There have been major developments in deep learning in computer vision since the 2010s. Deep learning has contributed to a wealth of data in medical image processing, and semantic segmentation is a salient technique in this field. This study retrospectively reviews recent studies on the application of deep learning for segmentation tasks in medical imaging and proposes potential directions for future development, including model development, data augmentation processing, and dataset creation. The strengths and deficiencies of studies on models and data augmentation, as well as their application to medical image segmentation, were analyzed. Fully convolutional network developments have led to the creation of the U-Net and its derivatives. Another noteworthy image segmentation model is DeepLab. Regarding data augmentation, due to the low data volume of medical images, most studies focus on means to increase the wealth of medical image data. Generative adversarial networks (GAN) increase data volume via deep learning. Despite the increasing types of medical image datasets, there is still a deficiency of datasets on specific problems, which should be improved moving forward. Considering the wealth of ongoing research on the application of deep learning processing to medical image segmentation, the data volume and practical clinical application problems must be addressed to ensure that the results are properly applied.

Background: Head and neck cancer is highly prevalent in Taiwan. Its treatment mainly relies on clinical staging, usually diagnosed from images. A major part of the diagnosis is whether lymph nodes are involved in the tumor. We present an algorithm for analyzing clinical images that integrates a deep learning model with image processing and attempt to analyze the features it uses to classify lymph nodes. Methods: We retrospectively collected pretreatment computed tomography images and surgery pathological reports for 271 patients diagnosed with, and subsequently treated for, naïve oral cavity, oropharynx, hypopharynx, and larynx cancer between 2008 and 2018. We chose a 3D UNet model trained for semantic segmentation, which was evaluated for inference in a test dataset of 29 patients. Results: We annotated 2527 lymph nodes. The detection rate of all lymph nodes was 80%, and Dice score was 0.71. The model has a better detection rate at larger lymph nodes. For those identified lymph nodes, we found a trend where the shorter the short axis, the more negative the lymph nodes. This is consistent with clinical observations. Conclusions: The model showed a convincible lymph node detection on clinical images. We will evaluate and further improve the model in collaboration with clinical physicians.

Ischemic cardiac or cerebrovascular disease (ICCD) survivors represent a subpopulation with a high cancer risk. Antiplatelet medications, such as aspirin, remain a fundamental therapy for the secondary prevention of ischemic attack in these patients. We conducted a population-based cohort study to investigate the association of long-term low-dose aspirin use with the risk of primary cancer in ICCD survivors. Patients aged ≥20 years with newly diagnosed ICCD (n = 98,519) between January 2000 and December 2013 were identified from the Taiwan National Health Insurance Research Database. The aspirin user and nonuser groups (each n = 24,030) were propensity-matched (1:1) for age, sex, comorbidities, prior medications, ICCD diagnosis year, and year of index dates. The incidence rate of primary cancer was significantly lower in the user group (6.49/1000 person-years) than in the nonuser group (14.04/1000 person-years). Multivariate Cox regression analysis indicated that aspirin use was an independent factor associated with a reduced risk of primary cancer (aHR (95% confidence interval) = 0.42 (0.38–0.45)) after adjustment. Kaplan–Meier curve analysis revealed that the cumulative incidence rate of primary cancer was significantly lower (p < 0.0001) in the user group than in the nonuser group over the 14-year follow-up period. Subgroup analyses demonstrated that this anticancer effect increased with duration of treatment and with similar estimates in women and men. In addition, aspirin use was associated with a reduced risk for seven out of the ten most common cancers in Taiwan. These findings suggest the anticancer effect of aspirin in ICCD survivors and provide information for assessing the benefit-to-risk profile of aspirin as an antiplatelet medication in these patients.