Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines

Hwang, Eo‐Jin; Jung, Joon-Yong; Lee, Seul Ki; Lee, Sung‐Eun; Jee, Won-Hee

doi:10.1038/s41598-019-42579-y

Cited by 15 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It showed the Random Forest as the best model for prediction with measurements (accuracy: 83.1%; specificity 89.5%; positive predictive value: 88.0% and AUC: 90.2%). One slightly different retrospective study 34 in the field of medical imaging with 467 cases (training set: 360 and test set: 107) constructed SVM texture classifier model to see the feasibility of differentiating bone marrow with hematologic diseases. With the above-mentioned training set, the values of accuracy, sensitivity and specificity and AUC were 82.8%, 81.7%, 83.9% and 0.895 (p < 0.001) respectively.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data

Syed-Abdul

Firdani

Chung

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Cell Population Data (CPD) provides various blood cell parameters that can be used for differential diagnosis. Data analytics using Machine Learning (ML) have been playing a pivotal role in revolutionizing medical diagnostics. This research presents a novel approach of using ML algorithms for screening hematologic malignancies using CPD. The data collection was done at Konkuk University Medical Center, Seoul. A total of (882 cases: 457 hematologic malignancy and 425 hematologic nonmalignancy) were used for analysis. In our study, seven machine learning models, i.e., SGD, SVM, RF, DT, Linear model, Logistic regression, and ANN, were used. In order to measure the performance of our ML models, stratified 10-fold cross validation was performed, and metrics, such as accuracy, precision, recall, and AUC were used. We observed outstanding performance by the ANN model as compared to other ML models. The diagnostic ability of ANN achieved the highest accuracy, precision, recall, and AUC ± Standard Deviation as follows: 82.8%, 82.8%, 84.9%, and 93.5% ± 2.6 respectively. ANN algorithm based on CPD appeared to be an efficient aid for clinical laboratory screening of hematologic malignancies. Our results encourage further work of applying ML to wider field of clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data

Syed-Abdul

Firdani

Chung

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The same images were used to detect osteoporosis, but the highest AUC was only 0.810 [7]. Our predictive performance was also higher than the recent study of discriminating diseased bone marrows with a support vector machine texture classifier, which gave the AUC of 0.895 [20] and another study of differentiating bone marrow metastatic diseases with the highest AUC of 0.912 [9]. Building a radiomics model involved various steps of postprocessing, feature selection and applying an appropriate classifier.…”

Section: Discussionmentioning

confidence: 84%

Bone Marrow Radiomics of T1-Weighted Lumber Spinal MRI to Identify Diffuse Hematologic Marrow Diseases: Comparison With Human Readings

2020

Self Cite

View full text Add to dashboard Cite

We developed a radiomics model to differentiate hematologic marrow diseases and compared the performance with radiologists' readings and a quantitative measurement. Patients were retrospectively analyzed from the diseased (n = 254) and control groups (n = 230). A sagittal T1-weighted lumbar spinal MR image was normalized by an intervertebral disk, and bone marrow was segmented. A hundred features were extracted, and final features were selected using Principle Component Analysis (PCA) and least absolute shrinkage and selection operator (LASSO). Finally, Random forest (RF) and logistic regression (LR) models were trained. Two radiologists with different levels of experience analyzed the images for the presence of bone marrow diseases, independently. The area under the receiver operating characteristic curves (AUC) and decision curve analysis (DCA) was evaluated. Among the subjects, 363 cases were assigned as a training set and 121 as a validation set. The combination of LASSO and RF produced the best results. With the validation set, the sensitivity (SE) was 87.3%, specificity (SP) was 86.2% and AUC was 0.928 (p < 0.05). We selected Firstorder-Maximum as the best feature to identify diseased marrows, which achieved SE of 75.0% and AUC of 0.787 (p < 0.05). The reader with 11 years of experience yielded SE of 86.5% and AUC of 0.861 (p < 0.05). The second reader with 1 year of experience yielded SE of 75.0% and AUC of 0.767 (p < 0.05). We demonstrated the advantage of bone marrow radiomics over conventional methods of diagnosing with radiologists' readings and quantitative measurements.

show abstract

“…ML has been proposed for various applications in the context of spine imaging [39]. Promising results have been reported for the differential diagnosis of bone marrow infiltration and normal signal patterns in hematologic diseases [40]. Similarly, initial investigations have shown that radiomic signatures could help in the prediction of metastasis appearance in vertebral bodies [41].…”

Section: Discussionmentioning

confidence: 99%

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study

Chianca

Cuocolo

Gitto

et al. 2021

European Journal of Radiology

View full text Add to dashboard Cite

Spinal lesion differential diagnosis remains challenging even in MRI. Radiomics and machine learning (ML) have proven useful even in absence of a standardized data mining pipeline. We aimed to assess ML diagnostic performance in spinal lesion differential diagnosis, employing radiomic data extracted by different software. Methods: Patients undergoing MRI for a vertebral lesion were retrospectively analyzed (n = 146, 67 males, 79 females; mean age 63 ± 16 years, range 8-89 years) and constituted the train (n = 100) and internal test cohorts (n = 46). Part of the latter had additional prior exams which constituted a multi-scanner, external test cohort (n = 35). Lesions were labeled as benign or malignant (2-label classification), and benign, primary malignant or metastases (3-label classification) for classification analyses. Features extracted via 3D Slicer heterogeneityCAD module (hCAD) and PyRadiomics were independently used to compare different combinations of feature selection methods and ML classifiers (n = 19). Results: In total, 90 and 1548 features were extracted by hCAD and PyRadiomics, respectively. The best feature selection method-ML algorithm combination was selected by 10 iterations of 10-fold cross-validation in the training data. For the 2-label classification ML obtained 94% accuracy in the internal test cohort, using hCAD data, and 86% in the external one. For the 3-label classification, PyRadiomics data allowed for 80% and 69% accuracy in the internal and external test sets, respectively. Conclusions: MRI radiomics combined with ML may be useful in spinal lesion assessment. More robust preprocessing led to better consistency despite scanner and protocol heterogeneity.

show abstract

Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines

Cited by 15 publications

References 37 publications

Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data

Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data

Bone Marrow Radiomics of T1-Weighted Lumber Spinal MRI to Identify Diffuse Hematologic Marrow Diseases: Comparison With Human Readings

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study

Contact Info

Product

Resources

About