A Deep Learning Approach to Bacterial Colony Segmentation

Slides:



Advertisements
Similar presentations
ENUMERATION OF MICROORGANISMS
Advertisements

Pure culture techniques laboratory (for bacterial cultures) OR Common sense laboratory! Jeet Kalia
Patch to the Future: Unsupervised Visual Prediction
Genetic Engineering First, the nucleus of human cells are burst Human cell Nucleus.
Aerobic Plate Count, Gram Stain, and Isolation
Introduction to Lab Ex. 19: Enumeration of Bacteria
Bacterial count.
Culturing Yeast Cells on Media. Pre Lab Definitions: Petri Dish: A round, shallow dish used to grow bacteria. Culture: To grow living organisms in a prepared.
Video Tracking Using Learned Hierarchical Features
Practical Part Microscopic Examination of Microorganisms Experiments Identification of MOs Different Staining Techniques.
Microbial Count Aim: Count the number of bacterial cells in a provided sample Methods: Total count, Viable count I. Total count This technique involves.
Tell Me What You See and I will Show You Where It Is Jia Xu 1 Alexander G. Schwing 2 Raquel Urtasun 2,3 1 University of Wisconsin-Madison 2 University.
MEMBRANE FILTRATION All images included in this file are reproduced with permission from the copyright holders and/or Companies producing the respective.
Skeleton Based Action Recognition with Convolutional Neural Network
1 End-to-End Learning for Automatic Cell Phenotyping Paolo Emilio Barbano, Koray Kavukcuoglu, Marco Scoffier, Yann LeCun April 26, 2006.
Automatic Image Classification for the Urinoculture Screening Ing. Paolo Andreini Ing. Simone Bonechi DIISM  University of Siena December 11th, 2015.
Lab 8Biology You will serially dilute a known mass of soil, make agar plates of the dilutions and estimate the number of microorganisms in the original.
بسم الله الرحمن الرحيم 140 MICRO LAB 5 : PURIFICATION OF MICROORGANISM.
Bacterial Cultures *Bacteria grow best in warm, moist, dark areas that contain a lot of food. -When we culture bacteria, we provide them with this environment.
Objectives Use appropriate microbiology media, test systems, and lab equipment. Describe the general properties and characteristics of bacteria – By doing.
Cancer Metastases Classification in Histological Whole Slide Images
Reinforcement Learning
LSUN Semantic Segmentation Extended PSPNet
Deep Learning for Dual-Energy X-Ray
CULTURE METHODS م.م رنا مشعل.
Culturing Bacteria Growth Media
Object Detection based on Segment Masks
DeepCount Mark Lenson.
Lab procedures when handling micro-organisms
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
CLASSIFICATION OF TUMOR HISTOPATHOLOGY VIA SPARSE FEATURE LEARNING Nandita M. Nayak1, Hang Chang1, Alexander Borowsky2, Paul Spellman3 and Bahram Parvin1.
A Pool of Deep Models for Event Recognition
Regularizing Face Verification Nets To Discrete-Valued Pain Regression
Introductory Seminar on Research: Fall 2017
Summary Presentation.
Learning Objectives i Understand the basic aseptic techniques used in culturing organisms. ii Understand the principles and techniques involved in culturing.
CS6890 Deep Learning Weizhen Cai
Tools of the Laboratory: Methods for Culturing of Microorganisms
Adversarially Tuned Scene Generation
النمو والعد البكتيري Microbial growth النمو الجرثومي.
Finding Clusters within a Class to Improve Classification Accuracy
Population Ecology with bacteria.
Historic Document Image De-Noising using Principal Component Analysis (PCA) and Local Pixel Grouping (LPG) Han-Yang Tang1, Azah Kamilah Muda1, Yun-Huoy.
Deep Learning Tutorial
RGB-D Image for Scene Recognition by Jiaqi Guo
INF 5860 Machine learning for image classification
Fine-Grained Visual Categorization
Pose Estimation for non-cooperative Spacecraft Rendevous using CNN
network of simple neuron-like computing elements
Metode Manual (Bergeys manual of bacteriology) sni.
Aline Martin ECE738 Project – Spring 2005
Genetic Engineering First, the nucleus of human cells are burst
Lab procedures when handling micro-organisms
Age and Gender Classification using Convolutional Neural Networks
On Convolutional Neural Network
Outline Background Motivation Proposed Model Experimental Results
CULTURE METHODS Culture methods employed depend on the purpose for which they are intended. The indications for culture are: To isolate bacteria in pure.
Writing a Lab The basics.
Genetic Engineering First, the nucleus of human cells are burst
Zhedong Zheng, Liang Zheng and Yi Yang
边缘检测年度进展概述 Ming-Ming Cheng Media Computing Lab, Nankai University
Automating stroke lesion segmentation in brain images using a multi-model multi-path convolutional neural network Yunzhe.
Image Processing and Multi-domain Translation
Deep Learning with Botanical Specimen Images
CRCV REU 2019 Kara Schatz.
Report 2 Brandon Silva.
Food Dish Classification using Convolutional Neural Networks
ICLR, 2019 Jiahe Li
Tschandl P1,2, Argenziano G3, Razmara M4, Yap J4
Presented By: Firas Gerges (fg92)
Presentation transcript:

A Deep Learning Approach to Bacterial Colony Segmentation Paolo Andreini, Simone Bonechi, Monica Bianchini, Alessandro Mecocci, Franco Scarselli DIISM, Department of Information Engineering and Mathematics University of Siena bonechi@diism.unisi.it 1/18

Outline Petri Plate Analysis Synthetic Data Generation Bacterial Segmentation Results Conclusions and Future Perspectives 2/18

Petri Plate Analysis – Standard Protocol Cylindrical glass or plastic dish used to culture cells Filled with a growing media designed to allow the bacterial growth Food and beverage safety, environmental control, clinical analyses, etc. Sample Seeding Incubation Visual analysis 3/18

Petri Plate Analysis - Why bother? Hundreds of plates each day in big labs, e.g. 200-300 in Careggi Hospital, Florence, urine samples only Highly repetitive and prone to error Costly in term of both time and resources 4/18

Automatic Petri Plate Analysis Automatic Petri Plate Analysis Pipeline [1]: Image Acquisition Bacterial Segmentation Colony Count Bacterial Classification [1] P. Andreini, S. Bonechi, M. Bianchini, A. Garzelli, A. Mecocci. Automatic Image Classification for the Urinoculture Screening. Computers in Biology and Medicine, vol. 70, pp. 12–22, 2016 5/18

Bacterial Segmentation CNN 6/18

CNNs Need Data A unique existing public dataset labeled for segmentation - Haemolysis Dataset [2]: Only one type of culturing substrate Only few hundreds annotated data But… [2] M. Savardi, A. Ferrari, A. Signoroni. Automatic hemolysis identification on aligned dual–lighting images of cultured blood agar plates. Computer Methods and Programs in Biomedicine, vol. 156, pp. 13–24, 2018 7/18

Synthetic Data Generation 8/18

Streaking Simulation 9/18

Colony Modeling 𝑚 𝑥,𝑦 = 𝑝 𝑥,𝑦 − argmin 𝑟 𝑘 ( 𝑝 𝑥,𝑦 − 𝑟 𝑘 ) 10/18

Opacity Simulation 11/18

Rendering and Blending 12/18

Advantages Suitable for different seeding path Just need different probability matrix Suitable for different growing media and colony types Just need new colony patches Free Annotations Generator 13/18

Examples of Synthetic Plates 14/18

Bacterial Segmentation PSP-Network [3] based on ResNet with 50 layers Syntetic dataset: 120000 synthetic images (119000 training and 1000 validation) MicrobIA Dataset: 324 images (221 training and 103 test images) Experimental setups: Training on synthetic data only Training on real data from the MicrobIA dataset only Training on synthetic data and fine–tuning on real data from the MicrobIA dataset [3] H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia. Pyramid Scene Parsing Network. Proc. of CVPR ’17 pp. 6230–6239, 2017. 15/18

Results Experimental Setup Mean IoU Pixel Accuracy Synthetic Images 82,79 % 98,29 % Real Images 85,30 % 99,19 % Synthetic and Real Images 86,33 % 99,26 % 16/18

Real and Synthetic Images Results Original Image Train on Synthetic Images Train on Real Images Train on both Real and Synthetic Images Target 17/18

Conclusions and Future Perspectives The proposed synthetic image generator allows to: Create images that resemble the originals Create large datasets for bacterial segmentation Train a deep neural network even if a public dataset of real images is not available Future Perspectives Better estimation of the seeding distribution Use of Generative Adversarial Networks to improve the quality of the simulated images 18/18