Haleh Akrami
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Haleh Akrami has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Richard M. Leahy
Department of Electrical and Computer Engineering University of Southern California Los Angeles 90089 CA USA
10 shared publications - Anand A. Joshi
Ming Hsieh Department of Electrical and Computer Engineering Viterbi School of Engineering, University of Southern California Los Angeles California USA
8 shared publications - Sergul Aydore
Amazon Web Services
4 shared publications - Andrei Irimia
Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, USA
3 shared publications - Jian Li
Center for Neurotechnology and Neurorecovery, Department of Neurology, Massachusetts General Hospital
2 shared publications - Omar Zamzam
Department of Electrical and Computer Engineering University of Southern California Los Angeles 90089 CA USA
2 shared publications
Latest Publications
- Open Access
Modeling and Reversing Brain Lesions Using Diffusion Models
Brain lesions are abnormalities or injuries in brain tissue that are often detectable using magnetic resonance imaging (MRI), which reveals structural changes in the affected areas. This broad definition of brain lesions includes areas of the brain that are irreversibly damaged, as well as areas of brain tissue that are deformed as a result of lesion growth or swelling. Despite the importance of differentiating between damaged and deformed tissue, existing lesion segmentation methods overlook this distinction, labeling both of them as a single anomaly. In this work, we introduce a diffusion model-based framework for analyzing and reversing the brain lesion process. Our pipeline first segments abnormal regions in the brain, then estimates and reverses tissue deformations by restoring displaced tissue to its original position, isolating the core lesion area representing the initial damage. Finally, we inpaint the core lesion area to arrive at an estimation of the pre-lesion healthy brain. This proposed framework reverses a forward lesion growth process model that is well-established in biomechanical studies that model brain lesions. Our results demonstrate improved accuracy in lesion segmentation, characterization, and brain labeling compared to traditional methods, offering a robust tool for clinical and research applications in brain lesion analysis. Since pre-lesion healthy versions of abnormal brains are not available in any public dataset for validation of the reverse process, we simulate a forward model to synthesize multiple lesioned brain images.
Open AccessModeling and Reversing Brain Lesions Using Diffusion Models
Brain lesions are abnormalities or injuries in brain tissue that are often detectable using magnetic resonance imaging (MRI), which reveals structural changes in the affected areas. This broad definition of brain lesions includes areas of the brain that are irreversibly damaged, as well as areas of brain tissue that are deformed as a result of lesion growth or swelling. Despite the importance of differentiating between damaged and deformed tissue, existing lesion segmentation methods overlook this distinction, labeling both of them as a single anomaly. In this work, we introduce a diffusion model-based framework for analyzing and reversing the brain lesion process. Our pipeline first segments abnormal regions in the brain, then estimates and reverses tissue deformations by restoring displaced tissue to its original position, isolating the core lesion area representing the initial damage. Finally, we inpaint the core lesion area to arrive at an estimation of the pre-lesion healthy brain. This proposed framework reverses a forward lesion growth process model that is well-established in biomechanical studies that model brain lesions. Our results demonstrate improved accuracy in lesion segmentation, characterization, and brain labeling compared to traditional methods, offering a robust tool for clinical and research applications in brain lesion analysis. Since pre-lesion healthy versions of abnormal brains are not available in any public dataset for validation of the reverse process, we simulate a forward model to synthesize multiple lesioned brain images.
- Open Access
Prediction of Post Traumatic Epilepsy using MRI-based Imaging Markers
Post-traumatic Epilepsy (PTE) is a debilitating neurological disorder that develops after traumatic brain injury (TBI). Despite the high prevalence of PTE, current methods for predicting its occurrence remain limited. In this study, we aimed to identify imaging-based markers for the prediction of PTE using machine learning. Specifically, we examined three imaging features: lesion volumes and resting-state fMRI-based measures of functional connectivity and amplitude of low-frequency fluctuation (ALFF). We employed three machine learning methods, namely, kernel support vector machine (KSVM), random forest, and a neural network, to develop predictive models. Our results showed that the KSVM classifier, with all three feature types as input, achieved the best prediction accuracy of 0.78 AUC (Area Under the Receiver Operating Characteristic (ROC) curve) using nested cross-validation. Furthermore, we performed voxel-wise and lobe-wise group difference analyses to investigate the specific brain regions and features that the model found to be most helpful in distinguishing PTE from non-PTE populations. Our statistical analysis uncovered significant differences in bilateral temporal lobes and cerebellum between PTE and non-PTE groups. Overall, our findings demonstrate the complementary prognostic value of MR-based markers in PTE prediction and provide new insights into the underlying structural and functional alterations associated with PTE.
Open AccessPrediction of Post Traumatic Epilepsy using MRI-based Imaging Markers
Post-traumatic Epilepsy (PTE) is a debilitating neurological disorder that develops after traumatic brain injury (TBI). Despite the high prevalence of PTE, current methods for predicting its occurrence remain limited. In this study, we aimed to identify imaging-based markers for the prediction of PTE using machine learning. Specifically, we examined three imaging features: lesion volumes and resting-state fMRI-based measures of functional connectivity and amplitude of low-frequency fluctuation (ALFF). We employed three machine learning methods, namely, kernel support vector machine (KSVM), random forest, and a neural network, to develop predictive models. Our results showed that the KSVM classifier, with all three feature types as input, achieved the best prediction accuracy of 0.78 AUC (Area Under the Receiver Operating Characteristic (ROC) curve) using nested cross-validation. Furthermore, we performed voxel-wise and lobe-wise group difference analyses to investigate the specific brain regions and features that the model found to be most helpful in distinguishing PTE from non-PTE populations. Our statistical analysis uncovered significant differences in bilateral temporal lobes and cerebellum between PTE and non-PTE groups. Overall, our findings demonstrate the complementary prognostic value of MR-based markers in PTE prediction and provide new insights into the underlying structural and functional alterations associated with PTE.
- Open Access
Learning A Disentangling Representation For PU Learning
In this paper, we address the problem of learning a binary (positive vs. negative) classifier given Positive and Unlabeled data commonly referred to as PU learning. Although rudimentary techniques like clustering, out-of-distribution detection, or positive density estimation can be used to solve the problem in low-dimensional settings, their efficacy progressively deteriorates with higher dimensions due to the increasing complexities in the data distribution. In this paper we propose to learn a neural network-based data representation using a loss function that can be used to project the unlabeled data into two (positive and negative) clusters that can be easily identified using simple clustering techniques, effectively emulating the phenomenon observed in low-dimensional settings. We adopt a vector quantization technique for the learned representations to amplify the separation between the learned unlabeled data clusters. We conduct experiments on simulated PU data that demonstrate the improved performance of our proposed method compared to the current state-of-the-art approaches. We also provide some theoretical justification for our two cluster-based approach and our algorithmic choices.
Open AccessLearning A Disentangling Representation For PU Learning
In this paper, we address the problem of learning a binary (positive vs. negative) classifier given Positive and Unlabeled data commonly referred to as PU learning. Although rudimentary techniques like clustering, out-of-distribution detection, or positive density estimation can be used to solve the problem in low-dimensional settings, their efficacy progressively deteriorates with higher dimensions due to the increasing complexities in the data distribution. In this paper we propose to learn a neural network-based data representation using a loss function that can be used to project the unlabeled data into two (positive and negative) clusters that can be easily identified using simple clustering techniques, effectively emulating the phenomenon observed in low-dimensional settings. We adopt a vector quantization technique for the learned representations to amplify the separation between the learned unlabeled data clusters. We conduct experiments on simulated PU data that demonstrate the improved performance of our proposed method compared to the current state-of-the-art approaches. We also provide some theoretical justification for our two cluster-based approach and our algorithmic choices.
- Open Access
- 4 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Speech MOS Multi-Task Learning and Rater Bias Correction
Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the quality of a speech sample. Recently, there has been increasing research interest in developing models for estimating MOS blindly. Here we propose a multitask framework to include additional labels and data in training to improve the performance of a blind MOS estimation model. Experimental results indicate that the proposed model can be trained to jointly estimate MOS, reverberation time (T60), and clarity (C50) by combining two disjoint data sets in training, one containing only MOS labels and the other containing only T60 and C50 labels. Furthermore, we use a semi-supervised framework to combine two MOS data sets in training, one containing only MOS labels (per ITU-T Recommendation P.808), and the other containing separate scores for speech signal, background noise, and overall quality (per ITU-T Recommendation P.835). Finally, we present preliminary results for addressing individual rater bias in the MOS labels.
- 4 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Open AccessSpeech MOS Multi-Task Learning and Rater Bias Correction
Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the quality of a speech sample. Recently, there has been increasing research interest in developing models for estimating MOS blindly. Here we propose a multitask framework to include additional labels and data in training to improve the performance of a blind MOS estimation model. Experimental results indicate that the proposed model can be trained to jointly estimate MOS, reverberation time (T60), and clarity (C50) by combining two disjoint data sets in training, one containing only MOS labels and the other containing only T60 and C50 labels. Furthermore, we use a semi-supervised framework to combine two MOS data sets in training, one containing only MOS labels (per ITU-T Recommendation P.808), and the other containing separate scores for speech signal, background noise, and overall quality (per ITU-T Recommendation P.835). Finally, we present preliminary results for addressing individual rater bias in the MOS labels.
- Open Access
- 4 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 16, 1-5
Learning From Positive and Unlabeled Data Using Observer-GAN
In the case of learning from positive and unlabeled data, the input data consist of (1) observations from the positive class and their corresponding labels and (2) unlabeled observations from both positive and negative classes. Generative Adversarial Networks (GANs) have been used to reduce the problem to the supervised setting with the advantage that supervised learning has state-of-the-art accuracy in classification tasks. In order to generate pseudo-negative observations, GANs are trained on positive and unlabeled observations with a modified loss. Using both positive and pseudo-negative observations leads to a supervised learning setting. The generation of pseudo-negative observations that are realistic enough to replace missing negative class samples is a bottleneck for current GAN-based algorithms. By including an additional classifier into the GAN architecture, we describe a novel GAN-based approach. The GAN discriminator instructs the generator to only produce samples that fall into the unlabeled data distribution, while a second classifier (observer) network monitors the GAN training to: (i) prevent the generated samples from falling into the positive distribution; and (ii) learn the features that are the key distinction between the positive and negative observations. Experiments on four image datasets demonstrate that our trained observer network performs better than existing techniques in discriminating between real unseen positive and negative samples.
- 4 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 16, 1-5
Open AccessLearning From Positive and Unlabeled Data Using Observer-GAN
In the case of learning from positive and unlabeled data, the input data consist of (1) observations from the positive class and their corresponding labels and (2) unlabeled observations from both positive and negative classes. Generative Adversarial Networks (GANs) have been used to reduce the problem to the supervised setting with the advantage that supervised learning has state-of-the-art accuracy in classification tasks. In order to generate pseudo-negative observations, GANs are trained on positive and unlabeled observations with a modified loss. Using both positive and pseudo-negative observations leads to a supervised learning setting. The generation of pseudo-negative observations that are realistic enough to replace missing negative class samples is a bottleneck for current GAN-based algorithms. By including an additional classifier into the GAN architecture, we describe a novel GAN-based approach. The GAN discriminator instructs the generator to only produce samples that fall into the unlabeled data distribution, while a second classifier (observer) network monitors the GAN training to: (i) prevent the generated samples from falling into the positive distribution; and (ii) learn the features that are the key distinction between the positive and negative observations. Experiments on four image datasets demonstrate that our trained observer network performs better than existing techniques in discriminating between real unseen positive and negative samples.
- 15 September 2022
- Published by Springer Nature
- p. 126-135
Sequential Multi-task Learning for Histopathology-Based Prediction of Genetic Mutations with Extremely Imbalanced Labels
- 15 September 2022
- Published by Springer Nature
- p. 126-135
Sequential Multi-task Learning for Histopathology-Based Prediction of Genetic Mutations with Extremely Imbalanced Labels
- Open Access
- 27 April 2022
- Published by Machine Learning for Biomedical Imaging in Machine Learning for Biomedical Imaging
- Vol. 1 (IPMI 2021) , 1-23
Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection
Despite impressive state-of-the-art performance on a wide variety of machine learning tasks in multiple applications, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we propose a novel approach that uses quantile regression for quantifying aleatoric uncertainty in both supervised and unsupervised lesion detection problems. The resulting confidence intervals can be used for lesion detection and segmentation. In the unsupervised settings, we combine quantile regression with the Variational AutoEncoder (VAE). The VAE is trained on lesion-free data, so when presented with an image with a lesion, it tends to reconstruct a lesion-free version of the image. To detect the lesion, we then compare the input (lesion) and output (lesion-free) images. Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection. The VAE models the output as a conditionally independent Gaussian characterized by its mean and variance. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. Here we describe an alternative Quantile-Regression VAE (QR-VAE) that avoids this variance shrinkage problem by directly estimating conditional quantiles for the input image. Using the estimated quantiles, we compute the conditional mean and variance for input image from which we then detect outliers by thresholding at a false-discovery-rate corrected p-value. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. We show how BQR can be used to capture uncertainty in lesion boundaries in a manner that characterizes expert disagreement.
- 27 April 2022
- Published by Machine Learning for Biomedical Imaging in Machine Learning for Biomedical Imaging
- Vol. 1 (IPMI 2021) , 1-23
Open AccessDeep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection
Despite impressive state-of-the-art performance on a wide variety of machine learning tasks in multiple applications, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we propose a novel approach that uses quantile regression for quantifying aleatoric uncertainty in both supervised and unsupervised lesion detection problems. The resulting confidence intervals can be used for lesion detection and segmentation. In the unsupervised settings, we combine quantile regression with the Variational AutoEncoder (VAE). The VAE is trained on lesion-free data, so when presented with an image with a lesion, it tends to reconstruct a lesion-free version of the image. To detect the lesion, we then compare the input (lesion) and output (lesion-free) images. Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection. The VAE models the output as a conditionally independent Gaussian characterized by its mean and variance. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. Here we describe an alternative Quantile-Regression VAE (QR-VAE) that avoids this variance shrinkage problem by directly estimating conditional quantiles for the input image. Using the estimated quantiles, we compute the conditional mean and variance for input image from which we then detect outliers by thresholding at a false-discovery-rate corrected p-value. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. We show how BQR can be used to capture uncertainty in lesion boundaries in a manner that characterizes expert disagreement.
- Open Access
Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection
Despite impressive state-of-the-art performance on a wide variety of machine learning tasks, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we propose a novel approach that uses quantile regression for quantifying aleatoric uncertainty in both supervised and unsupervised lesion detection problems. The resulting confidence intervals can be used for lesion detection and segmentation. In the unsupervised setting, we combine quantile regression with the Variational AutoEncoder (VAE). Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection. The VAE models the output as a conditionally independent Gaussian characterized by its mean and variance. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. Here we describe an alternative Quantile-Regression VAE (QR-VAE) that avoids this variance shrinkage problem by directly estimating conditional quantiles for the input image. Using the estimated quantiles, we compute the conditional mean and variance for the input image from which we then detect outliers by thresholding at a false-discovery-rate corrected p-value. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. We show how BQR can be used to capture uncertainty in lesion boundaries in a manner that characterizes expert disagreement.
Open AccessDeep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection
Despite impressive state-of-the-art performance on a wide variety of machine learning tasks, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we propose a novel approach that uses quantile regression for quantifying aleatoric uncertainty in both supervised and unsupervised lesion detection problems. The resulting confidence intervals can be used for lesion detection and segmentation. In the unsupervised setting, we combine quantile regression with the Variational AutoEncoder (VAE). Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection. The VAE models the output as a conditionally independent Gaussian characterized by its mean and variance. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. Here we describe an alternative Quantile-Regression VAE (QR-VAE) that avoids this variance shrinkage problem by directly estimating conditional quantiles for the input image. Using the estimated quantiles, we compute the conditional mean and variance for the input image from which we then detect outliers by thresholding at a false-discovery-rate corrected p-value. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. We show how BQR can be used to capture uncertainty in lesion boundaries in a manner that characterizes expert disagreement.
- 24 February 2022
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 43 (3) , 347-353
Neuroanatomic Markers of Posttraumatic Epilepsy Based on MR Imaging and Machine Learning
BACKGROUND AND PURPOSE: Although posttraumatic epilepsy is a common complication of traumatic brain injury, the relationship between these conditions is unclear and early posttraumatic epilepsy detection and prevention remain major unmet clinical challenges. This study aimed to identify imaging biomarkers that predict posttraumatic epilepsy among survivors of traumatic brain injury on the basis of an MR imaging data set. MATERIALS AND METHODS: We performed tensor-based morphometry to analyze brain-shape changes associated with traumatic brain injury and to derive imaging features for statistical group comparison. Additionally, machine learning was used to identify structural anomalies associated with brain lesions. Automatically generated brain lesion maps were used to identify brain regions where lesion load may indicate an increased incidence of posttraumatic epilepsy. We used 138 non-posttraumatic epilepsy subjects for training the machine learning method. Validation of lesion delineation was performed on 15 subjects. Group analysis of the relationship between traumatic brain injury and posttraumatic epilepsy was performed on an independent set of 74 subjects (37 subjects with and 37 randomly selected subjects without epilepsy). RESULTS: We observed significant F-statistics related to tensor-based morphometry analysis at voxels close to the pial surface, which may indicate group differences in the locations of edema, hematoma, or hemorrhage. The results of the F-test on lesion data showed significant differences between groups in both the left and right temporal lobes. We also saw significant differences in the right occipital lobe and cerebellum. CONCLUSIONS: Statistical analysis suggests that lesions in the temporal lobes, cerebellum, and the right occipital lobe are associated with an increased posttraumatic epilepsy incidence.
- 24 February 2022
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 43 (3) , 347-353
Neuroanatomic Markers of Posttraumatic Epilepsy Based on MR Imaging and Machine Learning
BACKGROUND AND PURPOSE: Although posttraumatic epilepsy is a common complication of traumatic brain injury, the relationship between these conditions is unclear and early posttraumatic epilepsy detection and prevention remain major unmet clinical challenges. This study aimed to identify imaging biomarkers that predict posttraumatic epilepsy among survivors of traumatic brain injury on the basis of an MR imaging data set. MATERIALS AND METHODS: We performed tensor-based morphometry to analyze brain-shape changes associated with traumatic brain injury and to derive imaging features for statistical group comparison. Additionally, machine learning was used to identify structural anomalies associated with brain lesions. Automatically generated brain lesion maps were used to identify brain regions where lesion load may indicate an increased incidence of posttraumatic epilepsy. We used 138 non-posttraumatic epilepsy subjects for training the machine learning method. Validation of lesion delineation was performed on 15 subjects. Group analysis of the relationship between traumatic brain injury and posttraumatic epilepsy was performed on an independent set of 74 subjects (37 subjects with and 37 randomly selected subjects without epilepsy). RESULTS: We observed significant F-statistics related to tensor-based morphometry analysis at voxels close to the pial surface, which may indicate group differences in the locations of edema, hematoma, or hemorrhage. The results of the F-test on lesion data showed significant differences between groups in both the left and right temporal lobes. We also saw significant differences in the right occipital lobe and cerebellum. CONCLUSIONS: Statistical analysis suggests that lesions in the temporal lobes, cerebellum, and the right occipital lobe are associated with an increased posttraumatic epilepsy incidence.
- 1 February 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 238
A robust variational autoencoder using beta divergence
- 1 February 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 238
A robust variational autoencoder using beta divergence