Automated Spinal Midline Delineation on Biplanar X-Rays Using Mask R-CNN

Yang, Zixin; Skalli, Wafa; Vergari, Claudio; Angelini, Elsa D.; Gajny, Laurent

doi:10.1007/978-3-030-32040-9_32

Cited by 4 publications

(4 citation statements)

References 19 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current instance segmentation network mainly adds a Mask branch to the object detection network, such as Mask R-CNN [ 12 ], Blend Mask [ 13 ], and Hybrid Task Cascade [ 14 ]. Instance segmentation is applied to segment lung fields, heart, clavicles, and ribs in chest radiographs [ 38 , 39 ]; pelvis [ 40 ]; delineate spinal midline [ 41 ]; and to identify unknown bodies by tooth [ 42 ].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Accurate Instance Segmentation in Pediatric Elbow Radiographs

Wei

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

Radiography is an essential basis for the diagnosis of fractures. For the pediatric elbow joint diagnosis, the doctor needs to diagnose abnormalities based on the location and shape of each bone, which is a great challenge for AI algorithms when interpreting radiographs. Bone instance segmentation is an effective upstream task for automatic radiograph interpretation. Pediatric elbow bone instance segmentation is a process by which each bone is extracted separately from radiography. However, the arbitrary directions and the overlapping of bones pose issues for bone instance segmentation. In this paper, we design a detection-segmentation pipeline to tackle these problems by using rotational bounding boxes to detect bones and proposing a robust segmentation method. The proposed pipeline mainly contains three parts: (i) We use Faster R-CNN-style architecture to detect and locate bones. (ii) We adopt the Oriented Bounding Box (OBB) to improve the localizing accuracy. (iii) We design the Global-Local Fusion Segmentation Network to combine the global and local contexts of the overlapped bones. To verify the effectiveness of our proposal, we conduct experiments on our self-constructed dataset that contains 1274 well-annotated pediatric elbow radiographs. The qualitative and quantitative results indicate that the network significantly improves the performance of bone extraction. Our methodology has good potential for applying deep learning in the radiography’s bone instance segmentation.

show abstract

Section: Related Workmentioning

confidence: 99%

“…There are some papers comparing the performance of semantic segmentation and instance segmentation. The work in [ 41 ] finds that Mask R-CNN has higher accuracy in pelvis segmentation than U-Net. The work in [ 43 ] illustrates that instance segmentation methods are superior to semantic segmentation in tooth segmentation tasks.…”

Section: Related Workmentioning

confidence: 99%

Accurate Instance Segmentation in Pediatric Elbow Radiographs

Wei

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, the publication of several papers which used machine learning methods to automatically or semiautomatically extract parameters from biplanar radiographs of the spine (Galbusera et al, 2019;Gajny et al, 2019;Vergari et al, 2019;Aubert et al, 2019;Zhang and Li, 2019;Yang et al, 2019) demonstrated the rising interest in the topic and these novel techniques, as well as the need for automatizing a manual process which is time-consuming and relatively user-dependent (Somoskeöy et al, 2012;Bagheri et al, 2018). Our own deep learning tool (Galbusera et al, 2019) proved to be able to perform a fully automated 3D reconstruction of the spine shape as well as to estimate quantities such as spinopelvic parameters, kyphosis and lordosis angles, and coronal Cobb angle with perceptually convincing outcomes for a wide range of clinical scenarios including mild and severe deformities.…”

Section: Introductionmentioning

confidence: 99%

A fresh look at spinal alignment and deformities: Automated analysis of a large database of 9832 biplanar radiographs

Galbusera

Bassani

Panico

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

We developed and used a deep learning tool to process biplanar radiographs of 9,832 non-surgical patients suffering from spinal deformities, with the aim of reporting the statistical distribution of radiological parameters describing the spinal shape and the correlations and interdependencies between them. An existing tool able to automatically perform a three-dimensional reconstruction of the thoracolumbar spine has been improved and used to analyze a large set of biplanar radiographs of the trunk. For all patients, the following parameters were calculated: spinopelvic parameters; lumbar lordosis; mismatch between pelvic incidence and lumbar lordosis; thoracic kyphosis; maximal coronal Cobb angle; sagittal vertical axis; T1-pelvic angle; maximal vertebral rotation in the transverse plane. The radiological parameters describing the sagittal alignment were found to be highly interrelated with each other, as well as dependent on age, while sex had relatively minor but statistically significant importance. Lumbar lordosis was associated with thoracic kyphosis, pelvic incidence and sagittal vertical axis. The pelvic incidence-lumbar lordosis mismatch was found to be dependent on the pelvic incidence and on age. Scoliosis had a distinct association with the sagittal alignment in adolescent and adult subjects. The deep learning-based tool allowed for the analysis of a large imaging database which would not be reasonably feasible if performed by human operators. The large set of results will be valuable to trigger new research questions in the field of spinal deformities, as well as to challenge the current knowledge.

show abstract

“…Besides, applications of machine learning are not limited to radiographs but also extend to computerized tomography [13] and magnetic resonance imaging [14,15]. ment anatomical landmarks [2,3,6,7], the full geometry of the spine [8,9] or specific geometrical parameters, such as Cobb angle [10], lumbar lordosis [11] and sagittal verti-However, to the best of our knowledge, no work has been done to automatically detect scoliosis treatment (brace, implant or lack thereof) in postero-anterior radiographs. This information is of value either to develop automatic radiographic analysis tools, but it is usually not available in radiographs' DICOM metadata.…”

Section: Introductionmentioning

confidence: 99%

A convolutional neural network to detect scoliosis treatment in radiographs

2020

Self Cite

View full text Add to dashboard Cite

The aim of this work is to propose a classification algorithm to automatically detect treatment for scoliosis (brace, implant or no treatment) in postero-anterior radiographs. Such automatic labelling of radiographs could represent a step towards global automatic radiological analysis. Methods Seven hundred and ninety-six frontal radiographies of adolescents were collected (84 patients wearing a brace, 325 with a spinal implant and 387 reference images with no treatment). The dataset was augmented to a total of 2096 images. A classification model was built, composed by a forward convolutional neural network (CNN) followed by a discriminant analysis; the output was a probability for a given image to contain a brace, a spinal implant or none. The model was validated with a stratified tenfold cross-validation procedure. Performance was estimated by calculating the average accuracy. Results 98.3% of the radiographs were correctly classified as either reference, brace or implant, excluding 2.0% unclassified images. 99.7% of brace radiographs were correctly detected, while most of the errors occurred in the reference group (i.e. 2.1% of reference images were wrongly classified). Conclusion The proposed classification model, the originality of which is the coupling of a CNN with discriminant analysis, can be used to automatically label radiographs for the presence of scoliosis treatment. This information is usually missing from DICOM metadata, so such method could facilitate the use of large databases. Furthermore, the same model architecture could potentially be applied for other radiograph classifications, such as sex and presence of scoliotic deformity.

show abstract

Automated Spinal Midline Delineation on Biplanar X-Rays Using Mask R-CNN

Cited by 4 publications

References 19 publications

Accurate Instance Segmentation in Pediatric Elbow Radiographs

Accurate Instance Segmentation in Pediatric Elbow Radiographs

A fresh look at spinal alignment and deformities: Automated analysis of a large database of 9832 biplanar radiographs

A convolutional neural network to detect scoliosis treatment in radiographs

Contact Info

Product

Resources

About