Performance Assessment of Carcinoma With Segmentation Techniques By Statistical Analysis
DOI:
https://doi.org/10.46243/jstj.2019.v4.i5.73Keywords:
Segmentation, Binarization, Carcinoma, Mammogram, Mean, Variance, Standard Deviation.Abstract
Carcinoma is the most deadly disease of which Lung cancer and Breast cancer are of high risk. This approach target at diagnosing carcinoma by considering certain techniques. In this approach, a mammogram image and microscopic Lung image are considered. These images are applied through different image segmentation techniques. Later, Binarization technique is applied to improve the contrast of the images within the affected area. Median filter is used for removing noise within the image. To the noise-free images, some of the statistical parameters are calculated. Correlation is calculated between the reference parameters and cancerous parameters. These approaches are done for the detection of cancer in statistical approach. Results are processed using MATLAB and Xilinx.
References
Cancer ifacts i& ifigures i2018, iAmerican icancer isociety, ihttps://www.cancer.org/
A ito iZ ilist iof iCancers, ihttps://www.cancer.gov/
A. iJemal, iR. iSiegel, iE.Ward, iY. iHao, iJ. iXu, iand iM. iJ. iThun,“Cancer istatistics, i2009,” iCA: iCancer iJournal ifor iClinicians,vol. i59, ino. i4, ipp. i225–249, i2009. Welch, iH. iG., iProrok, iP. iC., iO’Malley, iA. iJ., i& iKramer, iB. iS. i(2016). iBreast-cancer itumor isize, ioverdiagnosis, iand imammography iscreening effectiveness. iNew iEngland iJournal iof iMedicine, i375(15), i1438-1447
Litjens, iG., iSánchez, iC. iI., iTimofeeva, iN., iHermsen, iM., iNagtegaal, iI., iKovacs, iI., i... i& iVan iDer iLaak, iJ. i(2016). iDeep ilearning ias ia itool ifor iincreased iaccuracy iand iefficiency iof ihistopathological idiagnosis. iScientific ireports, i6, i26286. i i i i i i i i i i i i i i i i
Kumar iR., iSrivastava iR., iSrivastava iS. i“Detection iand iClassification iof iCancer ifrom iMicroscopic iBiopsy iImages iUsing iClinically iSignificant iand iBiologically iInterpretable iFeatures” iProc iof iJournal iof iMedical iEngineering, iVolume i2015 i(2015), iArticle iID i457906, i14 ipages
Srivaramangai, iR., iHiremath, iP., i& iPatil, iA. iS. i(2017). iPreprocessing imri iimages iof icolorectal icancer. iInternational iJournal iof iComputer iScience iIssues i(IJCSI), i14(1), i48
Garg, iN. i(2013). iBinarization iTechniques iused ifor igrey iscale iimages. iInternational iJournal iof iComputer iApplications, i71(1). i i i i i i i i i
Bafna, iY., iVerma, iK., iPanigrahi, iL., i& iSahu, iS. iP. i(2018). iAutomated iboundary idetection iof ibreast icancer iin iultrasound iimages i iusing iwatershed ialgorithm. iIn iAmbient icommunications iand icomputer isystems i(pp. i729-738). iSpringer, iSingapore. i i i
Hou, iZ., iHu, iQ., i& iNowinski, iW. iL. i(2006). iOn iminimum ivariance ithresholding. iPattern iRecognition iLetters, i27(14), i1732-1743. iBasim iAlhadidi i(2007). iMammogram iBreastCancer iImage iDetection iUsing iImageProcessing iFunctions, iInformation iTechnology iJournal, iVol.6, iNo.2, ipp.217-221
Kumar, iR., iArthanari, iM., i& iSivakumar, iM. i(2011). iImage isegmentation iusing idiscontinuity-based iapproach. iInt. iJ. iMultimedia iImage iProcess, i1, i72-78
Karthika, iM., i& iJames, iA. i(2015). iA inovel iapproach ifor idocument iimage ibinarization iusing ibit-plane islicing. iProcedia iTechnology, i19, i758-765
