TY - BOOK AU - Kiss, Bálint AU - Szirmay-Kalos, László TI - Proceedings of the Workshop on the Advances of Information Technology 2024 PB - BME Irányítástechnika és Informatika Tanszék CY - Budapest PY - 2024 SN - 9789634219422 UR - https://m2.mtmt.hu/api/publication/34562492 ID - 34562492 LA - English DB - MTMT ER - TY - JOUR AU - Sbert, Mateu AU - Szirmay-Kalos, László TI - A linear heuristic for multiple importance sampling JF - EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING J2 - EURASIP J ADV SIG PR VL - 2023 PY - 2023 IS - 1 SN - 1687-6172 DO - 10.1186/s13634-023-00990-8 UR - https://m2.mtmt.hu/api/publication/33734694 ID - 33734694 N1 - Correspondence Address: Sbert, M.; Department of Informatics, Campus de Montilivi, Spain; email: mateu@ima.udg.edu LA - English DB - MTMT ER - TY - BOOK AU - Kiss, Bálint AU - Szirmay-Kalos, László TI - Proceedings of the Workshop on the Advances of Information Technology 2023 PB - BME Irányítástechnika és Informatika Tanszék CY - Budapest PY - 2023 SN - 9789634218968 UR - https://m2.mtmt.hu/api/publication/33624046 ID - 33624046 LA - English DB - MTMT ER - TY - JOUR AU - Szirmay-Kalos, László AU - Magdics, Milán AU - Varnyú, Dóra TI - Direct dynamic tomographic reconstruction without explicit blood input function JF - BIOMEDICAL SIGNAL PROCESSING AND CONTROL J2 - BIOMED SIGNAL PROCES VL - 80 PY - 2023 PG - 10 SN - 1746-8094 DO - 10.1016/j.bspc.2022.104313 UR - https://m2.mtmt.hu/api/publication/33212860 ID - 33212860 N1 - Export Date: 8 November 2022 Correspondence Address: Szirmay-Kalos, L.; Budapest University of Technology and Economics, Hungary; email: szirmay@iit.bme.hu AB - With dynamic positron emission tomography (PET), we study the metabolic processes by monitoring the uptake of a radioactive tracer. The goal is to reconstruct the time-activity curves (TACs) of the voxels, from which the relevant kinetic parameters can be obtained. These curves are assumed to have the algebraic form of a pre-determined kinetic model. Plausible algebraic forms have a limited number of free parameters and thus can be used even for low-statistic measurements. The kinetic model typically involves the amount of radiotracer in the blood, which should be determined either by direct measurement or by extracting it from the PET data using image-derived or model-based methods. However, the direct measurement of the blood concentration is complicated, and the results of the image-derived and the model-based methods are also not reliable because of the partial volume effect and the unknown fraction of blood in the voxels. Moreover, in direct dynamic tomography, the kinetic model is fit from the very beginning of the reconstruction, thus the blood input function is needed even before the image-derived or model-based approaches can provide it. In this paper, we propose a method that is based on compartmental modeling and the Feng blood input function model defined by a fourth-order exponential equation with a pair of repeated eigenvalues, but does not require the blood input function and the fraction of blood parameters explicitly. Thus, the model can be used in cases when we wish to have the robustness and advantages of compartmental modeling, but no blood input function measurement is available. The test results show that the added error in the TACs of not knowing the blood input is reduced in comparison with the spline-based TAC representation. The method can be applied in reference tissue analysis and in image-derived input function approaches. LA - English DB - MTMT ER - TY - CHAP AU - Varnyú, Dóra AU - Szirmay-Kalos, László ED - Szirmay-Kalos, L ED - Renner, Gábor TI - Deep learning based regularization of PET reconstruction T2 - X. Magyar Számítógépes Grafika és Geometria Konferencia PB - Neumann János Számítógép-tudományi Társaság CY - Budapest SN - 9789634218715 PY - 2022 SP - 112 EP - 121 PG - 10 UR - https://m2.mtmt.hu/api/publication/33550845 ID - 33550845 LA - English DB - MTMT ER - TY - CHAP AU - Szirmay-Kalos, László AU - Varnyú, Dóra AU - Fridvalszky, András Máté AU - Szécsi, László ED - Szirmay-Kalos, L ED - Renner, Gábor TI - Virtual Reality Simulation of Surgical Procedures T2 - X. Magyar Számítógépes Grafika és Geometria Konferencia PB - Neumann János Számítógép-tudományi Társaság CY - Budapest SN - 9789634218715 PY - 2022 SP - 51 EP - 56 PG - 6 UR - https://m2.mtmt.hu/api/publication/33550817 ID - 33550817 LA - English DB - MTMT ER - TY - CHAP AU - Szirmay-Kalos, László ED - Kiss, Bálint ED - Szirmay-Kalos, László TI - Probabilistic versus fuzzy segmentation of volumetric medical data T2 - Proceedings of the Workshop on the Advances in Information Technology 2022 PB - OSZK CY - Budapest SN - 9789634218715 PY - 2022 SP - 105 EP - 110 PG - 6 UR - https://m2.mtmt.hu/api/publication/33538636 ID - 33538636 LA - English DB - MTMT ER - TY - CHAP AU - Csenge, Fábián AU - Szirmay-Kalos, László ED - Kiss, Bálint ED - Szirmay-Kalos, László TI - Volumetric transfer functions with differential rendering T2 - Proceedings of the Workshop on the Advances in Information Technology 2022 PB - OSZK CY - Budapest SN - 9789634218715 PY - 2022 SP - 34 EP - 38 PG - 5 UR - https://m2.mtmt.hu/api/publication/33538623 ID - 33538623 LA - English DB - MTMT ER - TY - JOUR AU - Varnyú, Dóra AU - Szirmay-Kalos, László TI - A Comparative Study of Deep Neural Networks for Real-Time Semantic Segmentation during the Transurethral Resection of Bladder Tumors JF - DIAGNOSTICS J2 - DIAGNOSTICS VL - 12 PY - 2022 IS - 11 SP - 2849 SN - 2075-4418 DO - 10.3390/diagnostics12112849 UR - https://m2.mtmt.hu/api/publication/33456128 ID - 33456128 N1 - Correspondence Address: Varnyú, D.; Department of Control Engineering and Information Technology, Műegyetem rkp. 3, Hungary; email: vdora@iit.bme.hu AB - Bladder cancer is a common and often fatal disease. Papillary bladder tumors are well detectable using cystoscopic imaging, but small or flat lesions are frequently overlooked by urologists. However, detection accuracy can be improved if the images from the cystoscope are segmented in real time by a deep neural network (DNN). In this paper, we compare eight state-of-the-art DNNs for the semantic segmentation of white-light cystoscopy images: U-Net, UNet++, MA-Net, LinkNet, FPN, PAN, DeepLabv3, and DeepLabv3+. The evaluation includes per-image classification accuracy, per-pixel localization accuracy, prediction speed, and model size. Results show that the best F-score for bladder cancer (91%), the best segmentation map precision (92.91%), and the lowest size (7.93 MB) are also achieved by the PAN model, while the highest speed (6.73 ms) is obtained by DeepLabv3+. These results indicate better tumor localization accuracy than reported in previous studies. It can be concluded that deep neural networks may be extremely useful in the real-time diagnosis and therapy of bladder cancer, and among the eight investigated models, PAN shows the most promising results. LA - English DB - MTMT ER - TY - CHAP AU - Varnyú, Dóra AU - Szirmay-Kalos, László ED - Tomita, H. ED - Nakamura, T. TI - Blood Input Function Estimation in Positron Emission Tomography with Deep Learning T2 - 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Piscataway (NJ) SN - 1665421142 T3 - IEEE conference record - Nuclear Science Symposium & Medical Imaging Conference, ISSN 1082-3654 PY - 2022 PG - 7 DO - 10.1109/NSS/MIC44867.2021.9875543 UR - https://m2.mtmt.hu/api/publication/33156891 ID - 33156891 AB - Dynamic positron emission tomography allows in vivo study of metabolic processes by monitoring the tissue uptake of a radioactive tracer. Its aim is to reconstruct the time-activity curves of the voxels of the measured volume, which are sought in the algebraic form of a predetermined kinetic model. This kinetic model typically depends on the blood input function, which describes the amount of radiotracer in the blood that can be absorbed by tissues. The blood input function can be estimated in parallel with the kinetic parameters of the voxels during the iterative reconstruction process. However, because kinetic parameter calculation requires the blood input even at the start of reconstruction, an initial approximation needs to be given. In this paper, a deep CNN-LSTM-DNN network is proposed to estimate the blood input function from the sinogram data. LA - English DB - MTMT ER -