Dynamic positron emission tomography (dPET) is currently a widely used medical imaging technique for the clinical diagnosis, staging and therapy guidance of all kinds of human cancers. Higher temporal imaging resolution for the early stage of radiotr
acer metabolism is desired; however, in this case, the reconstructed images with short frame durations always suffer from a limited image signal-to-noise ratio (SNR), which results in unsatisfactory image spatial resolution. In this work, we proposed a dPET processing method that denoises images with short frame durations via pixel-level time-activity curve (TAC) correction based on third-order Hermite interpolation (Pitch-In). The proposed method was validated using total-body dynamic PET image data and compared to several state-of-the-art methods to demonstrate its superior performance in terms of high temporal resolution dPET image noise reduction and imaging contrast. Higher stability and feasibility of the proposed Pitch-In method for future clinical application with high temporal resolution (HTR) dPET imaging can be expected.
A key promise of AI applications in healthcare is in increasing access to quality medical care in under-served populations and emerging markets. However, deep learning models are often only trained on data from advantaged populations that have the in
frastructure and resources required for large-scale data collection. In this paper, we aim to empirically investigate the potential impact of such biases on breast cancer detection in mammograms. We specifically explore how a deep learning algorithm trained on screening mammograms from the US and UK generalizes to mammograms collected at a hospital in China, where screening is not widely implemented. For the evaluation, we use a top-scoring model developed for the Digital Mammography DREAM Challenge. Despite the change in institution and population composition, we find that the model generalizes well, exhibiting similar performance to that achieved in the DREAM Challenge, even when controlling for tumor size. We also illustrate a simple but effective method for filtering predictions based on model variance, which can be particularly useful for deployment in new settings. While there are many components in developing a clinically effective system, these results represent a promising step towards increasing access to life-saving screening mammography in populations where screening rates are currently low.
Inspired by the profound physical connotations and potential application prospects of the valleytronics, we design a two-dimensional (2D) WS2/h-VN magnetic van der Waals (vdW) heterostructure and study the control of valley degree of freedom through
the first-principles calculations. A considerable spin splitting of 627 meV is obtained at the K valley, accompanied with a strong suppression of that at the K valley. An intrinsic large valley splitting of 376 meV is generated in the valence band, which corresponds to an effective Zeeman magnetic field of 2703 T. Besides of the valence band, the conduction band of WS2 possesses a remarkable spin splitting also, and valley labelled dark exciton states are present at the K valley. The strengths of spin and valley splitting relied on the interfacial orbital hybridization are further tuned continually by the in-plane strain and interlayer spacing. Maximum spin and valley splitting of 654 and 412 meV are finally achieved, respectively, and the effective Zeeman magnetic field can be enhanced to 2989T with a -3 % strain. Time-reversal symmetry breaking and the sizable Berry curvature in the heterostructure lead to a prominent anomalous Hall conductivity at the K and K valleys. Based on these finding, a prototype filter device for both the valley and spin is proposed.
