Iskanje po repozitoriju

A+ | A- | | SLO | ENG

Povzetek: In the setting of primary hyperparathyroidism (PHPT), [18F]fluorocholine PET/CT (FCH-PET) has excellent diagnostic performance, with experienced practitioners achieving 97.7% accuracy in localising hyperfunctioning parathyroid tissue (HPTT). Due to the relative triviality of the task for human readers, we explored the performance of deep learning (DL) methods for HPTT detection and localisation on FCH-PET images in the setting of PHPT. Patients and methods. We used a dataset of 93 subjects with PHPT imaged using FCH-PET, of which 74 subjects had visible HPTT while 19 controls had no visible HPTT on FCH-PET. A conventional Resnet10 as well as a novel mPETResnet10 DL model were trained and tested to detect (present, not present) and localise (upper left, lower left, upper right or lower right) HPTT. Our mPETResnet10 architecture also contained a region-of-interest masking algorithm that we evaluated qualitatively in order to try to explain the model’s decision process. Results. The models detected the presence of HPTT with an accuracy of 83% and determined the quadrant of HPTT with an accuracy of 74%. The DL methods performed statistically worse (p < 0.001) in both tasks compared to human readers, who localise HPTT with the accuracy of 97.7%. The produced region-of-interest mask, while not showing a consistent added value in the qualitative evaluation of model’s decision process, had correctly identified the foreground PET signal. Conclusions. Our experiment is the first reported use of DL analysis of FCH-PET in PHPT. We have shown that it is possible to utilize DL methods with FCH-PET to detect and localize HPTT. Given our small dataset of 93 subjects, results are nevertheless promising for further research
Ključne besede: primary hyperparathyroidism, deep learning, nuclear medicine
Objavljeno v DiRROS: 25.07.2024; Ogledov: 447; Prenosov: 163
Celotno besedilo (810,33 KB)
Gradivo ima več datotek! Več...

Ključne besede: population-based study, childhood cancer survivors, subsequent neoplasm
Objavljeno v DiRROS: 25.07.2024; Ogledov: 276; Prenosov: 122
Celotno besedilo (651,47 KB)

Povzetek: Background: The aim of the study was to evaluate if artificial neural networks can predict high-grade histopathology results after conisation from risk factors and their combinations in patients undergoing conisation because of pathological changes on uterine cervix. Patients and methods: We analysed 1475 patients who had conisation surgery at the University Clinic for Gynaecology and Obstetrics of University Clinical Centre Maribor from 1993-2005. The database in different datasets was arranged to deal with unbalance data and enhance classification performance. Weka open-source software was used for analysis with artificial neural networks. Last Papanicolaou smear (PAP) and risk factors for development of cervical dysplasia and carcinoma were used as input and high-grade dysplasia Yes/No as output result. 10-fold cross validation was used for defining training and holdout set for analysis. Results: Baseline classification and multiple runs of artificial neural network on various risk factors settings were performed. We achieved 84.19% correct classifications, area under the curve 0.87, kappa 0.64, F-measure 0.884 and Matthews correlation coefficient (MCC) 0.640 in model, where baseline prediction was 69.79%. Conclusions: With artificial neural networks we were able to identify more patients who developed high-grade squamous intraepithelial lesion on final histopathology result of conisation as with baseline prediction. But, characteristics of 1475 patients who had conisation in years 1993-2005 at the University Clinical Centre Maribor did not allow reliable prediction with artificial neural networks for every-day clinical practice.
Ključne besede: artificial neural networks, conisation, uterine cervical cancer, uterine cervical dysplasia, displazija materničnega vratu, rak materničnega vratu, konizacija, umetne nevronske mreže
Objavljeno v DiRROS: 24.07.2024; Ogledov: 309; Prenosov: 192
Celotno besedilo (663,31 KB)
Gradivo ima več datotek! Več...

Povzetek: The CDK4/6 inhibitor, ribociclib in combination with endocrine therapy significantly improved progression-free survival in the first line setting in post-menopausal patients with HR+/HER2- advanced breast cancer (ABC) in a pivotal phase 3, placebo-controlled trial (MONALEESA-2) and demonstrated superior overall survival in premenopausal patients with HR+/HER2- ABC (MONALEESA-7). The multinational, phase 3b, CompLEEment-1 trial, which assessed the safety and efficacy of ribociclib plus letrozole in a broader population of patients who have not received prior endocrine therapy for advanced disease, is the largest phase 3 clinical trial to date to evaluate the safety and efficacy of a CDK4/6 inhibitor. We report a subanalysis of data from patients (N = 339) enrolled in the central and south European countries of the SERCE (Southern Europe, RUC, Central Europe) cluster of CompLEEment-1. Patients and methods: Men and women of any menopausal status with HR+/HER2- ABC received once-daily oral ribociclib 600 mg (3-weeks on/1-week-off), plus letrozole 2.5 mg continuously. Men/premenopausal women also received a GnRH-agonist. The primary outcome was the number of patients with adverse events (AEs) over a timeframe of approximately 36 months. Time-to-progression, overall response rate, and clinical benefit rate were also measured. Results: Safety results in the SERCE subgroup were consistent with those in the pivotal clinical trials of ribociclib in combination with endocrine therapy. Treatment-related AEs leading to dose adjustments/interruption occurred in 63.1% of patients but led to treatment discontinuation in only 10.6%. The most common treatment-related AEs of grade ≥ 3 were neutropenia and transaminase elevations. There were no fatal treatment-related events. Conclusions: These findings from the SERCE subgroup support the safety and manageable tolerability of ribociclib in a broad range of patients with HR+/HER2- ABC more representative of patients in real-world clinical practice.
Ključne besede: CDK4/6 inhibitor, HER2−, HR+, advanced breast cancer, ribociclib
Objavljeno v DiRROS: 24.07.2024; Ogledov: 278; Prenosov: 245
Celotno besedilo (462,13 KB)

Povzetek: One of the new treatment options for unresectable locally advanced pancreatic cancer is electro-chemotherapy (ECT), a local ablative therapy that potentiates the entry of chemotherapeutic drugs into the cells, by the application of an electric field to the tumor. Its feasibility and safety were demonstrated in preclinical and clinical studies; however, there is a lack of preclinical studies assessing the actions of different drugs used in ECT, their mechanisms and interactions with other target drugs that are used in clinical practice. Materials and methods. The aim of the study was to determine the cytotoxicity of two chemotherapeutic drugs usually used in ECT (bleomycin and cisplatin) in the BxPC-3 human pancreatic carcinoma cell line and evaluate the interactions of ECT with the targeted drug sunitinib. First, the cytotoxicity of ECT using both chemotherapeutics was determined. In the next part, the interactions of ECT and sunitinib were evaluated through determination of combined cytotoxicity, sunitinib targets and kinetics of cell death.Results. The results demonstrate that ECT is effective in pancreatic cancer cell line, especially when bleomycin is used, with the onset of cell death in the first hours after the treatment, reaching a plateau at 20 hours after the treat-ment. Furthermore, we provide the rationale for combining ECT with bleomycin and the targeted drug sunitinib to potentiate cytotoxicity. The combined treatment of sunitinib and ECT was synergistic for bleomycin only at the high-est used concentration of bleomycin 0.14 μM, whereas with lower doses of bleomycin, this effect was not observed. The interaction of ECT and treatment with sunitinib was confirmed by course of the cell death, also indicating on synergism
Ključne besede: electrochemotherapy, pancreas, sunitinib, pancreatic cancer
Objavljeno v DiRROS: 24.07.2024; Ogledov: 318; Prenosov: 183
Celotno besedilo (1,01 MB)
Gradivo ima več datotek! Več...