Pulmonary function tests (PFTs) play an important role in screening and following-up pulmonary involvement in systemic sclerosis (SSc). However, some patients are not able to perform PFTs due to... Show morePulmonary function tests (PFTs) play an important role in screening and following-up pulmonary involvement in systemic sclerosis (SSc). However, some patients are not able to perform PFTs due to contraindications. In addition, it is unclear how lung function is affected by changes in lung structure in SSc. Therefore, this study aims to explore the potential of automatically estimating PFT results from chest CT scans of SSc patients and how different regions influence the estimation of PFTs. Deep regression networks were developed with transfer learning to estimate PFTs from 316 SSc patients. Segmented lungs and vessels were used to mask the CT images to train the network with different inputs: from entire CT scan, lungs-only to vessels-only. The network trained on entire CT scans with transfer learning achieved an ICC of 0.71, 0.76, 0.80, and 0.81 for the estimation of DLCO, FEV1, FVC and TLC, respectively. The performance of the networks gradually decreased when trained on data from lungs-only and vessels-only. Regression attention maps showed that regions close to large vessels were highlighted more than other regions, and occasionally regions outside the lungs were highlighted. These experiments show that apart from the lungs and large vessels, other regions contribute to PFT estimation. In addition, adding manually designed biomarkers increased the correlation (R) from 0.75, 0.74, 0.82, and 0.83 to 0.81, 0.83, 0.88, and 0.90, respectively. This suggests that that manually designed imaging biomarkers can still contribute to explaining the relation between lung function and structure. Show less
The ability to learn a foreign language, language aptitude, is known to differ between individuals. To better understand second-language learning, language aptitude tests, tapping into the... Show moreThe ability to learn a foreign language, language aptitude, is known to differ between individuals. To better understand second-language learning, language aptitude tests, tapping into the different components of second-language learning aptitude, are widely used. For valid conclusions on comparisons of learners with different language backgrounds, it is crucial that such tests be language neutral. Several studies have investigated the language neutrality of the freely available LLAMA tests (Granena, 2013; Rogers et al., 2016, 2017). So far, comparing a number of L1 backgrounds, including those using different writing systems such as Arabic and Mandarin, no significant differences between participants have been found. However, until now, neither participants with agglutinative language backgrounds nor with first-language backgrounds that use multiple writing systems have been included. Therefore, this study selected participants from three different first-language backgrounds: Dutch (non-agglutinative, phonogram/Latin alphabet), Hungarian (agglutinative, phonogram/Latin alphabet), and Japanese (agglutinative, phonogram/syllabic alphabet and logogram/Japanese kanji). The participants performed three subsets of the LLAMA test. Significant differences between the groups were found on two of these tests: The ability to implicitly recognize sounds (LLAMA_D subtest) and inductive grammar learning ability (LLAMA_F), but no differences were found on vocabulary learning ability (LLAMA_B). Additionally, for LLAMA_B, the number of languages learnt was a significant covariate, confirming earlier findings that some subtests seem to be linked to language learning experience. We discuss the implications of our findings on the validity of the LLAMA_D and LLAMA_F subtests. Show less
