We have innovatively introduced Visual Patient (VP) concept and method visually to represent and index patient imaging diagnostic records (IDR) in last year SPIE Medical Imaging (SPIE MI 2017), which can enable a doctor to review a large amount of IDR of a patient in a limited appointed time slot. In this presentation, we presented a new approach to design data processing architecture of VP system (VPS) to acquire, process and store various kinds of IDR to build VP instance for each patient in hospital environment based on Hadoop distributed processing structure. We designed this system architecture called Medical Information Processing System (MIPS) with a combination of Hadoop batch processing architecture and Storm stream processing architecture. The MIPS implemented parallel processing of various kinds of clinical data with high efficiency, which come from disparate hospital information system such as PACS, RIS LIS and HIS.

Hadoop-based implementation of processing medical diagnostic records for visual patient system

Abstract. To commemorate the SPIE Medical Imaging 50th anniversary, this article provides a brief review of the Picture Archiving and Communication Systems (PACS) and Informatics conferences. Important topics and advances, contributing researchers from both academia and industry, and key papers are noted.

SPIE Medical Imaging 50th anniversary: history of the Picture Archiving and Communication Systems Conference

This paper proposed a new generation PACS (Picture Archiving and Communication System) based on artificial intelligent visualization. It is developed from our GRIDPACS (patent number: US8805890), which combined with IHE XDS-I profile, to implement images communication, storage and display. It also uses 3D anatomical visualization model to extract multi-source data from PACS/RIS/HIS/EMR, to express patient disease location, size and severity, which was introduced as Visual Patent (VP) at previous SPIE Medical Imaging (SPIE MI 2018). It can integrate the training model of AI Imaging Diagnosis, to mark the focus and display the disease trends. The system not only has the original PACS functions, but also realizes the man-machine interaction (images and electronic medical record information between radiologist and patient) in a personalized, fast, comprehensive, quantitative and easy-to-understand way. It can be used in various medical institutions, image diagnostic centers, and imaging cloud, to support the healthy development of imaging technology in China.

Design and implementation of a new generation of PACS based on artificial intelligent visualization

The benign and malignant differential diagnosis of small pulmonary nodules (diameter < 20 mm) found in lung CT images is big challenges for most of radiologists. Here, we presented our preliminary study of benign and malignant differentiation of small pulmonary nodules in lung CT images by using deep learning Convolutional Neural Network (CNN). The 921 cases with small benign and malignant pulmonary nodules confirmed by pathology were collected from three data sources and were used to train and validate the CNN. The preliminary results of AUCs of ROC curves for differentiating benign and malignant pulmonary small nodules with various types and sizes of solid, semi-solid and ground glass nodules were presented and discussed.

Preliminary study of benign and malignant differentiation of small pulmonary nodules in lung CT images by using deep learning convolutional neural network

Yangfan Ni

Papers

Design and implementation of a new generation of PACS based on artificial intelligent visualization

Preliminary study of benign and malignant differentiation of small pulmonary nodules in lung CT images by using deep learning convolutional neural network