A5037594172- Lung Cancer Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Radiology practices and education
- Medical Imaging and Analysis
- Cardiac, Anesthesia and Surgical Outcomes
- Anatomy and Medical Technology
- AI in cancer detection
- Advanced X-ray and CT Imaging
- Cardiac Imaging and Diagnostics
- Hand Gesture Recognition Systems
- Seismology and Earthquake Studies
- Medical and Biological Sciences
- Pulmonary Hypertension Research and Treatments
- Healthcare Systems and Public Health
- COVID-19 and healthcare impacts
Skolkovo Institute of Science and Technology
2023
Skolkovo Foundation
2023
Accurate segmentation of all pathological findings in 3D medical images remains a significant challenge, as supervised models are limited to detecting only the few pathology classes annotated existing datasets. To address this, we frame an unsupervised visual anomaly (UVAS) problem, leveraging inherent rarity patterns compared healthy ones. We enhance density-based UVAS framework with two key innovations: (1) dense self-supervised learning (SSL) for feature extraction, eliminating need...
Interpretation of chest computed tomography (CT) is time-consuming. Previous studies have measured the time-saving effect using a deep-learning-based aid (DLA) for CT interpretation. We evaluated joint impact multi-pathology DLA on time and accuracy radiologists' reading. 40 radiologists were randomly split into three experimental arms: control (10), who interpret without assistance; informed group briefed about pathologies, but performed readings it; (20), interpreted half with DLA,...
We propose a self-supervised model producing 3D anatomical positional embeddings (APE) of individual medical image voxels. APE encodes voxels' closeness, i.e., voxels the same organ or nearby organs always have closer than more distant body parts. In contrast to existing models embeddings, our method is able efficiently produce map voxel-wise for whole volumetric input image, which makes it an optimal choice different downstream applications. train on 8400 publicly available CT images...
BACKGROUND: The use of chest computed tomography (CT) scans in Krasnoyarsk Krai, Russia, has increased since 2020, during the COVID-19 pandemic. This period also saw a 5.2% decrease lung cancer (LC) incidence. potential for missed LC cases led to investigation new diagnostic methods, including artificial intelligence (AI) analyzing retrospective data. AIM: study aimed evaluate effectiveness an AI algorithm identifying patients at high risk using CT data from METHODS: A analysis was conducted...
The article analyzes the results of a survey conducted in Ministry Digital Development State Administration Information Technologies and Communications Republic Tatarstan Labor, Employment Social Protection Tatarstan.Factors that influence labor efficiency have been identified studied.Proposals formulated to improve civil servants.
Aim: To present the ARILIS study aimed at assessing use of artificial intelligence to analyze chest computed tomography (CT) data predict and prevent non-cancer mortality in patients with cancer. Material methods: This cohort will include cancer diagnosed Arkhangelsk region (AR) within 2019–2023 period. The COVID-19 pneumonia, general medical conditions, population Know Your Heart Study are planned be enrolled as control groups. detect quantify CT signs cardiovascular, pulmonary, bone...
Abstract Purpose To evaluate the potential of using artificial intelligence (AI) focused pulmonary nodule search on chest CT data obtained during COVID-19 pandemic to identify lung cancer (LC) patients. Methods A multicenter, retrospective study in Krasnoyarsk region, Russia analyzed CTs patients automated algorithm, Chest-IRA by IRA Labs. Pulmonary nodules larger than 100 mm³ were identified AI and assessed four radiologists, who categorized them into three groups: “high probability LC”,...