| 1. |
- Kvist, Ola, et al.
(författare)
-
A cross-sectional magnetic resonance imaging study of factors influencing growth plate closure in adolescents and young adults
- 2021
-
Ingår i: Acta Paediatrica. - : John Wiley & Sons. - 0803-5253 .- 1651-2227. ; 110:4, s. 1249-1256
-
Tidskriftsartikel (refereegranskat)abstract
- Aim To assess growth plate fusion by magnetic resonance imaging (MRI) and evaluate the correlation with sex, age, pubertal development, physical activity and BMI. Methods Wrist, knee and ankle of 958 healthy subjects aged 14.0-21.5 years old were examined using MRI and graded by two radiologists. Correlations of growth plate fusion score with age, pubertal development, physical activity and BMI were assessed. Results Complete growth plate fusion occurred in 75%, 85%, 97%, 98%, 98% and 90%, 97%, 95%, 97%, 98% (radius, femur, proximal- and distal tibia and calcaneus) in 17-year-old females and 19-year-old males, respectively. Complete fusion occurs approximately 2 years earlier in girls than in boys. Pubertal development correlated with growth plate fusion score (rho = 0.514-0.598 for the different growth plate sites) but regular physical activity did not. BMI also correlated with growth plate fusion (rho = 0.186-0.384). Stratified logistic regression showed increased odds ratio (OR F: 2.65-8.71; M: 1.71-4.03) for growth plate fusion of obese or overweight subects versus normal-weight subjects. Inter-observer agreement was high (Kappa = 0.87-0.94). Conclusion Growth plate fusion can be assessed by MRI; occurs in an ascending order, from the foot to the wrist; and is significantly influenced by sex, pubertal development and BMI, but not by physical activity.
|
|
| 2. |
- Dallora Moraes, Ana Luiza, et al.
(författare)
-
Age assessment of youth and young adults using magnetic resonance imaging of the knee : A deep learning approach
- 2019
-
Ingår i: JMIR Medical Informatics. - : JMIR PUBLICATIONS. - 2291-9694. ; 7:4, s. 419-436
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Bone age assessment (BAA) is an important tool for diagnosis and in determining the time of treatment in a number of pediatric clinical scenarios, as well as in legal settings where it is used to estimate the chronological age of an individual where valid documents are lacking. Traditional methods for BAA suffer from drawbacks, such as exposing juveniles to radiation, intra- and interrater variability, and the time spent on the assessment. The employment of automated methods such as deep learning and the use of magnetic resonance imaging (MRI) can address these drawbacks and improve the assessment of age. Objective: The aim of this paper is to propose an automated approach for age assessment of youth and young adults in the age range when the length growth ceases and growth zones are closed (14-21 years of age) by employing deep learning using MRI of the knee. Methods: This study carried out MRI examinations of the knee of 402 volunteer subjects-221 males (55.0%) and 181 (45.0%) females-aged 14-21 years. The method comprised two convolutional neural network (CNN) models: the first one selected the most informative images of an MRI sequence, concerning age-assessment purposes; these were then used in the second module, which was responsible for the age estimation. Different CNN architectures were tested, both training from scratch and employing transfer learning. Results: The CNN architecture that provided the best results was GoogLeNet pretrained on the ImageNet database. The proposed method was able to assess the age of male subjects in the range of 14-20.5 years, with a mean absolute error (MAE) of 0.793 years, and of female subjects in the range of 14-19.5 years, with an MAE of 0.988 years. Regarding the classification of minors-with the threshold of 18 years of age-an accuracy of 98.1% for male subjects and 95.0% for female subjects was achieved. Conclusions: The proposed method was able to assess the age of youth and young adults from 14 to 20.5 years of age for male subjects and 14 to 19.5 years of age for female subjects in a fully automated manner, without the use of ionizing radiation, addressing the drawbacks of traditional methods. © 2019 Journal of Medical Internet Research. All rights reserved.
|
|
| 3. |
- Kvist, Ola F. T., et al.
(författare)
-
Comparison of reliability of magnetic resonance imaging using cartilage and T1-weighted sequences in the assessment of the closure of the growth plates at the knee
- 2020
-
Ingår i: Acta Radiologica Open. - London : Sage Publications. - 2058-4601. ; 9:9, s. 1-9
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Growth development is traditionally evaluated with plain radiographs of the hand and wrist to visualize bone structures using ionizing radiation. Meanwhile, MRI visualizes bone and cartilaginous tissue without radiation exposure. Purpose: To determine the state of growth plate closure of the knee in healthy adolescents and young adults and compare the reliability of staging using cartilage sequences and T1-weighted (T1W) sequence between pediatric and general radiologists. Material and Methods: A prospective, cross-sectional study of MRI of the knee with both cartilage and T1W sequences was performed in 395 male and female healthy subjects aged between 14.0 and 21.5 years old. The growth plate of the femur and the tibia were graded using a modified staging scale by two pediatric and two general radiologists. Femur and tibia were graded separately with both sequences. Results: The intraclass correlation was overall excellent. The inter- and intra-observer agreement for pediatric radiologists on T1W was 82% (kappa = 0.73) and 77% (kappa = 0.65) for the femur and 90% (kappa = 0.82) and 87% (kappa = 0.75) for the tibia. The inter-observer agreement for general radiologists on T1W was 69% (kappa = 0.56) for the femur and 56% (kappa = 0.34) for the tibia. Cohen's kappa coefficient showed a higher inter- and intra-observer agreement for cartilage sequences than for T1W: 93% (kappa = 0.86) and 89% (kappa = 0.79) for the femur and 95% (kappa = 0.90) and 91% (kappa = 0.81) for the tibia. Conclusion: Cartilage sequences are more reliable than T1W sequence in the assessment of the growth plate in adolescents and young adults. Pediatric radiology experience is preferable.
|
|
| 4. |
- Chaddad, Ahmad, et al.
(författare)
-
Magnetic resonance imaging based radiomic models of prostate cancer : A narrative review
- 2021
-
Ingår i: Cancers. - : MDPI AG. - 2072-6694. ; 13:3, s. 1-22
-
Forskningsöversikt (refereegranskat)abstract
- The management of prostate cancer (PCa) is dependent on biomarkers of biological aggression. This includes an invasive biopsy to facilitate a histopathological assessment of the tumor’s grade. This review explores the technical processes of applying magnetic resonance imaging based radiomic models to the evaluation of PCa. By exploring how a deep radiomics approach further optimizes the prediction of a PCa’s grade group, it will be clear how this integration of artificial intelligence mitigates existing major technological challenges faced by a traditional radiomic model: image acquisition, small data sets, image processing, labeling/segmentation, informative features, predicting molecular features and incorporating predictive models. Other potential impacts of artificial intelligence on the personalized treatment of PCa will also be discussed. The role of deep radiomics analysis‐a deep texture analysis, which extracts features from convolutional neural networks layers, will be highlighted. Existing clinical work and upcoming clinical trials will be reviewed, directing investigators to pertinent future directions in the field. For future progress to result in clinical translation, the field will likely require multi‐institutional collaboration in producing prospectively populated and expertly labeled imaging libraries. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
|
|
| 5. |
- Spjuth, Ola, 1977-, et al.
(författare)
-
E-Science technologies in a workflow for personalized medicine using cancer screening as a case study
- 2017
-
Ingår i: JAMIA Journal of the American Medical Informatics Association. - : Oxford University Press. - 1067-5027 .- 1527-974X. ; 24:5, s. 950-957
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: We provide an e-Science perspective on the workflow from risk factor discovery and classification of disease to evaluation of personalized intervention programs. As case studies, we use personalized prostate and breast cancer screenings.Materials and Methods: We describe an e-Science initiative in Sweden, e-Science for Cancer Prevention and Control (eCPC), which supports biomarker discovery and offers decision support for personalized intervention strategies. The generic eCPC contribution is a workflow with 4 nodes applied iteratively, and the concept of e-Science signifies systematic use of tools from the mathematical, statistical, data, and computer sciences.Results: The eCPC workflow is illustrated through 2 case studies. For prostate cancer, an in-house personalized screening tool, the Stockholm-3 model (S3M), is presented as an alternative to prostate-specific antigen testing alone. S3M is evaluated in a trial setting and plans for rollout in the population are discussed. For breast cancer, new biomarkers based on breast density and molecular profiles are developed and the US multicenter Women Informed to Screen Depending on Measures (WISDOM) trial is referred to for evaluation. While current eCPC data management uses a traditional data warehouse model, we discuss eCPC-developed features of a coherent data integration platform.Discussion and Conclusion: E-Science tools are a key part of an evidence-based process for personalized medicine. This paper provides a structured workflow from data and models to evaluation of new personalized intervention strategies. The importance of multidisciplinary collaboration is emphasized. Importantly, the generic concepts of the suggested eCPC workflow are transferrable to other disease domains, although each disease will require tailored solutions.
|
|
| 6. |
- Kvist, Ola, et al.
(författare)
-
DTI assessment of the maturing growth plate of the knee in adolescents and young adults
- 2023
-
Ingår i: European Journal of Radiology. - : Elsevier. - 0720-048X .- 1872-7727. ; 162
-
Tidskriftsartikel (refereegranskat)abstract
- PURPOSE: To assess the growth plates of the knee in a healthy population of young adults and adolescents using DTI, and to correlate the findings with chronological age and skeletal maturation.METHODS: A prospective, cross-sectional study to assess the tibial and femoral growth plates with DTI in 155 healthy volunteers aged between 14.0 and 21 years old. Echo-planar DTI with 15 directions and b value of 0 and 600 s/mm2 was performed on a 3 T whole-body scanner.RESULTS: A relationship was observed between chronological age and most DTI metrics (fractional anisotropy, mean diffusivity, and radial diffusivity), tract length and volume. (No significant relationship could be seen for axonal diffusivity and tract length.) Subdivision according to skeletal maturation showed the greatest tract lengths and volumes seen in stage 4b and not 4a. The intra-observer agreement was significant (P = 0.01) for all the measured variables, but agreement varied (femur 0.53 - 0.98; tibia 0.58 - 0.98). Spearman's correlation showed a significant correlation for age (P = 0.05; P = 0.01) as well as for the fractional anisotropy value within all variables in both femur and tibia. Tract number and volume had a similar correlation with most variables, especially the DTI metrics, and would seem to be interchangeable.CONCLUSION: The current study indicates that DTI metrics could be a tool to assess the skeletal maturation process of the growth plate and its activity. Tractography seems promising to assess the activity of the growth plate in a younger population but must be used with caution in the more mature growth plate.
|
|
| 7. |
- Kvist, Ola, et al.
(författare)
-
Magnetic resonance and diffusion tensor imaging of the adolescent rabbit growth plate of the knee
- 2023
-
Ingår i: Magnetic Resonance in Medicine. - : John Wiley & Sons. - 0740-3194 .- 1522-2594. ; 89:1, s. 331-342
-
Tidskriftsartikel (refereegranskat)abstract
- PURPOSE: To assess the ability of MRI-DTI to evaluate growth plate morphology and activity compared with that of histomorphometry and micro-CT in rabbits.METHODS: The hind limbs of female rabbits aged 16, 20, and 24 wk (n = 4 per age group) were studied using a 9.4T MRI scanner with a multi-gradient echo 3D sequence and DTI in 14 directions (b-value = 984 s/mm2 ). After MRI, the right and left hind limb were processed for histological analysis and micro-CT, respectively. The Wilcoxon signed-rank test was used to evaluate the height and volume of the growth plate. Intraclass correlation and Pearson correlation coefficient were used to evaluate the association between DTI metrics and age.RESULTS: The growth plate height and volume were similar for all modalities at each time point and age. Age was correlated with all tractography and DTI metrics in both the femur and tibia. A correlation was also observed between all the metrics at both sites. Tract number and volume declined with age; however, tract length did not show any changes. The fractional anisotropy color map showed lateral diffusion centrally in the growth plate and perpendicular diffusion in the hypertrophic zone, as verified by histology and micro-CT.CONCLUSION: MRI-DTI may be useful for evaluating the growth plates.
|
|
| 8. |
- Sarp, Salih, et al.
(författare)
-
An XAI approach for COVID-19 detection using transfer learning with X-ray images
- 2023
-
Ingår i: Heliyon. - : Elsevier. - 2405-8440. ; 9:4
-
Tidskriftsartikel (refereegranskat)abstract
- The coronavirus disease (COVID-19) has continued to cause severe challenges during this unprecedented time, affecting every part of daily life in terms of health, economics, and social development. There is an increasing demand for chest X-ray (CXR) scans, as pneumonia is the primary and vital complication of COVID-19. CXR is widely used as a screening tool for lung-related diseases due to its simple and relatively inexpensive application. However, these scans require expert radiologists to interpret the results for clinical decisions, i.e., diagnosis, treatment, and prognosis. The digitalization of various sectors, including healthcare, has accelerated during the pandemic, with the use and importance of Artificial Intelligence (AI) dramatically increasing. This paper proposes a model using an Explainable Artificial Intelligence (XAI) technique to detect and interpret COVID-19 positive CXR images. We further analyze the impact of COVID-19 positive CXR images using heatmaps. The proposed model leverages transfer learning and data augmentation techniques for faster and more adequate model training. Lung segmentation is applied to enhance the model performance further. We conducted a pre-trained network comparison with the highest classification performance (F1-Score: 98%) using the ResNet model. © 2023 The Author(s)
|
|
