scholarly journals The Effect of Training Sample Size on the Prediction of White Matter Hyperintensity Volume in a Healthy Population Using BIANCA

2022 ◽  
Vol 13 ◽  
Author(s):  
Niklas Wulms ◽  
Lea Redmann ◽  
Christine Herpertz ◽  
Nadine Bonberg ◽  
Klaus Berger ◽  
...  

Introduction: White matter hyperintensities of presumed vascular origin (WMH) are an important magnetic resonance imaging marker of cerebral small vessel disease and are associated with cognitive decline, stroke, and mortality. Their relevance in healthy individuals, however, is less clear. This is partly due to the methodological challenge of accurately measuring rare and small WMH with automated segmentation programs. In this study, we tested whether WMH volumetry with FMRIB software library v6.0 (FSL; https://fsl.fmrib.ox.ac.uk/fsl/fslwiki) Brain Intensity AbNormality Classification Algorithm (BIANCA), a customizable and trainable algorithm that quantifies WMH volume based on individual data training sets, can be optimized for a normal aging population.Methods: We evaluated the effect of varying training sample sizes on the accuracy and the robustness of the predicted white matter hyperintensity volume in a population (n = 201) with a low prevalence of confluent WMH and a substantial proportion of participants without WMH. BIANCA was trained with seven different sample sizes between 10 and 40 with increments of 5. For each sample size, 100 random samples of T1w and FLAIR images were drawn and trained with manually delineated masks. For validation, we defined an internal and external validation set and compared the mean absolute error, resulting from the difference between manually delineated and predicted WMH volumes for each set. For spatial overlap, we calculated the Dice similarity index (SI) for the external validation cohort.Results: The study population had a median WMH volume of 0.34 ml (IQR of 1.6 ml) and included n = 28 (18%) participants without any WMH. The mean absolute error of the difference between BIANCA prediction and manually delineated masks was minimized and became more robust with an increasing number of training participants. The lowest mean absolute error of 0.05 ml (SD of 0.24 ml) was identified in the external validation set with a training sample size of 35. Compared to the volumetric overlap, the spatial overlap was poor with an average Dice similarity index of 0.14 (SD 0.16) in the external cohort, driven by subjects with very low lesion volumes.Discussion: We found that the performance of BIANCA, particularly the robustness of predictions, could be optimized for use in populations with a low WMH load by enlargement of the training sample size. Further work is needed to evaluate and potentially improve the prediction accuracy for low lesion volumes. These findings are important for current and future population-based studies with the majority of participants being normal aging people.

2021 ◽  
Vol 66 (18) ◽  
pp. 185012
Author(s):  
Yingtao Fang ◽  
Jiazhou Wang ◽  
Xiaomin Ou ◽  
Hongmei Ying ◽  
Chaosu Hu ◽  
...  

PLoS ONE ◽  
2013 ◽  
Vol 8 (7) ◽  
pp. e68579 ◽  
Author(s):  
Li Shao ◽  
Xiaohui Fan ◽  
Ningtao Cheng ◽  
Leihong Wu ◽  
Yiyu Cheng

2020 ◽  
Author(s):  
Takeshi Teshigawara ◽  
Akira Meguro ◽  
Nobuhisa Mizuki

Abstract Background: We assessed the accuracy and tendency of the VERION image-guided system (Alcon) and the intra-ocular lens (IOL) Master 700 (Zeiss), by comparing mean refractive shift (MRS) of predicted post-operative refraction (PPR), mean absolute error (MAE) of PPR, recommended IOL power (RIP) and K-value before and after optimizing the IOL-constant in VERION, to show the importance of optimization.Methods: This retrospective study involved 72 eyes. K-value was measured with both biometers. Axial length (AL) and anterior chamber depth (ACD) measured by the IOL Master were applied to the VERION because it cannot measure these variables. The User group for Laser Interference Biometry (ULIB) IOL-constant for the IOL Master was applied to the VERION before optimizing the IOL constant, since no such official measure was established for it. MRS of PPR, MAE of PPR, RIP and K-value as measured by both biometers were compared before and after optimizing the IOL-constant in the VERION. Finally, correlations between the MRS, MAE, RIP, and K-value were analyzed in the VERION. The Wilcoxon signed-rank test was used for analysis.Results: Compared to the IOL Master, K-value was significantly higher in the VERION. Prior to optimization, MRS of PPR showed a significant myopic shift in the VERION, and MAE of PPR was significantly higher. Additionally, RIP in the VERION was significantly lower. After optimization, there were no significant differences in the MRS of PPR and RIP between the VERION and IOL Master. MAE of PPR in the IOL Master was significantly higher than in the VERION. No significant correlations were found between MRS and MAE of PPR and RIP with K-value in the VERION. Conclusions: Before optimization, the VERION was less reliable in MRS, MAE and RIP than the IOL Master. However, after optimization, the difference in MRS and RIP between the two devices became insignificant. This study indicates that optimization of IOL-constant in the VERION is vital. After optimization, the VERION is more accurate in PPR than the IOL Master.


2019 ◽  
Vol 9 (7) ◽  
pp. 1459 ◽  
Author(s):  
Huihui Mao ◽  
Jihua Meng ◽  
Fujiang Ji ◽  
Qiankun Zhang ◽  
Huiting Fang

Leaf area index (LAI) is a crucial crop biophysical parameter that has been widely used in a variety of fields. Five state-of-the-art machine learning regression algorithms (MLRAs), namely, artificial neural network (ANN), support vector regression (SVR), Gaussian process regression (GPR), random forest (RF) and gradient boosting regression tree (GBRT), have been used in the retrieval of cotton LAI with Sentinel-2 spectral bands. The performances of the five machine learning models are compared for better applications of MLRAs in remote sensing, since challenging problems remain in the selection of MLRAs for crop LAI retrieval, as well as the decision as to the optimal number for the training sample size and spectral bands to different MLRAs. A comprehensive evaluation was employed with respect to model accuracy, computational efficiency, sensitivity to training sample size and sensitivity to spectral bands. We conducted the comparison of five MLRAs in an agricultural area of Northwest China over three cotton seasons with the corresponding field campaigns for modeling and validation. Results show that the GBRT model outperforms the other models with respect to model accuracy in average ( R 2 ¯ = 0.854, R M S E ¯ = 0.674 and M A E ¯ = 0.456). SVR achieves the best performance in computational efficiency, which means it is fast to train, and to validate that it has great potentials to deliver near-real-time operational products for crop management. As for sensitivity to training sample size, GBRT behaves as the most robust model, and provides the best model accuracy on the average among the variations of training sample size, compared with other models ( R 2 ¯ = 0.884, R M S E ¯ = 0.615 and M A E ¯ = 0.452). Spectral bands sensitivity analysis with dCor (distance correlation), combined with the backward elimination approach, indicates that SVR, GPR and RF provide relatively robust performance to the spectral bands, while ANN outperforms the other models in terms of model accuracy on the average among the reduction of spectral bands ( R 2 ¯ = 0.881, R M S E ¯ = 0.625 and M A E ¯ = 0.480). A comprehensive evaluation indicates that GBRT is an appealing alternative for cotton LAI retrieval, except for its computational efficiency. Despite the different performance of the ML models, all models exhibited considerable potential for cotton LAI retrieval, which could offer accurate crop parameters information timely and accurately for crop fields management and agricultural production decisions.


2020 ◽  
Vol 12 (7) ◽  
pp. 1097
Author(s):  
Junghee Lee ◽  
Daehyeon Han ◽  
Minso Shin ◽  
Jungho Im ◽  
Junghye Lee ◽  
...  

This study compares some different types of spectral domain transformations for convolutional neural network (CNN)-based land cover classification. A novel approach was proposed, which transforms one-dimensional (1-D) spectral vectors into two-dimensional (2-D) features: Polygon graph images (CNN-Polygon) and 2-D matrices (CNN-Matrix). The motivations of this study are that (1) the shape of the converted 2-D images is more intuitive for human eyes to interpret when compared to 1-D spectral input; and (2) CNNs are highly specialized and may be able to similarly utilize this information for land cover classification. Four seasonal Landsat 8 images over three study areas—Lake Tapps, Washington, Concord, New Hampshire, USA, and Gwangju, Korea—were used to evaluate the proposed approach for nine land cover classes compared to several other methods: Random forest (RF), support vector machine (SVM), 1-D CNN, and patch-based CNN. Oversampling and undersampling approaches were conducted to examine the effect of the sample size on the model performance. The CNN-Polygon had better performance than the other methods, with overall accuracies of about 93%–95 % for both Concord and Lake Tapps and 80%–84% for Gwangju. The CNN-Polygon particularly performed well when the training sample size was small, less than 200 per class, while the CNN-Matrix resulted in similar or higher performance as sample sizes became larger. The contributing input variables to the models were carefully analyzed through sensitivity analysis based on occlusion maps and accuracy decreases. Our result showed that a more visually intuitive representation of input features for CNN-based classification models yielded higher performance, especially when the training sample size was small. This implies that the proposed graph-based CNNs would be useful for land cover classification where reference data are limited.


Sign in / Sign up

Export Citation Format

Share Document