Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Fundamenta Informaticae

2 2019

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Improvement of Cerebral Microbleeds Detection Based on Discriminative Feature Learning

Hong Jin, Cheng Hong, Wang Shui-Hua, Liu Jie

Fundamenta Informaticae

2019

Vol. 168, nr 2-4

231--248

The existence and distribution pattern of cerebral microbleeds (CMBs) are associated with some underlying aetiologies caused by intra-cerebral hemorrhage (ICH). CMBs as a kind of subclinical sign can be recognized via magnetic resonance (MR) imaging technique in a few years before the onset of the disease. Hence, detecting CMBs accurately is important for treating and preventing related cerebral disease. In this study, we employed convolution neural network (CNN) for CMBs detection because of its powerful ability in image recognition. In view of too many efforts on optimizing the structure of CNN for achieving a better performance, we introduced center loss, which can greatly enhance the discriminative power of the deeply learned features, to CMBs detection for the first time. It is found that the performances of convolution neural network (CNN) trained under the joint supervision of softmax loss and center loss were significantly better than that under the supervision of softmax loss, even if there are few mislabelled samples in training data. With this trick, we achieved a high performance with a sensitivity of 98.869 ± 1.026%, a specificity of 96.491 ± 0.367%, and an accuracy of 97.681 ± 0.497%, which is better than four state-of-the-art methods.

Abnormality Diagnosis in Mammograms by Transfer Learning Based on ResNet18

Yu Xiang, Wang Shui-Hua

Fundamenta Informaticae

2019

Vol. 168, nr 2-4

219--230

Breast cancer is one of the common cancers threatening the health of women while the incident rate of it is quite low in men to contribute to a major killer of men. Early syndromes of breast cancer including micro-calcification, mass, and distortion in mammography images can be very helpful for radiologists to make diagnosis of the cancer at early stage, which means the cancer can be treated or even be cured timely and thus make early diagnosis important. To assist radiologists with diagnosis, we set up a computer-aided diagnosis system to make diagnosis decision of breast cancer in this paper. We acquired regions of interests in mammographic images from public database, and labeled regions containing micro-calcification or mass as abnormality while regions without such abnormalities as normality. By transferring the state-of-the-art networks into our quest, we found that ResNet18 performed best and achieved mean accuracy of 95.91%.