There are some problems in positron emission tomography/ computed tomography (PET/CT) lung images, such as little information of feature pixels in lesion regions, complex and diverse shapes, and blurred boundaries between lesions and surrounding tissues, which lead to inadequate extraction of tumor lesion features by the model. To solve the above problems, this paper proposes a dense interactive feature fusion Mask RCNN (DIF-Mask RCNN) model. Firstly, a feature extraction network with cross-scale backbone and auxiliary structures was designed to extract the features of lesions at different scales. Then, a dense interactive feature enhancement network was designed to enhance the lesion detail information in the deep feature map by interactively fusing the shallowest lesion features with neighboring features and current features in the form of dense connections. Finally, a dense interactive feature fusion feature pyramid network (FPN) network was constructed, and the shallow information was added to the deep features one by one in the bottom-up path with dense connections to further enhance the model’s perception of weak features in the lesion region. The ablation and comparison experiments were conducted on the clinical PET/CT lung image dataset. The results showed that the APdet, APseg, APdet_s and APseg_s indexes of the proposed model were 67.16%, 68.12%, 34.97% and 37.68%, respectively. Compared with Mask RCNN (ResNet50), APdet and APseg indexes increased by 7.11% and 5.14%, respectively. DIF-Mask RCNN model can effectively detect and segment tumor lesions. It provides important reference value and evaluation basis for computer-aided diagnosis of lung cancer.
Objective To systematically evaluate the incidence and mortality burden of ischemic heart disease (IHD) in the elderly population (aged ≥60 years) globally and in China from 1990 to 2021, utilizing the Global Burden of Disease (GBD) 2021 database, and to predict its future trends, thereby providing data support for precise prevention and control decisions regarding IHD in an increasingly aging society. Methods Data on the incidence and mortality burden of IHD among the elderly globally, in China, and across five sociodemographic regions were extracted from the GBD 2021 database. Joinpoint regression analysis was used to examine the temporal trends of the age-standardized incidence rate (ASIR) and age-standardized death rate (ASDR). A Bayesian age-period-cohort model was employed to predict the trends of IHD burden from 2022 to 2040. Results In 2021, the number of IHD cases among the elderly was 21 975 600 globally and 5 445 100 in China. From 1990 to 2021, the global ASIR showed an overall decreasing trend (AAPC=?0.55%, P<0.001), whereas China exhibited an overall increasing trend (AAPC=0.41%, P<0.001). In 2021, the number of IHD deaths among the elderly was 7 444 000 globally and 1 742 800 in China. Similarly, the global ASDR demonstrated an overall decreasing trend from 1990 to 2021 (AAPC=?1.27%, P<0.001), while China showed an opposite trend (AAPC=0.68%, P=0.001). Additionally, in both 1990 and 2021, the ASIR and ASDR of IHD among elderly males (globally and in China) were higher than those among elderly females in the same period. In 2021, the age groups with the highest proportion of IHD cases among the elderly (both globally and in China) were 65–69 years and 70–74 years, while the 80–84 and 85–89 years groups had the highest proportions of IHD deaths. Predictive analysis indicated that from 2022 to 2040, the number of IHD cases and deaths among the total elderly population, both males and females, is likely to show a continuous upward trend both globally and in China. Conclusions The burden of IHD among elderly population remains substantial and growing globally and in China, in terms of incidence and mortality. Comprehensive strategies are urgently required, including policy guidance and health education to enhance public awareness, as well as early screening, diagnosis, and treatment to reduce the risk of disease progression. Such efforts are essential to effectively mitigate the increasingly heavy disease burden of IHD in the aging population.
