The presented database contains thermal images (thermograms) of the plantar region. The database was obtained from 122 subjects with a diabetes diagnosis (DM group) and 45 non-diabetic subjects (control group). The relevance of this database consists in to study how the temperature is distributed in the plantar region of both groups and how their differences can be measured. Previous reports in the literature have established that an increase in the plantar temperature is associated with a higher ulceration risk.


The files are organized in folders with unique nomenclature: two letters to indicate the group (CG for the control group and DM for the diabetic group), three digits to number the folder and the last letter indicating the subject gender (male (M) or female (F)). In each folder, thermograms of the left and right foot (*.png) are provided separately following the same name of the folder plus a letter indicating L (left) or R (right) foot, e. g. CG001_F_L.png. RGB thermograms are only illustrative since these do not contain direct temperature information but they provide a thermal map by using a false-color palette. For obtaining the temperature value associated with each pixel refer to the corresponding *.csv file (e. g. CG001_F_L.csv).  You can graph the *.csv file as an image and use any other color palette for visualizing the temperature map. The plantar analysis made in the associated work (same name of the database in IEEE Access Journal) and in other associated works (refer to the corresponding author link) have used the angiosome division of the plantar region. Then in each folder, there is a subfolder containing four images (*.png and *.csv) that correspond to the four plantar angiosomes of each foot. The same nomenclature is used with the inclusion of three letters at the end, indicating the angiosome LCA, LPA, MCA and MPA (e. g. CG001_F_L_MPA.csv) [1-2].  For each subject, the database contains 20 files, (10 *.png  images and 10 *.csv files), for a total of 1670 RGB images and 1670 temperature files. The database is expected to provide a valuable source to increase research about the potential of infrared thermography for the early diagnosis of diabetic foot problems [3-4], allowing the development of more powerful techniques. The script generate_thermogram.m (MATLAB) is provided for generating a 3D visualization of the data. Some related works are listed below:


[1] Peregrina-Barreto, H., Morales-Hernandez, L. A., Rangel-Magdaleno, J. J., Avina-Cervantes, J. G., Ramirez-Cortes, J. M., & Morales-Caporal, R. (2014). Quantitative estimation of temperature variations in plantar angiosomes: a study case for diabetic foot. Computational and mathematical methods in medicine2014.

[2] Hernandez-Contreras, D., Peregrina-Barreto, H., Rangel-Magdaleno, J., Gonzalez-Bernal, J. A., & Altamirano-Robles, L. (2017). A quantitative index for classification of plantar thermal changes in the diabetic foot. Infrared Physics & Technology81, 242-249.

[3] Hernandez-Contreras, D., Peregrina-Barreto, H., Rangel-Magdaleno, J., & Gonzalez-Bernal, J. (2016). Narrative review: Diabetic foot and infrared thermography. Infrared Physics & Technology78, 105-117.

[4] Hernandez-Contreras, D. A., Peregrina-Barreto, H., Rangel-Magdaleno, J. D. J., & Orihuela-Espina, F. (2019). Statistical Approximation of Plantar Temperature Distribution on Diabetic Subjects Based on Beta Mixture Model. IEEE Access7, 28383-28391.



This dataset contains 91 computed tomography pulmonary angiograms positive for pulmonary embolism. At least one experience radiologist has segmented all clots in each of the scans. The dataset was originated for the ISBI challenge cad-pe.


Each image in has a mask segmentation with the same name in Each emboli in each mask is numbered.


The purpose of this challenge is to provide standardization of methods for assessing and benchmarking deep learning approaches to ultrasound image formation from ultrasound channel data that will live beyond the challenge.

Last Updated On: 
Mon, 07/19/2021 - 08:40
Citation Author(s): 
Muyinatu A. Lediju Bell, Jiaqi Huang, Alycen Wiacek, Ping Gong, Shigao Chen, Alessandro Ramalli, Piero Tortoli, Ben Luijten, Massimo Mischi, Ole Marius Hoel Rindal, Vincent Perrot, Hervé Liebgott, Xi Zhang, Jianwen Luo, Eniola Oluyemi, Emily Ambinder


-------------------------------------------------- -------------------------------------------------- -----------




电话:+ 86-22-27404535传真:+ 86-22-27404535

团队网站:http : //


Hyperspectral (HS) imaging presents itself as a non-contact, non-ionizing and non-invasive technique, proven to be suitable for medical diagnosis. However, the volume of information contained in these images makes difficult providing the surgeon with information about the boundaries in real-time. To that end, High-Performance-Computing (HPC) platforms become necessary. This paper presents a comparison between the performances provided by five different HPC platforms while processing a spatial-spectral approach to classify HS images, assessing their main benefits and drawbacks.


Dataset description


1) Size of the images


- PD1C1: 1000 samples x 1000 lines x 100 bands

- PD1C2: 1000 samples x 1000 lines x 100 bands

- PD1C3: 1000 samples x 1000 lines x 100 bands


2) Image composition


- The information is stored band by band

- Within each band, the information is stored line by line

- The data type is float


3) Important information


This database only contains the dermatological images. The three brain images, obtained within the context of HELICoiD EU project, are already available in the following repository:


For downloading the brain images used in this research:

- PB1C1: Op12C1

- PB2C1: Op15C1

- PB3C1: Op20C1


Glaucoma is the leading cause of irreversible blindness in the world, and primary angle closure glaucoma (PACG) is one of the main subtypes. PACG patients have narrow chamber angle and can be diagnosed by goniscopy, which may cause discomfort and relies too much on personal experience. Anterior segment OCT is able to provide 3D scan of the anterior chamber and assist the ophthalmologists evaluate the condition of chamber angle. It’s faster and objective compare with goniscopy.


Welcome to the Retinal Fundus Glaucoma Challenge! REFUGE was organized as a half day Challenge in conjunction with the 5th MICCAI Workshop on Ophthalmic Medical Image Analysis (OMIA), a Satellite Event of the MICCAI 2018 conference in Granada, Spain. The goal of the challenge is to evaluate and compare automated algorithms for glaucoma detection and optic disc/cup segmentation on a common dataset of retinal fundus images. With this challenge, we made available a large dataset of 1200 annotated retinal fundus images.


Pathologic Myopia Challenge (PALM), as a part of the serial challenge iChallenge, is organized as a half day Challenge, a Satellite Event of the ISBI 2019 conference in Venice, Italy. The PALM challenge focuses on the investigation and development of algorithms associated with the diagnosis of Pathological Myopia (PM) and segmentation of lesions in fundus photos from PM patients. The goal of the challenge is to evaluate and compare automated algorithms for the detection of pathological myopia on a common dataset of retinal fundus images.


FRAP curve modeling using transient-sensitive analog computer unit with oscilloscopic CRT (Practicum, 2014)


RECOVERY-FA19 dataset is established for development and evaluation of retinal vessel detection algorithms in fluorescein angiography (FA). RECOVERY-FA19 provides 8 high-resolution ultra-widefield FA images acquired using Optos California P200DTx camera and corresponding labeled binary vessel maps.


Ultra-widefield fluorescein angiography images and corresponding labeled vessel maps are provided where the file names indicate the correspondence between them.

The vessel ground-truth labeling for the RECOVERY-FA19 dataset was performed using the methodology proposed in: 

L. Ding, M. H. Bawany, A. E. Kuriyan, R. S. Ramchandran, C. C. Wykoff, and G. Sharma, ``A novel deep learning pipeline for retinal vessel detection in fluorescein angiography,'' IEEE Trans. Image Proc., vol. 29, no. 1, pp. 6561–6573, 2020. 

Code for evaluating vessel segmentation and replicating results from the above paper can be found in the CodeOcean capsule referenced in the paper. Users of the dataset, should cite the above paper.