Ensemble of Convolutional Neural Networks for Classification of Breast Microcalcification from Mammograms

2017-07-15
Human level recall performance in detecting breast cancer considering microcalcifications from mammograms has a recall value between 74.5% and 92.3%. In this research, we approach to breast microcalcification classification problem using convolutional neural networks along with various preprocessing methods such as contrast scaling, dilation, cropping etc. and decision fusion using ensemble of networks. Various experiments on Digital Database for Screening Mammography dataset showed that preprocessing poses great importance on the classification performance. The stand-alone models using the dilation and cropping preprocessing techniques achieved the highest recall value of 91.3%. The ensembles of the stand-alone models surpass this recall value and a 97.3% value of recall is achieved. The ensemble having the highest F1 Score (harmonic mean of precision and recall), which is 94.5%, has a recall value of 94.0% and a precision value of 95.0%. This recall is still above human level performance and the models achieve competitive results in terms of accuracy, precision, recall and F1 score measures.

Suggestions

Using Deep Learning for Mammography Classification
Hepsag, Pinar Uskaner; ÖZEL, SELMA AYŞE; Yazıcı, Adnan (2017-10-08)
Breast biopsies based on the results of mammography and ultrasound have been diagnosed as benign at a rate of approximately 40 to 60 percent. Negative biopsy results have negative impacts on many aspects such as unnecessary operations, fear, pain, and cost. Therefore, there is a need for a more reliable technique to reduce the number of unnecessary biopsies in the diagnosis of breast cancer. So, computer-aided diagnostic methods are very important for doctors to make more accurate decisions and to avoid unn...
Effect of input size on the classification of lung nodules using convolutional neural networks Akciǧer nodüllerinin evrişimsel sinir aǧlari kullanilarak siniflandirilmasinda girdi boyutunun etkisi
POLAT, Gorkem; Serinağaoğlu Doğrusöz, Yeşim; Halıcı, Uğur (2018-05-05)
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces lung cancer mortality by 20% compared to traditional chest radiography. Therefore, CT lung screening has started to be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in a CT scan can be up to 600. Therefore, computer-aided-detection (CAD) systems are very important for faster and more accurate assessment of the data. In this...
Implementation of a fast simulation tool for the analysis of contrast mechanisms in HMMDI and enhancement of the SNR in the experimental set-up
İrgin, Ümit; Gençer, Nevzat Güneri; Top, Can Barış; Department of Electrical and Electronics Engineering (2021-9-06)
Clinical method for breast tumor detection is Mammography (X-rays), which have limitations and may yield inaccurate results. Alternative novel techniques are required to characterize the breast tissues and extract accurate information for identification of malignancies in the tissue. Harmonic Motion Microwave Doppler Imaging (HMMDI), which enhances hybridizing microwave signals and ultrasound techniques, has been recently proposed for detection of tumors in the tissue. In HMMDI method, the data is a combina...
Classification of lung nodules in CT images using convolutional neural networks
Polat, Görkem; Serinağaoğlu Doğrusöz, Yeşim; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2018)
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces lung cancer mortality by 20% compared to traditional chest radiography. Therefore, CT lung screening has started to be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in a CT scan can be up to 600. Therefore, computeraided-detection (CAD) systems are very important for faster and more accurate assessment of the data. In this ...
Comparison of the Diagnostic Accuracy of Next Generation Sequencing and Microarray Resequencing Methods for Detection of BRCA1 and BRCA2 Gene Mutations
Bahsi, Taha; Ergun, Sezen Güntekin; Ergun, Mehmet Ali; Perçin, E. Ferda (Gazi University, 2018-4-1)
Objective: Breast cancer constitutes 29 % of estimated new cases of cancer in women, and it is also one of the major cause of death in all cancer types. In this study, DNA samples of familial breast cancer patients with BRCA1 and BRCA2 mutations which had been analyzed using conventional DNA sequencing method, were also analyzed with new methods including microarray and next generation sequencing (NGS) in order to compare their results Methods: Seven patients with BRCA1 mutation, one patient with BRCA2 m...
Citation Formats
E. SERT, Ş. Ertekin Bolelli, and U. Halıcı, “Ensemble of Convolutional Neural Networks for Classification of Breast Microcalcification from Mammograms,” 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/47785.