mammographic phantom images using receiver operating ...
Recommend Documents
Adaptive contrast enhancement methods use a local contrast definition and then image ... histogram equalization for enhancing details in an image while preserving its ..... K. Zuiderveld, âAdaptive histogram equalisation and its variationsâ,.
Oct 27, 2006 - [26] Steve Webb, The Physics of Medical Imaging, IOP Publishing, Adam Hilger, Bristol and. Philadelphia, 1988. [27] H. Zhu, F.H.Y. Chan, F.K. ...
Apr 10, 2012 - ... Christian R Loehberg; Alexander Hein; Christian M Bayer; Carolin C ...... Huo Z, Giger ML, Wolverton DE, Zhong W, Cumming S, Olopade OI: ...
Combining Classifiers Using Their Receiver. Operating Characteristics and Maximum. Likelihood Estimation*. Steven Haker, William M. Wells III, Simon K.
Apr 10, 2012 - Michael Uder5, Matthias W Beckmann1 and Thomas Wittenberg2 ...... 2. McCormack VA, dos Santos Silva I: Breast density and parenchymal.
May 29, 2018 - (VHI) and the Greek translated version of Voice Evaluation Template (VEF) ... be used as a primary health care tool and a self-monitoring ...
Receiver operating characteristic curve is a standard method for reporting performance of a system. In this paper we show how to choose the optimal operating.
grams and differential diagnosis of pancreatic diseases), to investigate the confidence sur- faces produced for ... ROC analysis is now common in medicine and healthcare [4][13][14], particularly in radiology ...... York, Chapman & Hall, 1993. 26 S.
Areas under the receiver operating characteristic (ROC) curves were calculated ... TG-ROC curves showed that birth weight cutoffs were slightly higher in.
Jul 5, 2009 - of skewness and kurtosis in order to trace out Microcalcification in the mammographic images. The mammographic images are region grown ...
failure rates (AFR) and the area under the receiver operating characteristic (ROC) curve (AUC). In particular, we consider rare event detection problems,.
116â123, 2005. [12] U.S. Equal Employment Opportunity Commission, Health. Partners, Inc. To Pay $25, 000 to Resolve EEOC Disability. Discrimination Case ...
double sigmoid functions as the gray level transformation function. The mask is spatially moved over the region of interest (ROI) to produce an enhanced image.
eyewitness confidenceâaccuracy relation is weak under good lab- ..... door to the office was open, and a laptop computer could be plainly seen sitting on a ...
example was concerned with the winter of 1995-1996 when there were 77 .....
forecasts mention "Rain" in their summary but if one looks at details they also ...
CLINICAL. CHEMISTRY,. Vol. 41, No. 8(B), 1995. Mu Itivariate Receiver-Operating. Characteristic. Curve Analysis: Prostate Cancer. Screening as an Example.
Service Contact Sample. âDuring 1 mars â 30 september 2014 data a collected from 2 648 children and young people from 27 municipalities in Sweden who ...
Requirement engineering has an important role in software project development. .... software company provide new idea to specify project cost schedule and ...
Figure S1 â The ROC-like (Receiver Operating Characteristic) curve of. CURE-Chloroplast. The sensitivity and specificity changed with different upper.
Receiver Operating Characteristics (ROC) Curve. Area Analysis using the ROC ANALYZER. Robert M. Centor Gerald E. Keightley. Medical College of ...
Receiver Operating Characteristics of Perceptrons: In uence of Sample Size and Prevalence. Ansgar Freking, Michael Biehl, Christian Braun,. Wolfgang Kinzel ...
Dec 9, 2009 - SENTRY 100 and GENios Pro [25]. Also, four post-mortem tests giving either a positive or negative test result (binary outcome) were applied.
Estimating the area under a receiver operating characteristic. (ROC) curve: Parametric and nonparametric ways. Weichao Xu a,n, Jisheng Dai b, Y.S. Hung c, ...
Novel Fiber Ring Based PON Monitoring System. Maged Abdullah ..... The overview of fiber fault localization technology in TDM-PON networkâ, In Proc. of Int.
mammographic phantom images using receiver operating ...
Wan Hassan, as my supervisor for all his support, guidance, providing the time ... Kanser payudara adalah sejenis kanser penyebab utama kematian wanita di.
MAMMOGRAPHIC PHANTOM IMAGES USING RECEIVER OPERATING CHARACTERISTIC ANALYSIS
NOR’AIDA BINTI KHAIRUDDIN
UNIVERSITI TEKNOLOGI MALAYSIA
i
MAMMOGRAPHIC PHANTOM IMAGE ANALYSIS FROM RECEIVER OPERATING CHARACTERISTIC (ROC) CURVE
NOR’AIDA BINTI KHAIRUDDIN
A thesis submitted in fulfilment of the requirements for the award of the degree of Master of Science (Physics)
Faculty of Science Universiti Teknologi Malaysia
JULY 2014
iii
To my beloved mother, sisters and brothers
iv
ACKNOWLEDGEMENT
My period as a graduate student at Universiti Teknologi Malaysia has provided me with great opportunities from many aspects. I wish to extend my hearty thanks to all whom I am indebted for supporting me as I complete this thesis. An especially thanks are to Assoc Prof Dr Wan Muhammad Saridan Bin Wan Hassan, as my supervisor for all his support, guidance, providing the time to discuss my work and helpful discussions. I also thanks the radiologist and radiographers at Diagnostic Imaging Department, Hospital Sultan Ismail, namely Dr Hasnizan Bin Hassan, Puan Salabiah Binti Shapawi and Puan Tay Bee Hua who have given me an opportunity to have the use of equipments and for all their assistance and cooperation. In addition, I am grateful to Puan Norriza Binti Mohd Isa from Malaysian Nuclear Agency, Bangi for her kind assistance in experimental, constructive ideas and valuable suggestions. I wish to thanks my beloved mother Puan Hjh Zamnah Binti Hj Jiman for her unconditional love, support and guidance through all my years of schooling and to my beloved siblings and friends for all their encouragement. Finally, I would also like to express my gratitude to the Malaysian Ministry of Science, Technology and Innovation (MOSTI) for their financial funding through Science Fund grant and Universiti Teknologi Malaysia for providing the Zamalah research scholarship. I also wish to thanks to Malaysian Ministry of Education (MOE) for allowed me to undertake full time study leave.
ABSTRAK
Kanser payudara adalah sejenis kanser penyebab utama kematian wanita di seluruh dunia. Sebahagian imej mammografi digital mempunyai hingar dan kontras yang rendah. Teknik pemprosesan imej telah digunakan untuk meningkatkan kualiti imej. Tujuan penyelidikan ini adalah untuk melakukan analisis ciri operasi penerima (ROC) terhadap imej fantom mamografi yang dikenakan dua teknik peningkatan untuk menentusahkan sama ada teknik peningkatan itu meningkatkan kualiti imej. Imej mammografi digital ini ditingkatkan menggunakan teknik morfologi dan ubah bentuk gelombang kecil. Bagi teknik morfologi, imej dipertingkatkan menggunakan pembesaran untuk operasi morfologi dan penutupan morfologi. Bagi peningkatan ubah bentuk gelombang kecil, penuras wavelet biorthogonal 2.8 dengan dua tahap penguraian (L=2) telah digunakan. Empat orang pemerhati menilai imej yang mengandungi nodul, gentian dan mikronodul. Prestasi pengesanan terhadap imej asal dan imej yang telah diproses melalui tersebut dinilai dengan lengkung ROC. Imej juga dinilai berdasarkan tahap kontras, ketajaman serta kualiti imej keseluruhan. Analisis ROC menunjukkan pengesanan terhadap mikronodul memberi luas di bawah lengkungan dan nilai sensitiviti yang lebih tinggi daripada pengesanan terhadap nodul dan gentian. Bagi penilaian keseluruhan kualiti imej menggunakan skala penilaian subjektif pemerhati pula, imej asal menunjukkan nilai min yang lebih tinggi daripada imej yang ditingkatkan.
ABSTRACT
Breast cancer is a form of cancer which is a leading cause of death among women worldwide. Some digital mammographic images are noisy and have low contrast. Image processing techniques have been used to improve the quality of images. The aim of this study is to perform receiver operating characteristic (ROC) analysis on mammographic phantom images subjected to two enhancement techniques in order to verify whether the enhancements improve the quality of the images. The digital mammographic images were enhanced using the morphological and wavelet transform techniques. For the morphological techniques, the images were enhanced using dilation for morphological operation and morphological closing. For wavelet transform enhancement, biorthogonal 2.8 wavelet filter with two levels of decomposition (L=2) was used. Four observers evaluated the images that contain fibres, nodules and micronodules. The detection performances of the original and enhanced images were evaluated using ROC curves. The images were also rated based on contrast visibility, sharpness and overall image quality. The ROC analysis showed that detection of micronodules gave higher area index of curves and sensitivity than the detection of nodules and fibrils in all image datasets. For evaluation of overall image quality using observers’ subjective rating scale, original images have higher mean values than the enhanced images.
