RESUMO
BACKGROUND: To investigate the reproducibility of automated volumetric bone mineral density (vBMD) measurements from routine thoracoabdominal computed tomography (CT) assessed with segmentations by a convolutional neural network and automated correction of contrast phases, on diverse scanners, with scanner-specific asynchronous or scanner-agnostic calibrations. METHODS: We obtained 679 observations from 278 CT scans in 121 patients (77 males, 63.6%) studied from 04/2019 to 06/2020. Observations consisted of two vBMD measurements from Δdifferent reconstruction kernels (n = 169), Δcontrast phases (n = 133), scan Δsessions (n = 123), Δscanners (n = 63), or Δall of the aforementioned (n = 20), and observations lacking scanner-specific calibration (n = 171). Precision was assessed using root-mean-square error (RMSE) and root-mean-square coefficient of variation (RMSCV). Cross-measurement agreement was assessed using Bland-Altman plots; outliers within 95% confidence interval of the limits of agreement were reviewed. RESULTS: Repeated measurements from Δdifferent reconstruction kernels were highly precise (RMSE 3.0 mg/cm3; RMSCV 1.3%), even for consecutive scans with different Δcontrast phases (RMSCV 2.9%). Measurements from different Δscan sessions or Δscanners showed decreased precision (RMSCV 4.7% and 4.9%, respectively). Plot-review identified 12 outliers from different scan Δsessions, with signs of hydropic decompensation. Observations with Δall differences showed decreased precision compared to those lacking scanner-specific calibration (RMSCV 5.9 and 3.7, respectively). CONCLUSION: Automatic vBMD assessment from routine CT is precise across varying setups, when calibrated appropriately. Low precision was found in patients with signs of new or worsening hydropic decompensation, what should be considered an exclusion criterion for both opportunistic and dedicated quantitative CT. RELEVANCE STATEMENT: Automated CT-based vBMD measurements are precise in various scenarios, including cross-session and cross-scanner settings, and may therefore facilitate opportunistic screening for osteoporosis and surveillance of BMD in patients undergoing routine clinical CT scans. KEY POINTS: Artificial intelligence-based tools facilitate BMD measurements in routine clinical CT datasets. Automated BMD measurements are highly reproducible in various settings. Reliable, automated opportunistic osteoporosis diagnostics allow for large-scale application.
Assuntos
Densidade Óssea , Tomografia Computadorizada por Raios X , Humanos , Masculino , Tomografia Computadorizada por Raios X/métodos , Feminino , Reprodutibilidade dos Testes , Pessoa de Meia-Idade , Idoso , Adulto , Idoso de 80 Anos ou mais , Estudos Retrospectivos , Redes Neurais de ComputaçãoRESUMO
Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D-UNets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1w and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI additionally includes a lesion location annotation tool, labeling lesion location according to the 2017 McDonald criteria (periventricular, infratentorial, juxtacortical, subcortical). We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63-surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10mm3 and 100mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.
RESUMO
Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63-surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.
Assuntos
Aprendizado Profundo , Imageamento por Ressonância Magnética , Esclerose Múltipla , Substância Branca , Humanos , Esclerose Múltipla/diagnóstico por imagem , Esclerose Múltipla/patologia , Imageamento por Ressonância Magnética/métodos , Substância Branca/diagnóstico por imagem , Substância Branca/patologia , Encéfalo/diagnóstico por imagem , Encéfalo/patologia , Processamento de Imagem Assistida por Computador/métodos , Feminino , Neuroimagem/métodos , Neuroimagem/normas , Masculino , AdultoRESUMO
Background: To investigate reproducibility of texture features and volumetric bone mineral density (vBMD) extracted from trabecular bone in the thoracolumbar spine in routine clinical multi-detector computed tomography (MDCT) data in a single scanner environment. Methods: Patients who underwent two routine clinical thoraco-abdominal MDCT exams at a single scanner with a time interval of 6 to 26 months (n=203, 131 males; time interval mean, 13 months; median, 12 months) were included in this observational study. Exclusion criteria were metabolic and hematological disorders, bone metastases, use of bone-active medications, and history of osteoporotic vertebral fractures (VFs) or prior diagnosis of osteoporosis. A convolutional neural network (CNN)-based framework was used for automated spine labeling and segmentation (T5-L5), asynchronous Hounsfield unit (HU)-to-BMD calibration, and correction for the intravenous contrast medium phase. Vertebral vBMD and six texture features [varianceglobal, entropy, short-run emphasis (SRE), long-run emphasis (LRE), run-length non-uniformity (RLN), and run percentage (RP)] were extracted for mid- (T5-T8) and lower thoracic (T9-T12), and lumbar vertebrae (L1-L5), respectively. Relative annual changes were calculated in texture features and vBMD for each vertebral level and sorted by sex, and changes were checked for statistical significance (P<0.05) using paired t-tests. Root mean square coefficient of variation (RMSCV) and root mean square error (RMSE) were calculated as measures of variability. Results: SRE, LRE, RLN, and RP exhibited substantial reproducibility with RMSCV-values below 2%, for both sexes and at all spine levels, while vBMD was less reproducible (RMSCV =11.9-16.2%). Entropy showed highest variability (RMSCV =4.34-7.69%) due to statistically significant increases [range, mean ± standard deviation: (4.40±5.78)% to (8.36±8.66)%, P<0.001]. RMSCV of varianceglobal ranged from 1.60% to 3.03%. Conclusions: Opportunistic assessment of texture features in a single scanner environment using the presented CNN-based framework yields substantial reproducibility, outperforming vBMD reproducibility. Lowest scan-rescan variability was found for higher-order texture features. Further studies are warranted to determine, whether microarchitectural changes to the trabecular bone may be assessed through texture features.