Residual Block-based Multi-Label Classification and Localization Network with Integral Regression for Vertebrae Labeling

Qin, Chunli; Yao, Demin; Zhuang, Han; Wang, Hui; Shi, Yonghong; Song, Zhijian

doi:10.48550/arxiv.2001.00170

Cited by 3 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sekuboyina et al (2018) combine information across several 2D projections using a butterfly-like architecture and encode the local spine structure as an anatomic prior with an energy-based adversarial training. Liao et al (2018) and Qin et al (2020) develop a multi-label classification and localization network using FCN and residual blocks. They improve the classification branch with bidirectional recurrent neural network (Bi-RNN) to encode short and long range spatial and contextual information.…”

Section: Vertebrae Labellingmentioning

confidence: 99%

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

Meng,

Boyer,

Pujades

2021

Preprint

View full text Add to dashboard Cite

This paper considers the segmentation, identification and localization of vertebrae in CT images. Although these three tasks are related, they face specific problems that add up when they are addressed together. For example neighboring vertebrae with similar shapes perturb the identification and vertebrae with complex or even pathological morphologies impact the segmentation. Consequently, the three tasks tend to be approached independently, e.g. labelling (localization and identification) or segmenting only, or, when treated globally, a sequential strategy is used. Sequential methods however are prone to accumulate errors as they are not able to recover from mistakes of the previous module. In this work, we propose to combine all three tasks and leverage their interdependence : locations ease the segmentation, the segmentations in turn improve the locations and they all contribute and benefit from the identification task. To this purpose we propose a virtuous cycle to enforce coherence between the three tasks. Within such a cycle, the tasks interoperate and are iterated until a global consistency criterion is satisfied. Our experiments validate this strategy with anatomically coherent results that outperform the state of the art on the VerSe20 challenge benchmark. Our code and model are openly available for research purposes 1 .

show abstract

Section: Vertebrae Labellingmentioning

confidence: 99%

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

Meng,

Boyer,

Pujades

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Chen et al (2015) designed a joint model with a random forest classifier and CNN, improving the accuracy by a large margin compared to conventional methods. In more recent work, it has been recognized that the high intra-class similarity of vertebrae can strongly hinder accurate labeling (Liao et al 2018, Yang et al 2019, Chen et al 2020, Qin et al 2020. Local details of vertebrae appearance may be sufficient to distinguish vertebral regions (i.e.…”

Section: Introductionmentioning

confidence: 99%

“…Yang et al (2019) proposed a 3D U-Net-like architecture to process the 3D volume in an image-to-image manner, posing the detection problem as a multi-class segmentation problem, followed by a recurrent neural network (RNN) and refinement based on a shape dictionary to further refine the results. This combination of CNN and RNN has more recently been adopted by other investigators, including Liao et al (2018) and Qin et al (2020). While both methods utilize the RNN to incorporate contextual information from an extended length, the methods for vertebrae localization are different: the former utilizes a two-stage CNN and fully convolutional neural network (FCN), while the latter involves an end-to-end residual-block based network with integral regression for localization.…”

Section: Introductionmentioning

confidence: 99%

3D vertebrae labeling in spine CT: an accurate, memory-efficient (Ortho2D) framework

Huang¹,

Uneri²,

Jones³

et al. 2021

Phys. Med. Biol.

View full text Add to dashboard Cite

Purpose. Accurate localization and labeling of vertebrae in computed tomography (CT) is an important step toward more quantitative, automated diagnostic analysis and surgical planning. In this paper, we present a framework (called Ortho2D) for vertebral labeling in CT in a manner that is accurate and memory-efficient. Methods. Ortho2D uses two independent faster R-convolutional neural network networks to detect and classify vertebrae in orthogonal (sagittal and coronal) CT slices. The 2D detections are clustered in 3D to localize vertebrae centroids in the volumetric CT and classify the region (cervical, thoracic, lumbar, or sacral) and vertebral level. A post-process sorting method incorporates the confidence in network output to refine classifications and reduce outliers. Ortho2D was evaluated on a publicly available dataset containing 302 normal and pathological spine CT images with and without surgical instrumentation. Labeling accuracy and memory requirements were assessed in comparison to other recently reported methods. The memory efficiency of Ortho2D permitted extension to high-resolution CT to investigate the potential for further boosts to labeling performance. Results. Ortho2D achieved overall vertebrae detection accuracy of 97.1%, region identification accuracy of 94.3%, and individual vertebral level identification accuracy of 91.0%. The framework achieved 95.8% and 83.6% level identification accuracy in images without and with surgical instrumentation, respectively. Ortho2D met or exceeded the performance of previously reported 2D and 3D labeling methods and reduced memory consumption by a factor of ∼50 (at 1 mm voxel size) compared to a 3D U-Net, allowing extension to higher resolution datasets than normally afforded. The accuracy of level identification increased from 80.1% (for standard/low resolution CT) to 95.1% (for high-resolution CT). Conclusions. The Ortho2D method achieved vertebrae labeling performance that is comparable to other recently reported methods with significant reduction in memory consumption, permitting further performance boosts via application to high-resolution CT.

show abstract

Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization

Wang¹,

Zheng²,

Lü³

et al. 2020

Preprint

View full text Add to dashboard Cite

Accurate vertebra localization and identification are required in many clinical applications of spine disorder diagnosis and surgery planning. However, significant challenges are posed in this task by highly varying pathologies (such as vertebral compression fracture, scoliosis, and vertebral fixation) and imaging conditions (such as limited field of view and metal streak artifacts). This paper proposes a robust and accurate method that effectively exploits the anatomical knowledge of the spine to facilitate vertebra localization and identification. A key point localization model is trained to produce activation maps of vertebra centers. They are then re-sampled along the spine centerline to produce spine-rectified activation maps, which are further aggregated into 1-D activation signals. Following this, an anatomically-constrained optimization module is introduced to jointly search for the optimal vertebra centers under a soft constraint that regulates the distance between vertebrae and a hard constraint on the consecutive vertebra indices. When being evaluated on a major public benchmark of 302 highly pathological CT images, the proposed method reports the state of the art identification (id.) rate of 97.4%, and outperforms the best competing method of 94.7% id. rate by reducing the relative id. error rate by half.

show abstract

Residual Block-based Multi-Label Classification and Localization Network with Integral Regression for Vertebrae Labeling

Cited by 3 publications

References 29 publications

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

3D vertebrae labeling in spine CT: an accurate, memory-efficient (Ortho2D) framework

Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization

Contact Info

Product

Resources

About