Browsing by Subject "Annotation"

Sort by: Order: Results:

Now showing items 1-4 of 4
  • Peura, Heikki (Helsingin yliopisto, 2021)
    Aivoverenvuotojen diagnosointi pään tietokonetomografia (TT) –kuvista on kokeneellekin radiologille ajoittain haastava tehtävä. TT-kuvan tulkintaan vaikuttavat muun muassa aivoverenvuodosta kulunut aika, kuvanlaatu, potilaan liikehdintä kuvauksen aikana, sekä mahdollisesti potilaalle ennen kuvantamista suoritettujen kirurgisten toimenpiteiden yhteydessä kudoksiin jätettyjen röntgensäteitä läpäisemättömien materiaalien (metallit) aiheuttamat häiriöt, eli artefaktat. Kuvantamistutkimusten määrä kasvaa vuosittain samaan aikaan kun radiologien määrä ei pysy kasvuvauhdin asettaman tarpeen mukana. Tekoälyalgoritmeja tarvitaan helpottamaan lisääntyvistä kuvantamismääristä johtuvaa työkuormaa, sekä auttamaan mahdollisten virhediagnoosien tunnistamisessa, sillä diagnosoimatta jäänyt aivoverenvuoto voi pahimmassa tapauksessa johtaa potilaan kuolemaan. Aivoverenvuotoja tunnistavan tekoälyalgoritmin kehittämisessä tarvitaan kuvadataa, johon aivoverenvuodot on piirretty, eli segmentoitu, mahdollisimman tarkasti. Segmentoinnin perimmäinen tarkoitus on pyrkiä merkitsemään jokaiseen kuvaan jokainen pikseli, joka edustaa sitä löydöstä, jota tekoälyalgoritmin halutaan kuvasta oppivan tunnistamaan. Se, että segmentointi on tehty mahdollisimman korkeaa laatua ja tarkkuutta noudattaen on ensiarvoisen tärkeä osa aivoverenvuotoja tunnistavan tekoälyalgoritmin kehitysprosessissa, sillä mikäli segmentointi on tehty huonolla tarkkuudella ja sisältää esimerkiksi pikseleitä, jotka eivät edusta haluttua löydöstä, ei tekoälyalgoritmi opi tunnistamaan haluttua löydöstä riittävän hyvin. Eri aivoverenvuototyypit näyttäytyvät TT-kuvassa usein varsin eri näköisinä, tämän vuoksi kullekin aivoverenvuototyypille tulee valita sille parhaiten sopiva segmentointitekniikka. Segmentoinnissa voi tapauksesta riippuen hyödyntää automaattisia ja puoliautomaattisia työkaluja, jotka parhaimmassa tapauksessa nopeuttavat segmentointiin kuluvaa aikaa kymmenillä minuuteilla yhtä tapausta kohden. Tässä artikkelissa käymme läpi kokonaisvaltaisesti sen, mitä vaaditaan laadukkaaseen TT-kuvadatan käsittelyyn, kun tavoitteena on kehittää aivoverenvuotoja tunnistava tekoälyalgoritmi.
  • Kauttonen, Janne; Hlushchuk, Yevhen; Tikka, Pia (2015)
    One of the challenges of naturalistic neurosciences using movie-viewing experiments is how to interpret observed brain activations in relation to the multiplicity of time-locked stimulus features. As previous studies have shown less inter-subject synchronization across viewers of random video footage than story-driven films, new methods need to be developed for analysis of less story-driven contents. To optimize the linkage between our fMRI data collected during viewing of a deliberately non-narrative silent film 'At Land' by Maya Deren (1944) and its annotated content, we combined the method of elastic-net regularization with the model-driven linear regression and the well-established data-driven independent component analysis (ICA) and inter-subject correlation (ISC) methods. In the linear regression analysis, both IC and region-of-interest (ROI) time-series were fitted with time-series of a total of 36 binary-valued and one real-valued tactile annotation of film features. The elastic-net regularization and cross-validation were applied in the ordinary least-squares linear regression in order to avoid over-fitting due to the multicollinearity of regressors, the results were compared against both the partial least-squares (PLS) regression and the un-regularized full-model regression. Nonparametric permutation testing scheme was applied to evaluate the statistical significance of regression. We found statistically significant correlation between the annotation model and 9 ICs out of 40 ICs. Regression analysis was also repeated for a large set of cubic ROIs covering the grey matter. Both IC- and ROI-based regression analyses revealed activations in parietal and occipital regions, with additional smaller clusters in the frontal lobe. Furthermore, we found elastic-net based regression more sensitive than PLS and un-regularized regression since it detected a larger number of significant ICs and ROIs. Along with the ISC ranking methods, our regression analysis proved a feasible method for ordering the ICs based on their functional relevance to the annotated cinematic features. The novelty of our method is - in comparison to the hypothesis-driven manual pre-selection and observation of some individual regressors biased by choice - in applying data-driven approach to all content features simultaneously. We found especially the combination of regularized regression and ICA useful when analyzing fMRI data obtained using non-narrative movie stimulus with a large set of complex and correlated features. (C) 2015 The Authors. Published by Elsevier Inc.
  • Pyörälä, Eeva; Mäenpää, Saana; Heinonen, Leo; Folger, Daniel; Masalin, Teemu; Hervonen, Heikki (2019)
    BackgroundStudents use mobile devices extensively in their everyday life, and the new technology is adopted in study usage. Since 2013, the University of Helsinki has given new medical and dental students iPads for study use. Simultaneously, an action research project on mobile learning started focusing on these students' mobile device usage throughout their study years. Note taking is crucial in academic studies, but the research evidence in this area is scarce. The aims of this study were to explore medical and dental students' self-reported study uses of mobile devices and their best practices of mobile note taking.MethodAn action research project began in 2013 and followed the first student cohort (124 medical and 52 dental students) with iPads from the first until the fifth study year. We explored students' descriptions of their most important study uses of mobile devices and their perceptions of note taking with iPads. The longitudinal data were collected with online questionnaires over the years. The answers to open-ended questions were examined using qualitative content analysis. The findings were triangulated with another question on note taking and focus-group interviews.ResultsThe response rates varied between 73 and 95%. Note taking was the most frequently and consistently reported study use of iPads during the study years. While taking notes, students processed the new information in an accomplished way and personalised the digital learning materials by making comments, underlining, marking images and drawing. The visual nature of their learning materials stimulated learning. Students organised the notes for retention in their personalised digital library. In the clinical studies, medical students faced the teachers' resistance and ambivalence to mobile device usage. This hindered the full-scale benefit of the novel technology in the clinical context.ConclusionsEfficient digital note taking practices were pivotal to students in becoming mobile learners. Having all their notes and learning materials organised in their personal digital libraries enabled the students to retrieve them anywhere, anytime, both when studying for examinations and treating patients in the clinical practice. The challenges the medical students met using mobile devices in the clinical setting require further studies.
  • Pyörälä, Eeva; Mäenpää, Saana; Heinonen, Leo; Folger, Daniel; Masalin, Teemu; Hervonen, Heikki (BioMed Central, 2019)
    Abstract Background Students use mobile devices extensively in their everyday life, and the new technology is adopted in study usage. Since 2013, the University of Helsinki has given new medical and dental students iPads for study use. Simultaneously, an action research project on mobile learning started focusing on these students’ mobile device usage throughout their study years. Note taking is crucial in academic studies, but the research evidence in this area is scarce. The aims of this study were to explore medical and dental students’ self-reported study uses of mobile devices and their best practices of mobile note taking. Method An action research project began in 2013 and followed the first student cohort (124 medical and 52 dental students) with iPads from the first until the fifth study year. We explored students’ descriptions of their most important study uses of mobile devices and their perceptions of note taking with iPads. The longitudinal data were collected with online questionnaires over the years. The answers to open-ended questions were examined using qualitative content analysis. The findings were triangulated with another question on note taking and focus-group interviews. Results The response rates varied between 73 and 95%. Note taking was the most frequently and consistently reported study use of iPads during the study years. While taking notes, students processed the new information in an accomplished way and personalised the digital learning materials by making comments, underlining, marking images and drawing. The visual nature of their learning materials stimulated learning. Students organised the notes for retention in their personalised digital library. In the clinical studies, medical students faced the teachers’ resistance and ambivalence to mobile device usage. This hindered the full-scale benefit of the novel technology in the clinical context. Conclusions Efficient digital note taking practices were pivotal to students in becoming mobile learners. Having all their notes and learning materials organised in their personal digital libraries enabled the students to retrieve them anywhere, anytime, both when studying for examinations and treating patients in the clinical practice. The challenges the medical students met using mobile devices in the clinical setting require further studies.