PREDLOG SISTEMA VEŠTAČKE INTELIGENCIJE ZA POMOĆ U MAMOGRAFSKOJ DIJAGNOSTICI
Ključne reči:
mamografija, neuronske mreže, U-net, segmentacija
Apstrakt
Mamografija kao dijagnostička metoda za otkrivanje maligniteta široko je u upotrebi i oslanja se na ekspertsko tumačenje radiologa. U ovom radu istražena je prilika da se takav sistem unapredi veštačkom inteligencijom koja bi predstavljala podršku u donošenju odluka u vezi sa tumačenjem mamografskih snimaka. Istražen je model U-net za segmentaciju tkiva, opisana njegova generalna arhitektura i arhitektura prilagođena za opisani problem, kao i njegova primena na nekim od otvorenih skupova podataka. Opisan je proces i opisani su parametri treniranja modela.. Izneseni su i diskutovani rezultati primenjenog modela i sve to sumirano u zaključnom poglavlju.
Reference
[1] Ciritsis A, Rossi C, Vittoria De Martini I, Eberhard M, Marcon M, Becker AS, Berger N, Boss A. Determination of mammographic breast density using a deep convolutional neural network. Br J Radiol. 2019 Jan;92(1093):20180691. doi: 10.1259/bjr.20180691. Epub 2018 Oct 1. PMID: 30209957; PMCID: PMC6435091.
[2] https://www.kaggle.com/competitions/rsna-breast-cancer-detection/
[3] R.N.J. Graham, R.W. Perriss, A.F. Scarsbrook, DICOM demystified: A review of digital file formats and their use in radiological practice, Clinical Radiology, Volume 60, Issue 11, 2005, Pages 1133-1140, ISSN 0009-9260
[4] https://www.kaggle.com/code/theoviel/breast-density-classification-using-monai
[5] Vikash Gupta, Mutlu Demirer, Robert W. Maxwell, Richard D. White, Barbaros Selnur Erdal: “A multi-reconstruction study of breast density estimation using Deep Learning”, 2022; [https://arxiv.org/abs/2202.08238 arXiv:2202.08238]
[6] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich: “Going Deeper with Convolutions”, 2014; [https://arxiv.org/abs/1409.4842 arXiv:1409.4842]
[7] Pablo Fonseca, Julio Mendoza, Jacques Wainer, Jose Ferrer, Joseph Pinto, Jorge Guerrero, Benjamin Castaneda, "Automatic breast density classification using a convolutional neural network architecture search procedure," Proc. SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis, 941428 (20 March 2015); doi: 10.1117/12.2081576
[8] Ciritsis A, Rossi C, Vittoria De Martini I, Eberhard M, Marcon M, Becker AS, et al. Determination of mammographic breast density using a deep convolutional neural network. Br J Radiol 2019; 92: 20180691.
[9] Shen, L., Margolies, L.R., Rothstein, J.H. et al. Deep Learning to Improve Breast Cancer Detection on Screening Mammography. Sci Rep 9, 12495 (2019). https://doi.org/10.1038/s41598-019-48995-4
[10] Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, Ross Girshick: “Segment Anything”, 2023; [https://arxiv.org/abs/2304.02643 arXiv:2304.02643]
[11] Jun Ma, Bo Wang: “Segment Anything in Medical Images”, 2023; [https://arxiv.org/abs/2304.12306 arXiv:2304.12306]
[12] Olaf Ronneberger, Philipp Fischer, Thomas Brox: “U-Net: Convolutional Networks for Biomedical Image Segmentation”, 2015; [https://arxiv.org/abs/1505.04597 arXiv:1505.04597]
[13] https://towardsdatascience.com/active-learning-overview-strategies-and-uncertainty-measures-521565e0b0b
[2] https://www.kaggle.com/competitions/rsna-breast-cancer-detection/
[3] R.N.J. Graham, R.W. Perriss, A.F. Scarsbrook, DICOM demystified: A review of digital file formats and their use in radiological practice, Clinical Radiology, Volume 60, Issue 11, 2005, Pages 1133-1140, ISSN 0009-9260
[4] https://www.kaggle.com/code/theoviel/breast-density-classification-using-monai
[5] Vikash Gupta, Mutlu Demirer, Robert W. Maxwell, Richard D. White, Barbaros Selnur Erdal: “A multi-reconstruction study of breast density estimation using Deep Learning”, 2022; [https://arxiv.org/abs/2202.08238 arXiv:2202.08238]
[6] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich: “Going Deeper with Convolutions”, 2014; [https://arxiv.org/abs/1409.4842 arXiv:1409.4842]
[7] Pablo Fonseca, Julio Mendoza, Jacques Wainer, Jose Ferrer, Joseph Pinto, Jorge Guerrero, Benjamin Castaneda, "Automatic breast density classification using a convolutional neural network architecture search procedure," Proc. SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis, 941428 (20 March 2015); doi: 10.1117/12.2081576
[8] Ciritsis A, Rossi C, Vittoria De Martini I, Eberhard M, Marcon M, Becker AS, et al. Determination of mammographic breast density using a deep convolutional neural network. Br J Radiol 2019; 92: 20180691.
[9] Shen, L., Margolies, L.R., Rothstein, J.H. et al. Deep Learning to Improve Breast Cancer Detection on Screening Mammography. Sci Rep 9, 12495 (2019). https://doi.org/10.1038/s41598-019-48995-4
[10] Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, Ross Girshick: “Segment Anything”, 2023; [https://arxiv.org/abs/2304.02643 arXiv:2304.02643]
[11] Jun Ma, Bo Wang: “Segment Anything in Medical Images”, 2023; [https://arxiv.org/abs/2304.12306 arXiv:2304.12306]
[12] Olaf Ronneberger, Philipp Fischer, Thomas Brox: “U-Net: Convolutional Networks for Biomedical Image Segmentation”, 2015; [https://arxiv.org/abs/1505.04597 arXiv:1505.04597]
[13] https://towardsdatascience.com/active-learning-overview-strategies-and-uncertainty-measures-521565e0b0b
Objavljeno
2023-12-04
Sekcija
Elektrotehničko i računarsko inženjerstvo
