Try our AI tools for analysis of PET/CT and CT studies
We invite researchers to apply and evaluate our AI tools on their own PET/CT or CT studies. We are also happy to collaborate and develop customized AI tools for other tasks than those presented below.
Request access to our platform by mail to contact@recomia.org.
This video shows how to upload and apply AI tools to your CT or PET/CT studies.
NOTE: The AI tools are available for research purposes only, not for clinical use.
Lung Cancer FDG-PET/CT v1.2
Segmentation and quantification of lung tumors, thoracic lymph nodes, and bone metastases. Note that lymph nodes outside thorax are not detected in this version. The AI tool includes the Organ Segmentation CT v3.3 described below and is in addition trained on 320 FDG-PET/CT studies with manual annotations from patients with suspected lung cancer. An earlier version of this tool was presented in a paper recently accepted for publication in EJNMMI Physics by Borrelli et al.
Prostate Cancer PSMA-PET/CT v1.1
Segmentation and quantification of prostate tumor, lymph nodes, and bone metastases. The AI tool includes the Organ Segmentation CT v3.3 described below and is in addition trained on 586 PET/CT studies with manual lymph node segmentations from patients with prostate cancer. An earlier version of the AI tool is presented in a paper by Edenbrandt et al.
Organ Activity in PET/CT v3.3
The AI tool Organ Segmentation CT v3.3 described below can be used to quantify PET tracer uptake in different organs when applied to PET/CT studies.
Body Composition CT v1.0
3D-segmentation of muscle and subcutaneous adipose tissue. The AI tool is trained on 127 CT studies with manual annotations. Muscle and fat is segmented from coccyx and 25 cm up. The tool can be adjusted to cover a larger segment of the body. The method is described in a recent paper in Eur Radiol Experimental by Borrelli et al.
Organ Segmentation CT v3.3
The AI tool segments 57 different organs in CT. Spine is segmented in two parts, cervical and thoracic/lumbal part. The AI tool is trained on 445 CT studies with manual annotations. An early version of the AI tool is described in a paper by Trägårdh et al.
Aortic Wall v2.4
Quantification of PET tracer activity in the aortic wall. The AI tool segments the aortic arch, the abdominal, and the thoracic parts of the aorta in the CT images. The spine is also segmented in CT allowing high PET activity originating from the spine to be excluded from the aortic wall segmentations. The AI tool is presented in a paper by Piri et al., which recently was accepted for publication in the J Nucl Cardiol.
