Applying Quantitative Radiographic Image Markers to Predict Clinical Complications After Aneurysmal Subarachnoid Hemorrhage: A Pilot Study

Danala, Gopichandh; Desai, M.N.; Ray, Bappaditya; Heidari, Morteza; Maryada, Sai Kiran R.; Prodan, Călin I.

doi:10.1007/s10439-022-02926-z

Cited by 6 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4. Machine learning based computer-aided diagnosis (CAD) tools has great potential in medical imaging applications and have been widely investigated [10][11][12][13][14][15][16][17]. Although many different types of deep learning models have been investigated and developed in previous studies for segmentation tasks, as a proof-of-concept study, we selected one of the most popular segmentation models: U-Net [18].…”

Section: Methodsmentioning

confidence: 99%

Deep learning-based rectum segmentation on low-field prostate MRI to assist image-guided biopsy

Pham

Sadinski

et al. 2023

Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling

Self Cite

View full text Add to dashboard Cite

Efficient and accurate segmentation of the rectum in images acquired with a low-field (58-74mT), prostate Magnetic Resonance Imaging (MRI) scanner may be advantageous for MRI-guided prostate biopsy and focal treatment guidance. However, automated rectum segmentation on low-field MRI images is challenging due to spatial resolution and signalto-noise ratio (SNR) constraints. This study aims to develop a deep learning model to automatically segment the rectum in a low-field MRI prostate image. 132, 3D images from 10 patients were assembled. A 3D, U-Net model with the input matrix size 120×120×40 voxels was trained to detect and segment the rectum. The 3D U-Net can learn and integrate the relative information between adjacent MRI slices, which can enforce 3D patterns such as rectal wall smoothness and thus compensate for slice-to-slice variability in SNR and rectal boundary fuzziness [0]. Contrast stretching, histogram equalization, and brightness enhancement were also investigated and applied to normalize intra-and inter-image intensity heterogeneity. Data augmentation methods such as elastic deformation, flipping, rotation, and scaling were also applied to reduce the risk of overfitting in model training. The model was trained and tested using a 4-fold crossvalidation method with 3:1:2 split for training, validation, and testing. Study results show that the mean intersection over union score (IOUs) is 0.63 for the rectum on the testing dataset. Additionally, visual examination suggests that the displacement between the centroids of the ground truth and inferred volumetric segmentations is less than 3mm. Thus, this study demonstrates that (1) a 3D U-Net model can effectively segment the rectum on low-field MRI scans and (2) applying image processing and data augmentation can boost model performance.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep learning-based rectum segmentation on low-field prostate MRI to assist image-guided biopsy

Pham

Sadinski

et al. 2023

Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our previous pilot study, we developed a Computer-Aided Diagnosis (CAD) system primarily focusing on generating radiographic image markers related to sulcal volume for addressing post-aSAH complications. The study's results show promise, highlighting the system's capability to predict both shortterm and long-term clinical complications in patients with aSAH [7], surpassing models based on other biomarkers that can only predict selective prognoses [8]. In the current study, we are expanding on these efforts by developing an imaging biomarker based on blood volume in the ventricular and cisternal spaces.…”

Section: Introductionmentioning

confidence: 96%

Evaluation of deep learning frameworks coupled with an interactive user interface to predict clinical complications after aneurysmal subarachnoid hemorrhage

Faiz,

Danala,

Ray

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

Accurately predicting the clinical outcome of patients with aneurysmal subarachnoid hemorrhage (aSAH) presents notable challenges. This study sought to develop and assess a computer-aided detection (CAD) scheme employing a deep-learning classification architecture, utilizing brain computed tomography (CT) images to forecast aSAH patients' prognosis. A retrospective dataset encompassing 60 aSAH patients was collated, each with two CT images acquired upon admission and after 10-14 days of admission. The existing CAD scheme was utilized for preprocessing and data curation based on the presence of blood clot in the cisternal spaces. Two pre-trained architectures, DenseNet-121 and VGG16, were chosen as convolutional bases for feature extraction. The Convolution Based Attention Module (CBAM) was introduced atop the pre-trained architecture to enhance focus learning. Employing five-fold crossvalidation, the developed prediction model assessed three clinical outcomes following aSAH, and its performance was evaluated using multiple metrics. A comparison was conducted to analyze the impact of CBAM. The prediction model trained using CT images acquired at admission demonstrated higher accuracy in predicting short-term clinical outcomes. Conversely, the model trained using CT images acquired on 10/14 days accurately predicted long-term clinical outcomes. Notably, for short-term outcomes, high sensitivity performances (0.87 and 0.83) were reported from the first scan, while the sensitivity of (0.65 and 0.75) was reported from the last scan, showcasing the viability of predicting the prognosis of aSAH patients using novel deep learning-based quantitative image markers. The study demonstrated the potential of integrating deep-learning architecture with attention mechanisms to optimize predictive capabilities in identifying clinical complications among patients with aSAH.

show abstract

“…However, reading and interpreting medical images by clinicians is a difficult and time-consuming task which results in large intra-and interobserver variability [2]. To assist clinicians to more accurately read and diagnose medical images with less variability, many computer-aided detection and diagnosis (CAD) schemes for medical images have been developed in the last two decades for a variety of applications including identifying quantitative image markers, detecting diseases, classifying disease types or severities, and predicting disease prognosis or response to treatment [3][4][5][6][7][8][9]. Despite significant progress in developing CAD schemes of medical images, accurate segmentation of medical images and identification or selection of effectively handcrafted image features to train traditional machine learning classifiers remains difficult and not robust.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Synthetic Data Generation Algorithm to Improve Efficacy of Deep Learning Models of Medical Images

Maryada

Booker²,

Danala

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep Convolutional Neural Networks (DCNNs) have emerged as powerful components of computer-aided systems to detect and classify diseases in medical images. In order to robustly achieve high performance, a large and diverse dataset with annotated images is required to train or fine-tune DCNNs. However, such datasets are often very difficult and/or expensive to obtain due to demands on clinicians’ time and inter-reader variability. To address these challenges and increase training dataset size, we propose an efficient multi-stage algorithm to generate synthetic medical image data by extracting annotated diseased regions and randomly projecting them onto disease-free images. To test the feasibility of this new algorithm, the publicly available Indian Diabetic Retinopathy Image Dataset (IDRiD) is used. This dataset is comprised of the annotated fundus images acquired from 81 patients with two categories of diseases. Among them, 54 and 27 images are used for training and testing images, respectively. Using the proposed algorithm, we generate synthetic data by inserting extracted diseased lesions onto another set of 60 disease-free images, which results in 7,902 and 6,786 images for the two categories of diseases, respectively. Three transfer-learning-based DCNN models (VGG16, ResNet50, and Inception-v3) are trained using original IDRiD images and synthetic dataset, respectively. When applied to the same test images, the model trained with the synthetic dataset outperformed the model trained using he original IDRiD dataset by 7.4% in disease classification. These results indicate that this simple algorithm can generate diverse and useful synthetic lesion data to improve performance of DCNN models.

show abstract

Applying Quantitative Radiographic Image Markers to Predict Clinical Complications After Aneurysmal Subarachnoid Hemorrhage: A Pilot Study

Cited by 6 publications

References 24 publications

Deep learning-based rectum segmentation on low-field prostate MRI to assist image-guided biopsy

Deep learning-based rectum segmentation on low-field prostate MRI to assist image-guided biopsy

Evaluation of deep learning frameworks coupled with an interactive user interface to predict clinical complications after aneurysmal subarachnoid hemorrhage

An Efficient Synthetic Data Generation Algorithm to Improve Efficacy of Deep Learning Models of Medical Images

Contact Info

Product

Resources

About