VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images

Sekuboyina, Anjany; Husseini, Malek El; Bayat, Amirhossein; Löffler, Maximilian T.; Liebl, Hans; Li, Hongwei; Tetteh, Giles; Kukačka, Jan; Payer, Christian; Štern, Darko; Urschler, Martin; Chen, Maodong; Cheng, Dalong; Leßmann, Nikolas; Hu, Yujin; Wang, Tianfu; Yang, Dong; Xu, Daguang; Ambellan, Felix; Amiranashvili, Tamaz; Ehlke, Moritz; Lamecker, Hans; Lehnert, Sebastian; Lirio, Marilia; Olaguer, Nicolás Pérez de; Ramm, Heiko; Sahu, Manish; Tack, Alexander; Zachow, Stefan; Jiang, Tao; Ma, Xinjun; Angerman, Christoph; Wang, Xin; Brown, Kevin M.; Kirszenberg, Alexandre; Puybareau, Élodie; Chen, Di; Bai, Yiwei; Rapazzo, Brandon H.; Yeah, Timyoas; Zhang, Amber; Xu, Shangliang; Feng, Huanqing; He, Zhiqiang; Zeng, Chan; Zheng, Xiao; Xu, Liming; Netherton, Tucker; Mumme, Raymond; Court, Laurence E.; Huang, Zixun; He, Chenhang; Wang, Li Wen; Ling, Sai Ho; Huỳnh, Lê Duy; Boutry, Nicolas; Jakubíček, Roman; Chmelík, Jiří; Mulay, Supriti; Sivaprakasam, Mohanasankar; Paetzold, Johannes C.; Shit, Suprosanna; Ezhov, Ivan; Wiestler, Benedikt; Glocker, Ben; Valentinitsch, Alexander; Rempfler, Markus; Menze, Bjoern; Kirschke, Jan S.

doi:10.1016/j.media.2021.102166

Cited by 190 publications

(189 citation statements)

References 75 publications

Supporting

Mentioning

141

Contrasting

Order By: Relevance

“…Even though the neural network was trained with healthy individuals only, the automated segmentation process respected the present spinal osteolytic lesions (Fig. 3) [19,20].…”

Section: Results Of Automated Segmentationmentioning

confidence: 99%

“…All 35 three-dimensional CT datasets were roughly cropped to a longish cuboid containing the thoracolumbar spine. Automated segmentation of the spine was achieved by a pre-trained convolutional neural network [19,20]. Seventeen vertebrae counting from bottom upwards were marked as a volume of interest (VOI) by a Python script.…”

Section: Segmentation Of the Bm And Assessment Of Dect Datamentioning

confidence: 99%

See 1 more Smart Citation

Feasibility of artificial intelligence–supported assessment of bone marrow infiltration using dual-energy computed tomography in patients with evidence of monoclonal protein — a retrospective observational study

Fervers

Kottlors

et al. 2021

Eur Radiol

View full text Add to dashboard Cite

Objectives To demonstrate the feasibility of an automated, non-invasive approach to estimate bone marrow (BM) infiltration of multiple myeloma (MM) by dual-energy computed tomography (DECT) after virtual non-calcium (VNCa) post-processing. Methods Individuals with MM and monoclonal gammopathy of unknown significance (MGUS) with concurrent DECT and BM biopsy between May 2018 and July 2020 were included in this retrospective observational study. Two pathologists and three radiologists reported BM infiltration and presence of osteolytic bone lesions, respectively. Bone mineral density (BMD) was quantified CT-based by a CE-certified software. Automated spine segmentation was implemented by a pre-trained convolutional neural network. The non-fatty portion of BM was defined as voxels > 0 HU in VNCa. For statistical assessment, multivariate regression and receiver operating characteristic (ROC) were conducted. Results Thirty-five patients (mean age 65 ± 12 years; 18 female) were evaluated. The non-fatty portion of BM significantly predicted BM infiltration after adjusting for the covariable BMD (p = 0.007, r = 0.46). A non-fatty portion of BM > 0.93% could anticipate osteolytic lesions and the clinical diagnosis of MM with an area under the ROC curve of 0.70 [0.49–0.90] and 0.71 [0.54–0.89], respectively. Our approach identified MM-patients without osteolytic lesions on conventional CT with a sensitivity and specificity of 0.63 and 0.71, respectively. Conclusions Automated, AI-supported attenuation assessment of the spine in DECT VNCa is feasible to predict BM infiltration in MM. Further, the proposed method might allow for pre-selecting patients with higher pre-test probability of osteolytic bone lesions and support the clinical diagnosis of MM without pathognomonic lesions on conventional CT. Key Points • The retrospective study provides an automated approach for quantification of the non-fatty portion of bone marrow, based on AI-supported spine segmentation and virtual non-calcium dual-energy CT data. • An increasing non-fatty portion of bone marrow is associated with a higher infiltration determined by invasive biopsy after adjusting for bone mineral density as a control variable (p = 0.007, r = 0.46). • The non-fatty portion of bone marrow might support the clinical diagnosis of multiple myeloma when conventional CT images are negative (sensitivity 0.63, specificity 0.71).

show abstract

“…Even though the neural network was trained with healthy individuals only, the automated segmentation process respected the present spinal osteolytic lesions (Fig. 3) [19,20].…”

Section: Results Of Automated Segmentationmentioning

confidence: 99%

Section: Segmentation Of the Bm And Assessment Of Dect Datamentioning

confidence: 99%

Feasibility of artificial intelligence–supported assessment of bone marrow infiltration using dual-energy computed tomography in patients with evidence of monoclonal protein — a retrospective observational study

Fervers

Kottlors

et al. 2021

Eur Radiol

View full text Add to dashboard Cite

show abstract

“…Although vertebral body segmentation as well as texture analysis are not part of the clinical routine, approaches are feasible without considerable computational efforts. In detail, CT image segmentation and vBMD extraction are already established, automated, computationally optimized, and their computational effort can therefore be considered negligible in comparison to the remaining tasks (when implementing a pipeline such as the herein used CNN-based framework for vertebral body labeling and segmentation with parameter extraction) (43)(44)(45). Details on the computational efficiency of the water-fat separation for generating PDFF and T2* maps have been reported previously for a similar workflow (49).…”

Section: Discussionmentioning

confidence: 99%

“…From PACS, images were transferred to our in-house developed, convolutional neural network (CNN)-based framework (https:// anduin.bonescreen.de) (Figures 1 and 2) (43)(44)(45). This tool identifies and labels each vertebra in an automated process, followed by creating corresponding segmentation masks for each vertebra as well as its subregions.…”

Section: Image Processing and Segmentationmentioning

confidence: 99%

“…This tool identifies and labels each vertebra in an automated process, followed by creating corresponding segmentation masks for each vertebra as well as its subregions. Furthermore, it adjusts for the used scanner, scanning parameters, and contrast media (if administered during imaging) to asynchronously convert measured HU into vBMD (43)(44)(45).…”

Section: Image Processing and Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Texture Analysis Using CT and Chemical Shift Encoding-Based Water-Fat MRI Can Improve Differentiation Between Patients With and Without Osteoporotic Vertebral Fractures

et al. 2022

Self Cite

View full text Add to dashboard Cite

PurposeOsteoporosis is a highly prevalent skeletal disease that frequently entails vertebral fractures. Areal bone mineral density (BMD) derived from dual-energy X-ray absorptiometry (DXA) is the reference standard, but has well-known limitations. Texture analysis can provide surrogate markers of tissue microstructure based on computed tomography (CT) or magnetic resonance imaging (MRI) data of the spine, thus potentially improving fracture risk estimation beyond areal BMD. However, it is largely unknown whether MRI-derived texture analysis can predict volumetric BMD (vBMD), or whether a model incorporating texture analysis based on CT and MRI may be capable of differentiating between patients with and without osteoporotic vertebral fractures.Materials and MethodsTwenty-six patients (15 females, median age: 73 years, 11 patients showing at least one osteoporotic vertebral fracture) who had CT and 3-Tesla chemical shift encoding-based water-fat MRI (CSE-MRI) available were analyzed. In total, 171 vertebral bodies of the thoracolumbar spine were segmented using an automatic convolutional neural network (CNN)-based framework, followed by extraction of integral and trabecular vBMD using CT data. For CSE-MRI, manual segmentation of vertebral bodies and consecutive extraction of the mean proton density fat fraction (PDFF) and T2* was performed. First-order, second-order, and higher-order texture features were derived from texture analysis using CT and CSE-MRI data. Stepwise multivariate linear regression models were computed using integral vBMD and fracture status as dependent variables.ResultsPatients with osteoporotic vertebral fractures showed significantly lower integral and trabecular vBMD when compared to patients without fractures (p<0.001). For the model with integral vBMD as the dependent variable, T2* combined with three PDFF-based texture features explained 40% of the variance (adjusted R2[Ra2] = 0.40; p<0.001). Furthermore, regarding the differentiation between patients with and without osteoporotic vertebral fractures, a model including texture features from CT and CSE-MRI data showed better performance than a model based on integral vBMD and PDFF only (Ra2 = 0.47 vs. Ra2 = 0.81; included texture features in the final model: integral vBMD, CT_Short-run_emphasis, CT_Varianceglobal, and PDFF_Variance).ConclusionUsing texture analysis for spine CT and CSE-MRI can facilitate the differentiation between patients with and without osteoporotic vertebral fractures, implicating that future fracture prediction in osteoporosis may be improved.

show abstract

Lumbar spine segmentation method based on deep learning

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Aiming at the difficulties of lumbar vertebrae segmentation in computed tomography (CT) images, we propose an automatic lumbar vertebrae segmentation method based on deep learning. The method mainly includes two parts: lumbar vertebra positioning and lumbar vertebrae segmentation. First of all, we propose a lumbar spine localization network of Unet network, which can directly locate the lumbar spine part in the image. Then, we propose a three-dimensional XUnet lumbar vertebrae segmentation method to achieve automatic lumbar vertebrae segmentation. The method proposed in this paper was validated on the lumbar spine CT images on the public dataset VerSe 2020 and our hospital dataset. Through qualitative comparison and quantitative analysis, the experimental results show that the method proposed in this paper can obtain good lumbar vertebrae segmentation performance, which can be further applied to detection of spinal anomalies and surgical treatment.

show abstract

VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images

Cited by 190 publications

References 75 publications

Feasibility of artificial intelligence–supported assessment of bone marrow infiltration using dual-energy computed tomography in patients with evidence of monoclonal protein — a retrospective observational study

Feasibility of artificial intelligence–supported assessment of bone marrow infiltration using dual-energy computed tomography in patients with evidence of monoclonal protein — a retrospective observational study

Texture Analysis Using CT and Chemical Shift Encoding-Based Water-Fat MRI Can Improve Differentiation Between Patients With and Without Osteoporotic Vertebral Fractures

Lumbar spine segmentation method based on deep learning

Contact Info

Product

Resources

About