TY - CHAP AU - Lefkovits, Szidónia AU - Imre, László AU - Lefkovits, László ED - Moldovan, Liviu ED - Gligor, Adrian TI - Kidney Stone Detection and Delimitation in Computed Tomography Using YOLOv11 T2 - Proceedings of the 19th International Conference Inter-Eng 2025 Interdisciplinarity in Engineering Held During 3–4 October 2025 PB - Springer Nature Switzerland CY - Cham SN - 9783032170330 T3 - Lecture notes in networks and systems, ISSN 2367-3370 ; 1812. PY - 2026 SP - 96 EP - 114 PG - 19 DO - 10.1007/978-3-032-17033-0_7 UR - https://m2.mtmt.hu/api/publication/37540068 ID - 37540068 LA - English DB - MTMT ER - TY - CHAP AU - Lefkovits, Szidónia AU - Lupusor, Nicolae AU - Lefkovits, László ED - Moldovan, Liviu ED - Gligor, Adrian TI - Efficient Deep Learning-Based Fire and Smoke Detection with YOLO Architecture T2 - The 18th International Conference Interdisciplinarity in Engineering PB - Springer Nature Switzerland CY - Cham SN - 9783031816857 T3 - Lecture notes in networks and systems, ISSN 2367-3370 ; 1249. PY - 2025 SP - 132 EP - 147 PG - 16 UR - https://m2.mtmt.hu/api/publication/36960996 ID - 36960996 LA - English DB - MTMT ER - TY - JOUR AU - Lefkovits, Szidónia AU - Lefkovits, László AU - Szilágyi, László TI - HGG and LGG Brain Tumor Segmentation in Multi-Modal MRI Using Pretrained Convolutional Neural Networks of Amazon Sagemaker JF - APPLIED SCIENCES-BASEL J2 - APPL SCI-BASEL VL - 12 PY - 2022 IS - 7 SN - 2076-3417 DO - 10.3390/app12073620 UR - https://m2.mtmt.hu/api/publication/32799979 ID - 32799979 N1 - Export Date: 25 May 2022 Correspondence Address: Lefkovits, S.; Department of Electrical Engineering and Information Technology, Gheorghe Marinescu Street 38, Romania; email: szidonia.lefkovits@umfst.ro LA - English DB - MTMT ER - TY - JOUR AU - Lefkovits, Szidónia AU - Emerich, Simina AU - Lefkovits, László TI - Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants JF - MATHEMATICS J2 - MATHEMATICS-BASEL VL - 10 PY - 2022 IS - 15 SN - 2227-7390 DO - 10.3390/math10152620 UR - https://m2.mtmt.hu/api/publication/33048984 ID - 33048984 AB - The identification of vascular network structures is one of the key fields of research in medical imaging. The segmentation of dorsal hand vein patterns form NIR images is not only the basis for reliable biometric identification, but would also provide a significant tool in assisting medical intervention. Precise vein extraction would help medical workers to exactly determine the needle entry point to efficiently gain intravenous access for different clinical purposes, such as intravenous therapy, parenteral nutrition, blood analysis and so on. It would also eliminate repeated attempts at needle pricks and even facilitate an automatic injection procedure in the near future. In this paper, we present a combination of unsupervised and supervised dorsal hand vein segmentation from near-infrared images in the NCUT database. This method is convenient due to the lack of expert annotations of publicly available vein image databases. The novelty of our work is the automatic extraction of the veins in two phases. First, a geometrical approach identifies tubular structures corresponding to veins in the image. This step is considered gross segmentation and provides labels (Label I) for the second CNN-based segmentation phase. We visually observe that different CNNs obtain better segmentation on the test set. This is the reason for building an ensemble segmentor based on majority voting by nine different network architectures (U-Net, U-Net++ and U-Net3+, all trained with BCE, Dice and focal losses). The segmentation result of the ensemble is considered the second label (Label II). In our opinion, the new Label II is a better annotation of the NCUT database than the Label I obtained in the first step. The efficiency of computer vision algorithms based on artificial intelligence algorithms is determined by the quality and quantity of the labeled data used. Furthermore, we prove this statement by training ResNet–UNet in the same manner with the two different label sets. In our experiments, the Dice scores, sensitivity and specificity with ResNet–UNet trained on Label II are superior to the same classifier trained on Label I. The measured Dice scores of ResNet–UNet on the test set increase from 90.65% to 95.11%. It is worth mentioning that this article is one of very few in the domain of dorsal hand vein segmentation; moreover, it presents a general pipeline that may be applied for different medical image segmentation purposes. LA - English DB - MTMT ER - TY - JOUR AU - Lefkovits, Szidónia AU - Lefkovits, László TI - U-Net architecture variants for brain tumor segmentation of histogram corrected images JF - ACTA UNIVERSITATIS SAPIENTIAE INFORMATICA J2 - ACTA UNIV SAP INFORM VL - 14 PY - 2022 IS - 1 SP - 49 EP - 74 PG - 26 SN - 1844-6086 DO - 10.2478/ausi-2022-0004 UR - https://m2.mtmt.hu/api/publication/33357597 ID - 33357597 AB - In this paper we propose to create an end-to-end brain tumor segmentation system that applies three variants of the well-known U-Net convolutional neural networks. In our results we obtain and analyse the detection performances of U-Net, VGG16-UNet and ResNet-UNet on the BraTS2020 training dataset. Further, we inspect the behavior of the ensemble model obtained as the weighted response of the three CNN models. We introduce essential preprocessing and post-processing steps so as to improve the detection performances. The original images were corrected and the different intensity ranges were transformed into the 8-bit grayscale domain to uniformize the tissue intensities, while preserving the original histogram shapes. For post-processing we apply region connectedness onto the whole tumor and conversion of background pixels into necrosis inside the whole tumor. As a result, we present the Dice scores of our system obtained for WT (whole tumor), TC (tumor core) and ET (enhanced tumor) on the BraTS2020 training dataset. LA - English DB - MTMT ER - TY - JOUR AU - Szilágyi, László AU - Lefkovits, László AU - Iclanzan, Dávid András TI - A review on suppressed fuzzy c-means clustering models JF - ACTA UNIVERSITATIS SAPIENTIAE INFORMATICA J2 - ACTA UNIV SAP INFORM VL - 12 PY - 2020 IS - 2 SP - 302 EP - 324 PG - 23 SN - 1844-6086 DO - 10.2478/ausi-2020-0018 UR - https://m2.mtmt.hu/api/publication/31936094 ID - 31936094 LA - English DB - MTMT ER - TY - CHAP AU - Lefkovits, Szidónia AU - Szilágyi, László AU - Lefkovits, László ED - Crimi, Alessandro ED - Bakas, Spyridon ED - Kuijf, Hugo ED - Keyvan, Farahani ED - Reyes, Mauricio ED - van Walsum, Theo TI - Brain Tumor Segmentation and Survival Prediction Using a Cascade of Random Forests T2 - Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries : 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018 PB - Springer Cham CY - Cham SN - 9783030117252 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 11384. PY - 2019 SP - 334 EP - 345 PG - 12 DO - 10.1007/978-3-030-11726-9_30 UR - https://m2.mtmt.hu/api/publication/31121310 ID - 31121310 N1 - Department of Computer Science, University of Medicine, Pharmacy, Sciences and Technology, Tîrgu Mureş, Romania Department of Electrical Engineering, Sapientia Hungarian University of Transylvania, Tîrgu Mureş, Romania Export Date: 13 March 2025; Cited By: 17; Correspondence Address: S. Lefkovits; Department of Computer Science, University of Medicine, Pharmacy, Sciences and Technology, Tîrgu Mureş, Romania; email: szidonia.lefkovits@science.upm.ro; Conference name: 4th International MICCAI Brainlesion Workshop, BrainLes 2018 held in conjunction with the Medical Image Computing for Computer Assisted Intervention Conference, MICCAI 2018; Conference date: 16 September 2018 through 20 September 2018; Conference code: 223869 LA - English DB - MTMT ER - TY - CHAP AU - Lefkovits, Szidónia AU - Lefkovits, László AU - Szilágyi, László ED - Viviani, M. ED - Pasi, G. ED - Narukawa, Y. ED - Torra, V. TI - Applications of Different CNN Architectures for Palm Vein Identification T2 - Modeling Decisions for Artificial Intelligence: 16th International Conference, MDAI 2019 PB - Springer Cham CY - Cham SN - 9783030267735 T3 - Communications in Computer and Information Science, ISSN 1865-0929 ; 965. PY - 2019 SP - 295 EP - 306 PG - 12 DO - 10.1007/978-3-030-26773-5_26 UR - https://m2.mtmt.hu/api/publication/31121336 ID - 31121336 N1 - MDAI 2019, Milano LA - English DB - MTMT ER - TY - CHAP AU - Lefkovits, Szidónia AU - Lefkovits, László TI - Combining Subspace Methods and CNN Segmentation for Iris Identification T2 - 2019 IEEE 17TH WORLD SYMPOSIUM ON APPLIED MACHINE INTELLIGENCE AND INFORMATICS (SAMI 2019) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Herlany SN - 9781728102504 PY - 2019 SP - 305 EP - 310 PG - 6 DO - 10.1109/SAMI.2019.8782780 UR - https://m2.mtmt.hu/api/publication/33647966 ID - 33647966 LA - English DB - MTMT ER - TY - JOUR AU - Lefkovits, Szidónia AU - Lefkovits, László AU - Szilágyi, László TI - CNN Approaches for Dorsal Hand Vein Based Identification JF - JOURNAL OF WINTER SCHOOL OF COMPUTER GRAPHICS J2 - J WSCG VL - 2019 PY - 2019 SP - 51 EP - 60 PG - 10 SN - 1213-6972 DO - 10.24132/CSRN.2019.2902.2.7 UR - https://m2.mtmt.hu/api/publication/33647976 ID - 33647976 LA - English DB - MTMT ER -