A robust and efficient AI assistant for breast tumor segmentation from DCE-MRI via a spatial-temporal framework.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows screening, follow up, and diagnosis for breast tumor with high sensitivity. Accurate tumor segmentation from DCE-MRI can provide crucial information of tumor location and shape, which significantly influences the downstream clinical decisions. In this paper, we aim to develop an artificial intelligence (AI) assistant to automatically segment breast tumors by capturing dynamic changes in multi-phase DCE-MRI with a spatial-temporal framework. The main advantages of our AI assistant include (1) robustness, i.e., our model can handle MR data with different phase numbers and imaging intervals, as demonstrated on a large-scale dataset from seven medical centers, and (2) efficiency, i.e., our AI assistant significantly reduces the time required for manual annotation by a factor of 20, while maintaining accuracy comparable to that of physicians. More importantly, as the fundamental step to build an AI-assisted breast cancer diagnosis system, our AI assistant will promote the application of AI in more clinical diagnostic practices regarding breast cancer.

A quality improvement method for lung LDCT images.

BACKGROUND: Low dose computed tomography (LDCT) reduces radiation damage to patients. However, with the decrease of radiation dose, LDCT images of the lung often appear some serious problems such as poor contrast, noise and streak artifacts. OBJECTIVE: To improve the quality of lung LDCT images, this study proposed and investigated a new denoising method based on classification training structure combined dictionary for lung LDCT images. METHODS: First, top-hat transform and anisotropic diffusion with a shock filter (ADSF) algorithm are used to enhance the image contrast and image details. Second, an adaptive dictionary is trained and used for noise reduction. Third, more image details are extracted from the residual image by using the atom activity measurement. The final result is obtained by combining the dictionary denoising result with the extracted detail information. The proposed method is then validated by both simulated and clinical lung LDCT images. Four metrics including Contrast-to-Noise Ratio (CNR), Noise Suppression Index (NSI), Edge Preserving Index (EPI), and Blurring Index (BI) are computed to quantitatively evaluate image quality. RESULTS: The results showed that the CNR, NSI, EPI, and BI of our method reached 8.953, 0.9500, 0.7230 and 0.0170, respectively. Noise and streak artifacts can be removed from lung LDCT images while keeping and retaining more details. CONCLUSIONS: Comparing with the results of other methods tested using the same dataset, this study demonstrated that our new method significantly improved quality of the lung LDCT images.

Integration of Biochemical, Cellular, and Genetic Indicators for Understanding the Aging Process in a Bivalve Mollusk Chlamys farreri.

The major causal factors for the irreversible decline in physical vitality during organismal aging are postulated to be a chronic state of cellular redox imbalance, metabolic toxicity, and impaired energy homeostasis. We assessed whether the relevant enzyme activity, oxidative stress, and intracellular ATP might be causally involved in the aging of short-lived Chlamys farreri (life span 4~5 years). A total of eight related biochemical and cellular indicators were chosen for the subsequent analysis. All the indicators were measured in seven different tissues from scallops aged one to four years, and our data support that the aging of C. farreri is associated with attenuated tissue enzyme activity as well as a decreased metabolic rate. Through principal component analysis, we developed an integrated vigor index for each tissue for comprehensive age-related fitness evaluation. Remarkably, all tissue-integrated vigor indexes significantly declined with age, and the kidney was observed to be the most representative tissue. Further transcriptional profiling of the enzymatic genes provided additional detail on the molecular responses that may underlie the corresponding biochemical results. Moreover, these critical molecular responses may be attributed to the conserved hierarchical regulators, e.g., FOXO, AMPKs, mTOR, and IGF1R, which were identified as potentially novel markers for chronic fitness decline with age in bivalves. The present study provides a systematic approach that could potentially benefit the global assessment of the aging process in C. farreri and provide detailed evaluation of the biochemical, cellular, and genetic indicators that might be involved. This information may assist in a better understanding of bivalve adaptability and life span.

Genome-wide identification and expression profiling of the Wnt gene family in three bivalve molluscs.

Cellular signaling initiated by various secreted, cysteine-rich Wnt proteins plays essential roles in regulating animal development and cell stemness. By virtue of its functional diversity and importance, the Wnt gene family has received substantial research interests in a variety of animal species, from invertebrates to vertebrates. However, for bivalve molluscs, one of the ancient bilaterian groups with high morphological diversity, systematic identification and analysis of the Wnt gene family remain lacking. To shed some light on the evolutionary dynamics of this gene family and obtain a more comprehensive understanding, we analyzed the characteristics of the Wnt gene family in three bivalve molluscs, with both genome and extensive transcriptomic resources. Investigation of genomic signatures, functional domains as well as phylogenetic relationships was conducted, and 12, 11, 12 subfamilies were identified in Yesso scallop, Zhikong scallop and Pacific oyster respectively. Spatiotemporal expression profiling suggested that, some bivalve Wnts might coordinate and participate in adult organ/tissue morphogenesis and homeostasis as well as early embryonic development. The transcriptional regulation of oyster Wnt genes showed dynamic and responsive patterns under different environmental stresses, indicating that Wnts may play a role in coping with challenging intertidal environments in bivalves. To our best knowledge, this study presents the first genome-wide study of Wnt gene family in bivalves, and our findings would assist in better understanding of Wnt function and evolution in bivalve molluscs.

Characterization of an Atypical Metalloproteinase Inhibitors Like Protein (Sbp8-1) From Scallop Byssus.

Adhesion is a vital physiological process for many marine molluscs, including the mussel and scallop, and therefore it is important to characterize the proteins involved in these adhesives. Although several mussel byssal proteins were identified and characterized, the study for scallop byssal proteins remains scarce. Our previous study identified two foot-specific proteins (Sbp7, Sbp8-1), which were annotated as the tissue inhibitors of metalloproteinases (TIMPs). Evolutionary analysis suggests that the TIMP genes of Chlamys farreri had gone through multiple gene duplications during evolution, and their potential functional roles in foot may have an ancient evolutionary origin. Focusing on the Sbp8-1, the sequence alignment and biochemical analyses suggest that Sbp8-1 is an atypical TIMP. One significant feature is the presence of two extra free Cys residues at its C-terminus, which causes the Sbp8-1 polymerization. Considering the fact that the no inhibitory activity was observed and it is mainly distributed in byssal thread and plaque, we proposed that this atypical Sbp8-1 may play as the cross-linker in scallop byssus. This study facilitates not only the understanding of scallop byssus assembly, also provides the inspiration of water-resistant materials design.