Search

Knee osteoarthritis (OA) is the most common musculoskeletal disease without a cure, and current treatment options are limited to symptomatic relief. Prediction of OA progression is a very challenging and timely issue, and it could, if resolved, accelerate the disease modifying drug development and ultimately help to prevent millions of total joint replacement surgeries performed annually. Here, we present a multi-modal machine learning-based OA progression prediction model that utilises raw radiographic data, clinical examination results and previous medical history of the patient. We validated this approach on an independent test set of 3,918 knee images from 2,129 subjects. Our method yielded area under the ROC curve (AUC) of 0.79 (0.78-0.81) and Average Precision (AP) of 0.68 (0.66-0.70). In contrast, a reference approach, based on logistic regression, yielded AUC of 0.75 (0.74-0.77) and AP of 0.62 (0.60-0.64). The proposed method could significantly improve the subject selection process for OA drug-development trials and help the development of personalised therapeutic plans.

Purpose: Patients with 1p/19q codeleted low-grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative MRI., Experimental Design: Preoperative brain MR images from 284 patients who had undergone biopsy or resection of presumed LGG were used to train a support vector machine algorithm. The algorithm was trained on the basis of features extracted from post-contrast T1-weighted and T2-weighted MR images and on patients' age and sex. The performance of the algorithm compared with tissue diagnosis was assessed on an external validation dataset of MR images from 129 patients with LGG from The Cancer Imaging Archive (TCIA). Four clinical experts also predicted the 1p/19q status of the TCIA MR images., Results: The algorithm achieved an AUC of 0.72 in the external validation dataset. The algorithm had a higher predictive performance than the average of the neurosurgeons (AUC 0.52) but lower than that of the neuroradiologists (AUC of 0.81). There was a wide variability between clinical experts (AUC 0.45-0.83)., Conclusions: Our results suggest that our algorithm can noninvasively predict the 1p/19q status of presumed LGG with a performance that on average outperformed the oncological neurosurgeons. Evaluation on an independent dataset indicates that our algorithm is robust and generalizable., (©2019 American Association for Cancer Research.)

Simple Summary: This study aims to improve the preoperative classification of nerve sheath tumors using radiomics, a method that extracts quantitative data from medical images. By analyzing MRI scans, we seek to develop a more accurate way to distinguish between different types of nerve sheath tumors before surgery. Our findings could lead to better treatment planning and outcomes for patients with these tumors. This research has the potential to enhance the diagnostic process and contribute to more personalized care for individuals with nerve sheath tumors, ultimately benefiting the medical community and patients alike. Malignant peripheral nerve sheath tumors (MPNSTs) are aggressive soft-tissue tumors prevalent in neurofibromatosis type 1 (NF1) patients, posing a significant risk of metastasis and recurrence. Current magnetic resonance imaging (MRI) imaging lacks decisiveness in distinguishing benign peripheral nerve sheath tumors (BPNSTs) and MPNSTs, necessitating invasive biopsies. This study aims to develop a radiomics model using quantitative imaging features and machine learning to distinguish MPNSTs from BPNSTs. Clinical data and MRIs from MPNST and BPNST patients (2000–2019) were collected at a tertiary sarcoma referral center. Lesions were manually and semi-automatically segmented on MRI scans, and radiomics features were extracted using the Workflow for Optimal Radiomics Classification (WORC) algorithm, employing automated machine learning. The evaluation was conducted using a 100× random-split cross-validation. A total of 35 MPNSTs and 74 BPNSTs were included. The T1-weighted (T1w) MRI radiomics model outperformed others with an area under the curve (AUC) of 0.71. The incorporation of additional MRI scans did not enhance performance. Combining T1w MRI with clinical features achieved an AUC of 0.74. Experienced radiologists achieved AUCs of 0.75 and 0.66, respectively. Radiomics based on T1w MRI scans and clinical features show some ability to distinguish MPNSTs from BPNSTs, potentially aiding in the management of these tumors. [ABSTRACT FROM AUTHOR]

Distinguishing malignant from benign liver lesions based on magnetic resonance imaging (MRI) is an important but often challenging task, especially in noncirrhotic livers. We developed and externally validated a radiomics model to quantitatively assess T2-weighted MRI to distinguish the most common malignant and benign primary solid liver lesions in noncirrhotic livers. Data sets were retrospectively collected from three tertiary referral centers (A, B, and C) between 2002 and 2018. Patients with malignant (hepatocellular carcinoma and intrahepatic cholangiocarcinoma) and benign (hepatocellular adenoma and focal nodular hyperplasia) lesions were included. A radiomics model based on T2-weighted MRI was developed in data set A using a combination of machine learning approaches. The model was internally evaluated on data set A through cross-validation, externally validated on data sets B and C, and compared to visual scoring of two experienced abdominal radiologists on data set C. The overall data set included 486 patients (A: 187, B: 98, and C: 201). The radiomics model had a mean area under the curve (AUC) of 0.78 upon internal validation on data set A and a similar AUC in external validation (B: 0.74 and C: 0.76). In data set C, the two radiologists showed moderate agreement (Cohen's κ: 0.61) and achieved AUCs of 0.86 and 0.82. Our T2-weighted MRI radiomics model shows potential for distinguishing malignant from benign primary solid liver lesions. External validation indicated that the model is generalizable despite substantial MRI acquisition protocol differences. Pending further optimization and generalization, this model may aid radiologists in improving the diagnostic workup of patients with liver lesions. [ABSTRACT FROM AUTHOR]

With the increasing size of datasets used in medical imaging research, the need for automated data curation is arising. One important data curation task is the structured organization of a dataset for preserving integrity and ensuring reusability. Therefore, we investigated whether this data organization step can be automated. To this end, we designed a convolutional neural network (CNN) that automatically recognizes eight different brain magnetic resonance imaging (MRI) scan types based on visual appearance. Thus, our method is unaffected by inconsistent or missing scan metadata. It can recognize pre-contrast T1-weighted (T1w),post-contrast T1-weighted (T1wC), T2-weighted (T2w), proton density-weighted (PDw) and derived maps (e.g. apparent diffusion coefficient and cerebral blood flow). In a first experiment,we used scans of subjects with brain tumors: 11065 scans of 719 subjects for training, and 2369 scans of 192 subjects for testing. The CNN achieved an overall accuracy of 98.7%. In a second experiment, we trained the CNN on all 13434 scans from the first experiment and tested it on 7227 scans of 1318 Alzheimer's subjects. Here, the CNN achieved an overall accuracy of 98.5%. In conclusion, our method can accurately predict scan type, and can quickly and automatically sort a brain MRI dataset virtually without the need for manual verification. In this way, our method can assist with properly organizing a dataset, which maximizes the shareability and integrity of the data. [ABSTRACT FROM AUTHOR]

• We evaluated grand challenges on machine learning and neuroimaging in dementia. • The seven challenges were complementary regarding clinical questions and tasks. • Statistical analysis of factors improving performance could improve future challenges. • Impact would increase by clinical questions and data beyond Alzheimer's disease. • Grand challenges provide an opportunity for cross-cohort performance evaluation. Machine learning methods exploiting multi-parametric biomarkers, especially based on neuroimaging, have huge potential to improve early diagnosis of dementia and to predict which individuals are at-risk of developing dementia. To benchmark algorithms in the field of machine learning and neuroimaging in dementia and assess their potential for use in clinical practice and clinical trials, seven grand challenges have been organized in the last decade: MIRIAD (2012), Alzheimer's Disease Big Data DREAM (2014), CADDementia (2014), Machine Learning Challenge (2014), MCI Neuroimaging (2017), TADPOLE (2017), and the Predictive Analytics Competition (2019). Based on two challenge evaluation frameworks, we analyzed how these grand challenges are complementing each other regarding research questions, datasets, validation approaches, results and impact. The seven grand challenges addressed questions related to screening, clinical status estimation, prediction and monitoring in (pre-clinical) dementia. There was little overlap in clinical questions, tasks and performance metrics. Whereas this aids providing insight on a broad range of questions, it also limits the validation of results across challenges. The validation process itself was mostly comparable between challenges, using similar methods for ensuring objective comparison, uncertainty estimation and statistical testing. In general, winning algorithms performed rigorous data pre-processing and combined a wide range of input features. Despite high state-of-the-art performances, most of the methods evaluated by the challenges are not clinically used. To increase impact, future challenges could pay more attention to statistical analysis of which factors (i.e., features, models) relate to higher performance, to clinical questions beyond Alzheimer's disease, and to using testing data beyond the Alzheimer's Disease Neuroimaging Initiative. Grand challenges would be an ideal venue for assessing the generalizability of algorithm performance to unseen data of other cohorts. Key for increasing impact in this way are larger testing data sizes, which could be reached by sharing algorithms rather than data to exploit data that cannot be shared. Given the potential and lessons learned in the past ten years, we are excited by the prospects of grand challenges in machine learning and neuroimaging for the next ten years and beyond. [ABSTRACT FROM AUTHOR]

Rationale and Objectives: The aim of this study was to automatically detect and quantify calcium lesions for the whole heart as well as per coronary artery on non-contrast-enhanced cardiac computed tomographic images. Materials and Methods: Imaging data from 366 patients were randomly selected from patients who underwent computed tomographic calcium scoring assessments between July 2004 and May 2009 at Erasmum MC, Rotterdam. These data included data sets with 1.5-mm and 3.0-mm slice spacing reconstructions and were acquired using four different scanners. The scores of manual observers, who annotated the data using commercially available software, served as ground truth. An automatic method for detecting and quantifying calcifications for each of the four main coronary arteries and the whole heart was trained on 209 data sets and tested on 157 data sets. Statistical testing included determining Pearson''s correlation coefficients and Bland-Altman analysis to compare performance between the system and ground truth. Wilcoxon''s signed-rank test was used to compare the interobserver variability to the system''s performance. Results: Automatic detection of calcified objects was achieved with sensitivity of 81.2% per calcified object in the 1.5-mm data set and sensitivity of 86.6% per calcified object in the 3.0-mm data set. The system made an average of 2.5 errors per patient in the 1.5-mm data set and 2.2 errors in the 3.0-mm data set. Pearson''s correlation coefficients of 0.97 (P < .001) for both 1.5-mm and 3.0-mm scans with respect to the calcium volume score of the whole heart were found. The average R values over Agatston, mass, and volume scores for each of the arteries (left circumflex coronary artery, right coronary artery, and left main and left anterior descending coronary arteries) were 0.93, 0.96, and 0.99, respectively, for the 1.5-mm scans. Similarly, for 3.0-mm scans, R values were 0.94, 0.94, and 0.99, respectively. Risk category assignment was correct in 95% and 89% of the data sets in the 1.5-mm and 3-mm scans. Conclusions: An automatic vessel-specific coronary artery calcium scoring system was developed, and its feasibility for calcium scoring in individual vessels and risk category classification has been demonstrated. [Copyright &y& Elsevier]

Patients with BRAF mutated (BRAF-mt) metastatic melanoma benefit significantly from treatment with BRAF inhibitors. Currently, the BRAF status is determined on archival tumor tissue or on fresh tumor tissue from an invasive biopsy. The aim of this study was to evaluate whether radiomics can predict the BRAF status in a non-invasive manner. Patients with melanoma lung metastases, known BRAF status, and a pretreatment computed tomography scan were included. After semi-automatic annotation of the lung lesions (maximum two per patient), 540 radiomics features were extracted. A chest radiologist scored all segmented lung lesions according to the Lung Image Database Consortium (LIDC) criteria. Univariate analysis was performed to assess the predictive value of each feature for BRAF mutation status. A combination of various machine learning methods was used to develop BRAF decision models based on the radiomics features and LIDC criteria. A total of 169 lung lesions from 103 patients (51 BRAF-mt; 52 BRAF wild type) were included. There were no features with a significant discriminative value in the univariate analysis. Models based on radiomics features and LIDC criteria both performed as poorly as guessing. Hence, the BRAF mutation status in melanoma lung metastases cannot be predicted using radiomics features or visually scored LIDC criteria. [ABSTRACT FROM AUTHOR]

Radiomics applied in MRI has shown promising results in classifying prostate cancer lesions. However, many papers describe single-center studies without external validation. The issues of using radiomics models on unseen data have not yet been sufficiently addressed. The aim of this study is to evaluate the generalizability of radiomics models for prostate cancer classification and to compare the performance of these models to the performance of radiologists. Multiparametric MRI, photographs and histology of radical prostatectomy specimens, and pathology reports of 107 patients were obtained from three healthcare centers in the Netherlands. By spatially correlating the MRI with histology, 204 lesions were identified. For each lesion, radiomics features were extracted from the MRI data. Radiomics models for discriminating high-grade (Gleason score ≥ 7) versus low-grade lesions were automatically generated using open-source machine learning software. The performance was tested both in a single-center setting through cross-validation and in a multi-center setting using the two unseen datasets as external validation. For comparison with clinical practice, a multi-center classifier was tested and compared with the Prostate Imaging Reporting and Data System version 2 (PIRADS v2) scoring performed by two expert radiologists. The three single-center models obtained a mean AUC of 0.75, which decreased to 0.54 when the model was applied to the external data, the radiologists obtained a mean AUC of 0.46. In the multi-center setting, the radiomics model obtained a mean AUC of 0.75 while the radiologists obtained a mean AUC of 0.47 on the same subset. While radiomics models have a decent performance when tested on data from the same center(s), they may show a significant drop in performance when applied to external data. On a multi-center dataset our radiomics model outperformed the radiologists, and thus, may represent a more accurate alternative for malignancy prediction. [ABSTRACT FROM AUTHOR]

Purpose: Diagnosing desmoid-type fibromatosis (DTF) requires an invasive tissue biopsy with β-catenin staining and CTNNB1 mutational analysis, and is challenging due to its rarity. The aim of this study was to evaluate radiomics for distinguishing DTF from soft tissue sarcomas (STS), and in DTF, for predicting the CTNNB1 mutation types.Methods: Patients with histologically confirmed extremity STS (non-DTF) or DTF and at least a pretreatment T1-weighted (T1w) MRI scan were retrospectively included. Tumors were semi-automatically annotated on the T1w scans, from which 411 features were extracted. Prediction models were created using a combination of various machine learning approaches. Evaluation was performed through a 100x random-split cross-validation. The model for DTF vs. non-DTF was compared to classification by two radiologists on a location matched subset.Results: The data included 203 patients (72 DTF, 131 STS). The T1w radiomics model showed a mean AUC of 0.79 on the full dataset. Addition of T2w or T1w post-contrast scans did not improve the performance. On the location matched cohort, the T1w model had a mean AUC of 0.88 while the radiologists had an AUC of 0.80 and 0.88, respectively. For the prediction of the CTNNB1 mutation types (S45 F, T41A and wild-type), the T1w model showed an AUC of 0.61, 0.56, and 0.74.Conclusions: Our radiomics model was able to distinguish DTF from STS with high accuracy similar to two radiologists, but was not able to predict the CTNNB1 mutation status. [ABSTRACT FROM AUTHOR]