• Applied Microscopy
• /
• 제51권
• /
• pp.6.1-6.9
• /
• 2021

Histopathology is a well-established standard diagnosis employed for the majority of malignancies, including breast cancer. Nevertheless, despite training and standardization, it is considered operator-dependent and errors are still a concern. Fractal dimension analysis is a computational image processing technique that allows assessing the degree of complexity in patterns. We aimed here at providing a robust and easily attainable method for introducing computer-assisted techniques to histopathology laboratories. Slides from two databases were used: A) Breast Cancer Histopathological; and B) Grand Challenge on Breast Cancer Histology. Set A contained 2480 images from 24 patients with benign alterations, and 5429 images from 58 patients with breast cancer. Set B comprised 100 images of each type: normal tissue, benign alterations, in situ carcinoma, and invasive carcinoma. All images were analyzed with the FracLac algorithm in the ImageJ computational environment to yield the box count fractal dimension (Db) results. Images on set A on 40x magnification were statistically different (p = 0.0003), whereas images on 400x did not present differences in their means. On set B, the mean Db values presented promising statistical differences when comparing. Normal and/or benign images to in situ and/or invasive carcinoma (all p < 0.0001). Interestingly, there was no difference when comparing normal tissue to benign alterations. These data corroborate with previous work in which fractal analysis allowed differentiating malignancies. Computer-aided diagnosis algorithms may beneficiate from using Db data; specific Db cut-off values may yield ~ 99% specificity in diagnosing breast cancer. Furthermore, the fact that it allows assessing tissue complexity, this tool may be used to understand the progression of the histological alterations in cancer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• 한국방사선학회논문지
• /
• 제10권2호
• /
• pp.81-87
• /
• 2016

본 실험에서 제안된 질감특징분석 알고리즘은 지방간 환자의 CT영상을 이용하여 정상영상과 질환영상으로 구분하여, 정상 간 CT영상과 지방간 CT영상을 생성하고 제안된 질감특징분석을 이용한 컴퓨터보조 진단 시스템에 적용하여 6개의 파라메타로 정량적 분석을 통해 지방간 CT영상의 질환 인식률을 도출하고 평가하였다. 결과로 지방간 CT영상 30증례 중에서 각각의 파라메타별 질감특징 값에 대한 인식률은 평균 밝기의 경우 100%, 엔트로피의 경우 96.67%, 왜곡도의 경우 93.33%로 높게 나타났고, 평탄도의 경우 83.33%, 균일도의 경우 86.67%, 평균대조도의 경우 80%로 다소 낮은 질환 인식률을 보였다. 따라서 본 연구의 결과를 바탕으로 의료영상의 컴퓨터보조진단 시스템으로 발전된 프로그램을 구현한다면 지방간 CT영상의 질환부위 자동검출 및 정량적 진단이 가능해 컴퓨터보조진단 자료로서 활용이 가능할 것으로 판단되며 최종판독에서 객관성, 정확성, 판독시간 단축에 유용하게 사용 될 것으로 사료된다.

• 한국전기전자재료학회논문지
• /
• 제17권9호
• /
• pp.1006-1012
• /
• 2004

In this paper, neural networks is studied to apply as a PD source classification in XLPE power cable specimen. Two learning schemes are used to classification; BP(Back propagation algorithm), SOM(self organized map - kohonen network). As a PD source, using treeing discharge sources in the specimen, three defected models are made. And these data making use of a computer-aided discharge analyser, statistical and other discharge parameters is calculated to discrimination between different models of discharge sources. And a]so these distribution characteristics are applied to classify PD sources by two scheme of the neural networks. In conclusion, recognition efficiency of BP is superior to SOM.

• 한국정밀공학회지
• /
• 제15권8호
• /
• pp.71-80
• /
• 1998

A computer aided system has been developed for the focal length measurement/compensation in camera manufacture. Signal data proportional to light intensity is obtained and sampled very rapidly from the line CCD. Based on the measured signal, the MTF performance is calculated, where the MTF is the ratio of magnitude of the output image to the input image. In order to find the optimum MTF performance, an effcient algorithm has been implemented using the least squares technique. The developed system has been applied to a practical camera manufacturing process, and demonstrated high productivity with high precision.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.1299-1302
• /
• 2005

Current mechanical devices are trending toward being a small size, high speedy, automation. For performing these functions, machinery elements organizing a machine should be designed exactly. Cams have high confidence and economics in ablility to transmit a motion. Accordingly, A cam mechanism is very important for processing the machine automatically. This paper introduce an inverse cam mechanism. A square shaped cam which cannot be commonly analyzed is designed and manufactured by using the NURBS interpolation algorithm. The objective of this paper is to develop a computer-aided design program. In this paper, a displacement curve of oscillating motion inverse cam mechanism with square shaped follower is analyzed. The data is redistibuted by the NURBS algorithm. A cam shape is designed by the instant velocity center method, and simulated to verify the validity of the operation state.

• 한국통신학회논문지
• /
• 제29권7A호
• /
• pp.836-843
• /
• 2004

본 논문에서는 고속 TDMA (Time Division Multiple Access) 위성 통신 시스템에 적합한 위상 동기 방식을 제시하고, 추적 성능을 평가하였다. 낮은 SNR에서 작동하고 초기 포착 특성이 우수한 방식을 사용해야 하는 위성통신 시스템에 있어 채널 코딩은 필수적이다. 따라서 코딩에 적합한 위상 동기 방식이 필요하다. 그러나 기존의 DD (Decision Directed)나 NDA (Non-Data-Aided) 방식은 낮은 SNR에서 cyclic slipping 과 Hangup 현상에 민감하기 때문에 코딩 이득을 제대로 얻을 수 없다. 이러한 현상을 보완하기 위해 TD (Tentative Decision) 방식과 PSP (Per Survivor Processing) 방식이 제안되었다. PSP 방식은 TD 방식에 비해 성능이 뛰어나기는 하지만 복잡도가 크다는 단점을 가지고 있다. 따라서 본 논문에서는 채널 상태에 따라 적응적으로 PSP 방식과 TD 방식을 결합하여, 복잡도 문제를 해결하고 PSP 방식의 성능에 근접하는 ARSE (Adaptive Reduced State Estimator) 방식을 제안하였다.

• 한국통신학회논문지
• /
• 제36권7B호
• /
• pp.886-891
• /
• 2011

본 논문은 수중 센서 네트워크에서 효율적인 하향링크 멀티캐스트 데이터 전송기법을 제시하였다. 기존에 센서 네트워크에서 많은 멀티캐스트 전송 기법이 제안되었지만, 배터리를 지속적으로 공급받거나 충전시키기 어려운 환경에 있는 수중 센서 네트워크에 특화된 멀티캐스트 기법은 없었다. 본 논문에서는 이를 위하여 수중 센서 네트워크에서의 멀티캐스트 두 가지 특성을 파악하여 이를 알고리즘에 적용하였다. 싱크 노드에서 목적지 노드들의 위치 정보를 가공하여서 각도 정보를 추출하였고, 이렇게 추출한 목적지 노드들의 각도 정보를 바탕으로 가상의 유클리디언 스테이너 포인트를 이용한 최적의 멀티캐스트 전송 알고리즘을 제안하였다. 본 알고리즘은 저 계산 능력과 제한된 전송파워를 가지는 수중 센서 네트워크에서 구동하기에 알맞음을 시뮬레이션을 통하여 확인하였다. 제안한 방식은 기존의 방식들에 비하여 감소된 전송 전력과 감소된 라우팅 계산량을 보였다.

• 드라이브 ㆍ 컨트롤
• /
• 제14권4호
• /
• pp.29-36
• /
• 2017

Electronic control technologies that have long been developed for passenger cars spread to construction equipment and agricultural vehicles because of its outstanding performance achieved by embedded software. Especially, system program of transmission control unit (TCU) plays a crucial role for the superb shift quality, driving performance and fuel efficiency, etc. Since the control algorithm is embedded in software that is rarely analyzed, development of such a TCU cannot be conducted by conventional reverse engineering. Transmission simulator is a kind of electronic device that simulates the electric signals including driver operation command and output of various sensors installed in transmission. Standalone TCU can be run in normal operation mode with the signals provided by transmission simulator. In this research, transmission simulator for the tracked vehicle TCU is developed for the analysis of shift control algorithm from the experiments with standalone TCU. It was confirmed that shift experimental data for the simulator setup conditions can be used for the analysis of control algorithms on proportional solenoid valves and shift map.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.347-370
• /
• 2019

In the computer-aided detection (CAD) system of pulmonary nodules, a high false positive rate is common because the density and the computed tomography (CT) values of the vessel and the nodule in the CT images are similar, which affects the detection accuracy of pulmonary nodules. In this paper, a method of automatic detection of pulmonary nodules based on multi-scale enhancement filters and 3D shape features is proposed. The method uses an iterative threshold and a region growing algorithm to segment lung parenchyma. Two types of multi-scale enhancement filters are constructed to enhance the images of nodules and blood vessels in 3D lung images, and most of the blood vessel images in the nodular images are removed to obtain a suspected nodule image. An 18 neighborhood region growing algorithm is then used to extract the lung nodules. A new pulmonary nodules feature descriptor is proposed, and the features of the suspected nodules are extracted. A support vector machine (SVM) classifier is used to classify the pulmonary nodules. The experimental results show that our method can effectively detect pulmonary nodules and reduce false positive rates, and the feature descriptor proposed in this paper is valid which can be used to distinguish between nodules and blood vessels.