Supervised representation learning based on various levels of pediatric radiographic views for transfer learning.

Transfer learning plays a pivotal role in addressing the paucity of data, expediting training processes, and enhancing model performance. Nonetheless, the prevailing practice of transfer learning predominantly relies on pre-trained models designed for the natural image domain, which may not be well-suited for the medical image domain in grayscale. Recognizing the significance of leveraging transfer learning in medical research, we undertook the construction of class-balanced pediatric radiograph datasets collectively referred to as PedXnets, grounded in radiographic views using the pediatric radiographs collected over 24 years at Asan Medical Center. For PedXnets pre-training, approximately 70,000 X-ray images were utilized. Three different pre-training weights of PedXnet were constructed using Inception V3 for various radiation perspective classifications: Model-PedXnet-7C, Model-PedXnet-30C, and Model-PedXnet-68C. We validated the transferability and positive effects of transfer learning of PedXnets through pediatric downstream tasks including fracture classification and bone age assessment (BAA). The evaluation of transfer learning effects through classification and regression metrics showed superior performance of Model-PedXnets in quantitative assessments. Additionally, visual analyses confirmed that the Model-PedXnets were more focused on meaningful regions of interest.

MuSiC-ViT: A multi-task Siamese convolutional vision transformer for differentiating change from no-change in follow-up chest radiographs.

A major responsibility of radiologists in routine clinical practice is to read follow-up chest radiographs (CXRs) to identify changes in a patient's condition. Diagnosing meaningful changes in follow-up CXRs is challenging because radiologists must differentiate disease changes from natural or benign variations. Here, we suggest using a multi-task Siamese convolutional vision transformer (MuSiC-ViT) with an anatomy-matching module (AMM) to mimic the radiologist's cognitive process for differentiating baseline change from no-change. MuSiC-ViT uses the convolutional neural networks (CNNs) meet vision transformers model that combines CNN and transformer architecture. It has three major components: a Siamese network architecture, an AMM, and multi-task learning. Because the input is a pair of CXRs, a Siamese network was adopted for the encoder. The AMM is an attention module that focuses on related regions in the CXR pairs. To mimic a radiologist's cognitive process, MuSiC-ViT was trained using multi-task learning, normal/abnormal and change/no-change classification, and anatomy-matching. Among 406 K CXRs studied, 88 K change and 115 K no-change pairs were acquired for the training dataset. The internal validation dataset consisted of 1,620 pairs. To demonstrate the robustness of MuSiC-ViT, we verified the results with two other validation datasets. MuSiC-ViT respectively achieved accuracies and area under the receiver operating characteristic curves of 0.728 and 0.797 on the internal validation dataset, 0.614 and 0.784 on the first external validation dataset, and 0.745 and 0.858 on a second temporally separated validation dataset. All code is available at https://github.com/chokyungjin/MuSiC-ViT.

Unsupervised anomaly detection with generative adversarial networks in mammography.

Breast cancer is a common cancer among women, and screening mammography is the primary tool for diagnosing this condition. Recent advancements in deep-learning technologies have triggered the implementation of research studies via mammography. Semi-supervised or unsupervised methods are often used to overcome the limitations of supervised learning, such as manpower and time, for labeling in clinical situations where abnormal data are significantly lacking. Accordingly, we proposed a generative model that uses a state-of-the-art generative network (StyleGAN2) to create high-quality synthetic mammographic images and an anomaly detection method to detect breast cancer on mammograms in unsupervised methods. The generation model was trained via only normal mammograms and breast cancer classification was performed via anomaly detection using 50 breast cancer and 50 normal mammograms that did not overlap with the dataset for generative model learning. Our generative model has shown comparable fidelity to real images, and the anomaly detection method via this generative model showed high sensitivity, demonstrating its potential for breast cancer screening. This method could differentiate between normal and cancer-positive mammogram and help overcome the weakness of current supervised methods.

Downregulated angiopoietin-like protein 8 production at calving related to changes in lipid metabolism in dairy cows.

Acute physiological adaptation of lipid metabolism during the postpartum transition period of cows facilitates peripheral metabolic regulation. Hepatokines, which are hormones secreted from hepatocytes, are presumed to play a critical role in systemic metabolic regulation. Angiopoietin-like protein 8 (ANGPTL8) has been identified as a novel hepatokine associated with circulating triglyceride concentrations in mice and humans. However, regulation of ANGPTL8 and its physiological effects is still unknown in cattle. The present study aimed to reveal changes in ANGPTL8 expression and secretion during the periparturient period, and to investigate its regulatory effect on adipocytes and mammary epithelial cells. In the peripartum period, liver ANGPTL8 mRNA expression was lesser on the day of parturition and 1 wk postpartum than it was 1 wk before parturition (P < 0.05). Moreover, plasma ANGPTL8 concentrations decreased on the day of parturition as compared with that 1 wk before parturition (P < 0.05). In addition, ANGPTL8 expression in cultured bovine hepatocytes was downregulated after oleate and palmitate treatment but upregulated after insulin treatment (P < 0.05). ANGPTL8 decreased hormone-sensitive lipase (HSL) expression in differentiated adipocytes and cluster of differentiation 36 (CD36), fatty acid synthase (FAS), acetyl-coa carboxylase (ACC), and stearoyl-coa desaturase (SCD) in cultured bovine mammary epithelial cells (P < 0.05). These data suggest that hepatic ANGPTL8 production was downregulated postpartum when the cows experienced a negative energy balance. This downregulation was associated with increased concentrations of NEFA and decreased concentrations of insulin in lactating cows, and it facilitated lipid mobilization from adipose tissue to the mammary glands. We speculate that ANGPTL8 might have beneficial effects in reverting or improving the physiological adaptation and pathological processes of lipid metabolism during the peripartum period.

Identification of circulating miRNA involved in meat yield of Korean cattle.

Cattle plays an important role in providing essential nutrients through meat production. Thus, we focused on epigenetic factors associated with meat yield. To investigate circulating miRNAs that are involved with meat yield and connect biofluids and longissimus dorsi (LD) muscle in Korean cattle, we performed analyses of the carcass characteristics, miRNA array, qPCR, and bioinformatics. Carcass characteristics relative to the yield grade (YG) showed that the yield index and rib eye area were the highest, whereas the backfat thickness was the lowest for YG A (equal to high YG) cattle among the three YGs. miRNA array sorted the circulating miRNAs that connect biofluids and LD muscle. miRNA qPCR showed that miR-15a (r = 0.84), miR-26b (r = 0.91), and miR-29c (r = 0.92) had positive relationships with biofluids and LD muscle. In YG A cattle, miR-26b was considered to be a circulating miRNA connecting biofluids and LD muscle because the target genes of miR-26b were more involved with myogenesis. Then, miR-26b-targeted genes, DIAPH3 and YOD1, were downregulated in YG A cattle. Our results suggest that miR-15a, miR-26b, and miR-29c are upregulated in biofluids and LD muscle, whereas DIAPH3 and YOD1 are downregulated in the LD muscle of finishing cattle steers.