Parameter optimization of a computer-aided diagnosis system for detection of masses on digitized mammograms
Само за регистроване кориснике
2015
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
BACKGROUND: Reading mammograms is a difficult task and for this reason any development that may improve the performance in breast cancer screening is of great importance. OBJECTIVE: We proposed optimized computer aided diagnosis (CAD) system, equipped with reliability estimate module, for mass detection on digitized mammograms. METHODS: Proposed CAD system consists of four major steps: preprocessing, segmentation, feature extraction and classification. We propose a simple regression function as a threshold function for extraction of potential masses. By running optimization procedure we estimate parameters of the preprocessing and segmentation steps thus ensuring maximum mass detection sensitivity. In addition to the classification, where we tested seven different classifiers, the CAD system is equipped with reliability estimate module. RESULTS: By performing segmentation 91.3% of masses were correctly segmented with 4.14 false positives per image (FPpi). This result is improved in the... classification phase where, among the seven tested classifiers, multilayer perceptron neural network achieved the best result including 77.4% sensitivity and 0.49 FPpi. CONCLUSION: By using the proposed regression function and parameter optimization we were able to improve segmentation results comparing to the literature. In addition, we showed that CAD system has high potential for being equipped with reliability estimate module.
Кључне речи:
Breast cancer / computer-assisted image processing / data mining / mammography / optimizationИзвор:
Technology and Health Care, 2015, 23, 6, 757-774Издавач:
- IOS Press, Amsterdam
Финансирање / пројекти:
- Semantic Infostructure interlinking an open source Finite Element tool and libraries with a model repository for the multi-scale Modelling and 3d visualization of the inner-ear (EU-FP7-600933)
- Методе моделирања на више скала са применама у биомедицини (RS-MESTD-Basic Research (BR or ON)-174028)
- Примена биомедицинског инжењеринга у претклиничкој и клиничкој пракси (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-41007)
DOI: 10.3233/THC-151034
ISSN: 0928-7329
PubMed: 26409521
WoS: 000364411100006
Scopus: 2-s2.0-84946821949
Колекције
Институција/група
Geografski fakultetTY - JOUR AU - Radović, Miloš AU - Milošević, Marina AU - Ninković, Srđan AU - Filipović, Nenad AU - Peulić, Aleksandar PY - 2015 UR - https://gery.gef.bg.ac.rs/handle/123456789/710 AB - BACKGROUND: Reading mammograms is a difficult task and for this reason any development that may improve the performance in breast cancer screening is of great importance. OBJECTIVE: We proposed optimized computer aided diagnosis (CAD) system, equipped with reliability estimate module, for mass detection on digitized mammograms. METHODS: Proposed CAD system consists of four major steps: preprocessing, segmentation, feature extraction and classification. We propose a simple regression function as a threshold function for extraction of potential masses. By running optimization procedure we estimate parameters of the preprocessing and segmentation steps thus ensuring maximum mass detection sensitivity. In addition to the classification, where we tested seven different classifiers, the CAD system is equipped with reliability estimate module. RESULTS: By performing segmentation 91.3% of masses were correctly segmented with 4.14 false positives per image (FPpi). This result is improved in the classification phase where, among the seven tested classifiers, multilayer perceptron neural network achieved the best result including 77.4% sensitivity and 0.49 FPpi. CONCLUSION: By using the proposed regression function and parameter optimization we were able to improve segmentation results comparing to the literature. In addition, we showed that CAD system has high potential for being equipped with reliability estimate module. PB - IOS Press, Amsterdam T2 - Technology and Health Care T1 - Parameter optimization of a computer-aided diagnosis system for detection of masses on digitized mammograms VL - 23 IS - 6 SP - 757 EP - 774 DO - 10.3233/THC-151034 UR - https://hdl.handle.net/21.15107/rcub_gery_710 ER -
@article{ author = "Radović, Miloš and Milošević, Marina and Ninković, Srđan and Filipović, Nenad and Peulić, Aleksandar", year = "2015", abstract = "BACKGROUND: Reading mammograms is a difficult task and for this reason any development that may improve the performance in breast cancer screening is of great importance. OBJECTIVE: We proposed optimized computer aided diagnosis (CAD) system, equipped with reliability estimate module, for mass detection on digitized mammograms. METHODS: Proposed CAD system consists of four major steps: preprocessing, segmentation, feature extraction and classification. We propose a simple regression function as a threshold function for extraction of potential masses. By running optimization procedure we estimate parameters of the preprocessing and segmentation steps thus ensuring maximum mass detection sensitivity. In addition to the classification, where we tested seven different classifiers, the CAD system is equipped with reliability estimate module. RESULTS: By performing segmentation 91.3% of masses were correctly segmented with 4.14 false positives per image (FPpi). This result is improved in the classification phase where, among the seven tested classifiers, multilayer perceptron neural network achieved the best result including 77.4% sensitivity and 0.49 FPpi. CONCLUSION: By using the proposed regression function and parameter optimization we were able to improve segmentation results comparing to the literature. In addition, we showed that CAD system has high potential for being equipped with reliability estimate module.", publisher = "IOS Press, Amsterdam", journal = "Technology and Health Care", title = "Parameter optimization of a computer-aided diagnosis system for detection of masses on digitized mammograms", volume = "23", number = "6", pages = "757-774", doi = "10.3233/THC-151034", url = "https://hdl.handle.net/21.15107/rcub_gery_710" }
Radović, M., Milošević, M., Ninković, S., Filipović, N.,& Peulić, A.. (2015). Parameter optimization of a computer-aided diagnosis system for detection of masses on digitized mammograms. in Technology and Health Care IOS Press, Amsterdam., 23(6), 757-774. https://doi.org/10.3233/THC-151034 https://hdl.handle.net/21.15107/rcub_gery_710
Radović M, Milošević M, Ninković S, Filipović N, Peulić A. Parameter optimization of a computer-aided diagnosis system for detection of masses on digitized mammograms. in Technology and Health Care. 2015;23(6):757-774. doi:10.3233/THC-151034 https://hdl.handle.net/21.15107/rcub_gery_710 .
Radović, Miloš, Milošević, Marina, Ninković, Srđan, Filipović, Nenad, Peulić, Aleksandar, "Parameter optimization of a computer-aided diagnosis system for detection of masses on digitized mammograms" in Technology and Health Care, 23, no. 6 (2015):757-774, https://doi.org/10.3233/THC-151034 ., https://hdl.handle.net/21.15107/rcub_gery_710 .