Breast cancer is the most common cancer among women worldwide. Medical ultrasound imaging is one of the widely applied breast imaging methods for breast tumors. Automatic breast ultrasound (BUS) image segmentation can measure the size of tumors objectively. However, various ultrasound artifacts hinder segmentation. We proposed an attention-supervised full-resolution residual network (ASFRRN) to segment tumors from BUS images.

In the proposed method, Global Attention Upsample (GAU) and deep supervision were introduced into a full-resolution residual network (FRRN), where GAU learns to merge features at different levels with attention for deep supervision. Two datasets were employed for evaluation. One (Dataset A) consisted of 163 BUS images with tumors (53 malignant and 110 benign) from UDIAT Centre Diagnostic, and the other (Dataset B) included 980 BUS images with tumors (595 malignant and 385 benign) from the Sun Yat-sen University Cancer Center. The tumors from both datasets were manually segmented by mumors from BUS images. It achieved high segmentation accuracy with a reduced parameter number.

We proposed ASFRRN, which combined with FRRN, attention mechanism, and deep supervision to segment tumors from BUS images. It achieved high segmentation accuracy with a reduced parameter number.Hynobiidae are a clade of salamanders that diverged early within the crown radiation and that retain a considerable number of features plesiomorphic for the group. Their evolutionary history is informed by a fossil record that extends to the Middle Jurassic Bathonian time. Our understanding of the evolution within the total group of Hynobiidae has benefited considerably from recent discoveries of stem hynobiids but is constrained by inadequate anatomical knowledge of some extant forms. Pseudohynobius is a derived hynobiid clade consisting of five to seven extant species living endemic to southwestern China. Although this clade has been recognized for over 37 years, osteological details of these extant hynobiids remain elusive, which undoubtedly has contributed to taxonomic controversies over the hynobiid complex Liua-Protohynobius-Pseudohynobius. Here we provide a bone-by-bone study of the cranium in the five extant species of Pseudohynobius (Ps. flavomaculatus, Ps. Ki16425 LPA Receptor antagonist guizhouensis, Ps. jinfo, Ps. kuankuoshuiensis and Ps. shuichengensis) based on x-ray computer tomography data for 18 specimens. Our results indicate that the cranium in each of these species has a combination of differences in morphology, proportions and articulation patterns in both dermal and endochondral bones. Our study establishes a range of intraspecific differences that will serve as organizing hypotheses for future studies as more extensive collections of these species become available. Morphological features in the cranium for terrestrial ecological adaptation in Hynobiidae are summarized. Based on the results, we also discuss the evolution and development of several potential synapomorphies of Hynobiidae, including features of the orbitosphenoid and articular.

Population-based data on epilepsy syndromes and etiologies in early onset epilepsy are scarce. The use of next-generation sequencing (NGS) has hitherto not been reported in this context. The aim of this study is to describe children with epilepsy onset before 2years of age, and to explore to what degree whole exome and whole genome sequencing (WES/WGS) can help reveal a molecular genetic diagnosis.

Children presenting with a first unprovoked epileptic seizure before age 2years and registered in the Stockholm Incidence Registry of Epilepsy (SIRE) between September 1, 2001 and December 31, 2006, were retrieved and their medical records up to age 7years reviewed. Children who met the epilepsy criteria were included in the study cohort. WES/WGS was offered in cases of suspected genetic etiology regardless of whether a structural or metabolic diagnosis had been established.

One hundred sixteen children were included, of which 88 had seizure onset during the first year of life and 28 during the second, corresan identify a molecular diagnosis in a substantial number of children, and should be included in the work-up, especially in cases of epileptic encephalopathy, cerebral malformation, or metabolic disease without molecular diagnosis. A genetic diagnosis is essential to genetic counselling, prenatal diagnostics, and precision therapy.

To investigate the utility of gradient dose segmented analysis (GDSA) in combination with in vivo electronic portal imaging device (EPID) images to predict changes in the PTV mean dose for patient cases. Also, we use the GDSA to retrospectively analyze patients treated in our clinic to assess deviations for different treatment sites and use time-series data to observe any day-to-day changes.

In vivo EPID transit images acquired on the Varian Halcyon were analyzed for simulated errors in a phantom, including gas bubbles, weight loss, patient shifts, and an arm erroneously in the field. GDSA threshold parameters were tuned to maximize the coefficient of determination (R

) between GDSA metrics and the change in the PTV mean dose (D

) as estimated in a treatment planning system (TPS). Similarly for a gamma analysis, the gamma criteria were adjusted to maximize R

between gamma pass rate and the change in the PTV D

from the TPS. The predictive accuracy of these models was tested on patient data measurinthe change in the PTV D

, giving a simple, quantitative metric by which to flag patients with clinically meaningful deviations in treatment. Averaging the GDSA metric over all patients treated on a given day and tracking daily variations can also provide a flag for any systematic deviations in treatment due to machine performance.

GDSA of in vivo EPID images is a useful technique for monitoring patient changes during the course of treatment, particularly weight loss and tumor shrinkage. The GDSA mean provides a quantitative estimate of the change in the PTV Dmean , giving a simple, quantitative metric by which to flag patients with clinically meaningful deviations in treatment. Averaging the GDSA metric over all patients treated on a given day and tracking daily variations can also provide a flag for any systematic deviations in treatment due to machine performance.