Medical Imaging

This cell images dataset is collected using an ultrafast imaging system known as asymmetric-detection time-stretch optical microscopy (ATOM)  for training and evaluation. This novel imaging approach can achieve label-free and high-contrast flow imaging with good cellular resolution images at a very high speed. Each acquired image belongs to one of the four classes: THP1, MCF7, MB231 and PBMC.


Recent advances in scalp electroencephalography (EEG) as a neuroimaging tool have now allowed researchers to overcome technical challenges and movement restrictions typical in traditional neuroimaging studies.  Fortunately, recent mobile EEG devices have enabled studies involving cognition and motor control in natural environments that require mobility, such as during art perception and production in a museum setting, and during locomotion tasks.


This dataset consists of 462 field of views of Giemsa(dye)-stained and field(dye)-stained thin blood smear images acquired using an iPhone 10 mobile phone with a 12MP camera. The phone was attached to an Olympus microscope with 1000× objective lens. Half of the acquired images are red blood cells with a normal morphology and the other half have a Rouleaux formation morphology.


This paper explores the connections between traditional Large Deformation Diffeomorphic Metric Mapping methods and
unsupervised deep-learning approaches for non-rigid registration, particularly emphasizing diffeomorphic registration. The
study provides useful insights and establishes connections between the methods, thereby facilitating a profound understand-
ing of the methodological landscape. The methods considered in our study are extensively evaluated in T1w MRI images


Traditional Thai medicine (TTM) is an increasingly popular treatment option. Tongue diagnosis is a highly efficient method for determining overall health, practiced by TTM practitioners. However, the diagnosis naturally varies depending on the practitioner's expertise. In this work, we propose tongue image analysis using raw pixels and artificial intelligence (AI) to support TTM diagnoses. The target classification of Tri-Dhat consists of three classes: Vata, Pitta, and Kapha. We utilize our own organized genuine datasets collected from our university's TTM hospital.


 We conducted a retrospective collection, covering 167 children who were examined and treated at the Children's Hospital of Chongqing Medical University from March 12, 2014 to January 7, 2022, with a total of 1634 IRI image sequences. This study has been registered with the Chinese Clinical Trial Registry, registration number ChiCTR2200058971, and complied with the provisions of the Declaration of Helsinki (DoH). The study was approved by the Institutional Ethical Review Board (document number 2022,69), and a waiver of informed consent was obtained.


The overall ACDC dataset was created from real clinical exams acquired at the University Hospital of Dijon. Acquired data were fully anonymized and handled within the regulations set by the local ethical committee of the Hospital of Dijon (France). Our dataset covers several well-defined pathologies with enough cases to (1) properly train machine learning methods and (2) clearly assess the variations of the main physiological parameters obtained from cine-MRI (in particular diastolic volume and ejection fraction).


This dataset contains RF (Radio Frequency) signals obtained from simulations, which model ultrasound propagation in cortical bone.

The simulations were designed to provide insights into the behaviour of ultrasound waves in cortical bone tissues, both in intact and pathological conditions. The dataset covers a wide range of parameters, including varying thickness (1-8 mm), porosity (1-20%), and frequency (1-8 MHz), allowing to explore the impact of these factors on ultrasound signal characteristics.



With the goal of improving machine learning approaches in inverse scattering, we provide an experimental data set collected with a 2D near-field microwave imaging system. Machine learning approaches often train solely on synthetic data, and one of the reasons for this is that no experimentally-derived public data set exists. The imaging system consists of 24 antennas surrounding the imaging region, connected via a switch to a vector network analyzer. The data set contains over 1000 full Scattering parameter scans of five targets at numerous positions from 3-5 GHz.


This is a dataset on normal and early stage (stage I and II) endometrial cancer, comprising a total of 300 MRI images of patients (100 normal, 100 stage I and II), 207 patients (77 healthy, 100 stage IA (50 stage IA, 50 stage IB), and 30 stage II patients. From January 1, 2018 to December 31, 2020, he underwent 1.5-T MRI in Fujian Maternal and Child Health Hospital, with an average age of 55.7 years. Patient age The images in this dataset were all provided by the Radiology Department of Fujian Provincial Maternal and Child Health Care Hospital and may contain privacy concerns.