Diabetes risk assessment with imaging: a radiomics study of abdominal CT

Lu, Chun-Qiang; Wang, Yuancheng; Meng, Xiang-Pan; Zhao, Hai-Tong; Zeng, Chu Hui; Xu, Wei; Gao, Yating; Ju, Shenghong

doi:10.1007/s00330-018-5865-5

Cited by 21 publications

(27 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In models A and B, it is not consuming to finish the prediction and the AUCs remain satisfactory. Furthermore, these nomograms [13,15,16] did not have sufficient calibration to provide evidence on predicted probability in accordance with actual observed probability. In our model, all risk models were internally validated using the bootstrap sampling method and externally validated in the validation set.…”

Section: Plos Onementioning

confidence: 92%

“…In China, there are many T2DM risk prediction scores or models generated [7][8][9][10][11][12][13][14][15][16], Common risk factors included age, sex, ethnicity, waist circumference, BMI and hypertension. Although these unmodifiable risk factors played roles in T2DM, changes in modifiable factors…”

Section: Plos Onementioning

confidence: 99%

“…In our study, the China Health and Nutritional survey was conducted in 10 provinces including the municipalities of Beijing and Shanghai from 1989 to 2015. Five used nomograms [13][14][15][16]25]. And five used risk score [8][9][10][11][12].…”

Section: Plos Onementioning

confidence: 99%

“…Compared to risk score, a nomogram is more user friendly and accurate based on continuous variables and simple algorithm diagrams. One nomogram used data from an abdominal CT [15], however, the costs of a CT make it unsuitable for screening and extensive use. K. Wang et al established their nomogram using semi-lab indicators [16], however, there is a lack of medical examinations routinely performed in China.…”

Section: Plos Onementioning

confidence: 99%

“…Risk scores derived from Caucasian populations may not be suitable for Chinese populations as there is significant geographical and biological variation in China. There have been many types of T2DM risk prediction scores and models generated in China [7][8][9][10][11][12][13][14][15][16], but they all face several limitations. Most do not account for lifestyle variations, such as physical activity, dietary behavior or sleep duration.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Development and validation of a prediction model estimating the 10-year risk for type 2 diabetes in China

et al. 2020

View full text Add to dashboard Cite

To derive and validate a concise prediction model estimating the 10-year risk for type 2 diabetes (T2DM) in China. Methods A total of 11494 subjects from the China Health and Nutrition Survey recorded from 2004 to 2015 were analyzed and only 6023 participants were enrolled in this study. Four logistic models were analyzed using the derivation cohort. Methods of calibration and discrimination were used for the validation cohort. Results In the derivation cohort, 257 patients were identified from a total of 4498 cases. In the validation cohort, 92 patients were identified from a total of 1525 cases. Four models performed nicely for both calibration and discrimination. The AUC in the derivation cohort for models A, B, C and D were 0.788 (0.761-0.816), 0.807 (0.780-0.834), 0.905 (0.879-0.932) and 0.882 (0.853-0.912), respectively. The Youden index for models A, B, C and D were 1.46, 1.48, 1.67 and 1.65, respectively. Model C showed the highest sensitivity and model D showed the highest specificity. Conclusion Models A and B were non-invasive and can be used to identify high-risk patients for broad screening. Models C and D may be used to provide more accurate assessments of diabetes risk. Furthermore, model C showed the best performance for predicting T2DM risk and identifying individuals who are in need of interventions, current approach improvement and additional follow-up.

show abstract

Section: Plos Onementioning

confidence: 92%

Section: Plos Onementioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Development and validation of a prediction model estimating the 10-year risk for type 2 diabetes in China

et al. 2020

View full text Add to dashboard Cite

show abstract

Two‐stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra‐reader and inter‐reader reliability at full and reduced radiation dose on an external dataset

et al. 2021

View full text Add to dashboard Cite

To develop a two-stage three-dimensional (3D) convolutional neural networks (CNNs) for fully automated volumetric segmentation of pancreas on computed tomography (CT) and to further evaluate its performance in the context of intra-reader and inter-reader reliability at full dose and reduced radiation dose CTs on a public dataset. Methods: A dataset of 1994 abdomen CT scans (portal venous phase, slice thickness ≤ 3.75-mm, multiple CT vendors) was curated by two radiologists (R1 and R2) to exclude cases with pancreatic pathology, suboptimal image quality, and image artifacts (n = 77). Remaining 1917 CTs were equally allocated between R1 and R2 for volumetric pancreas segmentation [ground truth (GT)]. This internal dataset was randomly divided into training (n = 1380), validation (n = 248), and test (n = 289) sets for the development of a two-stage 3D CNN model based on a modified U-net architecture for automated volumetric pancreas segmentation. Model's performance for pancreas segmentation and the differences in model-predicted pancreatic volumes vs GT volumes were compared on the test set. Subsequently, an external dataset from The Cancer Imaging Archive (TCIA) that had CT scans acquired at standard radiation dose and same scans reconstructed at a simulated 25% radiation dose was curated (n = 41). Volumetric pancreas segmentation was done on this TCIA dataset by R1 and R2 independently on the full dose and then at the reduced radiation dose CT images. Intra-reader and inter-reader reliability, model's segmentation performance, and reliability between model-predicted pancreatic volumes at full vs reduced dose were measured. Finally, model's performance was tested on the benchmarking National Institute of Health (NIH)-Pancreas CT (PCT) dataset. Results: Three-dimensional CNN had mean (SD) Dice similarity coefficient (DSC): 0.91 (0.03) and average Hausdorff distance of 0.15 (0.09) mm on the test set. Model's performance was equivalent between males and females (P = 0.08) and across different CT slice thicknesses (P > 0.05) based on noninferiority statistical testing. There was no difference in model-predicted and GT pancreatic volumes [mean predicted volume 99 cc (31cc); GT volume 101 cc (33 cc), P = 0.33]. Mean pancreatic volume difference was À2.7 cc (percent difference: À2.4% of GT volume) with excellent correlation between model-predicted and GT volumes [concordance correlation coefficient (CCC)=0.97]. In the external TCIA dataset, the model had higher reliability than R1 and R2 on full vs reduced dose CT scans [model mean (SD) DSC: 0.96 (0.02), CCC = 0.995 vs R1 DSC: 0.83 (0.07), CCC = 0.89, and R2 DSC:0.87 (0.04), CCC = 0.97]. The DSC and volume concordance correlations for R1 vs R2 (inter-reader reliability) were 0.85 (0.07), CCC = 0.90 at full dose and 0.83 (0.07), CCC = 0.96 at reduced dose datasets. There was good reliability between model and R1 at both full and reduced dose CT [full dose: DSC: 0.81 (0.07), CCC = 0.83 and reduced dose DSC:0.81 (0.08), CCC = 0.87]. Likewise, there was good reliability betw...

show abstract

Development of a volumetric pancreas segmentation CT dataset for AI applications through trained technologists: a study during the COVID 19 containment phase

et al. 2020

View full text Add to dashboard Cite

Purpose To evaluate the performance of trained technologists vis-à-vis radiologists for volumetric pancreas segmentation and to assess the impact of supplementary training on their performance. Methods In this IRB-approved study, 22 technologists were trained in pancreas segmentation on portal venous phase CT through radiologist-led interactive videoconferencing sessions based on an image-rich curriculum. Technologists segmented pancreas in 188 CTs using freehand tools on custom image-viewing software. Subsequent supplementary training included multimedia videos focused on common errors, which were followed by second batch of 159 segmentations. Two radiologists reviewed all cases and corrected inaccurate segmentations. Technologists' segmentations were compared against radiologists' segmentations using Dice-Sorenson coefficient (DSC), Jaccard coefficient (JC), and Bland-Altman analysis. Results Corrections were made in 71 (38%) cases from first batch [26 (37%) oversegmentations and 45 (63%) undersegmentations] and in 77 (48%) cases from second batch [12 (16%) oversegmentations and 65 (84%) undersegmentations]. DSC, JC, false positive (FP), and false negative (FN) [mean (SD)] in first versus second batches were 0.63 (0.15) versus 0.63 (0.16), 0.48 (0.15) versus 0.48 (0.15), 0.29 (0.21) versus 0.21 (0.10), and 0.36 (0.20) versus 0.43 (0.19), respectively. Differences were not significant (p > 0.05). However, range of mean pancreatic volume difference reduced in the second batch [− 2.74 cc (min − 92.96 cc, max 87.47 cc) versus − 23.57 cc (min − 77.32, max 30.19)]. Conclusion Trained technologists could perform volumetric pancreas segmentation with reasonable accuracy despite its complexity. Supplementary training further reduced range of volume difference in segmentations. Investment into training technologists could augment and accelerate development of body imaging datasets for AI applications.

show abstract

Diabetes risk assessment with imaging: a radiomics study of abdominal CT

Cited by 21 publications

References 43 publications

Development and validation of a prediction model estimating the 10-year risk for type 2 diabetes in China

Development and validation of a prediction model estimating the 10-year risk for type 2 diabetes in China

Two‐stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra‐reader and inter‐reader reliability at full and reduced radiation dose on an external dataset

Development of a volumetric pancreas segmentation CT dataset for AI applications through trained technologists: a study during the COVID 19 containment phase

Contact Info

Product

Resources

About