1,036 results on '"Rubin, Daniel L."'
Search Results
2. Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models
- Author
-
Tang, Siyi, Dunnmon, Jared A., Qu, Liangqiong, Saab, Khaled K., Baykaner, Tina, Lee-Messer, Christopher, and Rubin, Daniel L.
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence ,Electrical Engineering and Systems Science - Signal Processing - Abstract
Multivariate biosignals are prevalent in many medical domains, such as electroencephalography, polysomnography, and electrocardiography. Modeling spatiotemporal dependencies in multivariate biosignals is challenging due to (1) long-range temporal dependencies and (2) complex spatial correlations between the electrodes. To address these challenges, we propose representing multivariate biosignals as time-dependent graphs and introduce GraphS4mer, a general graph neural network (GNN) architecture that improves performance on biosignal classification tasks by modeling spatiotemporal dependencies in biosignals. Specifically, (1) we leverage the Structured State Space architecture, a state-of-the-art deep sequence model, to capture long-range temporal dependencies in biosignals and (2) we propose a graph structure learning layer in GraphS4mer to learn dynamically evolving graph structures in the data. We evaluate our proposed model on three distinct biosignal classification tasks and show that GraphS4mer consistently improves over existing models, including (1) seizure detection from electroencephalographic signals, outperforming a previous GNN with self-supervised pre-training by 3.1 points in AUROC; (2) sleep staging from polysomnographic signals, a 4.1 points improvement in macro-F1 score compared to existing sleep staging models; and (3) 12-lead electrocardiogram classification, outperforming previous state-of-the-art models by 2.7 points in macro-F1 score., Comment: Published as a conference paper at CHIL 2023
- Published
- 2022
3. Co-Clinical Imaging Metadata Information (CIMI) for Cancer Research to Promote Open Science, Standardization, and Reproducibility in Preclinical Imaging
- Author
-
Moore, Stephen M, Quirk, James D, Lassiter, Andrew W, Laforest, Richard, Ayers, Gregory D, Badea, Cristian T, Fedorov, Andriy Y, Kinahan, Paul E, Holbrook, Matthew, Larson, Peder EZ, Sriram, Renuka, Chenevert, Thomas L, Malyarenko, Dariya, Kurhanewicz, John, Houghton, A McGarry, Ross, Brian D, Pickup, Stephen, Gee, James C, Zhou, Rong, Gammon, Seth T, Manning, Henry Charles, Roudi, Raheleh, Daldrup-Link, Heike E, Lewis, Michael T, Rubin, Daniel L, Yankeelov, Thomas E, and Shoghi, Kooresh I
- Subjects
Biomedical and Clinical Sciences ,Oncology and Carcinogenesis ,Cancer ,Rare Diseases ,Biomedical Imaging ,Good Health and Well Being ,Animals ,Mice ,Humans ,Metadata ,Reproducibility of Results ,Diagnostic Imaging ,Neoplasms ,Reference Standards ,co-clinical imaging ,metadata ,Digital Imaging and Communications in Medicine ,preclinical imaging ,reproducibility ,open science ,standardization - Abstract
Preclinical imaging is a critical component in translational research with significant complexities in workflow and site differences in deployment. Importantly, the National Cancer Institute's (NCI) precision medicine initiative emphasizes the use of translational co-clinical oncology models to address the biological and molecular bases of cancer prevention and treatment. The use of oncology models, such as patient-derived tumor xenografts (PDX) and genetically engineered mouse models (GEMMs), has ushered in an era of co-clinical trials by which preclinical studies can inform clinical trials and protocols, thus bridging the translational divide in cancer research. Similarly, preclinical imaging fills a translational gap as an enabling technology for translational imaging research. Unlike clinical imaging, where equipment manufacturers strive to meet standards in practice at clinical sites, standards are neither fully developed nor implemented in preclinical imaging. This fundamentally limits the collection and reporting of metadata to qualify preclinical imaging studies, thereby hindering open science and impacting the reproducibility of co-clinical imaging research. To begin to address these issues, the NCI co-clinical imaging research program (CIRP) conducted a survey to identify metadata requirements for reproducible quantitative co-clinical imaging. The enclosed consensus-based report summarizes co-clinical imaging metadata information (CIMI) to support quantitative co-clinical imaging research with broad implications for capturing co-clinical data, enabling interoperability and data sharing, as well as potentially leading to updates to the preclinical Digital Imaging and Communications in Medicine (DICOM) standard.
- Published
- 2023
4. TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring
- Author
-
Bhaskhar, Nandita, Rubin, Daniel L., and Lee-Messer, Christopher
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
Continuous monitoring of trained ML models to determine when their predictions should and should not be trusted is essential for their safe deployment. Such a framework ought to be high-performing, explainable, post-hoc and actionable. We propose TRUST-LAPSE, a "mistrust" scoring framework for continuous model monitoring. We assess the trustworthiness of each input sample's model prediction using a sequence of latent-space embeddings. Specifically, (a) our latent-space mistrust score estimates mistrust using distance metrics (Mahalanobis distance) and similarity metrics (cosine similarity) in the latent-space and (b) our sequential mistrust score determines deviations in correlations over the sequence of past input representations in a non-parametric, sliding-window based algorithm for actionable continuous monitoring. We evaluate TRUST-LAPSE via two downstream tasks: (1) distributionally shifted input detection, and (2) data drift detection. We evaluate across diverse domains - audio and vision using public datasets and further benchmark our approach on challenging, real-world electroencephalograms (EEG) datasets for seizure detection. Our latent-space mistrust scores achieve state-of-the-art results with AUROCs of 84.1 (vision), 73.9 (audio), and 77.1 (clinical EEGs), outperforming baselines by over 10 points. We expose critical failures in popular baselines that remain insensitive to input semantic content, rendering them unfit for real-world model monitoring. We show that our sequential mistrust scores achieve high drift detection rates; over 90% of the streams show < 20% error for all domains. Through extensive qualitative and quantitative evaluations, we show that our mistrust scores are more robust and provide explainability for easy adoption into practice., Comment: Keywords: Mistrust Scores, Latent-Space, Model monitoring, Trustworthy AI, Explainable AI, Semantic-guided AI
- Published
- 2022
- Full Text
- View/download PDF
5. Examination of fully automated mammographic density measures using LIBRA and breast cancer risk in a cohort of 21,000 non-Hispanic white women
- Author
-
Habel, Laurel A., Alexeeff, Stacey E., Achacoso, Ninah, Arasu, Vignesh A., Gastounioti, Aimilia, Gerstley, Lawrence, Klein, Robert J., Liang, Rhea Y., Lipson, Jafi A., Mankowski, Walter, Margolies, Laurie R., Rothstein, Joseph H., Rubin, Daniel L., Shen, Li, Sistig, Adriana, Song, Xiaoyu, Villaseñor, Marvella A., Westley, Mark, Whittemore, Alice S., Yaffe, Martin J., Wang, Pei, Kontos, Despina, and Sieh, Weiva
- Published
- 2023
- Full Text
- View/download PDF
6. Supervised Machine Learning Algorithm for Detecting Consistency between Reported Findings and the Conclusions of Mammography Reports
- Author
-
Berdichevsky, Alexander, Peleg, Mor, and Rubin, Daniel L.
- Subjects
Computer Science - Computation and Language - Abstract
Objective. Mammography reports document the diagnosis of patients' conditions. However, many reports contain non-standard terms (non-BI-RADS descriptors) and incomplete statements, which can lead to conclusions that are not well-supported by the reported findings. Our aim was to develop a tool to detect such discrepancies by comparing the reported conclusions to those that would be expected based on the reported radiology findings. Materials and Methods. A deidentified data set from an academic hospital containing 258 mammography reports supplemented by 120 reports found on the web was used for training and evaluation. Spell checking and term normalization was used to unambiguously determine the reported BI-RADS descriptors. The resulting data were input into seven classifiers that classify mammography reports, based on their Findings sections, into seven BI-RADS final assessment categories. Finally, the semantic similarity score of a report to each BI-RADS category is reported. Results. Our term normalization algorithm correctly identified 97% of the BI-RADS descriptors in mammography reports. Our system provided 76% precision and 83% recall in correctly classifying the reports according to BI-RADS final assessment category. Discussion. The strength of our approach relies on providing high importance to BI-RADS terms in the summarization phase, on the semantic similarity that considers the complex data representation, and on the classification into all seven BI-RADs categories. Conclusion. BI-RADS descriptors and expected final assessment categories could be automatically detected by our approach with fairly good accuracy, which could be used to make users aware that their reported findings do not match well with their conclusion., Comment: 11 single spaced pages(current version is double spaced), 3 tables, 4 figures
- Published
- 2022
7. Automating Scoliosis Measurements in Radiographic Studies with Machine Learning: Comparing Artificial Intelligence and Clinical Reports
- Author
-
Ha, Audrey Y, Do, Bao H, Bartret, Adam L, Fang, Charles X, Hsiao, Albert, Lutz, Amelie M, Banerjee, Imon, Riley, Geoffrey M, Rubin, Daniel L, Stevens, Kathryn J, Wang, Erin, Wang, Shannon, Beaulieu, Christopher F, and Hurt, Brian
- Subjects
Bioengineering ,Adolescent ,Artificial Intelligence ,Humans ,Lumbar Vertebrae ,Machine Learning ,Reproducibility of Results ,Retrospective Studies ,Scoliosis ,Cobb angle ,Spine ,Artificial intelligence ,Deep learning ,Convolutional neural network ,Clinical Sciences ,Nuclear Medicine & Medical Imaging - Abstract
Scoliosis is a condition of abnormal lateral spinal curvature affecting an estimated 2 to 3% of the US population, or seven million people. The Cobb angle is the standard measurement of spinal curvature in scoliosis but is known to have high interobserver and intraobserver variability. Thus, the objective of this study was to build and validate a system for automatic quantitative evaluation of the Cobb angle and to compare AI generated and human reports in the clinical setting. After IRB was obtained, we retrospectively collected 2150 frontal view scoliosis radiographs at a tertiary referral center (January 1, 2019, to January 1, 2021, ≥ 16 years old, no hardware). The dataset was partitioned into 1505 train (70%), 215 validation (10%), and 430 test images (20%). All thoracic and lumbar vertebral bodies were segmented with bounding boxes, generating approximately 36,550 object annotations that were used to train a Faster R-CNN Resnet-101 object detection model. A controller algorithm was written to localize vertebral centroid coordinates and derive the Cobb properties (angle and endplate) of dominant and secondary curves. AI-derived Cobb angle measurements were compared to the clinical report measurements, and the Spearman rank-order demonstrated significant correlation (0.89, p
- Published
- 2022
8. Privacy preservation for federated learning in health care
- Author
-
Pati, Sarthak, Kumar, Sourav, Varma, Amokh, Edwards, Brandon, Lu, Charles, Qu, Liangqiong, Wang, Justin J., Lakshminarayanan, Anantharaman, Wang, Shih-han, Sheller, Micah J., Chang, Ken, Singh, Praveer, Rubin, Daniel L., Kalpathy-Cramer, Jayashree, and Bakas, Spyridon
- Published
- 2024
- Full Text
- View/download PDF
9. Mirrored X-Net: Joint classification and contrastive learning for weakly supervised GA segmentation in SD-OCT
- Author
-
Ji, Zexuan, Ma, Xiao, Leng, Theodore, Rubin, Daniel L., and Chen, Qiang
- Published
- 2024
- Full Text
- View/download PDF
10. An Experimental Study of Data Heterogeneity in Federated Learning Methods for Medical Imaging
- Author
-
Qu, Liangqiong, Balachandar, Niranjan, and Rubin, Daniel L
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Federated learning enables multiple institutions to collaboratively train machine learning models on their local data in a privacy-preserving way. However, its distributed nature often leads to significant heterogeneity in data distributions across institutions. In this paper, we investigate the deleterious impact of a taxonomy of data heterogeneity regimes on federated learning methods, including quantity skew, label distribution skew, and imaging acquisition skew. We show that the performance degrades with the increasing degrees of data heterogeneity. We present several mitigation strategies to overcome performance drops from data heterogeneity, including weighted average for data quantity skew, weighted loss and batch normalization averaging for label distribution skew. The proposed optimizations to federated learning methods improve their capability of handling heterogeneity across institutions, which provides valuable guidance for the deployment of federated learning in real clinical applications.
- Published
- 2021
11. SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging
- Author
-
Zhang, Miao, Qu, Liangqiong, Singh, Praveer, Kalpathy-Cramer, Jayashree, and Rubin, Daniel L.
- Subjects
Computer Science - Machine Learning ,Electrical Engineering and Systems Science - Image and Video Processing - Abstract
Federated learning is an emerging research paradigm for enabling collaboratively training deep learning models without sharing patient data. However, the data from different institutions are usually heterogeneous across institutions, which may reduce the performance of models trained using federated learning. In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning. Unlike previous federated methods that require complex heuristic training or hyper parameter tuning, our SplitAVG leverages the simple network split and feature map concatenation strategies to encourage the federated model training an unbiased estimator of the target data distribution. We compare SplitAVG with seven state-of-the-art federated learning methods, using centrally hosted training data as the baseline on a suite of both synthetic and real-world federated datasets. We find that the performance of models trained using all the comparison federated learning methods degraded significantly with the increasing degrees of data heterogeneity. In contrast, SplitAVG method achieves comparable results to the baseline method under all heterogeneous settings, that it achieves 96.2% of the accuracy and 110.4% of the mean absolute error obtained by the baseline in a diabetic retinopathy binary classification dataset and a bone age prediction dataset, respectively, on highly heterogeneous data partitions. We conclude that SplitAVG method can effectively overcome the performance drops from variability in data distributions across institutions. Experimental results also show that SplitAVG can be adapted to different base networks and generalized to various types of medical imaging tasks.
- Published
- 2021
12. Abdominal CT metrics in 17,646 patients reveal associations between myopenia, myosteatosis, and medical phenotypes: a phenome-wide association study
- Author
-
Zambrano Chaves, Juan M., Lenchik, Leon, Gallegos, Isabel O., Blankemeier, Louis, Liang, Tie, Rubin, Daniel L., Willis, Marc H., Chaudhari, Akshay S., and Boutin, Robert D.
- Published
- 2024
- Full Text
- View/download PDF
13. COVID-19 Lung Lesion Segmentation Using a Sparsely Supervised Mask R-CNN on Chest X-rays Automatically Computed from Volumetric CTs
- Author
-
Ramesh, Vignav, Rister, Blaine, and Rubin, Daniel L.
- Subjects
Electrical Engineering and Systems Science - Image and Video Processing ,Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning - Abstract
Chest X-rays of coronavirus disease 2019 (COVID-19) patients are frequently obtained to determine the extent of lung disease and are a valuable source of data for creating artificial intelligence models. Most work to date assessing disease severity on chest imaging has focused on segmenting computed tomography (CT) images; however, given that CTs are performed much less frequently than chest X-rays for COVID-19 patients, automated lung lesion segmentation on chest X-rays could be clinically valuable. There currently exists a universal shortage of chest X-rays with ground truth COVID-19 lung lesion annotations, and manually contouring lung opacities is a tedious, labor-intensive task. To accelerate severity detection and augment the amount of publicly available chest X-ray training data for supervised deep learning (DL) models, we leverage existing annotated CT images to generate frontal projection "chest X-ray" images for training COVID-19 chest X-ray models. In this paper, we propose an automated pipeline for segmentation of COVID-19 lung lesions on chest X-rays comprised of a Mask R-CNN trained on a mixed dataset of open-source chest X-rays and coronal X-ray projections computed from annotated volumetric CTs. On a test set containing 40 chest X-rays of COVID-19 positive patients, our model achieved IoU scores of 0.81 $\pm$ 0.03 and 0.79 $\pm$ 0.03 when trained on a dataset of 60 chest X-rays and on a mixed dataset of 10 chest X-rays and 50 projections from CTs, respectively. Our model far outperforms current baselines with limited supervised training and may assist in automated COVID-19 severity quantification on chest X-rays., Comment: 8 pages, 5 figures
- Published
- 2021
14. Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis
- Author
-
Tang, Siyi, Dunnmon, Jared A., Saab, Khaled, Zhang, Xuan, Huang, Qianying, Dubost, Florian, Rubin, Daniel L., and Lee-Messer, Christopher
- Subjects
Electrical Engineering and Systems Science - Signal Processing ,Computer Science - Artificial Intelligence ,Computer Science - Machine Learning - Abstract
Automated seizure detection and classification from electroencephalography (EEG) can greatly improve seizure diagnosis and treatment. However, several modeling challenges remain unaddressed in prior automated seizure detection and classification studies: (1) representing non-Euclidean data structure in EEGs, (2) accurately classifying rare seizure types, and (3) lacking a quantitative interpretability approach to measure model ability to localize seizures. In this study, we address these challenges by (1) representing the spatiotemporal dependencies in EEGs using a graph neural network (GNN) and proposing two EEG graph structures that capture the electrode geometry or dynamic brain connectivity, (2) proposing a self-supervised pre-training method that predicts preprocessed signals for the next time period to further improve model performance, particularly on rare seizure types, and (3) proposing a quantitative model interpretability approach to assess a model's ability to localize seizures within EEGs. When evaluating our approach on seizure detection and classification on a large public dataset, we find that our GNN with self-supervised pre-training achieves 0.875 Area Under the Receiver Operating Characteristic Curve on seizure detection and 0.749 weighted F1-score on seizure classification, outperforming previous methods for both seizure detection and classification. Moreover, our self-supervised pre-training strategy significantly improves classification of rare seizure types. Furthermore, quantitative interpretability analysis shows that our GNN with self-supervised pre-training precisely localizes 25.4% focal seizures, a 21.9 point improvement over existing CNNs. Finally, by superimposing the identified seizure locations on both raw EEG signals and EEG graphs, our approach could provide clinicians with an intuitive visualization of localized seizure regions., Comment: Published as a conference paper at ICLR 2022
- Published
- 2021
15. Addressing catastrophic forgetting for medical domain expansion
- Author
-
Gupta, Sharut, Singh, Praveer, Chang, Ken, Qu, Liangqiong, Aggarwal, Mehak, Arun, Nishanth, Vaswani, Ashwin, Raghavan, Shruti, Agarwal, Vibha, Gidwani, Mishka, Hoebel, Katharina, Patel, Jay, Lu, Charles, Bridge, Christopher P., Rubin, Daniel L., and Kalpathy-Cramer, Jayashree
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant decline in performance when tested at other institutions. While pooling datasets from multiple institutions and retraining may provide a straightforward solution, it is often infeasible and may compromise patient privacy. An alternative approach is to fine-tune the model on subsequent institutions after training on the original institution. Notably, this approach degrades model performance at the original institution, a phenomenon known as catastrophic forgetting. In this paper, we develop an approach to address catastrophic forget-ting based on elastic weight consolidation combined with modulation of batch normalization statistics under two scenarios: first, for expanding the domain from one imaging system's data to another imaging system's, and second, for expanding the domain from a large multi-institutional dataset to another single institution dataset. We show that our approach outperforms several other state-of-the-art approaches and provide theoretical justification for the efficacy of batch normalization modulation. The results of this study are generally applicable to the deployment of any clinical deep learning model which requires domain expansion., Comment: First three authors contributed equally
- Published
- 2021
16. Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation
- Author
-
Yamashita, Rikiya, Long, Jin, Banda, Snikitha, Shen, Jeanne, and Rubin, Daniel L.
- Subjects
Electrical Engineering and Systems Science - Image and Video Processing ,Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning - Abstract
Suboptimal generalization of machine learning models on unseen data is a key challenge which hampers the clinical applicability of such models to medical imaging. Although various methods such as domain adaptation and domain generalization have evolved to combat this challenge, learning robust and generalizable representations is core to medical image understanding, and continues to be a problem. Here, we propose STRAP (Style TRansfer Augmentation for histoPathology), a form of data augmentation based on random style transfer from non-medical style source such as artistic paintings, for learning domain-agnostic visual representations in computational pathology. Style transfer replaces the low-level texture content of an image with the uninformative style of randomly selected style source image, while preserving the original high-level semantic content. This improves robustness to domain shift and can be used as a simple yet powerful tool for learning domain-agnostic representations. We demonstrate that STRAP leads to state-of-the-art performance, particularly in the presence of domain shifts, on two particular classification tasks in computational pathology.
- Published
- 2021
- Full Text
- View/download PDF
17. The unreasonable effectiveness of Batch-Norm statistics in addressing catastrophic forgetting across medical institutions
- Author
-
Gupta, Sharut, Singh, Praveer, Chang, Ken, Aggarwal, Mehak, Arun, Nishanth, Qu, Liangqiong, Hoebel, Katharina, Patel, Jay, Gidwani, Mishka, Vaswani, Ashwin, Rubin, Daniel L, and Kalpathy-Cramer, Jayashree
- Subjects
Computer Science - Machine Learning - Abstract
Model brittleness is a primary concern when deploying deep learning models in medical settings owing to inter-institution variations, like patient demographics and intra-institution variation, such as multiple scanner types. While simply training on the combined datasets is fraught with data privacy limitations, fine-tuning the model on subsequent institutions after training it on the original institution results in a decrease in performance on the original dataset, a phenomenon called catastrophic forgetting. In this paper, we investigate trade-off between model refinement and retention of previously learned knowledge and subsequently address catastrophic forgetting for the assessment of mammographic breast density. More specifically, we propose a simple yet effective approach, adapting Elastic weight consolidation (EWC) using the global batch normalization (BN) statistics of the original dataset. The results of this study provide guidance for the deployment of clinical deep learning models where continuous learning is needed for domain expansion., Comment: Accepted as oral presentation in Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract ; 6 pages and 4 figures
- Published
- 2020
18. Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset
- Author
-
Tang, Siyi, Ghorbani, Amirata, Yamashita, Rikiya, Rehman, Sameer, Dunnmon, Jared A., Zou, James, and Rubin, Daniel L.
- Subjects
Computer Science - Machine Learning ,Computer Science - Computer Vision and Pattern Recognition ,Electrical Engineering and Systems Science - Image and Video Processing - Abstract
The reliability of machine learning models can be compromised when trained on low quality data. Many large-scale medical imaging datasets contain low quality labels extracted from sources such as medical reports. Moreover, images within a dataset may have heterogeneous quality due to artifacts and biases arising from equipment or measurement errors. Therefore, algorithms that can automatically identify low quality data are highly desired. In this study, we used data Shapley, a data valuation metric, to quantify the value of training data to the performance of a pneumonia detection algorithm in a large chest X-ray dataset. We characterized the effectiveness of data Shapley in identifying low quality versus valuable data for pneumonia detection. We found that removing training data with high Shapley values decreased the pneumonia detection performance, whereas removing data with low Shapley values improved the model performance. Furthermore, there were more mislabeled examples in low Shapley value data and more true pneumonia cases in high Shapley value data. Our results suggest that low Shapley value indicates mislabeled or poor quality images, whereas high Shapley value indicates data that are valuable for pneumonia detection. Our method can serve as a framework for using data Shapley to denoise large-scale medical imaging datasets.
- Published
- 2020
- Full Text
- View/download PDF
19. Probabilistic bounds on neuron death in deep rectifier networks
- Author
-
Rister, Blaine and Rubin, Daniel L.
- Subjects
Computer Science - Machine Learning ,Computer Science - Neural and Evolutionary Computing ,Statistics - Machine Learning - Abstract
Neuron death is a complex phenomenon with implications for model trainability: the deeper the network, the lower the probability of finding a valid initialization. In this work, we derive both upper and lower bounds on the probability that a ReLU network is initialized to a trainable point, as a function of model hyperparameters. We show that it is possible to increase the depth of a network indefinitely, so long as the width increases as well. Furthermore, our bounds are asymptotically tight under reasonable assumptions: first, the upper bound coincides with the true probability for a single-layer network with the largest possible input set. Second, the true probability converges to our lower bound as the input set shrinks to a single point, or as the network complexity grows under an assumption about the output variance. We confirm these results by numerical simulation, showing rapid convergence to the lower bound with increasing network depth. Then, motivated by the theory, we propose a practical sign flipping scheme which guarantees that the ratio of living data points in a $k$-layer network is at least $2^{-k}$. Finally, we show how these issues are mitigated by network design features currently seen in practice, such as batch normalization, residual connections, dense networks and skip connections. This suggests that neuron death may provide insight into the efficacy of various model architectures.
- Published
- 2020
20. Changes in Cancer Management due to COVID-19 Illness in Patients with Cancer in Northern California.
- Author
-
Wu, Julie Tsu-Yu, Kwon, Daniel H, Glover, Michael J, Henry, Solomon, Wood, Douglas, Rubin, Daniel L, Koshkin, Vadim S, Schapira, Lidia, and Shah, Sumit A
- Subjects
Biomedical and Clinical Sciences ,Oncology and Carcinogenesis ,Cancer ,Administration ,Oral ,Adolescent ,Adult ,Aged ,Aged ,80 and over ,Antineoplastic Agents ,COVID-19 ,California ,Child ,Child ,Preschool ,Female ,Humans ,Infusions ,Intravenous ,Injections ,Intramuscular ,Male ,Middle Aged ,Neoplasms ,Palliative Care ,Radiotherapy ,Retrospective Studies ,SARS-CoV-2 ,Surgical Procedures ,Operative ,Time Factors ,Time-to-Treatment ,Young Adult ,Oncology and carcinogenesis - Abstract
PurposeThe response to the COVID-19 pandemic has affected the management of patients with cancer. In this pooled retrospective analysis, we describe changes in management patterns for patients with cancer diagnosed with COVID-19 in two academic institutions in the San Francisco Bay Area.Materials and methodsAdult and pediatric patients diagnosed with COVID-19 with a current or historical diagnosis of malignancy were identified from the electronic medical record at the University of California, San Francisco, and Stanford University. The proportion of patients undergoing active cancer management whose care was affected was quantified and analyzed for significant differences with regard to management type, treatment intent, and the time of COVID-19 diagnosis. The duration and characteristics of such changes were compared across subgroups.ResultsA total of 131 patients were included, of whom 55 were undergoing active cancer management. Of these, 35 of 55 (64%) had significant changes in management that consisted primarily of delays. An additional three patients not undergoing active cancer management experienced a delay in management after being diagnosed with COVID-19. The decision to change management was correlated with the time of COVID-19 diagnosis, with more delays identified in patients treated with palliative intent earlier in the course of the pandemic (March/April 2020) compared with later (May/June 2020) (OR, 4.2; 95% CI, 1.03 to 17.3; P = .0497). This difference was not seen among patients treated with curative intent during the same timeframe.ConclusionWe found significant changes in the management of cancer patients with COVID-19 treated with curative and palliative intent that evolved over time. Future studies are needed to determine the impact of changes in management and treatment on cancer outcomes for patients with cancer and COVID-19.
- Published
- 2021
21. Towards trustworthy seizure onset detection using workflow notes
- Author
-
Saab, Khaled, Tang, Siyi, Taha, Mohamed, Lee-Messer, Christopher, Ré, Christopher, and Rubin, Daniel L.
- Published
- 2024
- Full Text
- View/download PDF
22. Clinical outcome prediction using observational supervision with electronic health records and audit logs
- Author
-
Bhaskhar, Nandita, Ip, Wui, Chen, Jonathan H., and Rubin, Daniel L.
- Published
- 2023
- Full Text
- View/download PDF
23. Plexus Convolutional Neural Network (PlexusNet): A novel neural network architecture for histologic image analysis
- Author
-
Eminaga, Okyaz, Abbas, Mahmoud, Kunder, Christian, Loening, Andreas M., Shen, Jeanne, Brooks, James D., Langlotz, Curtis P., and Rubin, Daniel L.
- Subjects
Quantitative Biology - Quantitative Methods ,Computer Science - Artificial Intelligence ,Computer Science - Computer Vision and Pattern Recognition ,Electrical Engineering and Systems Science - Image and Video Processing ,Quantitative Biology - Tissues and Organs - Abstract
Different convolutional neural network (CNN) models have been tested for their application in histological image analyses. However, these models are prone to overfitting due to their large parameter capacity, requiring more data or valuable computational resources for model training. Given these limitations, we introduced a novel architecture (termed PlexusNet). We utilized 310 Hematoxylin and Eosin stained (H&E) annotated histological images of prostate cancer cases from TCGA-PRAD and Stanford University and 398 H&E whole slides images from the Camelyon 2016 challenge. PlexusNet-architecture -derived models were compared to models derived from several existing "state of the art" architectures. We measured discrimination accuracy, calibration, and clinical utility. An ablation study was conducted to study the effect of each component of PlexusNet on model performance. A well-fitted PlexusNet-based model delivered comparable classification performance (AUC: 0.963) in distinguishing prostate cancer from healthy tissues, although it was at least 23 times smaller, had a better model calibration and clinical utility than the comparison models. A separate smaller PlexusNet model accurately detected slides with breast cancer metastases (AUC: 0.978); it helped reduce the slide number to examine by 43.8% without consequences, although its parameter capacity was 200 times smaller than ResNet18. We found that the partitioning of the development set influences the model calibration for all models. However, with PlexusNet architecture, we could achieve comparable well-calibrated models trained on different partitions. In conclusion, PlexusNet represents a novel model architecture for histological image analysis that achieves classification performance comparable to other models while providing orders-of-magnitude parameter reduction.
- Published
- 2019
24. Self-Attention Capsule Networks for Object Classification
- Author
-
Hoogi, Assaf, Wilcox, Brian, Gupta, Yachee, and Rubin, Daniel L.
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
We propose a novel architecture for object classification, called Self-Attention Capsule Networks (SACN). SACN is the first model that incorporates the Self-Attention mechanism as an integral layer within the Capsule Network (CapsNet). While the Self-Attention mechanism supplies a long-range dependencies, results in selecting the more dominant image regions to focus on, the CapsNet analyzes the relevant features and their spatial correlations inside these regions only. The features are extracted in the convolutional layer. Then, the Self-Attention layer learns to suppress irrelevant regions based on features analysis and highlights salient features useful for a specific task. The attention map is then fed into the CapsNet primary layer that is followed by a classification layer. The proposed SACN model was designed to solve two main limitations of the baseline CapsNet - analysis of complex data and significant computational load. In this work, we use a shallow CapsNet architecture and compensates for the absence of a deeper network by using the Self-Attention module to significantly improve the results. The proposed Self-Attention CapsNet architecture was extensively evaluated on six different datasets, mainly on three different medical sets, in addition to the natural MNIST, SVHN and CIFAR10. The model was able to classify images and their patches with diverse and complex backgrounds better than the baseline CapsNet. As a result, the proposed Self-Attention CapsNet significantly improved classification performance within and across different datasets and outperformed the baseline CapsNet, ResNet-18 and DenseNet-40 not only in classification accuracy but also in robustness.
- Published
- 2019
25. Deep Learning Enables Automatic Detection and Segmentation of Brain Metastases on Multi-Sequence MRI
- Author
-
Grøvik, Endre, Yi, Darvin, Iv, Michael, Tong, Elisabeth, Rubin, Daniel L., and Zaharchuk, Greg
- Subjects
Electrical Engineering and Systems Science - Image and Video Processing ,Computer Science - Machine Learning ,Statistics - Machine Learning - Abstract
Detecting and segmenting brain metastases is a tedious and time-consuming task for many radiologists, particularly with the growing use of multi-sequence 3D imaging. This study demonstrates automated detection and segmentation of brain metastases on multi-sequence MRI using a deep learning approach based on a fully convolution neural network (CNN). In this retrospective study, a total of 156 patients with brain metastases from several primary cancers were included. Pre-therapy MR images (1.5T and 3T) included pre- and post-gadolinium T1-weighted 3D fast spin echo, post-gadolinium T1-weighted 3D axial IR-prepped FSPGR, and 3D fluid attenuated inversion recovery. The ground truth was established by manual delineation by two experienced neuroradiologists. CNN training/development was performed using 100 and 5 patients, respectively, with a 2.5D network based on a GoogLeNet architecture. The results were evaluated in 51 patients, equally separated into those with few (1-3), multiple (4-10), and many (>10) lesions. Network performance was evaluated using precision, recall, Dice/F1 score, and ROC-curve statistics. For an optimal probability threshold, detection and segmentation performance was assessed on a per metastasis basis. The area under the ROC-curve (AUC), averaged across all patients, was 0.98. The AUC in the subgroups was 0.99, 0.97, and 0.97 for patients having 1-3, 4-10, and >10 metastases, respectively. Using an average optimal probability threshold determined by the development set, precision, recall, and Dice-score were 0.79, 0.53, and 0.79, respectively. At the same probability threshold, the network showed an average false positive rate of 8.3/patient (no lesion-size limit) and 3.4/patient (10 mm3 lesion size limit). In conclusion, a deep learning approach using multi-sequence MRI can aid in the detection and segmentation of brain metastases.
- Published
- 2019
- Full Text
- View/download PDF
26. PlexusNet: A neural network architectural concept for medical image classification
- Author
-
Eminaga, Okyaz, Abbas, Mahmoud, Shen, Jeanne, Laurie, Mark, Brooks, James D., Liao, Joseph C., and Rubin, Daniel L.
- Published
- 2023
- Full Text
- View/download PDF
27. Identification of 31 loci for mammographic density phenotypes and their associations with breast cancer risk
- Author
-
Sieh, Weiva, Rothstein, Joseph H, Klein, Robert J, Alexeeff, Stacey E, Sakoda, Lori C, Jorgenson, Eric, McBride, Russell B, Graff, Rebecca E, McGuire, Valerie, Achacoso, Ninah, Acton, Luana, Liang, Rhea Y, Lipson, Jafi A, Rubin, Daniel L, Yaffe, Martin J, Easton, Douglas F, Schaefer, Catherine, Risch, Neil, Whittemore, Alice S, and Habel, Laurel A
- Subjects
Human Genome ,Prevention ,Aging ,Genetics ,Breast Cancer ,Cancer ,2.1 Biological and endogenous factors ,Aetiology ,Adult ,Aged ,Aged ,80 and over ,Breast Density ,Breast Neoplasms ,Female ,Genetic Predisposition to Disease ,Genome-Wide Association Study ,Humans ,Mammography ,Mendelian Randomization Analysis ,Middle Aged ,Polymorphism ,Single Nucleotide - Abstract
Mammographic density (MD) phenotypes are strongly associated with breast cancer risk and highly heritable. In this GWAS meta-analysis of 24,192 women, we identify 31 MD loci at P
- Published
- 2020
28. CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss
- Author
-
Rister, Blaine, Yi, Darvin, Shivakumar, Kaushik, Nobashi, Tomomi, and Rubin, Daniel L.
- Subjects
Computer Science - Neural and Evolutionary Computing ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Fully-convolutional neural networks have achieved superior performance in a variety of image segmentation tasks. However, their training requires laborious manual annotation of large datasets, as well as acceleration by parallel processors with high-bandwidth memory, such as GPUs. We show that simple models can achieve competitive accuracy for organ segmentation on CT images when trained with extensive data augmentation, which leverages existing graphics hardware to quickly apply geometric and photometric transformations to 3D image data. On 3 mm^3 CT volumes, our GPU implementation is 2.6-8X faster than a widely-used CPU version, including communication overhead. We also show how to automatically generate training labels using rudimentary morphological operations, which are efficiently computed by 3D Fourier transforms. We combined fully-automatic labels for the lungs and bone with semi-automatic ones for the liver, kidneys and bladder, to create a dataset of 130 labeled CT scans. To achieve the best results from data augmentation, our model uses the intersection-over-union (IOU) loss function, a close relative of the Dice loss. We discuss its mathematical properties and explain why it outperforms the usual weighted cross-entropy loss for unbalanced segmentation tasks. We conclude that there is no unique IOU loss function, as the naive one belongs to a broad family of functions with the same essential properties. When combining data augmentation with the IOU loss, our model achieves a Dice score of 78-92% for each organ. The trained model, code and dataset will be made publicly available, to further medical imaging research., Comment: Journal submission pre-print
- Published
- 2018
29. An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring
- Author
-
Bhaskhar, Nandita, primary, Rubin, Daniel L., additional, and Lee-Messer, Christopher, additional
- Published
- 2024
- Full Text
- View/download PDF
30. Uncovering interpretable potential confounders in electronic medical records
- Author
-
Zeng, Jiaming, Gensheimer, Michael F., Rubin, Daniel L., Athey, Susan, and Shachter, Ross D.
- Published
- 2022
- Full Text
- View/download PDF
31. A Scalable Machine Learning Approach for Inferring Probabilistic US-LI-RADS Categorization
- Author
-
Banerjee, Imon, Choi, Hailey H., Desser, Terry, and Rubin, Daniel L.
- Subjects
Computer Science - Computation and Language ,Computer Science - Artificial Intelligence - Abstract
We propose a scalable computerized approach for large-scale inference of Liver Imaging Reporting and Data System (LI-RADS) final assessment categories in narrative ultrasound (US) reports. Although our model was trained on reports created using a LI-RADS template, it was also able to infer LI-RADS scoring for unstructured reports that were created before the LI-RADS guidelines were established. No human-labelled data was required in any step of this study; for training, LI-RADS scores were automatically extracted from those reports that contained structured LI-RADS scores, and it translated the derived knowledge to reasoning on unstructured radiology reports. By providing automated LI-RADS categorization, our approach may enable standardizing screening recommendations and treatment planning of patients at risk for hepatocellular carcinoma, and it may facilitate AI-based healthcare research with US images by offering large scale text mining and data gathering opportunities from standard hospital clinical data repositories., Comment: AMIA Annual Symposium 2018 (accepted)
- Published
- 2018
32. Abstract: Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients
- Author
-
Banerjee, Imon, Gensheimer, Michael Francis, Wood, Douglas J., Henry, Solomon, Chang, Daniel, and Rubin, Daniel L.
- Subjects
Computer Science - Artificial Intelligence - Abstract
We propose a deep learning model - Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients (PPES-Met) for estimating short-term life expectancy (3 months) of the patients by analyzing free-text clinical notes in the electronic medical record, while maintaining the temporal visit sequence. In a single framework, we integrated semantic data mapping and neural embedding technique to produce a text processing method that extracts relevant information from heterogeneous types of clinical notes in an unsupervised manner, and we designed a recurrent neural network to model the temporal dependency of the patient visits. The model was trained on a large dataset (10,293 patients) and validated on a separated dataset (1818 patients). Our method achieved an area under the ROC curve (AUC) of 0.89. To provide explain-ability, we developed an interactive graphical tool that may improve physician understanding of the basis for the model's predictions. The high accuracy and explain-ability of the PPES-Met model may enable our model to be used as a decision support tool to personalize metastatic cancer treatment and provide valuable assistance to the physicians.
- Published
- 2018
33. Intelligent Word Embeddings of Free-Text Radiology Reports
- Author
-
Banerjee, Imon, Madhavan, Sriraman, Goldman, Roger Eric, and Rubin, Daniel L.
- Subjects
Computer Science - Information Retrieval ,Computer Science - Computation and Language - Abstract
Radiology reports are a rich resource for advancing deep learning applications in medicine by leveraging the large volume of data continuously being updated, integrated, and shared. However, there are significant challenges as well, largely due to the ambiguity and subtlety of natural language. We propose a hybrid strategy that combines semantic-dictionary mapping and word2vec modeling for creating dense vector embeddings of free-text radiology reports. Our method leverages the benefits of both semantic-dictionary mapping as well as unsupervised learning. Using the vector representation, we automatically classify the radiology reports into three classes denoting confidence in the diagnosis of intracranial hemorrhage by the interpreting radiologist. We performed experiments with varying hyperparameter settings of the word embeddings and a range of different classifiers. Best performance achieved was a weighted precision of 88% and weighted recall of 90%. Our work offers the potential to leverage unstructured electronic health record data by allowing direct analysis of narrative clinical notes., Comment: AMIA Annual Symposium 2017
- Published
- 2017
34. Institutionally Distributed Deep Learning Networks
- Author
-
Chang, Ken, Balachandar, Niranjan, Lam, Carson K, Yi, Darvin, Brown, James M, Beers, Andrew, Rosen, Bruce R, Rubin, Daniel L, and Kalpathy-Cramer, Jayashree
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Learning ,Physics - Medical Physics - Abstract
Deep learning has become a promising approach for automated medical diagnoses. When medical data samples are limited, collaboration among multiple institutions is necessary to achieve high algorithm performance. However, sharing patient data often has limitations due to technical, legal, or ethical concerns. In such cases, sharing a deep learning model is a more attractive alternative. The best method of performing such a task is unclear, however. In this study, we simulate the dissemination of learning deep learning network models across four institutions using various heuristics and compare the results with a deep learning model trained on centrally hosted patient data. The heuristics investigated include ensembling single institution models, single weight transfer, and cyclical weight transfer. We evaluated these approaches for image classification in three independent image collections (retinal fundus photos, mammography, and ImageNet). We find that cyclical weight transfer resulted in a performance (testing accuracy = 77.3%) that was closest to that of centrally hosted patient data (testing accuracy = 78.7%). We also found that there is an improvement in the performance of cyclical weight transfer heuristic with high frequency of weight transfer.
- Published
- 2017
35. Inferring Generative Model Structure with Static Analysis
- Author
-
Varma, Paroma, He, Bryan, Bajaj, Payal, Banerjee, Imon, Khandwala, Nishith, Rubin, Daniel L., and Ré, Christopher
- Subjects
Computer Science - Learning ,Computer Science - Artificial Intelligence ,Statistics - Machine Learning - Abstract
Obtaining enough labeled data to robustly train complex discriminative models is a major bottleneck in the machine learning pipeline. A popular solution is combining multiple sources of weak supervision using generative models. The structure of these models affects training label quality, but is difficult to learn without any ground truth labels. We instead rely on these weak supervision sources having some structure by virtue of being encoded programmatically. We present Coral, a paradigm that infers generative model structure by statically analyzing the code for these heuristics, thus reducing the data required to learn structure significantly. We prove that Coral's sample complexity scales quasilinearly with the number of heuristics and number of relations found, improving over the standard sample complexity, which is exponential in $n$ for identifying $n^{\textrm{th}}$ degree relations. Experimentally, Coral matches or outperforms traditional structure learning approaches by up to 3.81 F1 points. Using Coral to model dependencies instead of assuming independence results in better performance than a fully supervised model by 3.07 accuracy points when heuristics are used to label radiology data without ground truth labels., Comment: NIPS 2017
- Published
- 2017
36. The use of texture-based radiomics CT analysis to predict outcomes in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy
- Author
-
Starkov, Pierre, Aguilera, Todd A, Golden, Daniel I, Shultz, David B, Trakul, Nicholas, Maxim, Peter G, Le, Quynh-Thu, Loo, Billy W, Diehn, Maximillan, Depeursinge, Adrien, and Rubin, Daniel L
- Subjects
Biomedical and Clinical Sciences ,Oncology and Carcinogenesis ,Biomedical Imaging ,Lung Cancer ,Lung ,Cancer ,Bioengineering ,Good Health and Well Being ,Aged ,Aged ,80 and over ,Carcinoma ,Non-Small-Cell Lung ,Female ,Humans ,Lung Neoplasms ,Male ,Middle Aged ,Prognosis ,Proportional Hazards Models ,Radiosurgery ,Survival Analysis ,Tomography ,X-Ray Computed ,Clinical Sciences ,Nuclear Medicine & Medical Imaging ,Clinical sciences ,Oncology and carcinogenesis - Abstract
Objective:Stereotactic ablative radiotherapy (SABR) is being increasingly used as a non-invasive treatment for early-stage non-small cell lung cancer (NSCLC). A non-invasive method to estimate treatment outcomes in these patients would be valuable, especially since access to tissue specimens is often difficult in these cases.Methods:We developed a method to predict survival following SABR in NSCLC patients using analysis of quantitative image features on pre-treatment CT images. We developed a Cox Lasso model based on two-dimensional Riesz wavelet quantitative texture features on CT scans with the goal of separating patients based on survival.Results:The median log-rank p-value for 1000 cross-validations was 0.030. Our model was able to separate patients based upon predicted survival. When we added tumor size into the model, the p-value lost its significance, demonstrating that tumor size is not a key feature in the model but rather decreases significance likely due to the relatively small number of events in the dataset. Furthermore, running the model using Riesz features extracted either from the solid component of the tumor or from the ground glass opacity (GGO) component of the tumor maintained statistical significance. However, the p-value improved when combining features from the solid and the GGO components, demonstrating that there are important data that can be extracted from the entire tumor.Conclusions:The model predicting patient survival following SABR in NSCLC may be useful in future studies by enabling prediction of survival-based outcomes using radiomics features in CT images.Advances in knowledge:Quantitative image features from NSCLC nodules on CT images have been found to significantly separate patient populations based on overall survival (p = 0.04). In the long term, a non-invasive method to estimate treatment outcomes in patients undergoing SABR would be valuable, especially since access to tissue specimens is often difficult in these cases.
- Published
- 2019
37. The Use of Quantitative Imaging in Radiation Oncology: A Quantitative Imaging Network (QIN) Perspective
- Author
-
Press, Robert H, Shu, Hui-Kuo G, Shim, Hyunsuk, Mountz, James M, Kurland, Brenda F, Wahl, Richard L, Jones, Ella F, Hylton, Nola M, Gerstner, Elizabeth R, Nordstrom, Robert J, Henderson, Lori, Kurdziel, Karen A, Vikram, Bhadrasain, Jacobs, Michael A, Holdhoff, Matthias, Taylor, Edward, Jaffray, David A, Schwartz, Lawrence H, Mankoff, David A, Kinahan, Paul E, Linden, Hannah M, Lambin, Philippe, Dilling, Thomas J, Rubin, Daniel L, Hadjiiski, Lubomir, and Buatti, John M
- Subjects
Medical and Biological Physics ,Physical Sciences ,Biomedical and Clinical Sciences ,Oncology and Carcinogenesis ,Cancer ,Clinical Research ,Clinical Trials and Supportive Activities ,Good Health and Well Being ,Humans ,Magnetic Resonance Imaging ,Magnetic Resonance Spectroscopy ,Neoplasms ,Positron-Emission Tomography ,Radiation Oncology ,Tomography ,X-Ray Computed ,Tumor Hypoxia ,Other Physical Sciences ,Clinical Sciences ,Oncology & Carcinogenesis ,Oncology and carcinogenesis ,Theoretical and computational chemistry ,Medical and biological physics - Abstract
Modern radiation therapy is delivered with great precision, in part by relying on high-resolution multidimensional anatomic imaging to define targets in space and time. The development of quantitative imaging (QI) modalities capable of monitoring biologic parameters could provide deeper insight into tumor biology and facilitate more personalized clinical decision-making. The Quantitative Imaging Network (QIN) was established by the National Cancer Institute to advance and validate these QI modalities in the context of oncology clinical trials. In particular, the QIN has significant interest in the application of QI to widen the therapeutic window of radiation therapy. QI modalities have great promise in radiation oncology and will help address significant clinical needs, including finer prognostication, more specific target delineation, reduction of normal tissue toxicity, identification of radioresistant disease, and clearer interpretation of treatment response. Patient-specific QI is being incorporated into radiation treatment design in ways such as dose escalation and adaptive replanning, with the intent of improving outcomes while lessening treatment morbidities. This review discusses the current vision of the QIN, current areas of investigation, and how the QIN hopes to enhance the integration of QI into the practice of radiation oncology.
- Published
- 2018
38. Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence
- Author
-
Bai, Xiang, Wang, Hanchen, Ma, Liya, Xu, Yongchao, Gan, Jiefeng, Fan, Ziwei, Yang, Fan, Ma, Ke, Yang, Jiehua, Bai, Song, Shu, Chang, Zou, Xinyu, Huang, Renhao, Zhang, Changzheng, Liu, Xiaowu, Tu, Dandan, Xu, Chuou, Zhang, Wenqing, Wang, Xi, Chen, Anguo, Zeng, Yu, Yang, Dehua, Wang, Ming-Wei, Holalkere, Nagaraj, Halin, Neil J., Kamel, Ihab R., Wu, Jia, Peng, Xuehua, Wang, Xiang, Shao, Jianbo, Mongkolwat, Pattanasak, Zhang, Jianjun, Liu, Weiyang, Roberts, Michael, Teng, Zhongzhao, Beer, Lucian, Sanchez, Lorena E., Sala, Evis, Rubin, Daniel L., Weller, Adrian, Lasenby, Joan, Zheng, Chuangsheng, Wang, Jianming, Li, Zhen, Schönlieb, Carola, and Xia, Tian
- Published
- 2021
- Full Text
- View/download PDF
39. Out of Distribution Detection for Medical Images
- Author
-
Zhang, Oliver, Delbrouck, Jean-Benoit, Rubin, Daniel L., Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Sudre, Carole H., editor, Licandro, Roxane, editor, Baumgartner, Christian, editor, Melbourne, Andrew, editor, Dalca, Adrian, editor, Hutter, Jana, editor, Tanno, Ryutaro, editor, Abaci Turk, Esra, editor, Van Leemput, Koen, editor, Torrents Barrena, Jordina, editor, Wells, William M., editor, and Macgowan, Christopher, editor
- Published
- 2021
- Full Text
- View/download PDF
40. Biomedical Imaging Informatics
- Author
-
Rubin, Daniel L., Greenspan, Hayit, Hoogi, Assaf, Shortliffe, Edward H., editor, Cimino, James J., editor, and Chiang, Michael F., Section Editor
- Published
- 2021
- Full Text
- View/download PDF
41. A Fully-Automated Pipeline for Detection and Segmentation of Liver Lesions and Pathological Lymph Nodes
- Author
-
Hoogi, Assaf, Lambert, John W., Zheng, Yefeng, Comaniciu, Dorin, and Rubin, Daniel L.
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
We propose a fully-automated method for accurate and robust detection and segmentation of potentially cancerous lesions found in the liver and in lymph nodes. The process is performed in three steps, including organ detection, lesion detection and lesion segmentation. Our method applies machine learning techniques such as marginal space learning and convolutional neural networks, as well as active contour models. The method proves to be robust in its handling of extremely high lesion diversity. We tested our method on volumetric computed tomography (CT) images, including 42 volumes containing liver lesions and 86 volumes containing 595 pathological lymph nodes. Preliminary results under 10-fold cross validation show that for both the liver lesions and the lymph nodes, a total detection sensitivity of 0.53 and average Dice score of $0.71 \pm 0.15$ for segmentation were obtained., Comment: Workshop on Machine Learning in Healthcare, Neural Information Processing Systems (NIPS). Barcelona, Spain, 2016
- Published
- 2017
42. Computerized Multiparametric MR image Analysis for Prostate Cancer Aggressiveness-Assessment
- Author
-
Banerjee, Imon, Hahn, Lewis, Sonn, Geoffrey, Fan, Richard, and Rubin, Daniel L.
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
We propose an automated method for detecting aggressive prostate cancer(CaP) (Gleason score >=7) based on a comprehensive analysis of the lesion and the surrounding normal prostate tissue which has been simultaneously captured in T2-weighted MR images, diffusion-weighted images (DWI) and apparent diffusion coefficient maps (ADC). The proposed methodology was tested on a dataset of 79 patients (40 aggressive, 39 non-aggressive). We evaluated the performance of a wide range of popular quantitative imaging features on the characterization of aggressive versus non-aggressive CaP. We found that a group of 44 discriminative predictors among 1464 quantitative imaging features can be used to produce an area under the ROC curve of 0.73., Comment: NIPS 2016 Workshop on Machine Learning for Health (NIPS ML4HC)
- Published
- 2016
43. Revealing cancer subtypes with higher-order correlations applied to imaging and omics data
- Author
-
Graim, Kiley, Liu, Tiffany Ting, Achrol, Achal S, Paull, Evan O, Newton, Yulia, Chang, Steven D, Harsh, Griffith R, Cordero, Sergio P, Rubin, Daniel L, and Stuart, Joshua M
- Subjects
Biomedical and Clinical Sciences ,Oncology and Carcinogenesis ,Brain Cancer ,Brain Disorders ,Rare Diseases ,Urologic Diseases ,Clinical Research ,Cancer ,4.1 Discovery and preclinical testing of markers and technologies ,Detection ,screening and diagnosis ,Computational Biology ,DNA Copy Number Variations ,Genotype ,Glioblastoma ,Humans ,Magnetic Resonance Imaging ,Mutation ,Phenotype ,Molecular subtyping ,Community detection ,MRI ,Magnetic resonance imaging ,Clustering ,Genetics ,Medical Biochemistry and Metabolomics ,Genetics & Heredity ,Medical biochemistry and metabolomics - Abstract
BackgroundPatient stratification to identify subtypes with different disease manifestations, severity, and expected survival time is a critical task in cancer diagnosis and treatment. While stratification approaches using various biomarkers (including high-throughput gene expression measurements) for patient-to-patient comparisons have been successful in elucidating previously unseen subtypes, there remains an untapped potential of incorporating various genotypic and phenotypic data to discover novel or improved groupings.MethodsHere, we present HOCUS, a unified analytical framework for patient stratification that uses a community detection technique to extract subtypes out of sparse patient measurements. HOCUS constructs a patient-to-patient network from similarities in the data and iteratively groups and reconstructs the network into higher order clusters. We investigate the merits of using higher-order correlations to cluster samples of cancer patients in terms of their associations with survival outcomes.ResultsIn an initial test of the method, the approach identifies cancer subtypes in mutation data of glioblastoma, ovarian, breast, prostate, and bladder cancers. In several cases, HOCUS provides an improvement over using the molecular features directly to compare samples. Application of HOCUS to glioblastoma images reveals a size and location classification of tumors that improves over human expert-based stratification.ConclusionsSubtypes based on higher order features can reveal comparable or distinct groupings. The distinct solutions can provide biologically- and treatment-relevant solutions that are just as significant as solutions based on the original data.
- Published
- 2017
44. AI-based structure-function correlation in age-related macular degeneration
- Author
-
von der Emde, Leon, Pfau, Maximilian, Holz, Frank G., Fleckenstein, Monika, Kortuem, Karsten, Keane, Pearse A., Rubin, Daniel L., and Schmitz-Valckenberg, Steffen
- Published
- 2021
- Full Text
- View/download PDF
45. Piecewise convexity of artificial neural networks
- Author
-
Rister, Blaine and Rubin, Daniel L
- Subjects
Computer Science - Learning ,Computer Science - Artificial Intelligence ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Although artificial neural networks have shown great promise in applications including computer vision and speech recognition, there remains considerable practical and theoretical difficulty in optimizing their parameters. The seemingly unreasonable success of gradient descent methods in minimizing these non-convex functions remains poorly understood. In this work we offer some theoretical guarantees for networks with piecewise affine activation functions, which have in recent years become the norm. We prove three main results. Firstly, that the network is piecewise convex as a function of the input data. Secondly, that the network, considered as a function of the parameters in a single layer, all others held constant, is again piecewise convex. Finally, that the network as a function of all its parameters is piecewise multi-convex, a generalization of biconvexity. From here we characterize the local minima and stationary points of the training objective, showing that they minimize certain subsets of the parameter space. We then analyze the performance of two optimization algorithms on multi-convex problems: gradient descent, and a method which repeatedly solves a number of convex sub-problems. We prove necessary convergence conditions for the first algorithm and both necessary and sufficient conditions for the second, after introducing regularization to the objective. Finally, we remark on the remaining difficulty of the global optimization problem. Under the squared error objective, we show that by varying the training data, a single rectifier neuron admits local minima arbitrarily far apart, both in objective value and parameter space.
- Published
- 2016
46. Adaptive Local Window for Level Set Segmentation of CT and MRI Liver Lesions
- Author
-
Hoogi, Assaf, Beaulieu, Christopher F., Cunha, Guilherme M., Heba, Elhamy, Sirlin, Claude B., Napel, Sandy, and Rubin, Daniel L.
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of the segmentation process, and for each individual object. Our method considers the object scale, the spatial texture, and changes of the energy functional over iterations. Global and local statistics are considered by calculating several gray level co-occurrence matrices. We demonstrate the capabilities of the method in the domain of medical imaging for segmenting 233 images with liver lesions. To illustrate the strength of our method, those images were obtained by either Computed Tomography or Magnetic Resonance Imaging. Moreover, we analyzed images using three different energy models. We compare our method to a global level set segmentation and to local framework that uses predefined fixed-size square windows. The results indicate that our proposed method outperforms the other methods in terms of agreement with the manual marking and dependence on contour initialization or the energy model used. In case of complex lesions, such as low contrast lesions, heterogeneous lesions, or lesions with a noisy background, our method shows significantly better segmentation with an improvement of 0.25+- 0.13 in Dice similarity coefficient, compared with state of the art fixed-size local windows (Wilcoxon, p < 0.001)., Comment: 24 pages, 11 figures, 3 tables
- Published
- 2016
47. Regulatory Frameworks for Development and Evaluation of Artificial Intelligence–Based Diagnostic Imaging Algorithms: Summary and Recommendations
- Author
-
Larson, David B., Harvey, Hugh, Rubin, Daniel L., Irani, Neville, Tse, Justin R., and Langlotz, Curtis P.
- Published
- 2021
- Full Text
- View/download PDF
48. Comparison of segmentation-free and segmentation-dependent computer-aided diagnosis of breast masses on a public mammography dataset
- Author
-
Sawyer Lee, Rebecca, Dunnmon, Jared A., He, Ann, Tang, Siyi, Ré, Christopher, and Rubin, Daniel L.
- Published
- 2021
- Full Text
- View/download PDF
49. Magnetic resonance perfusion image features uncover an angiogenic subgroup of glioblastoma patients with poor survival and better response to antiangiogenic treatment
- Author
-
Liu, Tiffany T, Achrol, Achal S, Mitchell, Lex A, Rodriguez, Scott A, Feroze, Abdullah, Iv, Michael, Kim, Christine, Chaudhary, Navjot, Gevaert, Olivier, Stuart, Josh M, Harsh, Griffith R, Chang, Steven D, and Rubin, Daniel L
- Subjects
Biomedical Imaging ,Clinical Trials and Supportive Activities ,Neurosciences ,Rare Diseases ,Cancer ,Brain Cancer ,Biotechnology ,Brain Disorders ,Clinical Research ,Adult ,Aged ,Aged ,80 and over ,Angiogenesis Inhibitors ,Brain Neoplasms ,Cluster Analysis ,Cohort Studies ,Female ,Genotype ,Glioblastoma ,Humans ,Kaplan-Meier Estimate ,Magnetic Resonance Angiography ,Male ,Middle Aged ,Neovascularization ,Pathologic ,Treatment Outcome ,Young Adult ,angiogenesis ,antiangiogenic therapy ,patient stratification ,quantitative perfusion-weighted imaging ,radiogenomic analysis ,Oncology and Carcinogenesis ,Oncology & Carcinogenesis - Abstract
BackgroundIn previous clinical trials, antiangiogenic therapies such as bevacizumab did not show efficacy in patients with newly diagnosed glioblastoma (GBM). This may be a result of the heterogeneity of GBM, which has a variety of imaging-based phenotypes and gene expression patterns. In this study, we sought to identify a phenotypic subtype of GBM patients who have distinct tumor-image features and molecular activities and who may benefit from antiangiogenic therapies.MethodsQuantitative image features characterizing subregions of tumors and the whole tumor were extracted from preoperative and pretherapy perfusion magnetic resonance (MR) images of 117 GBM patients in 2 independent cohorts. Unsupervised consensus clustering was performed to identify robust clusters of GBM in each cohort. Cox survival and gene set enrichment analyses were conducted to characterize the clinical significance and molecular pathway activities of the clusters. The differential treatment efficacy of antiangiogenic therapy between the clusters was evaluated.ResultsA subgroup of patients with elevated perfusion features was identified and was significantly associated with poor patient survival after accounting for other clinical covariates (P values 3) consistently found in both cohorts. Angiogenesis and hypoxia pathways were enriched in this subgroup of patients, suggesting the potential efficacy of antiangiogenic therapy. Patients of the angiogenic subgroups pooled from both cohorts, who had chemotherapy information available, had significantly longer survival when treated with antiangiogenic therapy (log-rank P=.022).ConclusionsOur findings suggest that an angiogenic subtype of GBM patients may benefit from antiangiogenic therapy with improved overall survival.
- Published
- 2017
50. Adaptive local window for level set segmentation of CT and MRI liver lesions
- Author
-
Hoogi, Assaf, Beaulieu, Christopher F, Cunha, Guilherme M, Heba, Elhamy, Sirlin, Claude B, Napel, Sandy, and Rubin, Daniel L
- Subjects
Biomedical and Clinical Sciences ,Engineering ,Biomedical Imaging ,Bioengineering ,Digestive Diseases ,Algorithms ,Humans ,Image Processing ,Computer-Assisted ,Liver ,Magnetic Resonance Imaging ,Tomography ,X-Ray Computed ,Adaptive local window ,Deformable models ,Lesion segmentation ,cs.CV ,Medical and Health Sciences ,Nuclear Medicine & Medical Imaging ,Biomedical and clinical sciences - Abstract
We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of the segmentation process, and for each individual object. Our method considers the object scale, the spatial texture, and the changes of the energy functional over iterations. Global and local statistics are considered by calculating several gray level co-occurrence matrices. We demonstrate the capabilities of the method in the domain of medical imaging for segmenting 233 images with liver lesions. To illustrate the strength of our method, those lesions were screened by either Computed Tomography or Magnetic Resonance Imaging. Moreover, we analyzed images using three different energy models. We compared our method to a global level set segmentation, to a local framework that uses predefined fixed-size square windows and to a local region-scalable fitting model. The results indicate that our proposed method outperforms the other methods in terms of agreement with the manual marking and dependence on contour initialization or the energy model used. In case of complex lesions, such as low contrast lesions, heterogeneous lesions, or lesions with a noisy background, our method shows significantly better segmentation with an improvement of 0.25 ± 0.13 in Dice similarity coefficient, compared with state of the art fixed-size local windows (Wilcoxon, p
- Published
- 2017
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.