Licandro, Roxane

Hofmanninger, Johannes

Perkonigg, Matthias

Röhrich, Sebastian

Weber, Marc-André

Wennmann, Markus

Kintzele, Laurent

Piraud, Marie

Menze, Bjoern

Langs, Georg

2022-10-20T11:56:15Z

2022-10-20T11:56:15Z

2020-07

<div class="csl-bib-body"> <div class="csl-entry">Licandro, R., Hofmanninger, J., Perkonigg, M., Röhrich, S., Weber, M.-A., Wennmann, M., Kintzele, L., Piraud, M., Menze, B., &#38; Langs, G. (2020). <i>Evolution Risk Prediction of Bone Lesions in Multiple Myeloma</i>. European Congress of Radiology 2020, Wien, Austria. http://hdl.handle.net/20.500.12708/87090</div> </div>

http://hdl.handle.net/20.500.12708/87090

Purpose The earliest possible detection of bone lesions is key to facilitate timely treatment decisions in patients with Multiple Myeloma (MM). The clinical relevance lies in providing a machine-learning based score to assess the risk of localized bone regions to evolve into diffuse or osteolytic lesions based on pre-stage infiltration patterns in whole body Magnetic Resonance Imaging (wbMRI). Materials and Methods 63 patients received multiple T1 weighted wbMRI scans with the average time of 13 months between the scans. Overall, 170 locations evolved to either diffuse or osteolytic lesions. Here, we propose a methodology to predict future bone lesion growth and emergence from T1 weighted wbMRI images resulting in a full body risk score map. We propose an asymmetric cascade architecture of U-Nets consisting of an MR image-based bone segmentation net and a patch-based lesion prediction net. The algorithm identifies early signatures of emerging lesions and visualizes high risk locations accordingly. Results The proposed approach is evaluated for two body parts ((1) thorax, (2) legs) and lesion types. The bone segmentation net detects bones with a mean Area Under the Curve (AUC) of 0.76423 (1) and 0.8023 (2). The lesion prediction net predicts emerging lesions (which are reported in the future but not in the observed scan), with a mean AUC of 0.6083 (1) and 0.5304 (2) and changing lesions (which are annotated continuously) with a mean AUC of 0.5855 and 0.6840. Conclusion We propose a risk predictor for lesions to emerge or to progress and map high-risk regions accordingly. We first segment bones and then predict lesions within bones using asymmetric cascaded U-Nets. This is the first approach that predicts lesions on full volumetric wbMRI data, showing feasible results, but false positives occur in areas of anomaly, that do not progress to lesions. Our findings indicate hidden imaging markers beyond lesion size, currently used for categorization and risk stratification in MM.

Purpose The earliest possible detection of bone lesions is key to facilitate timely treatment decisions in patients with Multiple Myeloma (MM). The clinical relevance lies in providing a machine-learning based score to assess the risk of localized bone regions to evolve into diffuse or osteolytic lesions based on pre-stage infiltration patterns in whole body Magnetic Resonance Imaging (wbMRI). Materials and Methods 63 patients received multiple T1 weighted wbMRI scans with the average time of 13 months between the scans. Overall, 170 locations evolved to either diffuse or osteolytic lesions. Here, we propose a methodology to predict future bone lesion growth and emergence from T1 weighted wbMRI images resulting in a full body risk score map. We propose an asymmetric cascade architecture of U-Nets consisting of an MR image-based bone segmentation net and a patch-based lesion prediction net. The algorithm identifies early signatures of emerging lesions and visualizes high risk locations accordingly. Results The proposed approach is evaluated for two body parts ((1) thorax, (2) legs) and lesion types. The bone segmentation net detects bones with a mean Area Under the Curve (AUC) of 0.76423 (1) and 0.8023 (2). The lesion prediction net predicts emerging lesions (which are reported in the future but not in the observed scan), with a mean AUC of 0.6083 (1) and 0.5304 (2) and changing lesions (which are annotated continuously) with a mean AUC of 0.5855 and 0.6840. Conclusion We propose a risk predictor for lesions to emerge or to progress and map high-risk regions accordingly. We first segment bones and then predict lesions within bones using asymmetric cascaded U-Nets. This is the first approach that predicts lesions on full volumetric wbMRI data, showing feasible results, but false positives occur in areas of anomaly, that do not progress to lesions. Our findings indicate hidden imaging markers beyond lesion size, currently used for categorization and risk stratification in MM.

en

Artificial Intelligence

Radiology, Nuclear Medicine and imaging

Muskoskelatal

Computer-Aided Diagnoses

Cancer

Evolution Risk Prediction of Bone Lesions in Multiple Myeloma

Präsentation

Presentation

Poster Presentation

false

https://doi.org/10.1186/s13244-020-00851-0

E193-01 - Forschungsbereich Computer Vision

E193 - Institut für Visual Computing and Human-Centered Technology

European Congress of Radiology 2020

15-07-2020

19-07-2020

Online

Event for scientific audience

Wien

AT

Licandro, Roxane

Online

Informatik

Sonstige Humanmedizin, Gesundheitswissenschaften

1020

3059

Visual Computing and Human-Centered Technology (VC + HCT)

Visual Computing and Human-Centered Technology (VC + HCT)

E180

en

conference poster not in proceedings

none

no Fulltext

Publications

http://purl.org/coar/resource_type/c_18co

E193 - Institut für Visual Computing and Human-Centered Technology

E186 - Institut für Computergraphik und Algorithmen

E193 - Institut für Visual Computing and Human-Centered Technology

Medical University of Vienna

E193 - Institut für Visual Computing and Human-Centered Technology

0000-0001-9066-4473

E180 - Fakultät für Informatik

E180 - Fakultät für Informatik

E180 - Fakultät für Informatik

E180 - Fakultät für Informatik