On the use of icobrain's prepopulated radiology reporting template for multiple sclerosis follow-up

Congress:

ECR 2020

Poster Number:

C-11342

Type:

Scientific Exhibit

Keywords:

Not applicable, Retrospective, Image verification, Computer Applications-Detection, diagnosis, MR, Neuroradiology brain, Artificial Intelligence and Machine Learning, Multicentre study

Authors:

D. Sima¹, G. Wilms¹, T. Vande Vyvere², W. Van Hecke³, D. Smeets¹; ¹Leuven/BE, ²Leuven, Be/BE, ³icometrix, Belgium/BE

DOI:

10.26044/ecr2020/C-11342

DOI-Link:

https://dx.doi.org/10.26044/ecr2020/C-11342

Fig. 5: Comparison of reporting time: significantly faster reporting was observed when...

Fig. 6: Comparison of reporting conclusions: patients considered stable do not have new...

Fig. 2: Color-coding of longitudinal lesion overlay based on icobrain ms.

Fig. 1: FLAIR images as presented to the radiologist, with or without color-coded...

Purpose

Radiological reporting in multiple sclerosis (MS) and other neurological conditions is an important tool that facilitates communication between radiologist and neurologist. In this work we assess the added value of automatically prepopulated radiology reporting templatesfor MS follow-upbased on the automated icobrain software.

Methods and materials

Longitudinal MRI acquisitions approximately 1 year apart were collected from 25 multiple sclerosis patients. The icobrain software [1] was used to compute lesion load (including new and enlarging lesions) and brain volumetry (including annualized atrophy). These findings were automatically inserted in a radiology reporting template. Each MRI dataset, which included images from two time points (TP1 and TP2, see figure 1), was presented in random order to an experienced radiologist twice: once without and once with automatically generated report. In the latter case, besides color-coded...

Results

With respect to timing, the median time for conventional radiological reporting was 7min17s (interquartile range 4min40s), while the median computer-aided reporting time was 4min37s (interquartile range 3min35s), with the latter significantly faster (paired t-test and Wilcoxon signed-rank test p

Conclusion

Computer-aided radiological reportinghas been found to be faster than conventional reporting, with approximately 8 conventional reports per hour versus 13 computer-aided reports per hour. Stable patients identified by the computer-aided technique were also deemed stable by conventional radiological reading, but the software also reported cases of subtle cerebral atrophy. We conclude that computer-aided radiological reports are more efficientand bring objectivity to conventional reporting. Standardization of radiologic reporting and incorporation of brain atrophy are steps toward improvement in the clinical management of MS patients.

Personal information and conflict of interest

D. Sima; Leuven/BE - Employee at icometrix D. Smeets; Leuven/BE - Employee at icometrix W. van Hecke; Icometrix, BELGIUM/BE - CEO at icometrix T. Vande Vyvere; Leuven, BE/BE - Employee at icometrix G. Wilms; Leuven/BE - Consultant at icometrix

References

[1] Jain S, Sima DM, Ribbens A, Cambron M, Maertens A, Van Hecke W, et al. Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images. NeuroImage Clinical 2015; 8: 367-75.