anfis Dotaz Zobrazit nápovědu
Background: Breast cancer is one of the leading cancers in woman worldwide both in developed and developing nations as per the records from World Health Organization. Many studies have shown that mammography is very effective tool for the breast cancer diagnosis. Mass segmentation plays an important step for the cancer detection. Objective: The objective of the proposed method is to segment the mass and to classify the mass with high accuracy. Methods: The segmentation includes two main steps. First, a rough initial segmentation through iterative thresholding, and second, an active contour based segmentation. The relevant statistical features are extracted and the classification is done by using Adaptive Neuro Fuzzy Inference System (ANFIS). Results: The proposed mass detection scheme achieves sensitivity of 87.5% and specificity of 100% for a set of twenty two images. The overall segmentation accuracy obtained is 91.30%. Conclusions: This work appears to be of high clinical significance since the mass detection plays an important role in diagnosis of breast cancer.
Objective: The objective of this work is to develop efficient classification systems using intelligent computing techniques for classification of normal and abnormal EEG signals. Methods: In this work, EEG recordings were carried out on volunteers (N=170). The features for classification of clinical EEG signals were extracted using wavelet transform and the feature selection was carried out using Principal Component Analysis. Intelligent techniques like Back Propagation Network (BPN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Particle Swarm Optimization Neural network (PSONN) and Radial Basis function Neural network (RBFNN) were trained for diagnosing seizures. Further, the performance of the developed classifiers was compared. Results: Results demonstrate that RBFNN classifies normal and abnormal EEG signals better than the other methods. It appears that the RBFNN is able to detect Generalized Tonic-Clonic Seizure (GTCS) more efficiently than the Complex Partial Seizures (CPS). Positive predictive value was better in PSONN and ANFIS than BPN method. Conclusions: It appears that the combination of Wavelet transform method and PCA derived features along with RBFNN classifier is efficient for automated EEG signal classification.
We present many solutions to predict 1-year the post-operative survival expectancy in thoracic lung cancer surgery base on artificial intelligence. We implement multi-layer architecture of SUB- Adaptive neuro fuzzy inference system (MLA-ANFIS) approach with various combinations of multiple input features, neural networks, regression and ELM (extreme learning machine) based on the used thoracic surgery data set with sixteen input features. Our results contribute to the ELM (wave kernel) based on 16 features is more accurate than different proposed methods for predict the post-operative survival expectancy in thoracic lung cancer surgery purpose.
Cíl práce: Posoudit úspěšnost léčby chronické hepatitídy B interferonem (IFN) u pacientů infikovaných „wild" typem viru i HBeAg - mínus mutantou. Materiál a metody. Retrospektivně byl posouzen efekt antivirové terapie u 56 pacientů s chronickou virovou hepatitídou HBsAg, HBeAg, HBV DNA pozitivní. Všichni byli léčeni IFN v dávce b miliónů jednotek (MU) 3-krát týdně šest měsíců (soubor A). Sedm z těch, co neodpověděli vymizením HBV DNA a sérokonverzí HBeAg na anti-HBe, podstoupilo druhou kúru IFN stejnými dávkami a po stejnou dobu (soubor B). Stejným způsobem bylo léčeno i dalších sedm nemocných s chronickou hepatitídou B vyvolanou HBeAg-mínus mutantou (soubor C). Výsledky: V souboru A mělo negativní HBV DNA v séru v době ukončení léčby 34 % nemocných, za 6 měsíců po léčbě 41 % a za 12 měsíců 46 %. Ve stejných obdobích mělo negativní HBeAg 36 %, 39 % a 46 %, pozitivní anti-HBe 36 %, 38 % a 46 %, negativní HBsAg 9 %, 11 % a 14 % a normální ALT 23 %, 39 % a 44 % léčených. Lze tedy pozorovat trend ke zlepšování výsledků léčby s prodlužujícím se intervalem po jejím skončení, i když rozdíly nebyly statisticky významné. V souboru A byl zjištěn lepší efekt léčby u pacientů s nižší vstupní virémií a vyšší aktivitou ALT. Závislost na vstupní histologické aktivitě prokázána nebyla. Ze sedmi nemocných v souboru B měli ve stejných obdobích negativní HBV DNA 4, 5 a 4 pacienti, negativní HBeAg 2, 4 a 3, pozitivní anti-HBe 1, 3 a 3, normální ALT 3, 4 a 3 pacienti. K negativizaci HBsAg nedošlo. V souboru C vymizela HBV DNA během léčby u všech pacientů, do 6 měsíců po léčbě však dva relabovali a během dalšího půl roku ještě jeden. U jednoho nemocného byla zaznamenána HBsAg negativita po 12 měsících od léčby. K normalizaci AIT došlo během léčby u čtyřech nemocných a během dalších 6 měsíců ještě u jednoho. Soubory B a C byly příliš malé na exaktní statistické zpracování. Závěr: Léčba alfa-IFN je účinná téměř u poloviny nemocných s chronickou hepatitídou B infikovaných „wild" typem viru. Druhá kúra IFN může být účinná u významné čású původně nereagujících nemocných. Při infekci HBeAg-mínus mutantním virem dochází po výborné iniciální odpovědi k častým relapsům.
Aim of the study: To evaluate the effect of chronic B hepaúús therapy with alfa interferon (IFN) at pafients infected by wild type virus and by HBeAg-minus mutant. Materials and methods: The anfiviral therapy effect was analysed at 56 patients with chronic viral hepafifis HBsAg, HBeAg, HBV DNA positive retrospectively. All of them were treated with IFN at dose 5 millions of units (MU) 3 fimes a week for six month (Group A). Seven patients, who did not react by disappearance of HBV DNA and by seroconversion HBeAg to anti-HBe, underwent the second course of INF at the same doses and interval (Group B). The next seven patients with chronic B hepatitis caused by HBeAg-minus mutant were treated by the same manner(GroupC). Results: There was 34 % of patients HBV DNA negaúve from group A at the end of therapy, 41 % of pafienls was negative after 6 months from the end of therapy and 46 % after 12 months. HBeAg was negaúve at 36 %, 39 % and 46 % of pafienLs, anfi-HBe was positive at 36 %, 38 % and 46 % of pafients, HBsAg was negafive at 9 %, 11 % and 14 % of pafienLs and ALT reached the normal range at 23 %, 39 % and 44 % of patients in the same time intervals. It is possible to see a trend for improvement of therapy results with extending interval from the end of therapy, although differences are not significant. Better effect of therapy showed patients with lower baseline viraemia and higher ALT activity from group A. No dependence was proven on baseline histological activity. In the same time intervals 4, 5 and 4 patients were HBV DNA negative from 7 B group patients, 2, 4 and 3 pafients were HBeAg negative, 1,3 and 3 patients were anti HBe positive, 3, 4 and 3 patients had normal AIT. HBsAg negativity was not remarked at any patient. HBV DNA disappeared during therapy in all patients from group C, 2 patients relapsed until 6 months and one more pafient relapsed during the next half of the year. HBsAg negafivity was remarked at one patient 12 months after therapy. ALT reached the normal range at 4 patients during therapy and at one more patient during next 6 months. Group B and C were too small to be exactly evaluated. Conclusion: IFN-alfa therapy is effective at about one half of patients suffering from chronic B hepatitis infected by wild type virus. The second IFN course can be effective at significant portion of previously non-responding patients. Good initial response and freguent relapses are characteristic for HBeAg-minus mutant virus infection.
- MeSH
- antigeny virové imunologie krev MeSH
- chronická hepatitida B farmakoterapie krev virologie MeSH
- DNA virů krev MeSH
- dospělí MeSH
- interferon alfa terapeutické užití MeSH
- jaterní testy statistika a číselné údaje MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- senioři MeSH
- virus hepatitidy B genetika imunologie MeSH
- Check Tag
- dospělí MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mužské pohlaví MeSH
- senioři MeSH
- ženské pohlaví MeSH
- Publikační typ
- srovnávací studie MeSH
