20.500.12556/RUL-132951 Spremljanje kakovosti mamogramov s kvantitativno analizo slik Quality control in digital mammography with quantitative image analysis Za zagotavljanje kakovosti mamografskih slik na vsakem mamografu redno, tipično dnevno, opravijo slikanje homogenega fantoma. Vizualen pregled slik je zamuden, poleg tega pa lahko kakšno nepravilnost, predvsem manjšo, spregledamo. Zaradi tega potrebujemo nove metode, ki bodo dovolj občutljive za avtomatsko zaznavanje nepravilnosti. V magistrski nalogi bom predstavila metodo, s katero lahko na podlagi preproste statistične mere, koeficienta asimetrije $g_1$, zelo hitro odkrijemo nepravilnosti, ki se pojavljajo na slikah fantoma. S to metodo sem pri 18 mamografih, vključenih v Državni presejalni program za raka dojk DORA, v obdobju od oktobra 2019 do marca 2021 odkrila 13 točkovnih nepravilnosti in 4 linijske nepravilnosti. Nekatere nepravilnosti so izginile po kalibraciji ali po menjavi detektorja, nekatere pa so ostale. Za določene mamografe sem narisala časovno odvisnost $P_{98\%}|{g_1}|$ ter časovno odvisnost ${g_1}^{max}$ in ${g_1}^{min}$. Na koncu sem narisala še skupno časovno odvisnost prej omenjenih spremenljivk za mamografe proizvajalca Siemens in Hologic. Parameter $g_1$ se je izkazal kot zanesljiva in robustna cenilka točkovnih in linijskih nepravilnosti mamografskih aparatov in je potencialna avtomatizirana mera pravilnosti delovanja tovrstnih naprav. As part of the quality control of the Slovenian Breast Cancer Screening Programme (DORA), regular, preferably daily, scans of homogeneous phantom are performed at each mammography unit. Visual inspection of images is time consuming, and in addition, some iregularities, especially minor, can be overlooked. We need new methods, sensitive enough to automatically detect such irregularities. In my thesis I introduce a method based on a simple statistical measure, skewness $g_1$, with which we can quickly detect irregularities that appear in phantom images. With this method I have discovered 13 point artefacts and 4 line artefacts that have appeared from October 2019 to March 2021 on images of mammographs that are part of the DORA programme. Some artefacts have disappeared after calibration or detector replacement, but some have stayed. For a few mammographs I made graphs of the time dependence of $P_{98\%}$ $|{g_1}|$, ${g_1}^{max}$ and ${g_1}^{min}$. I made a graph of total time dependence for Siemens and Hologic mammography systems. The parameter $g_1$ has proven to be a reliable and robust estimator of point and line artefacts of mammography units and is a potential automated measure for quality control. preverjanje kakovosti artefakti koeficient asimetrije quality control artefacts skewness true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2021-11-07 08:15:03 2021-11-07 08:15:10 2022-09-12 04:14:25 0000-00-00 00:00:00 2021 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 122917 85153539 4257.pdf 4257.pdf 1 7B975872198D5726D79275DC7A43A908 6fec41a526afad84f9be7b4d06dba2ca4b516e27e4414919bd416083090ae6f5 65fb50f0-3f9a-11ec-abdb-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=150701 Fakulteta za matematiko in fiziko 0 0 0