Image-based modelling for Adolescent Idiopathic Scoliosis: Mechanistic machine learning analysis and prediction

Tajdari, Mahsa; Pawar, Aishwarya; Li, Hengyang; Tajdari, Farzam; Maqsood, Ayesha; Cleary, Emmett; Saha, Sourav; Zhang, Yongjie; Sarwark, John F.; Liu, Wing Kam

doi:10.1016/j.cma.2020.113590

Cited by 49 publications

(36 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning such as convolutional neural networks has emerged as a powerful technique for medical image analysis and achieved promising performance in various clinical applications 31 – 33 . Future development of advanced deep learning techniques including physics-reinforced or physics-award algorithms 34 – 36 that can lead to further improvement for more reliable automated tumor segmentation 37 , which will allow consistent identification of imaging subtypes defined here.…”

Section: Discussionmentioning

confidence: 99%

Radiological tumour classification across imaging modality and histology

Gensheimer

et al. 2021

Nat Mach Intell

View full text Add to dashboard Cite

Radiomics refers to the high-throughput extraction of quantitative features from radiological scans and is widely used to search for imaging biomarkers for prediction of clinical outcomes. Current radiomic signatures suffer from limited reproducibility and generalizability, because most features are dependent on imaging modality and tumor histology, making them sensitive to variations in scan protocol. Here, we propose novel radiological features that are specially designed to ensure compatibility across diverse tissues and imaging contrast. These features provide systematic characterization of tumor morphology and spatial heterogeneity. In an international multi-institution study of 1,682 patients, we discover and validate four unifying imaging subtypes across three malignancies and two major imaging modalities. These tumor subtypes demonstrate distinct molecular characteristics and prognoses after conventional therapies. In advanced lung cancer treated with immunotherapy, one subtype is associated with improved survival and increased tumor-infiltrating lymphocytes compared with the others. Deep learning enables automatic tumor segmentation and reproducible subtype identification, which can facilitate practical implementation. The unifying radiological tumor classification may inform prognosis and treatment response for precision medicine.

show abstract

Section: Discussionmentioning

confidence: 99%

Radiological tumour classification across imaging modality and histology

Gensheimer

et al. 2021

Nat Mach Intell

View full text Add to dashboard Cite

show abstract

“…Though it was successfully applied in many applications, e.g. gender scoring [6], statistical shape modeling [7], computer vision [8], multimedia applications [9], human-computer interactions [10], 3D deformation of the human spinal column detection [11], image face alignment [12], and 3D human body analysis [13], the non-rigid registration is a non-trivial and ill-defined problem with a high number of degrees-offreedom (DOFs). Accordingly, there are many challenges for preserving features of the source surface in the design and implementation of a non-rigid ICP registration algorithm [14], where the features account for salient geometric features which form compound higher-level descriptors.…”

Section: Introductionmentioning

confidence: 99%

Feature Preserving Non-Rigid Iterative Weighted Closest Point and Semi-Curvature Registration

Tajdari

Huysmans

Yang

et al. 2022

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

“…In most participants with relatively low angle deformation (<25°) of the spine, CDSSs without nonionized radiation diagnostic devices have emerged as appropriate screening diagnostic tools in the coronal plane of the spine. Recently, several studies for scoliosis screening have used deep learning and machine learning to predict curve progression and curvature classi cation that uses comparative images of scoliosis and normal spine curvature with training dataset [22,23]. CDSS studies are highly useful for early detection of AIS.…”

Section: Introductionmentioning

confidence: 99%

Conformity assessment of a computer vision-based clinical decision support system for the detection of postural spinal deformity

Sohn

Kim

2022

Preprint

View full text Add to dashboard Cite

Background: This study evaluates the conformity of using a computer vision-based posture analysis system as a screening assessment for postural deformity detection in spine that is easily applicable to clinical practice.Methods: One hundred forty participants were enrolled for screening of the postural deformation. Factors that determine the presence or absence of spinal deformation, such as shoulder height difference (SHD), pelvic height difference (PHD), and leg length mismatch (LLD), were used as parameters for the clinical decision support system (CDSS) using a commercial computer vision-based posture analysis system. For conformity analysis, the probability of postural deformation provided by CDSS, the Cobb angle, the PHD, and the SHD were compared and analyzed between the system and radiographic parameters. A principal component analysis (PCA) of the CDSS and correlation analysis were conducted.Results: The Cobb angles of the 140 participants ranged from 0° to 61°, with an average of 6.16° ± 8.50°. The postural deformation of CDSS showed 94% conformity correlated with radiographic assessment. The participants of postural deformation with normal (0-9°) and mild (10-25°) range of scoliosis were more accurate in conformity assessment result (98.57%). The referenced SHD and the SHD of the CDSS showed statistical significance (p < 0.001) on a paired t-test. SHD and PHD for PCA were the predominant factors (PC1 SHD for 79.97%, PC2 PHD for 19.86%).Conclusion: The CDSS showed 94% conformity for the screening of postural spinal deformity. The main factors determining diagnostic suitability were analyzed as two main variables: SHD and PHD. In conclusion, a computer vision-based posture analysis system can be utilized as a safe, efficient and convenient CDSS for early diagnosis of spinal posture deformation, including scoliosis.

show abstract

Image-based modelling for Adolescent Idiopathic Scoliosis: Mechanistic machine learning analysis and prediction

Cited by 49 publications

References 52 publications

Radiological tumour classification across imaging modality and histology

Radiological tumour classification across imaging modality and histology

Feature Preserving Non-Rigid Iterative Weighted Closest Point and Semi-Curvature Registration

Conformity assessment of a computer vision-based clinical decision support system for the detection of postural spinal deformity

Contact Info

Product

Resources

About