Using Machine Learning to Identify Intravenous Contrast Phases on Computed Tomography

Muhamedrahimov, Raouf; Bar, Amir; Laserson, Jonathan; Akselrod-Ballin, Ayelet; Elnekave, Eldad

doi:10.1016/j.cmpb.2021.106603

Cited by 9 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This performance is consistent with previous studies exploring 2D architectures of four phase classification. 5,7,12 Similar to prior studies, 4,7 we found that only 15% of our dataset had informative phase descriptions in the DICOM header. This highlights the need for automated methods to annotate the phase of CT scans to aid in high quality dataset curation which is essential for deep learning algorithmic development.…”

Section: Discussionsupporting

confidence: 83%

See 1 more Smart Citation

Automated classification of intravenous contrast enhancement phase of CT scans using residual networks

Anand¹,

Liu²,

Shen³

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

Intravenous contrast enhancement phase information is important for computer-aided diagnosis of CT scans because the visual appearance of the scans varies substantially among the different phases. Although phase information could help to refine training data curation for downstream tasks, it is seldom included in the process of data augmentation for training a deep learning model. Unfortunately, in the current clinical settings, phase information is either unavailable or unreliable in most PACS systems. This motivates us to develop a method to automatically classify multiphase CT scans. In this study, a residual network (ResNet34) was utilized to classify five CT phases commonly used in the clinical environment: non-contrast, arterial, portal venous, nephrographic, and delayed contrast phases. A dataset of 395 multiphase CT scans was weakly labeled using keywords. The weakly-labeled dataset was split into 316 training, and 79 test CT scans. We compared the ResNet34 with two other popular classification models, VGG19 and DenseNet121. ResNet34 achieved the highest accuracy of 99%, while the accuracy of VGG19 and DenseNet121 were 97% and 95%, respectively. In addition, ResNet34 had fewer parameters to train in comparison with two other models, which could reduce the inference time to 35 seconds per scan and enhance generalizability of the model. High accuracy of multiphase classification suggests a potential way to improve data curation based on CT contrast enhancement phase. This would be useful to improve deep learning models by enhancing dataset curation and providing more realistic augmented data.

show abstract

Section: Discussionsupporting

confidence: 83%

“…3,4 It was expanded to predict four contrast phases including non-contrast, arterial, portal venous, and delayed later on. [5][6][7][8] This work extends the task to five phase classification through the addition of nephrographic phase. Our contributions are three-fold.…”

Section: Introductionmentioning

confidence: 99%

Automated classification of intravenous contrast enhancement phase of CT scans using residual networks

Anand¹,

Liu²,

Shen³

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

show abstract

“…Our F1-score (0.9852) was better than the one reported by Zhou et al 17 (0.977) and Dao et al 19 (0.9209). The achieved accuracy (0.9936) was also higher than the one reported by Tang et al 18 (0.93) and Muhamedrahimov et al 20 (0.933).…”

Section: Foldcontrasting

confidence: 51%

“…The evaluation of their algorithm on external datasets reported F1 scores of 0.7679 and 0.8694 on two manually annotated online databases. Muhamedrahimov et al 20 used CE-CT images and the time from injection as the ground truth to train a regression machine learning model to predict the time from injection. Then they used these times to classify images and reported an overall accuracy of 0.933 in classification.…”

Section: Introductionmentioning

confidence: 99%

Fully automated explainable abdominal CT contrast media phase classification using organ segmentation and machine learning

Salimi,

Mansouri,

Hajianfar

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundContrast‐enhanced computed tomography (CECT) provides much more information compared to non‐enhanced CT images, especially for the differentiation of malignancies, such as liver carcinomas. Contrast media injection phase information is usually missing on public datasets and not standardized in the clinic even in the same region and language. This is a barrier to effective use of available CECT images in clinical research.PurposeThe aim of this study is to detect contrast media injection phase from CT images by means of organ segmentation and machine learning algorithms.MethodsA total number of 2509 CT images split into four subsets of non‐contrast (class #0), arterial (class #1), venous (class #2), and delayed (class #3) after contrast media injection were collected from two CT scanners. Seven organs including the liver, spleen, heart, kidneys, lungs, urinary bladder, and aorta along with body contour masks were generated by pre‐trained deep learning algorithms. Subsequently, five first‐order statistical features including average, standard deviation, 10, 50, and 90 percentiles extracted from the above‐mentioned masks were fed to machine learning models after feature selection and reduction to classify the CT images in one of four above mentioned classes. A 10‐fold data split strategy was followed. The performance of our methodology was evaluated in terms of classification accuracy metrics.ResultsThe best performance was achieved by Boruta feature selection and RF model with average area under the curve of more than 0.999 and accuracy of 0.9936 averaged over four classes and 10 folds. Boruta feature selection selected all predictor features. The lowest classification was observed for class #2 (0.9888), which is already an excellent result. In the 10‐fold strategy, only 33 cases from 2509 cases (∼1.4%) were misclassified. The performance over all folds was consistent.ConclusionsWe developed a fast, accurate, reliable, and explainable methodology to classify contrast media phases which may be useful in data curation and annotation in big online datasets or local datasets with non‐standard or no series description. Our model containing two steps of deep learning and machine learning may help to exploit available datasets more effectively.

show abstract

“…This loss was necessary because the standard categorical cross-validation counts all the classification error as equal while in our task the errors between classes far from each other is more relevant and should therefore be more penalizing to the loss. We expect that the standard categorical cross-entropy can be directly used without loss of performance in case of a significant increase of the training set available (Muhamedrahimov et al, 2021 ; i.e., several thousand cases). We also showed that using a warm-up learning rate schedule we could stabilize the training in order to obtain models performance uniform across different folds.…”

Section: Discussionmentioning

confidence: 99%

Siamese model for collateral score prediction from computed tomography angiography images in acute ischemic stroke

Fortunati,

Su,

Wolff

et al. 2024

Front. Neuroimaging

View full text Add to dashboard Cite

IntroductionImaging biomarkers, such as the collateral score as determined from Computed Tomography Angiography (CTA) images, play a role in treatment decision making for acute stroke patients. In this manuscript, we present an end-to-end learning approach for automatic determination of a collateral score from a CTA image. Our aim was to investigate whether such end-to-end learning approaches can be used for this classification task, and whether the resulting classification can be used in existing outcome prediction models.MethodsThe method consists of a preprocessing step, where the CTA image is aligned to an atlas and divided in the two hemispheres: the affected side and the healthy side. Subsequently, a VoxResNet based convolutional neural network is used to extract features at various resolutions from the input images. This is done by using a Siamese model, such that the classification is driven by the comparison between the affected and healthy using a unique set of features for both hemispheres. After masking the resulting features for both sides with the vascular region and global average pooling (per hemisphere) and concatenation of the resulting features, a fully connected layer is used to determine the categorized collateral score.ExperimentsSeveral experiments have been performed to optimize the model hyperparameters and training procedure, and to validate the final model performance. The hyperparameter optimization and subsequent model training was done using CTA images from the MR CLEAN Registry, a Dutch multi-center multi-vendor registry of acute stroke patients that underwent endovascular treatment. A separate set of images, from the MR CLEAN Trial, served as an external validation set, where collateral scoring was assessed and compared with both human observers and a recent more traditional model. In addition, the automated collateral scores have been used in an existing functional outcome prediction model that uses both imaging and non-imaging clinical parameters.ConclusionThe results show that end-to-end learning of collateral scoring in CTA images is feasible, and does perform similar to more traditional methods, and the performance also is within the inter-observer variation. Furthermore, the results demonstrate that the end-to-end classification results also can be used in an existing functional outcome prediction model.

show abstract

Using Machine Learning to Identify Intravenous Contrast Phases on Computed Tomography

Cited by 9 publications

References 27 publications

Automated classification of intravenous contrast enhancement phase of CT scans using residual networks

Automated classification of intravenous contrast enhancement phase of CT scans using residual networks

Fully automated explainable abdominal CT contrast media phase classification using organ segmentation and machine learning

Siamese model for collateral score prediction from computed tomography angiography images in acute ischemic stroke

Contact Info

Product

Resources

About