Dataset for Automatic Region-based Coronary Artery Disease Diagnostics Using X-Ray Angiography Images.

X-ray coronary angiography is the most common tool for the diagnosis and treatment of coronary artery disease. It involves the injection of contrast agents into coronary vessels using a catheter to highlight the coronary vessel structure. Typically, multiple 2D X-ray projections are recorded from different angles to improve visualization. Recent advances in the development of deep-learning-based tools promise significant improvement in diagnosing and treating coronary artery disease. However, the limited public availability of annotated X-ray coronary angiography image datasets presents a challenge for objective assessment and comparison of existing tools and the development of novel methods. To address this challenge, we introduce a novel ARCADE dataset with 2 objectives: coronary vessel classification and stenosis detection. Each objective contains 1500 expert-labeled X-ray coronary angiography images representing: i) coronary artery segments; and ii) the locations of stenotic plaques. These datasets will serve as a benchmark for developing new methods and assessing existing approaches for the automated diagnosis and risk assessment of coronary artery disease.

Epidemiology of pediatric hematological malignancies in Kazakhstan: Data from Unified National Electronic Healthcare System 2014-2021.

We aimed to describe incidence and all-cause mortality of hematological pediatric malignancies (leukemia and lymphomas) in Kazakhstan based on nationwide large-scale healthcare data from the Unified National Electronic Healthcare System (UNEHS) for the 2014-2021 year period. The cohort included data of patients less than 18 years old with the diagnosis of hematological malignancies registered in the UNEHS (inpatient and outpatient registries) for the year period 2014-2021. Descriptive statistics were conducted to indicate socio-demographic characteristics of the cohort. Incidence and all-cause mortality were calculated per 100,000 population. Cox proportional hazard regression analysis was performed to investigate the association between determinants with the all-cause mortality. The total cohort consisted of 3357 children with leukemia and 1474 children with lymphomas. The mean age at diagnosis of leukemia and lymphomas was 7.3 ± 4.7 and 9.9 ± 4.9 years, respectively. The incidence rate of hematological malignancies was 6.8 per 100,000 in 2021. Patients with ALL had a higher incidence rate than patients with AML (3.4 and 1.2 per 100,000 in 2021, respectively). The incidence rate of HL and NHL was relatively similar which varied from 0.6 to 2.6 per 100,000 in 2014-2021. All-cause mortality of pediatric hematological malignancies varied from 1.1 to 1.5 per 100,000 in 2014-2021, with the peak in 2016 (1.7 per 100,000). Younger age is significantly associated with increased risk of all-cause mortality in children with AML. CONCUSION: Patients with ALL had a higher incidence rate than patients with AML. The incidence rate of HL and NHL was relatively similar. All-cause mortality rates for leukemia and lymphomas were quite stable during the study period. Younger age is significantly associated with increased all-cause mortality among AML patients. However, there is no significant association of age with all-cause mortality among ALL, HL and NHL. In order to obtain more reliable data and analysis on pediatric (hematological) malignancies, specific registries for childhood tumors (including detailed information on relapses, treatments, short and long-term side effects, and specific death causes) should be implemented. WHAT IS KNOWN: • Leukemias and lymphomas together account for around 45% of all pediatric malignancies. • Lymphoma accounts for 12% of all childhood malignancies; non-Hodgkin's lymphomas (NHL) are more frequent than Hodgkin's lymphomas (HL). WHAT IS NEW: • The incidence rate of ALL was higher than the incidence rate of AML throughout the whole study period, whereas all-cause mortality of ALL and AML was quite stable. • According to Cox PH analysis, younger age (0-5 years old) was associated with a higher risk of death among AML children compared to older children, and no significant association of age was observed with all-cause mortality among ALL and lymphomas.

AIROGS: Artificial Intelligence for Robust Glaucoma Screening Challenge.

The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening.