The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 맞춤형 임베디드 DSP에 대장내시경 영상을 이용한 대장암 진단 지원 시스템의 하드웨어 구현을 제시한다. 내시경 영상에서는 병변 부위에 색 변화, 흐릿함, 빛의 반사 등이 발생하는데, 이는 컴퓨터의 판별 결과에 영향을 미칩니다. 따라서 이러한 비디오 프레임에 특화된 이미지에 대한 높은 견고성과 안정적인 분류로 병변을 식별하기 위해 Convolutional Neural Network( CNN) 기능 및 SVM(Support Vector Machine) 분류. CNN과 SVM은 많은 MAC(곱셈과 누산) 연산을 수행해야 하기 때문에 제안된 하드웨어 시스템을 맞춤형 임베디드 DSP에 구현합니다. 이는 VLIW(Very Long Instruction Word)를 통한 고속 MAC 연산 및 병렬 처리를 실현할 수 있습니다. 맞춤형 임베디드 DSP를 구현하기 전에 CAD 시스템의 처리 주기를 프로파일링 및 분석하고 병목 현상을 최적화합니다. 내시경 영상영상 임베디드 시스템에 대한 실시간 진단 지원 시스템의 유효성을 보여준다. 프로토타입 시스템은 비디오 프레임 속도(30fps @ 200MHz 이상)에 대한 실시간 처리와 90% 이상의 정확도를 보여주었습니다.
Masayuki ODAGAWA
Hiroshima University,Cadence Design Systems Japan
Takumi OKAMOTO
Cadence Design Systems Japan
Tetsushi KOIDE
Hiroshima University
Toru TAMAKI
Hiroshima University
Bisser RAYTCHEV
Hiroshima University
Kazufumi KANEDA
Hiroshima University
Shigeto YOSHIDA
Medical Corporation JR Hiroshima Hospital
Hiroshi MIENO
Medical Corporation JR Hiroshima Hospital
Shinji TANAKA
Hiroshima University
Takayuki SUGAWARA
Cadence Design Systems Japan
Hiroshi TOISHI
Cadence Design Systems Japan
Masayuki TSUJI
Cadence Design Systems Japan
Nobuo TAMBA
Cadence Design Systems Japan
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Masayuki ODAGAWA, Takumi OKAMOTO, Tetsushi KOIDE, Toru TAMAKI, Bisser RAYTCHEV, Kazufumi KANEDA, Shigeto YOSHIDA, Hiroshi MIENO, Shinji TANAKA, Takayuki SUGAWARA, Hiroshi TOISHI, Masayuki TSUJI, Nobuo TAMBA, "A Hardware Implementation on Customizable Embedded DSP Core for Colorectal Tumor Classification with Endoscopic Video toward Real-Time Computer-Aided Diagnosais System" in IEICE TRANSACTIONS on Fundamentals,
vol. E104-A, no. 4, pp. 691-701, April 2021, doi: 10.1587/transfun.2020EAP1069.
Abstract: In this paper, we present a hardware implementation of a colorectal cancer diagnosis support system using a colorectal endoscopic video image on customizable embedded DSP. In an endoscopic video image, color shift, blurring or reflection of light occurs in a lesion area, which affects the discrimination result by a computer. Therefore, in order to identify lesions with high robustness and stable classification to these images specific to video frame, we implement a computer-aided diagnosis (CAD) system for colorectal endoscopic images with Narrow Band Imaging (NBI) magnification with the Convolutional Neural Network (CNN) feature and Support Vector Machine (SVM) classification. Since CNN and SVM need to perform many multiplication and accumulation (MAC) operations, we implement the proposed hardware system on a customizable embedded DSP, which can realize at high speed MAC operations and parallel processing with Very Long Instruction Word (VLIW). Before implementing to the customizable embedded DSP, we profile and analyze processing cycles of the CAD system and optimize the bottlenecks. We show the effectiveness of the real-time diagnosis support system on the embedded system for endoscopic video images. The prototyped system demonstrated real-time processing on video frame rate (over 30fps @ 200MHz) and more than 90% accuracy.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020EAP1069/_p
부
@ARTICLE{e104-a_4_691,
author={Masayuki ODAGAWA, Takumi OKAMOTO, Tetsushi KOIDE, Toru TAMAKI, Bisser RAYTCHEV, Kazufumi KANEDA, Shigeto YOSHIDA, Hiroshi MIENO, Shinji TANAKA, Takayuki SUGAWARA, Hiroshi TOISHI, Masayuki TSUJI, Nobuo TAMBA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Hardware Implementation on Customizable Embedded DSP Core for Colorectal Tumor Classification with Endoscopic Video toward Real-Time Computer-Aided Diagnosais System},
year={2021},
volume={E104-A},
number={4},
pages={691-701},
abstract={In this paper, we present a hardware implementation of a colorectal cancer diagnosis support system using a colorectal endoscopic video image on customizable embedded DSP. In an endoscopic video image, color shift, blurring or reflection of light occurs in a lesion area, which affects the discrimination result by a computer. Therefore, in order to identify lesions with high robustness and stable classification to these images specific to video frame, we implement a computer-aided diagnosis (CAD) system for colorectal endoscopic images with Narrow Band Imaging (NBI) magnification with the Convolutional Neural Network (CNN) feature and Support Vector Machine (SVM) classification. Since CNN and SVM need to perform many multiplication and accumulation (MAC) operations, we implement the proposed hardware system on a customizable embedded DSP, which can realize at high speed MAC operations and parallel processing with Very Long Instruction Word (VLIW). Before implementing to the customizable embedded DSP, we profile and analyze processing cycles of the CAD system and optimize the bottlenecks. We show the effectiveness of the real-time diagnosis support system on the embedded system for endoscopic video images. The prototyped system demonstrated real-time processing on video frame rate (over 30fps @ 200MHz) and more than 90% accuracy.},
keywords={},
doi={10.1587/transfun.2020EAP1069},
ISSN={1745-1337},
month={April},}
부
TY - JOUR
TI - A Hardware Implementation on Customizable Embedded DSP Core for Colorectal Tumor Classification with Endoscopic Video toward Real-Time Computer-Aided Diagnosais System
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 691
EP - 701
AU - Masayuki ODAGAWA
AU - Takumi OKAMOTO
AU - Tetsushi KOIDE
AU - Toru TAMAKI
AU - Bisser RAYTCHEV
AU - Kazufumi KANEDA
AU - Shigeto YOSHIDA
AU - Hiroshi MIENO
AU - Shinji TANAKA
AU - Takayuki SUGAWARA
AU - Hiroshi TOISHI
AU - Masayuki TSUJI
AU - Nobuo TAMBA
PY - 2021
DO - 10.1587/transfun.2020EAP1069
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E104-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2021
AB - In this paper, we present a hardware implementation of a colorectal cancer diagnosis support system using a colorectal endoscopic video image on customizable embedded DSP. In an endoscopic video image, color shift, blurring or reflection of light occurs in a lesion area, which affects the discrimination result by a computer. Therefore, in order to identify lesions with high robustness and stable classification to these images specific to video frame, we implement a computer-aided diagnosis (CAD) system for colorectal endoscopic images with Narrow Band Imaging (NBI) magnification with the Convolutional Neural Network (CNN) feature and Support Vector Machine (SVM) classification. Since CNN and SVM need to perform many multiplication and accumulation (MAC) operations, we implement the proposed hardware system on a customizable embedded DSP, which can realize at high speed MAC operations and parallel processing with Very Long Instruction Word (VLIW). Before implementing to the customizable embedded DSP, we profile and analyze processing cycles of the CAD system and optimize the bottlenecks. We show the effectiveness of the real-time diagnosis support system on the embedded system for endoscopic video images. The prototyped system demonstrated real-time processing on video frame rate (over 30fps @ 200MHz) and more than 90% accuracy.
ER -