Improved Productivity Using Deep Learning–assisted Reporting                     for Lumbar Spine MRI

Lim, Desmond Shi Wei; Makmur, Andrew; Zhu, Lei; Zhang, Wenqiao; Cheng, Amanda J L; Sia, David Soon Yiew; Eide, Sterling Ellis; Ong, Hean‐Yee; Jagmohan, Pooja; Tan, Wei; Khoo, Vanessa Meihui; Wong, Ying Mei; Thian, Yee Liang; Baskar, Sangeetha; Teo, Ee Chin; Algazwi, Diyaa Abdul Rauf; Yap, Qai Ven; Chan, Yiong Huak; Tan, Jiong Hao; Kumar, Naresh; Ooi, Beng Chin; Yoshioka, Hiroshi; Quek, Swee Tian; Hallinan, James Thomas Patrick Decourcy

doi:10.1148/radiol.220076

Cited by 21 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the aid of machine learning models, researchers develop ways of increasing the pace of reading imaging studies without compromising the quality, all the while reducing interobserver variability. For example, Lim et al [ 30 ] recently published a study that applied deep learning algorithms for lumbar spine MRI assessment, which reduced reading time and improved the consistency of the stenosis rating between radiologists.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning-Based Segmentation and Volume Calculation of Pediatric Lymphoma on Contrast-Enhanced Computed Tomographies

Klimont

Oronowicz-Jaśkowiak²,

Flieger³

et al. 2023

JPM

View full text Add to dashboard Cite

Lymphomas are the ninth most common malignant neoplasms as of 2020 and the most common blood malignancies in the developed world. There are multiple approaches to lymphoma staging and monitoring, but all of the currently available ones, generally based either on 2-dimensional measurements performed on CT scans or metabolic assessment on FDG PET/CT, have some disadvantages, including high inter- and intraobserver variability and lack of clear cut-off points. The aim of this paper was to present a novel approach to fully automated segmentation of thoracic lymphoma in pediatric patients. Manual segmentations of 30 CT scans from 30 different were prepared by the authors. nnU-Net, an open-source deep learning-based segmentation method, was used for the automatic segmentation. The highest Dice score achieved by the model was 0.81 (SD = 0.17) on the test set, which proves the potential feasibility of the method, albeit it must be underlined that studies on larger datasets and featuring external validation are required. The trained model, along with training and test data, is shared publicly to facilitate further research on the topic.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning-Based Segmentation and Volume Calculation of Pediatric Lymphoma on Contrast-Enhanced Computed Tomographies

Klimont

Oronowicz-Jaśkowiak²,

Flieger³

et al. 2023

JPM

View full text Add to dashboard Cite

show abstract

“…Using automated methods such as those based on deep learning (DL) can facilitate large-scale studies and help identify reliable insights from data with low human error, cost, and time. 21 DL has been successfully used in spine image analysis for automatic segmentation and classification. [22][23][24][25] It is shown that DL improves data processing efficiency with consistent results for lumbar spine magnetic resonance imaging (LSMRI).…”

mentioning

confidence: 99%

“…[22][23][24][25] It is shown that DL improves data processing efficiency with consistent results for lumbar spine magnetic resonance imaging (LSMRI). 21 This work aims to introduce a DL-based method that can reliably scale and eventually replace the time-consuming manual measurements of FJ angles using routine T2-weighted axial LSMRI. We hypothesize that FT can be an important clinical biomarker that may further explain LSD such as DD.…”

mentioning

confidence: 99%

“…Therefore, the studies can be constrained to a few hundred subjects, as it is time-consuming and requires relevant expertise to reliably measure the angles at different spine levels for large populations. Using automated methods such as those based on deep learning (DL) can facilitate large-scale studies and help identify reliable insights from data with low human error, cost, and time 21 …”

mentioning

confidence: 99%

“…DL has been successfully used in spine image analysis for automatic segmentation and classification 22–25 . It is shown that DL improves data processing efficiency with consistent results for lumbar spine magnetic resonance imaging (LSMRI) 21 . This work aims to introduce a DL-based method that can reliably scale and eventually replace the time-consuming manual measurements of FJ angles using routine T2-weighted axial LSMRI.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Semi-automatic Assessment of Facet Tropism from Lumbar Spine MRI using Deep Learning

Kowlagi,

Kemppainen,

Panfilov

et al. 2023

Spine

View full text Add to dashboard Cite

Study Design. This is a retrospective, cross-sectional, population-based study that automatically measured the Facet Joint angles from T2-weighted axial MRIs of the Lumbar Spine using deep learning. Objective. This work aimed to introduce a semi-automatic framework that measures the Facet Joint (FJ) angles using deep learning and study Facet Tropism (FT) in a large Finnish population-based cohort. Summary of Data. T2-weighted axial MRIs of the lumbar spine (L3/4 through L5/S1) for (n=1288) in the NFBC1966 Finnish population-based cohort were used for this study. Materials and Methods. A deep learning model was developed and trained on 430 participants’ MRI images. We computed FJ angles from the model’s prediction for each level, i.e., L3/4 through L5/S1, for the male and female subgroups. Inter and intra-rater reliability was analyzed for 60 participants using annotations made by two radiologists and a musculoskeletal researcher. With the developed method, we examined FT in the entire NFBC1966 cohort, adopting the literature definitions of FT thresholds at 7° and 10°. The rater agreement was evaluated both for the annotations and the FJ angles computed based on the annotations. FJ asymmetry ( - was used to evaluate the agreement and correlation between the raters. Bland-Altman (BA) analysis was used to assess the agreement and systemic bias in the FJ asymmetry. We used the Dice score as the metric to compare the annotations between the raters. We evaluated the model predictions on the independent test set and compared them against the ground truth annotations. Results. Our model scored Dice (92.7±0.1) and IoU (87.1±0.2) aggregated across all the regions of interest, i.e., Vertebral Body (VB), Facet Joints (FJ) and Posterior Arch (PA). The mean FJ angles measured for the male and female sub-groups were in agreement with the literature findings. Intra-rater reliability was high, with a Dice score of VB (97.3), FJ (82.5), and PA (90.3). The inter-rater reliability was better between the radiologists with a Dice score of VB (96.4), FJ (75.5), and PA (85.8) than between the radiologists and the musculoskeletal researcher. Prevalence of FT was higher in the male subgroup, with L4/5 found to be the most affected region. Conclusion. We developed a deep learning-based framework that enabled us to study FT in a large cohort. Using the proposed method, we present the prevalence of FT in a Finnish population-based cohort.

show abstract

A fully automatic MRI‐guided decision support system for lumbar disc herniation using machine learning

Zhang,

Du,

Shi

et al. 2024

JOR Spine

View full text Add to dashboard Cite

BackgroundNormalized decision support system for lumbar disc herniation (LDH) will improve reproducibility compared with subjective clinical diagnosis and treatment. Magnetic resonance imaging (MRI) plays an essential role in the evaluation of LDH. This study aimed to develop an MRI‐based decision support system for LDH, which evaluates lumbar discs in a reproducible, consistent, and reliable manner.MethodsThe research team proposed a system based on machine learning that was trained and tested by a large, manually labeled data set comprising 217 patients' MRI scans (3255 lumbar discs). The system analyzes the radiological features of identified discs to diagnose herniation and classifies discs by Pfirrmann grade and MSU classification. Based on the assessment, the system provides clinical advice.ResultsEventually, the accuracy of the diagnosis process reached 95.83%. An 83.5% agreement was observed between the system's prediction and the ground‐truth in the Pfirrmann grade. In the case of MSU classification, 95.0% precision was achieved. With the assistance of this system, the accuracy, interpretation efficiency and interrater agreement among surgeons were improved substantially.ConclusionThis system showed considerable accuracy and efficiency, and therefore could serve as an objective reference for the diagnosis and treatment procedure in clinical practice.

show abstract

Improved Productivity Using Deep Learning–assisted Reporting for Lumbar Spine MRI

Cited by 21 publications

References 20 publications

Deep Learning-Based Segmentation and Volume Calculation of Pediatric Lymphoma on Contrast-Enhanced Computed Tomographies

Deep Learning-Based Segmentation and Volume Calculation of Pediatric Lymphoma on Contrast-Enhanced Computed Tomographies

Semi-automatic Assessment of Facet Tropism from Lumbar Spine MRI using Deep Learning

A fully automatic MRI‐guided decision support system for lumbar disc herniation using machine learning

Contact Info

Product

Resources

About