Background The clinicopathological features and prognosis of breast cancer in Asia are different from those in the Western countries. Tumor‐infiltrating immune cells can influence the outcome of patients with breast cancer, but they have not been systemically evaluated in Asian patients with breast cancer. Methods We compared the immune score, composition, and prognostic impact of infiltrating immune cells between Asian and Western patients with breast cancer by analyzing gene expression profiles from eight Gene Expression Omnibus data sets and The Cancer Genome Atlas data set. The Estimation of Stromal and Immune Cells in Malignant Tumours Using Expression Data (ESTIMATE) and Cell Type Identification by Estimating Relative Subsets of Known RNA Transcripts (CIBERSORT) algorithms were used to determine the immune score and composition of tumor‐infiltrating immune cells, respectively. Findings This study included 462 Asian patients and 2,186 Western patients. Tumors of Asian patients had significantly higher immune score, particularly in the luminal B and HER2‐enriched subtypes. High immune score was associated with favorable prognosis in both Asian and Western patients, and Asian race with a high ESTIMATE immune score provided additional power to predict longer disease‐free survival. Activated CD4 T cells and M2 macrophages were the most strongly associated with survival in both Asian and Western patients. Interpretation Our study highlights the difference in tumor immune microenvironments between Asian and Western patients. The higher ESTIMATE immune score, which represents more abundant tumor‐infiltrating immune cells, in tumors of Asian patients partly explains their favorable prognosis. Implications for Practice The tumor microenvironment serves as an interface that affects the human body's reaction to cancer cells. Evidence has revealed that tumor‐infiltrating immune cells were associated with patient prognosis. This study demonstrated the disparity of tumor microenvironments and their prognostic impact between Asian and Western patients with breast cancer. The differences in immune score partially explained the racial survival differences noted in recent studies. Integrated analysis of tumor cells, tumor microenvironment, and racial effect may significantly improve recurrence risk prediction for patients with stage I–III breast cancer. Because the effect of tumor microenvironment varies across different populations, a model of interaction between immune score and race/ethnicity is recommended in accessing the risk of patients with cancer.

Background: Tumor-infiltrating leukocytes (TILs) are immune cells surrounding tumor cells, and several studies have shown that TILs are potential survival predictors in different cancers. However, few studies have dissected the differences between hepatitis B- and hepatitis C-related hepatocellular carcinoma (HBV−HCC and HCV−HCC). Therefore, we aimed to determine whether the abundance and composition of TILs are potential predictors for survival outcomes in HCC and which TILs are the most significant predictors. Methods: Two bioinformatics algorithms, ESTIMATE and CIBERSORT, were utilized to analyze the gene expression profiles from 6 datasets, from which the abundance of corresponding TILs was inferred. The ESTIMATE algorithm examined the overall abundance of TILs, whereas the CIBERSORT algorithm reported the relative abundance of 22 different TILs. Both HBV−HCC and HCV−HCC were analyzed. Results: The results indicated that the total abundance of TILs was higher in non-tumor tissue regardless of the HCC type. Alternatively, the specific TILs associated with overall survival (OS) and recurrence-free survival (RFS) varied between subtypes. For example, in HBV−HCC, plasma cells (hazard ratio [HR] = 1.05; 95% CI 1.00–1.10; p = 0.034) and activated dendritic cells (HR = 1.08; 95% CI 1.01–1.17; p = 0.03) were significantly associated with OS, whereas in HCV−HCC, monocytes (HR = 1.21) were significantly associated with OS. Furthermore, for RFS, CD8+ T cells (HR = 0.98) and M0 macrophages (HR = 1.02) were potential biomarkers in HBV−HCC, whereas neutrophils (HR = 1.01) were an independent predictor in HCV−HCC. Lastly, in both HBV−HCC and HCV−HCC, CD8+ T cells (HR = 0.97) and activated dendritic cells (HR = 1.09) had a significant association with OS, while γ delta T cells (HR = 1.04), monocytes (HR = 1.05), M0 macrophages (HR = 1.04), M1 macrophages (HR = 1.02), and activated dendritic cells (HR = 1.15) were highly associated with RFS. Conclusions: These findings demonstrated that TILs are potential survival predictors in HCC and different kinds of TILs are observed according to the virus type. Therefore, further investigations are warranted to elucidate the role of TILs in HCC, which may improve immunotherapy outcomes.

Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed and tiny ball accurately. In this paper, we develop a deep learning network, called TrackNet, to track the tennis ball from broadcast videos in which the ball images are small, blurry, and sometimes with afterimage tracks or even invisible. The proposed heatmap-based deep learning network is trained to not only recognize the ball image from a single frame but also learn flying patterns from consecutive frames. TrackNet takes images with the size of 640 × 360 to generate a detection heatmap from either a single frame or several consecutive frames to position the ball and can achieve high precision even on public domain videos. The network is evaluated on the video of the men's singles final at the 2017 Summer Universiade, which is available on YouTube. The precision, recall, and F1-measure of TrackNet reach 99.7%, 97.3%, and 98.5%, respectively. To prevent overfitting, 9 additional videos are partially labeled together with a subset from the previous dataset to implement 10-fold cross validation, and the precision, recall, and F1-measure are 95.3%, 75.7%, and 84.3%, respectively. A conventional image processing algorithm is also implemented to compare with TrackNet. Our experiments indicate that TrackNet outperforms conventional method by a big margin and achieves exceptional ball tracking performance. The dataset and demo video are available at https://nol.cs.nctu.edu.tw/ndo3je6av9/.

Key Points• Through lncRNA profiling, we identified an MDS patient subset with distinct clinical and mutational patterns along with inferior outcomes.• A concise yet powerful 4-lncRNA risk-scoring system was devised with the potential to improve current MDS risk stratification.Long noncoding RNAs (lncRNAs) not only participate in normal hematopoiesis but also contribute to the pathogenesis of acute leukemia. However, their clinical and prognostic relevance in myelodysplastic syndromes (MDSs) remains unclear to date. In this study, we profiled lncRNA expressions in 176 adult patients with primary MDS, and identified 4 lncRNAs whose expression levels were significantly associated with overall survival (OS). We then constructed a risk-scoring system with the weighted sum of these 4 lncRNAs. Higher lncRNA scores were associated with higher marrow blast percentages, higher-risk subtypes of MDSs (based on both the Revised International Prognostic Scoring System [IPSS-R] and WorldHealth Organization classification), complex cytogenetic changes, and mutations in RUNX1, ASXL1, TP53, SRSF2, and ZRSR2, whereas they were inversely correlated with SF3B1 mutation. Patients with higher lncRNA scores had a significantly shorter OS and a higher 5-year leukemic transformation rate compared with those with lower scores. The prognostic significance of our 4-lncRNA risk score could be validated in an independent MDS cohort. In multivariate analysis, higher lncRNA scores remained an independent unfavorable risk factor for OS (relative risk, 4.783; P , .001) irrespective of age, cytogenetics, IPSS-R, and gene mutations. To our knowledge, this is the first report to provide a lncRNA platform for risk stratification of MDS patients. In conclusion, our integrated 4-lncRNA risk-scoring system is correlated with distinctive clinical and biological features in MDS patients, and serves as an independent prognostic factor for survival and leukemic transformation. This concise yet powerful lncRNA-based scoring system holds the potential to improve the current risk stratification of MDS patients.