Related Experiment Video
Updated: Sep 16, 2025
Database-guided Flow-cytometry for Evaluation of Bone Marrow Myeloid Cell Maturation
Published on: November 3, 2018
Automated Detection of Focal Bone Marrow Lesions From MRI: A Multi-center Feasibility Study in Patients with
Markus Wennmann1, Jessica Kächele2, Arvin von Salomon3
1Division of Radiology, German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120 Heidelberg, Germany (M.W., A.V.S., M.G., F.B., L.T.R., K.S.Z., S.D., H.P.S.); Diagnostic and Interventional Radiology, Heidelberg University Hospital, Im Neuenheimer Feld 410, 69120 Heidelberg, Germany (M.W., T.N., V.R., T.M., T.F.W.).
Rationale And Objectives:
To train and test an AI-based algorithm for automated detection of focal bone marrow lesions (FL) from MRI.
Materials And Methods:
This retrospective feasibility study included 444 patients with monoclonal plasma cell disorders. For this feasibility study, only FLs in the left pelvis were included. Using the nnDetection framework, the algorithm was trained based on 334 patients with 494 FLs from center 1, and was tested on an internal test set (36 patients, 89 FLs, center 1) and a multicentric external test set (74 patients, 262 FLs, centers 2-11). Mean average precision (mAP), F1-score, sensitivity, positive predictive value (PPV), and Spearman correlation coefficient between automatically determined and actual number of FLs were calculated.
Results:
On the internal/external test set, the algorithm achieved a mAP of 0.44/0.34, F1-Score of 0.54/0.44, sensitivity of 0.49/0.34, and a PPV of 0.61/0.61, respectively. In two subsets of the external multicentric test set with high imaging quality, the performance nearly matched that of the internal test set, with mAP of 0.45/0.41, F1-Score of 0.50/0.53, sensitivity of 0.44/0.43, and a PPV of 0.60/0.71, respectively. There was a significant correlation between the automatically determined and actual number of FLs on both the internal (r=0.51, p=0.001) and external multicentric test set (r=0.59, p<0.001).
Conclusion:
This study demonstrates that the automated detection of FLs from MRI, and thereby the automated assessment of the number of FLs, is feasible.
Insights
An AI algorithm can automatically detect focal bone marrow lesions (FLs) on MRI scans. This automated detection and counting of FLs shows feasibility in clinical settings.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Monoclonal plasma cell disorders can manifest as focal bone marrow lesions (FLs) on MRI.
- Accurate detection and quantification of FLs are crucial for disease assessment and management.
Purpose of the Study:
- To develop and evaluate an AI-based algorithm for the automated detection of FLs from MRI.
- To assess the feasibility of automated FL detection and quantification in patients with monoclonal plasma cell disorders.
Main Methods:
- A retrospective study involving 444 patients with monoclonal plasma cell disorders.
- An AI algorithm was trained using the nnDetection framework on MRI data from 334 patients.
- The algorithm was validated on an internal test set (36 patients) and a multicentric external test set (74 patients), focusing on FLs in the left pelvis.
Main Results:
- The AI algorithm demonstrated feasibility in detecting FLs, achieving a mean average precision (mAP) of 0.44 on the internal test set and 0.34 on the external test set.
- Performance metrics, including F1-score, sensitivity, and positive predictive value (PPV), indicated the algorithm's potential.
- A significant positive correlation (r=0.51 to 0.59) was observed between the algorithm's FL count and the actual number of FLs.
Conclusions:
- Automated detection of focal bone marrow lesions from MRI is feasible using AI.
- The AI algorithm shows potential for automated assessment of FLs, aiding in the management of monoclonal plasma cell disorders.
More Related Videos
07:53Interphase Fluorescence in situ Hybridization of Bone Marrow Smears of Multiple Myeloma
Published on: April 15, 2022
09:01Flow Cytometry to Estimate Leukemia Stem Cells in Primary Acute Myeloid Leukemia and in Patient-derived-xenografts, at Diagnosis and Follow Up
Published on: March 26, 2018