Milja Holstila
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Milja Holstila has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Kalle Koskensalo
Department of Medical Physics, Turku University Hospital, Turku, Finland
2 shared publications Kirsi A. Virtanen
Turku PET Centre, Turku University Hospital, Turku, Finland
2 shared publicationsAlexander Biehl
Turku Bioscience Centre, University of Turku and Åbo Akademi University , Turku
1 shared publication- Hidehiro Iida
Turku PET Centre, University of Turku, Turku, Finland
1 shared publication - Hiroshi Akima
Graduate School of Education and Human Development Nagoya University Nagoya Aichi Japan
1 shared publication Jenni Harjula
1 shared publication
Latest Publications
- Open Access
- 18 October 2024
- Published by Elsevier in Journal of Orthopaedic Reports
- Vol. 4 (4)
Structural auto- and allograft glenoid bone grafting in reverse shoulder arthroplasty - Retrospective radiological analysis of 38 cases
- 18 October 2024
- Published by Elsevier in Journal of Orthopaedic Reports
- Vol. 4 (4)
Open AccessStructural auto- and allograft glenoid bone grafting in reverse shoulder arthroplasty - Retrospective radiological analysis of 38 cases
- Open Access
- 10 April 2024
- Published by Oxford University Press (OUP) in Rheumatology
- Vol. 64 (3) , 1068-1076
Deep learning enables automatic detection of joint damage progression in rheumatoid arthritis—model development and external validation
Although deep learning has demonstrated substantial potential in automatic quantification of joint damage in rheumatoid arthritis (RA), evidence for detecting longitudinal changes at an individual patient level is lacking. Here, we introduce and externally validate our automated RA scoring algorithm (AuRA), and demonstrate its utility for monitoring radiographic progression in a real-world setting. The algorithm, originally developed during the Rheumatoid Arthritis 2–Dialogue for Reverse Engineering Assessment and Methods (RA2-DREAM) challenge, was trained to predict expert-curated Sharp-van der Heijde total scores in hand and foot radiographs from two previous clinical studies (n = 367). We externally validated AuRA against data (n = 205) from Turku University Hospital and compared the performance against two top-performing RA2-DREAM solutions. Finally, for 54 patients, we extracted additional radiograph sets from another control visit to the clinic (average time interval of 4.6 years). In the external validation cohort, with a root-mean-square-error (RMSE) of 23.6, AuRA outperformed both top-performing RA2-DREAM algorithms (RMSEs 35.0 and 35.6). The improved performance was explained mostly by lower errors at higher expert-assessed scores. The longitudinal changes predicted by our algorithm were significantly correlated with changes in expert-assessed scores (Pearson’s R = 0.74, p< 0.001). AuRA had the best external validation performance and demonstrated potential for detecting longitudinal changes in joint damage. Available in https://hub.docker.com/r/elolab/aura, our algorithm can easily be applied for automatic detection of radiographic progression in the future, reducing the need for laborious manual scoring.
- 10 April 2024
- Published by Oxford University Press (OUP) in Rheumatology
- Vol. 64 (3) , 1068-1076
Open AccessDeep learning enables automatic detection of joint damage progression in rheumatoid arthritis—model development and external validation
Although deep learning has demonstrated substantial potential in automatic quantification of joint damage in rheumatoid arthritis (RA), evidence for detecting longitudinal changes at an individual patient level is lacking. Here, we introduce and externally validate our automated RA scoring algorithm (AuRA), and demonstrate its utility for monitoring radiographic progression in a real-world setting. The algorithm, originally developed during the Rheumatoid Arthritis 2–Dialogue for Reverse Engineering Assessment and Methods (RA2-DREAM) challenge, was trained to predict expert-curated Sharp-van der Heijde total scores in hand and foot radiographs from two previous clinical studies (n = 367). We externally validated AuRA against data (n = 205) from Turku University Hospital and compared the performance against two top-performing RA2-DREAM solutions. Finally, for 54 patients, we extracted additional radiograph sets from another control visit to the clinic (average time interval of 4.6 years). In the external validation cohort, with a root-mean-square-error (RMSE) of 23.6, AuRA outperformed both top-performing RA2-DREAM algorithms (RMSEs 35.0 and 35.6). The improved performance was explained mostly by lower errors at higher expert-assessed scores. The longitudinal changes predicted by our algorithm were significantly correlated with changes in expert-assessed scores (Pearson’s R = 0.74, p< 0.001). AuRA had the best external validation performance and demonstrated potential for detecting longitudinal changes in joint damage. Available in https://hub.docker.com/r/elolab/aura, our algorithm can easily be applied for automatic detection of radiographic progression in the future, reducing the need for laborious manual scoring.
- 25 September 2021
- Published by Springer Nature in European Journal of Applied Physiology
- Vol. 122 (1) , 81-90
Brown adipose tissue fat-fraction is associated with skeletal muscle adiposity
Purpose While brown adipose tissue (BAT) activity is known to be associated with both muscle and adipose tissue volumes, the association between BAT and muscle composition remains unclear, especially in adults. Therefore, the present study aimed to examine the association between BAT parameters (glucose uptake and fat-fraction) and muscle volumes and intramuscular adipose tissue contents among healthy young and middle-aged men. Methods BAT glucose uptake was determined using positron emission tomography with [18F]-2-deoxy-2-fluoro-D-glucose (18F-FDG) during cold exposure in 19 young and middle-aged men (36.3 ± 10.7 years). The fat-fraction of BAT was determined from volumes of interest set in cervical and supraclavicular adipose tissue depots using signal fat-fraction maps via magnetic resonance imaging (MRI). Muscle volumes and intramuscular adipose tissue contents of m. tibialis anterior and m. multifidus lumborum were measured using MRI. Results The fat-fraction of BAT was significantly associated with intramuscular adipose tissue content in m. tibialis anterior (n = 13, rs = 0.691, P = 0.009). A similar trend was also observed in m. multifidus lumborum (n = 19, rs = 0.454, P = 0.051). However, BAT glucose uptake was not associated with intramuscular adipose tissue contents in both muscles, nor were muscle volumes associated with the BAT glucose uptake and fat-fraction. Conclusion The fat-fraction of BAT increases with skeletal muscle adiposity, especially in the lower leg, among healthy young and middle-aged men.
- 25 September 2021
- Published by Springer Nature in European Journal of Applied Physiology
- Vol. 122 (1) , 81-90
Brown adipose tissue fat-fraction is associated with skeletal muscle adiposity
Purpose While brown adipose tissue (BAT) activity is known to be associated with both muscle and adipose tissue volumes, the association between BAT and muscle composition remains unclear, especially in adults. Therefore, the present study aimed to examine the association between BAT parameters (glucose uptake and fat-fraction) and muscle volumes and intramuscular adipose tissue contents among healthy young and middle-aged men. Methods BAT glucose uptake was determined using positron emission tomography with [18F]-2-deoxy-2-fluoro-D-glucose (18F-FDG) during cold exposure in 19 young and middle-aged men (36.3 ± 10.7 years). The fat-fraction of BAT was determined from volumes of interest set in cervical and supraclavicular adipose tissue depots using signal fat-fraction maps via magnetic resonance imaging (MRI). Muscle volumes and intramuscular adipose tissue contents of m. tibialis anterior and m. multifidus lumborum were measured using MRI. Results The fat-fraction of BAT was significantly associated with intramuscular adipose tissue content in m. tibialis anterior (n = 13, rs = 0.691, P = 0.009). A similar trend was also observed in m. multifidus lumborum (n = 19, rs = 0.454, P = 0.051). However, BAT glucose uptake was not associated with intramuscular adipose tissue contents in both muscles, nor were muscle volumes associated with the BAT glucose uptake and fat-fraction. Conclusion The fat-fraction of BAT increases with skeletal muscle adiposity, especially in the lower leg, among healthy young and middle-aged men.
- 1 May 2017
- Published by Elsevier in Metabolism
- Vol. 70, 23-30
MR signal-fat-fraction analysis and T2* weighted imaging measure BAT reliably on humans without cold exposure
- 1 May 2017
- Published by Elsevier in Metabolism
- Vol. 70, 23-30
MR signal-fat-fraction analysis and T2* weighted imaging measure BAT reliably on humans without cold exposure