Wednesday, March 28, 2018

Xanadu Based Medical Big Data CBIR System for Automated Diseases Diagnosis

For some diseases, assessment of historical medical records in the database is sufficient for quick and accurate diagnosis. Many of such historical medical records are in form of images, such as images of affected body parts of the patients indicating a disease or abnormality. The doctors can study new images by comparing them to similar images available in the database. Moreover, since such historical records are generally stored along with their corresponding diagnoses in the database, it becomes easier for the doctors to diagnose a patient.

As the number of records in the database increases, the database may become comprehensive and exhaustive resulting into a consequent improvement in accuracy of a diagnosis based on the database. However, handling of such large amount of data poses a challenge. It is difficult to implement an architecture that enables archiving of such large number of records that allows quick retrieval of relevant records on demand at low cost.

Xanadu is a big data management technology. Xanadu provides resilient, durable, scalable, and consistent distributed big data database. Xanadu enables competitive big data management in the clouds or enterprises.
Xanadu’s high scalability makes it an ideal choice for the above mentioned type of problem. Xanadu distributed hash means thousands of images can be stored and retrieved efficiently using commodity hardware with a very low cost per GB. Xanadu’s query system can also be leveraged to retrieve images quickly even when the total images in the database grows into the millions, or even billions. For details regarding Xanadu, please see following references.

A content based image retrieval (CBIR) system enables search and retrieval of images similar to a target image in large databases base on contents of images (e.g. colors, shapes, textures). A common use-case of CBIR in medical diagnosis is where imaging methods are used to highlight small areas (lesions) in otherwise healthy tissue. Early breast cancer can be seen as small shadows on a Mamogram (X-Ray of the breast), PET scans highlight small areas of increased metabolic activity that can characterize cancerous growths and Retinal images show small bleeds (microaneurysms) that highlight eye disease as well as wider metabolic problems such as type II diabetes.

To demonstrate the performance and capability of Xanadu based medical big data CBIR system, a prototype CBIR system for retinal images is developed. In the case of the retina (the light sensing surface at the rear of the eye), a simple non-invasive photograph of the eye is sufficient to determine whether a patient suffers from a range of diseases. Indeed, the signs of other diseases such as diabetes, high blood pressure and other circulatory disorders can be diagnosed and assessed from a single retinal image.

The prototype CBIR system collects each retinal image together with its expert reviewed diagnosis. Then, the system breaks each image into small patches that are as small as possible without losing the ability to contain the typical lesions that can indicate disease. The system utilizes the PCA technique to cluster images together in a way that naturally groups similar images. For improving the accuracy, the system uses machine learning techniques (e.g. random forest or deep neural networks). The machine learning techniques also enable to infer an overall diagnosis of a patch given the disease “score” and “distance” (in image pixel terms) from known examples. The result is a detailed (pixel by pixel) report for doctors where all areas of concern have been highlighted and a detailed list of comparative images (showing the similarities) can be viewed in the graphic user interface for final clinical assessment.

If you are interested in collaboration regarding medical big data CBIR applications utilizing medical big data archive, please let me know: Alex G. Lee (

Sunday, November 19, 2017

Xanadu Based Big Data Deep Learning for Medical Data Analysis


Part I
Deep Learning for Medical Data Analysis Introduction
Automated Skin Cancer Classification
Automated Diabetic Retinopathy Classification
Brain Tumor Research
Alzheime Prediction
A Survey on Medical Image Deep Learning Research
Cardiac Arrhthymia Detection
ICU Patient Care

Part II
Deep Learning Introduction
Convolution Process Details
Issues with Big Data Deep Learning
Distributed Deep Learning for Medical Big Data Analysis
Challenges of Deep Learning for Medical Data Analysis
Content Based Image Retrieval (CBIR)

Part III
Xanadu Functionality
Xanadu Commodity Storage System Use Case
Xanadu Cloud Computing Use Case
Xanadu + Deep Learning + Hadoop + Spark Integration
Xanadu based Big Data Deep Learning System for Medical Data Analysis
Xanadu CBIR Demo


Friday, October 27, 2017

(Seminar) Xanadu Big Data Deep Learning System for Medical Data Analysis

의료 빅데이터 딥러닝 시스템 및 빅데이터 센터 심포지움
일시: 2017년 11월 9일(목요일), 오전 10:00 ~ 12:00
장소: 중앙보훈병원 중앙관 지하2층 대강당 (
10.00 ~ 10.50
제나두 기반 의료 빅데이터 딥러닝 시스템
이근호 박사 (미국 제나두 빅데이터 대표)
10.50 ~ 11.05
홍익대학교 빅데이터 센터 소개
표창우 교수 (홍익대학교 공대학장)
11.05 ~ 11.30
Pub/Sub 기반 이종 의료 정보 실시간 패턴 분석 (CEP) 및 전파
윤영 교수 (홍익대학교 컴퓨터공학과)
11.30 ~ 12.00
패널토론: 제나두 기반 의료 빅데이터 딥러닝 시스템 구축 및 상호협력 연구 프로젝트 추진 방안
사회: 김억 교수 (홍익대학교 빅데이터 센터)
패널: 이근호 박사, 표창우 교수, 윤영 교수, 보훈병원 김봉석 기조실장 및 관계자들

Monday, September 25, 2017

Fourth Industrial Revolution & Xanadu: Big Data + IoT + Deep Learning Integration Strategy

Part I
The Fourth Industrial Revolution?
Big Data Introduction
Big Data Analysis Flow
Big Data Use Cases

Part II
Big Data Use Cases
IoT Introduction
IoT Use Cases

Part III
IoT Use Cases
Artificial Intelligence Overview
Deep Learning Introduction
Deep Learning Use Cases

Part IV
Deep Learning Use Cases
Big Data in IoT & Deep Learning
Challenges of IoT Big Data Analytics Applications
Distributed Deep Learning
Xanadu Functionality
Xanadu Performance BMT
Xanadu Fault Tolerance Test Demo
Xanadu Use Cases
Xanadu Commodity Storage System Use Case
Xanadu Cloud Computing Use Case

Part V
Xanadu Cloud Computing Use Case
Xanadu + Deep Learning + Spark + Hadoop Integration
Xanadu based Big Data Deep Learning System

Monday, July 10, 2017

Xanadu for Big Data + IoT + Deep Learning + Cloud Integration Strategy (YouTube Presentation Video)

Silicon Valley Xanadu Promotional Event Presentation Part I
Big Data in IoT & Deep Learning
Challenges of IoT Big Data Analytics Applications
Challenges of Cloud-based IoT Platform
Cloud-based IoT Platform Use Case: GE Predix for Smart Building Energy Management

Silicon Valley Xanadu Promotional Event Presentation Part II
Fog/Edge Computing & Micro Data Centers
Deep Learning for IoT Big Data Analytics Introduction
Deep Learning for IoT Big Data Analytics Use Case
Distributed Deep Learning

Silicon Valley Xanadu Promotional Event Presentation Part III
Big Data + IoT + Cloud + Deep Learning Insights from Patents
Big Data + IoT + Cloud + Deep Learning Strategy Development

Silicon Valley Xanadu Promotional Event Presentation Part IV
Designing Data-Intensive Applications
Xanadu Functionality
Xanadu Use Case
Xanadu + Deep Learning + Hadoop Integration

Part I+ II + III + IV Presentation Slide

Friday, June 30, 2017

Xanadu for Big Data + Deep Learning + Cloud + IoT Integration Strategy Presentation


Monday, June 12, 2017

Xanadu for Big Data + Deep Learning + Cloud + IoT Integration Strategy

Event Description:
Alex G. Lee, a managing partner of Xanadu Big Data, LLC, will talk about Xanadu technology and use cases for Big Data + Deep Learning + Cloud + IoT Integration Strategy.

Xanadu is the most advanced big data management platform technology that is developed to take care of the requirement of high speed processing of diverse type of high volume data. Xanadu can provide a massively scalable fault tolerance system that can connect multiple storages. Xanadu can provide high throughput and low latency data management system. Xanadu provides ACID compliance data management system. Xanadu is designed to be a composable architecture in order to be selected and integrated with other big data system elements such as IT infrastructures and data analytics to satisfy specific big data use requirements. Xanadu is designed for the heaviest workloads that can supports concurrent queries without conflict. For example, Xanadu can support thousands of sensors accessing and updating data at the same time. Thus, Xanadu enables real-time IoT analytics for industrial IoT applications. Xanadu also can support data-intensive distributed deep learning applications involving massive volume multimedia data.

Please join to meet Alex G. Lee for lunch and introduction of Xanadu.

Date: 6/29/2017

Time: 11.30 am – 3 pm

Location: DLA Piper in Palo Alto, 2000 University Ave, Palo Alto, CA 94303

11.30 am – 12.00 pm Check-in
12.00 pm – 1.00 pm Lunch & Networking
1.00 pm – 1.10 pm Introduction by DLA Piper
1.10 pm – 2.30 pm Presentation by Alex G. Lee
2.30 pm – 3.00 pm Networking
3.00 pm Meeting adjourn

This event is by invitation only. If you want to attend the event please send RSVP to Alex G. Lee ( with your name, company name, title and email address.

Friday, May 19, 2017

Xanadu Cloud Computing Use Case: Protection of PCs from Ransomware

Xanadu Cloud Computing Use Case
Demo: Daeil Foreign Language High School, S. Korea

Xanadu is a key-value NoSQL big data management platform technology that provides fault tolerant ACID property and high throughput/low latency with massive scalability. Xanadu is designed for the heaviest workloads, and supports support concurrent queries without conflict.

Xanadu can be exploited for the back-end storage technology that allows remote client computers can access data and computing/application resources via the standard iSCSI network protocol. With iSCSI supported natively by any operating system, Xanadu makes it easy to securely store and access data from any machine on the network. Xanadu also can be used for providing services that allow remote computer systems to “boot” from a stored system drive image. With diskless units on users’ desks and all data (including the operating system disk) remains in the secure cloud servers, administrators are free to deploy diskless PCs to the desktop with their inherent advantages of higher data security, quicker disaster recovery, smaller office footprint and better energy consumption.

In-built deduplication functionality of Xanadu enable saving of cloud data storage resources a lot. For example, Xanadu can store thousands of 25GB basic Windows 7 disk images in only a few hundred gigabytes of actual storage. Xanadu, therefore, enables a simple and highly efficient means to centrally manage cloud data storage, particularly for standardised PC installations that need to be booted almost identically in many places. Time stamping functionality of Xanadu also offers an efficient snapshot capability that enables users to “reset” their stores to a previous saved “good” state. Especially, this resetting capability will be a good solution for proving protection of client PCs from malwares including notorious Ransomwares.

Xanadu for Protection of PCs from Ransomware.

Contact: Alex G. Lee (