# Multimodal Medical Chatbot We are interested to build a medical chatbot that having a picture we can give you symptoms and solutions. First wer need to build our dataset. # Medical-Images Datasets * A list of Medical imaging datasets. Source : https://sites.google.com/site/aacruzr/image-datasets * An additional, possibly overlapping list can be found at : https://github.com/beamandrew/medical-data ### Multimodal databases * Center for Invivo Microscopy (CIVM), Embrionic and Neonatal Mouse (H&E, MR) http://www.civm.duhs.duke.edu/devatlas/ user guide: http://www.civm.duhs.duke.edu/devatlas/UserGuide.pdf * LONI image data archive https://ida.loni.usc.edu/services/Menu/IdaData.jsp?project= * Radiology (Ultrasound, Mammographs, X-Ray, CT, MRI, fMRI, etc.) * Collaborative Informatics and Neuroimaging Suite (COINS) https://portal.mrn.org/micis/index.php?subsite=dx * The Cancer Imaging Archive (TCIA) http://www.cancerimagingarchive.net/ (Collections) * Alzheimer’s Disease Neuroimaging Initiative (ADNI) http://adni.loni.ucla.edu/ * The Open Access Series of Imaging Studies (OASIS) http://www.oasis-brains.org/ * Breast Cancer Digital Repository https://bcdr.eu/ * DDSM: Digital Database for Screening Mammography http://marathon.csee.usf.edu/Mammography/Database.html * The Mammographic Image Analysis Society (MIAS) mini-database http://peipa.essex.ac.uk/info/mias.html * Mammography Image Databases 100 or more images of mammograms with ground truth. Additional images available by request, and links to several other mammography databases are provided http://marathon.csee.usf.edu/Mammography/Database.html * NLM HyperDoc Visible Human Project color, CAT and MRI image samples - over 30 images http://www.nlm.nih.gov/research/visible/visible_human.html * CT Scans for Colon Cancer https://wiki.cancerimagingarchive.net/display/Public/CT+COLONOGRAPHY#e88604ec5c654f60a897fa77906f88a6 * [[BreastScreening](http://breastscreening.github.io/)] UTA4: Breast Cancer Medical Imaging DICOM Files Dataset & Resources (MG, US and MRI) https://github.com/MIMBCD-UI/dataset-uta4-dicom * [[MIMBCD-UI](http://mimbcd-ui.github.io/)] UTA7: Breast Cancer Medical Imaging DICOM Files Dataset & Resources (MG, US and MRI) https://github.com/MIMBCD-UI/dataset-uta7-dicom * [[Facebook AI + NYU FastMRI](https://fastmri.org/dataset/)] includes two types of MRI scans: knee MRIs and the brain (neuro) MRIs, containing training, validation, and masked test sets. Also includes PyTorch data loaders in open-sourced [GitHub Repository](https://github.com/facebookresearch/fastMRI/) * BCNB: Early Breast Cancer Core-Needle Biopsy WSI Dataset, https://bupt-ai-cz.github.io/BCNB/, https://github.com/bupt-ai-cz/BALNMP#bcnb-dataset ### Histology and Histopathology (H&E, IHQ, ...) * The Cancer Genome Atlas (TCGA) http://cancergenome.nih.gov/ https://tcga-data.nci.nih.gov/tcga/ * International Cancer Genome Consortium http://icgc.org, (Data portal) http://dcc.icgc.org/ * Stanford Tissue Microarray Database (TMA) http://tma.im * MITOS dataset http://www.ipal.cnrs.fr/event/icpr-2012 * Cancer Image Database (caIMAGE) https://emice.nci.nih.gov/caimage * DPA’s Whole Slide Imaging Repository https://digitalpathologyassociation.org/whole-slide-imaging-repository * ITK Analysis of Large Histology Datasets http://www.na-mic.org/Wiki/index.php/ITK_Analysis_of_Large_Histology_Datasets * Histology Photo Album http://www.histology-world.com/photoalbum/thumbnails.php?album=52 * Slide Library of Virtual pathology, University of Leeds http://www.virtualpathology.leeds.ac.uk/ * Aperio Images http://images.aperio.com/ * HAPS Histology Image Database http://hapshistology.wikifoundry.com/ * Microscopy (Cell, Cytology, Biology, Protein, Molecular, Fluorescence, etc.) * BDGP images from the FlyExpress database www.flyexpress.net * The UCSB Bio-Segmentation Benchmark dataset http://www.bioimage.ucsb.edu/research/biosegmentation * Pap Smear database http://mde-lab.aegean.gr/index.php/downloads * Histology (CIMA) dataset http://cmp.felk.cvut.cz/~borovji3/?page=dataset * ANHIR dataset https://anhir.grand-challenge.org/ * Genome RNAi dataset http://www.genomernai.org/ * Chinese Hamster Ovary cells (CHO) dataset http://www.chogenome.org/data.html * Locate Endogenus mouse sub-cellular organelles (END) database http://locate.imb.uq.edu.au/ * 2D HeLa dataset (HeLa) dataset https://ome.grc.nia.nih.gov/iicbu2008/hela/index.html * Allen Brain Atlas http://www.brain-map.org/ * 1000 Functional Connectomes Project http://fcon_1000.projects.nitrc.org/ * The Cell Centered Database (CCDB) https://library.ucsd.edu/dc/collection/bb5940732k * The Encyclopedia of DNA Elements (ENCODE) http://genome.ucsc.edu/ENCODE/ user guide: http://www.plosbiology.org/article/info:doi/10.1371/journal.pbio.1001046 * The Human Protein Atlas: http://www.proteinatlas.org/ * DRIVE: Digital Retinal Images for Vessel Extraction http://www.isi.uu.nl/Research/Databases/DRIVE/ (Ground truth) * El Salvador Atlas of Gastrointestinal VideoEndoscopy Images and Videos of hi-res of studies taken from Gastrointestinal Video endoscopy http://www.gastrointestinalatlas.com/ * BCNB: Early Breast Cancer Core-Needle Biopsy WSI Dataset, https://bupt-ai-cz.github.io/BCNB/, https://github.com/bupt-ai-cz/BALNMP#bcnb-dataset ### Databases you can use for benchmarking * http://peipa.essex.ac.uk/benchmark/databases/ * http://mulan.sourceforge.net/datasets-mlc.html * https://archive.ics.uci.edu/ml/datasets.php * Datasets reporting formats for pathologists http://www.rcpath.org/publications-media/publications/datasets * DermNet - Skin disease atlas (23 image classes and 23,000 images): http://www.dermnet.com/ ### State of the art / Challenges * Grand Challenges in Medical Image Analysis https://grand-challenge.org/ * Challenges in global health and development problems https://grandchallenges.org/#/map * Current state of the art of most used computer vision datasets: Who is the best at X? http://rodrigob.github.io/are_we_there_yet/build/ * Automatic Non-rigid Histological Image Registration (ANHIR) challenge https://anhir.grand-challenge.org/