{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nfrom IPython.display import Image","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-06-22T19:34:16.944721Z","iopub.execute_input":"2022-06-22T19:34:16.945115Z","iopub.status.idle":"2022-06-22T19:34:16.949853Z","shell.execute_reply.started":"2022-06-22T19:34:16.945084Z","shell.execute_reply":"2022-06-22T19:34:16.948636Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# HuBMAP + HPA - Hacking the Human Body Biological Background Information","metadata":{}},{"cell_type":"markdown","source":"## Human Biomolecular Atlas Program (HuBMAP)\nHuBMAP aims to create an open, global atlas of the healthy human body at the cellular level, see the [HuBMAP Consortium](https://hubmapconsortium.org/about/) and [Visible Human Massive Open Online Course (VHMOOC)](https://expand.iu.edu/browse/sice/cns/courses/hubmap-visible-human-mooc). One component of this overarching goal is to identify medically relevant functional tissue units (FTUs) within whole slide microscopy images of human tissues. Once these FTUs are detected, information on size, shape, variability in number and location within the tissue samples can be used to help build a spatially accurate and semantically explicit model of the human body.\n","metadata":{}},{"cell_type":"markdown","source":"## Human Protein Atlas (HPA)\nThe [Human Protein Atlas](https://www.proteinatlas.org/) is a Swedish-based program initiated in 2003 with the aim to map all the human proteins in cells, tissues, and organs using an integration of various omics technologies, including antibody-based imaging, mass spectrometry-based proteomics, transcriptomics, and systems biology. All the data in the knowledge resource is open access to allow scientists both in academia and industry to freely access the data for exploration of the human proteome. The images for this competition are from the [Tissue Atlas](https://www.proteinatlas.org/humanproteome/tissue), which maps the protein expression profile across human tissues.","metadata":{}},{"cell_type":"markdown","source":"## Functional Tissue Units (FTUs)\nBernard de Bono and his team coined the term “functional tissue unit” in 2013 as: “... a three-dimensional block of cells centered around a capillary, such that each cell in this block is within diffusion distance from any other cell in the same block” to support tissue modeling ([de Bono, 2013](https://www.ncbi.nlm.nih.gov/pubmed/24103658)). For the purposes of Human Reference Atlas ([Börner, 2021](https://www.nature.com/articles/s41556-021-00788-6), [Godwin, 2021](https://www.biorxiv.org/content/10.1101/2021.11.09.467810v1), [Börner, 2021](https://www.biorxiv.org/content/10.1101/2021.12.30.474265v1)) construction and usage,we define an FTU as the smallest level of tissue organization (i.e., a cell population neighborhood) that performs the organ’s major physiological function.  One example of an FTU is the glomerulus found in the outer layer of kidney tissue known as the cortex, which in humans has an area of about 800 mm2 and average depth of about 9 mm ([Mounier-Vehier, 2002](https://doi.org/10.1046/j.1523-1755.2002.00167.x)). Glomeruli consist of capillaries that facilitate filtration of waste products out of blood. Normal glomeruli typically range from 100-350 μm in diameter with a roughly spherical shape ([Kannan, 2019](https://www.kireports.org/article/S2468-0249(19)). Refer to Fig. 1 for a zoom sequence from the human body to single-cell level for the kidney.","metadata":{}},{"cell_type":"code","source":"print(\"Figure 1: Zoom sequence from the human body in left to single-cell level for the kidney.\")\nImage(filename=\"../input/hacking-the-human-body-background-info-images/img-1.png\", width=500, height=300)","metadata":{"execution":{"iopub.status.busy":"2022-06-22T19:34:37.608741Z","iopub.execute_input":"2022-06-22T19:34:37.609080Z","iopub.status.idle":"2022-06-22T19:34:37.646175Z","shell.execute_reply.started":"2022-06-22T19:34:37.609053Z","shell.execute_reply":"2022-06-22T19:34:37.645172Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Similarly, FTUs in other organs presented in this competition are: crypt in the large intestine, alveolus in the lung, glandular acinus in the prostate, and white pulp in the spleen, see Fig. 2. ","metadata":{}},{"cell_type":"code","source":"print(\"Figure 2. FTUs in this competition are: (a) glomeruli in kidney, (b) crypt in the large intestine, (c) alveolus in the lung, (d) glandular acinus in the prostate, and (e) white pulp in the spleen.\")\nImage(filename=\"../input/hacking-the-human-body-background-info-images/img-2.png\", width=500, height=300)","metadata":{"execution":{"iopub.status.busy":"2022-06-22T19:34:56.592599Z","iopub.execute_input":"2022-06-22T19:34:56.592985Z","iopub.status.idle":"2022-06-22T19:34:56.710583Z","shell.execute_reply.started":"2022-06-22T19:34:56.592952Z","shell.execute_reply":"2022-06-22T19:34:56.709293Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Used Terminology\n* **Tissue Preservation**: Different types of tissue preservation techniques are used to maintain the integrity of tissue for downstream biomolecular assays analysis.\n* **Fresh Frozen Tissue Preservation**: Fresh frozen tissue is frozen in liquid nitrogen (-190°C) within 30-60 minutes after surgical excision; this type of preservation has been the method of choice for transcriptomics and immunohistochemistry ([Robbe, 2018](https://doi.org/10.1038/gim.2017.241), [Stoeckli, 2007](https://doi.org/10.1016/j.ijms.2006.10.007)).\n* **Formalin Fixed, Paraffin Embedded (FFPE) Tissue Preservation**: FFPE tissue is the preferred method for clinical pathology samples for histology assessment ([Bass, 2014](https://doi.org/10.5858/arpa.2013-0691-RA)).\n* **Periodic acid-Schiff (PAS) Stain Microscopy**: [PAS](https://en.wikipedia.org/wiki/Periodic_acid%E2%80%93Schiff_stain) is a histology stain that detects complex sugars in tissue sections.\n* **Hematoxylin and Eosin (H&E) Stain Microscopy**: [H&E](https://en.wikipedia.org/wiki/H%26E_stain) stain is one of the principal tissue stains used in histology.\n* **IHC staining**: [Immunohistochemical](https://en.wikipedia.org/wiki/Immunohistochemistry) staining is accomplished with antibodies that recognize the target antigen.","metadata":{}},{"cell_type":"markdown","source":"## Datasets\n### Data Origin: HuBMAP & HPA\nThis competition uses data from two different consortia:\n    \n* **HPA Data** comprises images of 1 mm diameter tissue microarray cores stained with antibodies visualized with 3,3'-diaminobenzidine (DAB) and counterstained with hematoxylin. \n* **HuBMAP Data** comprises Periodic acid-Schiff (PAS)/hematoxylin and eosin (H&E) stain images of human tissue.\n\nThe Ground Truth segmentations were manually created and further reviewed by Subject Matter Experts (SMEs) for quality assurance.\n","metadata":{}},{"cell_type":"markdown","source":"## Related Work\n* Leah L. Godwin, Yingnan Ju, Naveksha Sood, Yashvardhan Jain, Ellen M. Quardokus, Andreas Bueckle, Teri Longacre, Aaron Horning, Yiing Lin, Edward D. Esplin, John W. Hickey, Michael P. Snyder, N. Heath Patterson, Jeffrey M. Spraggins, Katy Börner. “Robust and generalizable segmentation of human functional tissue units”; bioRxiv 2021.11.09.467810; doi: https://doi.org/10.1101/2021.11.09.467810\n* Sheehan, Susan M., and Ron Korstanje. 2018. “Automatic Glomerular Identification and Quantification of Histological Phenotypes Using Image Analysis and Machine Learning.” American Journal of Physiology - Renal Physiology 315 (6): F1644–51. https://doi.org/10.1152/ajprenal.00629.2017.\n* Gallego, Jaime, Anibal Pedraza, Samuel Lopez, Georg Steiner, Lucia Gonzalez, Arvydas Laurinavicius, and Gloria Bueno. 2018. “Glomerulus Classification and Detection Based on Convolutional Neural Networks.” Journal of Imaging 4 (1): 20. https://doi.org/10.3390/jimaging4010020.\n* Govind, Darshana, Brandon Ginley, Brendon Lutnick, John E. Tomaszewski, and Pinaki Sarder. 2018. “Glomerular Detection and Segmentation from Multimodal Microscopy Images Using a Butterworth Band-Pass Filter.” In Medical Imaging 2018: Digital Pathology, 10581:1058114. International Society for Optics and Photonics. https://doi.org/10.1117/12.2295446.\n* Bukowy, John D., Alex Dayton, Dustin Cloutier, Anna D. Manis, Alexander Staruschenko, Julian H. Lombard, Leah C. Solberg Woods, Daniel A. Beard, and Allen W. Cowley. 2018. “Region-Based Convolutional Neural Nets for Localization of Glomeruli in Trichrome-Stained Whole Kidney Sections.” Journal of the American Society of Nephrology 29 (8): 2081–88. https://doi.org/10.1681/ASN.2017111210.\n* Kannan, Shruti, Laura A. Morgan, Benjamin Liang, McKenzie G. Cheung, Christopher Q. Lin, Dan Mun, Ralph G. Nader, et al. 2019. “Segmentation of Glomeruli Within Trichrome Images Using Deep Learning.” Kidney International Reports 4 (7): 955–62. https://doi.org/10.1016/j.ekir.2019.04.008.\n* Nassim Bouteldja, Barbara M. Klinkhammer, Roman D. Bülow, Patrick Droste, Simon W. Otten, Saskia Freifrau von Stillfried, Julia Moellmann, Susan M. Sheehan, Ron Korstanje, Sylvia Menzel, Peter Bankhead, Matthias Mietsch, Charis Drummer, Michael Lehrke, Rafael Kramann, Jürgen Floege, Peter Boor, Dorit Merhof. “Deep Learning–Based Segmentation and Quantification in Experimental Kidney Histopathology”; JASN Jan 2021 32 (1) 52-68; https://doi.org/10.1681/ASN.2020050597\n* Brandon Ginley, Brendon Lutnick, Kuang-Yu Jen, Agnes B. Fogo, Sanjay Jain, Avi Rosenberg, Vighnesh Walavalkar, Gregory Wilding, John E. Tomaszewski, Rabi Yacoub, Giovanni Maria Rossi, Pinaki Sarder.“Computational Segmentation and Classification of Diabetic Glomerulosclerosis”; JASN Oct 2019, 30 (10) 1953-1967; https://doi.org/10.1681/ASN.2018121259","metadata":{"execution":{"iopub.status.busy":"2022-06-22T19:35:28.551996Z","iopub.execute_input":"2022-06-22T19:35:28.553357Z","iopub.status.idle":"2022-06-22T19:35:28.571270Z","shell.execute_reply.started":"2022-06-22T19:35:28.553296Z","shell.execute_reply":"2022-06-22T19:35:28.569432Z"}}}]}