Be sure to download the most recent version of this dataset to maintain accuracy.

This dataset contains thousands of validated OCT and Chest X-Ray images described and analyzed in "Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning". The images are split into a training set and a testing set of independent patients. Images are labeled as (disease)-(randomized patient ID)-(image number by this patient) and split into 4 directories: CNV, DME, DRUSEN, and NORMAL.

This repository of images is made available for use in research only. How to cite this data: Kermany D, Goldbaum M, Cai W et al. Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell. 2018; 172(5):1122-1131. doi:10.1016/j.cell.2018.02.010.

A collection of 22 data set of 50+ requirements each, expressed as user stories. These were all found online, or retrieved from software companies with a permission to disclose.

The data sets have been originally used to conduct experiments about ambiguity detection with the REVV-Light tool: https://github.com/RELabUU/revv-light

Dataset of validated OCT and Chest X-Ray images described and analyzed in "Deep learning-based classification and referral of treatable human diseases". The OCT Images are split into a training set and a testing set of independent patients. OCT Images are labeled as (disease)-(randomized patient ID)-(image number by this patient) and split into 4 directories: CNV, DME, DRUSEN, and NORMAL.

The construction of diabetes dataset was explained. The data were collected from the Iraqi society, as they data were acquired from the laboratory of Medical City Hospital and (the Specializes Center for Endocrinology and Diabetes-Al-Kindy Teaching Hospital). Patients' files were taken and data extracted from them and entered in to the database to construct the diabetes dataset. The data consist of medical information, laboratory analysis. The data attribute are: The data consist of medical information, laboratory analysis… etc. The data that have been entered initially into the system are: No. of Patient, Sugar Level Blood, Age, Gender, Creatinine ratio(Cr), Body Mass Index (BMI), Urea, Cholesterol (Chol), Fasting lipid profile, including total, LDL, VLDL, Triglycerides(TG) and HDL Cholesterol , HBA1C, Class (the patient's diabetes disease class may be Diabetic, Non-Diabetic, or Predict-Diabetic).

These data consist of a collection of legitimate as well as phishing website instances. Each website is represented by the set of features which denote, whether website is legitimate or not. Data can serve as an input for machine learning process.

In this repository the two variants of the Phishing Dataset are presented.

Full variant - dataset_full.csv Short description of the full variant dataset: Total number of instances: 88,647 Number of legitimate website instances (labeled as 0): 58,000 Number of phishing website instances (labeled as 1): 30,647 Total number of features: 111

Small variant - dataset_small.csv Short description of the small variant dataset: Total number of instances: 58,645 Number of legitimate website instances (labeled as 0): 27,998 Number of phishing website instances (labeled as 1): 30,647 Total number of features: 111

Type of data: 240x320 mango leaf images. Data format: JPG. Number of images: 4000 images. Of these, around 1800 are of distinct leaves, and the rest are prepared by zooming and rotating where deemed necessary. Diseases considered: Seven diseases, namely Anthracnose, Bacterial Canker, Cutting Weevil, Die Back, Gall Midge, Powdery Mildew, and Sooty Mould. Number of classes: Eight (including the healthy category). Distribution of instances: Each of the eight categories contains 500 images. How data are acquired: Captured from mango trees through the mobile phone camera. Data source locations: Four mango orchards of Bangladesh, namely Sher-e-Bangla Agricultural University orchard, Jahangir Nagar University orchard, Udaypur village mango orchard, and Itakhola village mango orchard. Where applicable: Suitable for distinguishing healthy and diseases leaves (two-class prediction) as well as for differentiating among various diseases (multi-class prediction).

This dataset consists of anonymized and deidentified panoramic dental X-rays of 116 patients, taken at Noor Medical Imaging Center, Qom, Iran. The subjects cover a wide range of dental conditions from healthy, to partial and complete edentulous cases. The mandibles of all cases are manually segmented by two dentists. This dataset is used as the basis for the article by Abdi et al [1].

[1] A. H. Abdi, S. Kasaei, and M. Mehdizadeh, “Automatic segmentation of mandible in panoramic x-ray,” J. Med. Imaging, vol. 2, no. 4, p. 44003, 2015.

This dataset contains count matrices and per-cells metadata tables for RNA sequencing of 39778 single nuclei from healthy primary lung samples of 12 lung adenocarcinoma patients as well as 17451 single human bronchiole epithelial cells from 4 donors. All samples were processed using the 10X Genomics Chromium platform with v2 chemistry and sequenced with one sample per lane on an Illumina HiSeq4000. Reads were aligned to the hg19 reference genome version 1.2.0 obtained from 10X Genomics. Data processing was performed using Seurat3. The metadata table includes patient ID, sex, age, smoking status, and cell type, as well as QC statistics (number of genes, number of cells, ratio of mitochondrial reads).

The Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases (IQ-OTH/NCCD) lung cancer dataset was collected in the above-mentioned specialist hospitals over a period of three months in fall 2019. It includes CT scans of patients diagnosed with lung cancer in different stages, as well as healthy subjects. IQ-OTH/NCCD slides were marked by oncologists and radiologists in these two centers. The dataset contains a total of 1190 images representing CT scan slices of 110 cases (see Figure 1). These cases are grouped into three classes: normal, benign, and malignant. of these, 40 cases are diagnosed as malignant; 15 cases diagnosed with benign; and 55 cases classified as normal cases. The CT scans were originally collected in DICOM format. The scanner used is SOMATOM from Siemens. CT protocol includes: 120 kV, slice thickness of 1 mm, with window width ranging from 350 to 1200 HU and window center from 50 to 600 were used for reading. with breath hold at full inspiration. All images were de-identified before performing analysis. Written consent was waived by the oversight review board. The study was approved by the institutional review board of participating medical centers. Each scan contains several slices. The number of these slices range from 80 to 200 slices, each of them represents an image of the human chest with different sides and angles. The 110 cases vary in gender, age, educational attainment, area of residence and living status. Some of them are employees of the Iraqi ministries of Transport and Oil, others are farmers and gainers. Most of them come from places in the middle region of Iraq, particularly, the provinces of Baghdad, Wasit, Diyala, Salahuddin, and Babylon.

The dataset contains information about the contents of 100 Terms of Service (ToS) of online platforms. The documents were analyzed and evaluated from the point of view of the European Union consumer law. The main results have been presented in the table titled "Terms of Service Analysis and Evaluation_RESULTS." This table is accompanied by the instruction followed by the annotators, titled "Variables Definitions," allowing for the interpretation of the assigned values. In addition, we provide the raw data (analyzed ToS, in the folder "Clear ToS") and the annotated documents (in the folder "Annotated ToS," further subdivided).

SAMPLE: The sample contains 100 contracts of digital platforms operating in sixteen market sectors: Cloud storage, Communication, Dating, Finance, Food, Gaming, Health, Music, Shopping, Social, Sports, Transportation, Travel, Video, Work, and Various. The selected companies' main headquarters span four legal surroundings: the US, the EU, Poland specifically, and Other jurisdictions. The chosen platforms are both privately held and publicly listed and offer both fee-based and free services. Although the sample cannot be treated as representative of all online platforms, it nevertheless accounts for the most popular consumer services in the analyzed sectors and contains a diverse and heterogeneous set.

CONTENT: Each ToS has been assigned the following information: 1. Metadata: 1.1. the name of the service; 1.2. the URL; 1.3. the effective date; 1.4. the language of ToS; 1.5. the sector; 1.6. the number of words in ToS; 1.7–1.8. the jurisdiction of the main headquarters; 1.9. if the company is public or private; 1.10. if the service is paid or free. 2. Evaluative Variables: remedy clauses (2.1– 2.5); dispute resolution clauses (2.6–2.10); unilateral alteration clauses (2.11–2.15); rights to police the behavior of users (2.16–2.17); regulatory requirements (2.18–2.20); and various (2.21–2.25). 3. Count Variables: the number of clauses seen as unclear (3.1) and the number of other documents referred to by the ToS (3.2). 4. Pull-out Text Variables: rights and obligations of the parties (4.1) and descriptions of the service (4.2)

ACKNOWLEDGEMENT: The research leading to these results has received funding from the Norwegian Financial Mechanism 2014-2021, project no. 2020/37/K/HS5/02769, titled “Private Law of Data: Concepts, Practices, Principles & Politics.”

This dataset presents a large-scale collection of millions of Twitter posts related to the coronavirus pandemic in Spanish language. The collection was built by monitoring public posts written in Spanish containing a diverse set of hashtags related to the COVID-19, as well as tweets shared by the official Argentinian government offices, such as ministries and secretaries at different levels. Data was collected between March and June 2020 using the Twitter API, and will be periodically updated.

In addition to tweets IDs, the dataset includes information about mentions, retweets, media, URLs, hashtags, replies, users and content-based user relations, allowing the observation of the dynamics of the shared information. Data is presented in different tables that can be analysed separately or combined.

The dataset aims at serving as source for studying several coronavirus effects in people through social media, including the impact of public policies, the perception of risk and related disease consequences, the adoption of guidelines, the emergence, dynamics and propagation of disinformation and rumours, the formation of communities and other social phenomena, the evolution of health related indicators (such as fear, stress, sleep disorders, or children behaviour changes), among other possibilities. In this sense, the dataset can be useful for multi-disciplinary researchers related to the different fields of data science, social network analysis, social computing, medical informatics, social sciences, among others.

The application of Artificial Intelligence (AI) has been evident in the agricultural sector recently. The main goal of AI in agriculture is to improve crop yield, control crop pests/diseases, and reduce cost. The agricultural sector in developing countries faces severe in the form of disease and pest infestation, the knowledge gap between farmers and technology, and a lack of storage facilities, among others. To help address some of these challenges, this work presents crop pests/disease datasets sourced from local farms in Ghana. The dataset is presented in two folds; the raw images which consists of 24,881 images ( 6,549-Cashew, 7,508-Cassava, 5,389-Maize, and 5,435-Tomato) and augmented images which is further split into train and test set consists of 102,976 images (25,811-Cashew, 26,330-Cassava, 23,657-Maize, and 27,178-Tomato), categorized into 22 classes. All images are de-identified, validated by expert plant virologists, and freely available for use by the research community.

DAWN (Detection in Adverse Weather Nature) dataset consists of real-world images collected under various adverse weather conditions. This dataset emphasizes a diverse traffic environment (urban, highway and freeway) as well as a rich variety of traffic flow. The DAWN dataset comprises a collection of 1000 images from real-traffic environments, which are divided into four sets of weather conditions: fog, snow, rain and sandstorms. The dataset is annotated with object bounding boxes for autonomous driving and video surveillance scenarios. This data helps interpreting effects caused by the adverse weather conditions on the performance of vehicle detection systems. Also, it is required by researchers work in autonomous vehicles and intelligent visual traffic surveillance systems fields. All the rights of the DAWN dataset are reserved and commercial use/distribution of this database is strictly prohibited.

The dataset includes color images of oral lesions captured using mobile cameras and intraoral cameras. These images can be used for identifying potential oral malignancies by image analysis. These images have been collected in consultation with doctors from different hospitals and colleges in Karnataka, India. This dataset contains two folders - original_data and augmented_data. The first folder contains images of 165 benign lesions and 158 malignant lesions. The second folder contains images created by augmenting the original images. The augmentation techniques used are flipping, rotation and resizing.

This data set contains anonymised clinical MRI study, or a set of scans, of 515 patients with symptomatic back pains. Each patient data can have one or more MRI studies associated with it. Each study contains slices, i.e., individual images taken from either sagittal or axial view, of the lowest three vertebrae and the lowest three IVDs. The axial view slices are mainly taken from the last three IVDs – including the one between the last vertebrae and the sacrum. The orientation of the slices of the last IVD are made to follow the spine curve whereas those of the other IVDs are usually made in blocks – i.e., parallel to each other. There are between four to five slices per IVD and they begin from the top of the IVD towards its bottom. Many of the top and bottom slices cut through the vertebrae leaving between one to three slices that cut the IVD cleanly and show purely the image of that IVD. In most cases, the total number of slices in axial view ranges from 12 to 15. However, in some cases, there may be up to 20 slices because the study contains slices of more than last three vertebrae. The scans in sagittal view also vary but all contain at least the last seven vertebrae and the sacrum. While the number of vertebrae varies, each scan always includes the first two sacral links.

There are a total 48,345 MRI slices in our dataset. The majority of the slices have an image resolution of 320x320 pixels, however, there are slices from three studies with 320x310 pixel resolution. The pixels in all slices have 12-bit per pixel precision which is higher than the standard 8-bit greyscale images. Specifically for all axial-view slices, the slice thickness are uniformly 4 mm with centre-to-centre distance between adjacent slices to be 4.4 mm. The horizontal and vertical pixel spacing is 0.6875 mm uniformly across all axial-view slices.

The majority of the MRI studies were taken with the patient in Head-First-Supine position with the rests were taken with the patient in in Feet-First-Supine position. Each study can last between 15 to 45 minutes and a patient may have one or more study associated with them taken at a different time or a few days apart.

You can download and read the research papers detailing our methodology on boundary delineation for lumbar spinal stenosis detection using the URLs provided in the Related Links at the end of this page. You can also check out other dataset and source code related to this program from that section.

We kindly request you to cite our papers when using our data or program in your research.

The dataset includes 458 hi-res images together with their alpha maps (BW) indicating the crack presence. The ground truth for semantic segmentation has two classes to conduct binary pixelwise classification. The photos are captured in various buildings located in Middle East Technical University.

You can access a larger dataset containing images with 227x227 px dimensions for classification which are produced from this dataset from http://dx.doi.org/10.17632/5y9wdsg2zt.1 .

ECG images dataset of Cardiac Patients created under the auspices of Ch. Pervaiz Elahi Institute of Cardiology Multan, Pakistan that aims to help the scientific community for conducting the research for Cardiovascular diseases.

This heart disease dataset is acquired from one o f the multispecialty hospitals in India. Over 14 common features which makes it one of the heart disease dataset available so far for research purposes. This dataset consists of 1000 subjects with 12 features. This dataset will be useful for building a early-stage heart disease detection as well as to generate predictive machine learning models.

While a publicly available benchmark dataset provides a base for the development of new algorithms and comparison of results, hospital-based data collected from the real-world clinical setup is also very important in automated AI-based medical research likewise in disease diagnosis or categorization of predicted disease for tissue level staging or any class identification as per standard protocol so that the developed algorithm works with as much accuracy as possible in the regional context. The repository supports research work related to image segmentation and final classification for a complete decision support system. Liquid based cytology is one of the cervical screening tests. The repository consists of total 963 images sub-divided into four sets of images representing the four classes of pre-cancerous and cancerous lesions of cervical cancer as per standards under The Bethesda System. The pap smear images were captured in 40x magnification using Leica ICC50 HD microscope which is collected and prepared using the liquid-based cytology technique from 460 patients. Microscopic investigation of abnormal changes in cell-level enables detection of malignancy or pre-malignant characteristics. This procedure is time-consuming and subject to inter or intra-observer variability which is why computer-assisted diagnosis can improve the overall disease diagnosis time period to proceed with rapid treatment and therapy which can limit late diagnosis of cervical cancer.

The included tests were performed at McMaster University in Hamilton, Ontario, Canada by Dr. Phillip Kollmeyer (phillip.kollmeyer@gmail.com). If this data is utilized for any purpose, it should be appropriately referenced. -A brand new 3Ah LG HG2 cell was tested in an 8 cu.ft. thermal chamber with a 75amp, 5 volt Digatron Firing Circuits Universal Battery Tester channel with a voltage and current accuracy of 0.1% of full scale. these data are used in the design process of an SOC estimator using a deep feedforward neural network (FNN) approach. The data also includes a description of data acquisition, data preparation, development of an FNN example script.

-Instructions for Downloading and Running the Script: 1-Select download all files from the Mendeley Data page (https://data.mendeley.com/datasets/cp3473x7xv/2).
2-The files will be downloaded as a zip file. Unzip the file to a folder, do not modify the folder structure.
3-Navigate to the folder with "FNN_xEV_Li_ion_SOC_EstimatorScript_March_2020.mlx" 4-Open and run "FNN_xEV_Li_ion_SOC_EstimatorScript_March_2020.mlx" 5-The matlab script should run without any modification, if there is an issue it's likely due to the testing and training data not being in the expected place. 6-The script is set by default to train for 50 epochs and to repeat the training 3 times. This should take 5-10 minutes to execute. 7-To recreate the results in the paper, set number of epochs to 5500 and number of repetitions to 10.

-The test data, or similar data, has been used for some publications, including: [1] C. Vidal, P. Kollmeyer, M. Naguib, P. Malysz, O. Gross, and A. Emadi, “Robust xEV Battery State-of-Charge Estimator Design using Deep Neural Networks,” in Proc WCX SAE World Congress Experience, Detroit, MI, Apr 2020 [2] C. Vidal, P. Kollmeyer, E. Chemali and A. Emadi, "Li-ion Battery State of Charge Estimation Using Long Short-Term Memory Recurrent Neural Network with Transfer Learning," 2019 IEEE Transportation Electrification Conference and Expo (ITEC), Detroit, MI, USA, 2019, pp. 1-6.