEMS mirror scans ± 30° optical angles about both x and y-axis at only 5.5V DC voltage. An endoscopic probe with an outer diameter of 5.8 mm has been designed, manufactured and packaged. The probe scans an average transverse area of 2 mm × 2 mm. The imaging speed of the probe is about 2.5 frames per second, limited by the speed of the employed optical delay line.

Breast cancer diagnosis is one of the many areas that has taken advantage of artificial intelligence to achieve better performance, despite the fact that the availability of a large medical image dataset remains a challenge. Transfer learning (TL) is a phenomenon that enables deep learning algorithms to overcome the issue of shortage of training data in constructing an efficient model by transferring knowledge from a given source task to a target task. However, in most cases, ImageNet (natural images) pre-trained models that do not include medical images, are utilized for transfer learning to medical images. Considering the utilization of microscopic cancer cell line images that can be acquired in large amount, we argue that learning from both natural and medical datasets improves performance in ultrasound breast cancer image classification. The proposed multistage transfer learning (MSTL) algorithm was implemented using three pre-trained models: EfficientNetB2, InceptionV3, and ResNet50 with three optimizers: Adam, Adagrad, and stochastic gradient de-scent (SGD). Dataset sizes of 20,400 cancer cell images, 200 ultrasound images from Mendeley and 400 ultrasound images from the MT-Small-Dataset were used. ResNet50-Adagrad-based MSTL achieved a test accuracy of 99 ± 0.612% on the Mendeley dataset and 98.7 ± 1.1% on the MT-Small-Dataset, averaging over 5-fold cross validation. A p-value of 0.01191 was achieved when comparing MSTL against ImageNet based TL for the Mendeley dataset. The result is a significant improvement in the performance of artificial intelligence methods for ultrasound breast cancer classification compared to state-of-the-art methods and could remarkably improve the early diagnosis of breast cancer in young women.

Breast mass identification is a crucial procedure during mammogram-based early breast cancer diagnosis. However, it is difficult to determine whether a breast lump is benign or cancerous at early stages. Convolutional neural networks (CNNs) have been used to solve this problem and have provided useful advancements. However, CNNs focus only on a certain portion of the mammogram while ignoring the remaining and present computational complexity because of multiple convolutions. Recently, vision transformers have been developed as a technique to overcome such limitations of CNNs, ensuring better or comparable performance in natural image classification. However, the utility of this technique has not been thoroughly investigated in the medical image domain. In this study, we developed a transfer learning technique based on vision transformers to classify breast mass mammograms. The area under the receiver operating curve of the new model was estimated as 1 ± 0, thus outperforming the CNN-based transfer-learning models and vision transformer models trained from scratch. The technique can, hence, be applied in a clinical setting, to improve the early diagnosis of breast cancer.