arXiv subjects
Publications and source records attributed to Adam Wang.
For a fixed arbitrary matrix depending on $n$ variables, one may ask whether a Prenex Normal Form (PNF) implies another. A RAM algorithm running in linear time is presented and shown to be asymptotically optimal.
The following note proves that conditional entropy of a sequence is almost time-reversal invariant, specifically they only differ by a small constant factor dependent only upon the forward and backward models that the entropies are being calculated with respect to. This gives rise to a numerical value that quantifies learnability, as well as a methodology to control for distributional shift between datasets. Rough guidelines are given for practitioners.
X-ray computed tomography (CT) is widely used for medical diagnosis and treatment planning; however, concerns about ionizing radiation exposure drive efforts to optimize image quality at lower doses. This study introduces Poisson Flow Consistency Models (PFCM), a novel family of deep generative models that combines the robustness of PFGM++ with the efficient single-step sampling of consistency models. PFCM are derived by generalizing consistency distillation to PFGM++ through a change-of-variables and an updated noise distribution. As a distilled version of PFGM++, PFCM inherit the ability to trade off robustness for rigidity via the hyperparameter $D \in (0,\infty)$. A fact that we exploit to adapt this novel generative model for the task of low-dose CT image denoising, via a ``task-specific'' sampler that ``hijacks'' the generative process by replacing an intermediate state with the low-dose CT image. While this ``hijacking'' introduces a severe mismatch -- the noise characteristics of low-dose CT images are different from that of intermediate states in the Poisson flow process -- we show that the inherent robustness of PFCM at small $D$ effectively mitigates this issue. The resulting sampler achieves excellent performance in terms of LPIPS, SSIM, and PSNR on the Mayo low-dose CT dataset. By contrast, an analogous sampler based on standard consistency models is found to be significantly less robust under the same conditions, highlighting the importance of a tunable $D$ afforded by our novel framework. To highlight generalizability, we show effective denoising of clinical images from a prototype photon-counting system reconstructed using a sharper kernel and at a range of energy levels.
While drastic improvements in CT technology have occurred in the past 25 years, spatial resolution is one area where progress has been limited until recently. New photon counting CT systems, are capable of much better spatial resolution than their (energy integrating) predecessors. These improvements have the potential to improve the evaluation obstructive coronary artery disease by enabling more accurate delineation between calcified plaque and coronary vessel lumen. A new set of vessel phantoms has been designed and manufactured for quantifying this improvement. Comparisons are made between an existing clinical CT system, a prototype photon counting system, with images from a micro CT system being used as the gold standard. Scans were made of the same objects on all three systems. The resulting images were registered and the luminal cross section areas were compared. Luminal cross-sections near calcified plaques were reduced due to blooming, but this effect was much less pronounced in images from the prototype photon counting system as compared to the images from the clinical CT system.
Purpose: Estimation of patient-specific organ doses is required for more comprehensive dose metrics, such as effective dose. Currently, available methods are performed retrospectively using the CT images themselves, which can only be done after the scan. To optimize CT acquisitions before scanning, rapid prediction of patient-specific organ dose is needed prospectively, using available scout images. We, therefore, devise an end-to-end, fully-automated deep learning solution to perform real-time, patient-specific, organ-level dosimetric estimation of CT scans. Approach: We propose the Scout-Net model for CT dose prediction at six different organs as well as for the overall patient body, leveraging the routinely obtained frontal and lateral scout images of patients, before their CT scans. To obtain reference values of the organ doses, we used Monte Carlo simulation and 3D segmentation methods on the corresponding CT images of the patients. Results: We validate our proposed Scout-Net model against real patient CT data and demonstrate the effectiveness in estimating organ doses in real-time (only 27 ms on average per scan). Additionally, we demonstrate the efficiency (real-time execution), sufficiency (reasonable error rates), and robustness (consistent across varying patient sizes) of the Scout-Net model. Conclusions: An effective, efficient, and robust Scout-Net model, once incorporated into the CT acquisition plan, could potentially guide the automatic exposure control for balanced image quality and radiation dose.
Recent development of photon-counting CT (PCCT) brings great opportunities for plaque characterization with much-improved spatial resolution and spectral imaging capability. While existing coronary plaque PCCT imaging results are based on detectors made of CZT or CdTe materials, deep-silicon photon-counting detectors have unique performance characteristics and promise distinct imaging capabilities. In this work, we report a systematic simulation study of a deep-silicon PCCT scanner with a new clinically-relevant digital plaque phantom with realistic geometrical parameters and chemical compositions. This work investigates the effects of spatial resolution, noise, motion artifacts, radiation dose, and spectral characterization. Our simulation results suggest that the deep-silicon PCCT design provides adequate spatial resolution for visualizing a necrotic core and quantitation of key plaque features. Advanced denoising techniques and aggressive bowtie filter designs can keep image noise to acceptable levels at this resolution while keeping radiation dose comparable to that of a conventional CT scan. The ultrahigh resolution of PCCT also means an elevated sensitivity to motion artifacts. It is found that a tolerance of less than 0.4 mm residual movement range requires the application of accurate motion correction methods for best plaque imaging quality with PCCT.
Traditional deep learning (DL) models have two ubiquitous limitations. First, they assume training samples are independent and identically distributed (i.i.d), an assumption often violated in real-world datasets where samples have additional correlation due to repeat measurements (e.g., on the same participants in a longitudinal study or cells from the same sequencer). This leads to performance degradation, limited generalization, and covariate confounding, which induces Type I and Type II errors. Second, DL models typically prioritize overall accuracy, favoring accuracy on the majority while sacrificing performance for underrepresented subpopulations, leading to unfair, biased models. This is critical to remediate, particularly in models which influence decisions regarding loan approvals and healthcare. To address these issues, we propose the Fair Mixed Effects Deep Learning (Fair MEDL) framework. This framework quantifies cluster-invariant fixed effects (FE) and cluster-specific random effects (RE) through: 1) a cluster adversary for learning invariant FE, 2) a Bayesian neural network for RE, and 3) a mixing function combining FE and RE for final predictions. Fairness is enhanced through architectural and loss function changes introduced by an adversarial debiasing network. We formally define and demonstrate improved fairness across three metrics: equalized odds, demographic parity, and counterfactual fairness, for both classification and regression tasks. Our method also identifies and de-weights confounded covariates, mitigating Type I and II errors. The framework is comprehensively evaluated across three datasets spanning two industries, including finance and healthcare. The Fair MEDL framework improves fairness by 86.4% for Age, 64.9% for Race, 57.8% for Sex, and 36.2% for Marital status, while maintaining robust predictive performance.
Disease diagnosis from medical images via supervised learning is usually dependent on tedious, error-prone, and costly image labeling by medical experts. Alternatively, semi-supervised learning and self-supervised learning offer effectiveness through the acquisition of valuable insights from readily available unlabeled images. We present Semi-Supervised Relational Contrastive Learning (SRCL), a novel semi-supervised learning model that leverages self-supervised contrastive loss and sample relation consistency for the more meaningful and effective exploitation of unlabeled data. Our experimentation with the SRCL model explores both pre-train/fine-tune and joint learning of the pretext (contrastive learning) and downstream (diagnostic classification) tasks. We validate against the ISIC 2018 Challenge benchmark skin lesion classification dataset and demonstrate the effectiveness of our semi-supervised method on varying amounts of labeled data.
Purpose: Conventional x-ray imaging and fluoroscopy have limitations in quantitation due to several challenges, including scatter, beam hardening, and overlapping tissues. In this work, we propose single-shot quantitative imaging (SSQI) by combining the use of a primary modulator (PM) and dual-layer (DL) detector, which enables motion-free dual-energy (DE) imaging with scatter correction in a single shot. Methods: The SSQI algorithm allows simultaneous recovery of two material-specific images and two scatter images using four sub-measurements from the PM encoding. For validation, we set up SSQI on our tabletop system and imaged acrylic and copper slabs with known thicknesses, estimated scatter with our SSQI algorithm, and compared the material decomposition (MD) for different combinations of the two materials with ground truth. Second, we imaged an anthropomorphic chest phantom containing contrast in the coronary arteries and compared the MD with and without SSQI. Lastly, to evaluate SSQI in dynamic applications, we constructed a flow phantom that enabled dynamic imaging of iodine contrast. Results: The root mean squared error (RMSE) of SSQI estimation was 0.13 cm for acrylic and 0.04 mm for copper. For the anthropomorphic phantom, direct MD resulted in incorrect interpretation of contrast and soft tissue, while SSQI successfully distinguished them and reduced RMSE in material-specific images by 38% to 92%. For the flow phantom, SSQI was able to perform accurate dynamic quantitative imaging, separating contrast from the background. Conclusions: We demonstrated the potential of SSQI for robust quantitative x-ray imaging. The simplicity of SSQI may enable its widespread adoption, including radiography and dynamic imaging such as real-time image guidance and cone-beam CT.
Deep learning-based models, when trained in a fully-supervised manner, can be effective in performing complex image analysis tasks, although contingent upon the availability of large labeled datasets. Especially in the medical imaging domain, however, expert image annotation is expensive, time-consuming, and prone to variability. Semi-supervised learning from limited quantities of labeled data has shown promise as an alternative. Maximizing knowledge gains from copious unlabeled data benefits semi-supervised learning models. Moreover, learning multiple tasks within the same model further improves its generalizability. We propose MultiMix, a new multi-task learning model that jointly learns disease classification and anatomical segmentation in a semi-supervised manner, while preserving explainability through a novel saliency bridge between the two tasks. Our experiments with varying quantities of multi-source labeled data in the training sets confirm the effectiveness of MultiMix in the simultaneous classification of pneumonia and segmentation of the lungs in chest X-ray images. Moreover, both in-domain and cross-domain evaluations across these tasks further showcase the potential of our model to adapt to challenging generalization scenarios.
CT image quality is heavily reliant on radiation dose, which causes a trade-off between radiation dose and image quality that affects the subsequent image-based diagnostic performance. However, high radiation can be harmful to both patients and operators. Several (deep learning-based) approaches have been attempted to denoise low dose images. However, those approaches require access to large training sets, specifically the full dose CT images for reference, which can often be difficult to obtain. Self-supervised learning is an emerging alternative for lowering the reference data requirement facilitating unsupervised learning. Currently available self-supervised CT denoising works are either dependent on foreign domain or pretexts are not very task-relevant. To tackle the aforementioned challenges, we propose a novel self-supervised learning approach, namely Self-Supervised Window-Leveling for Image DeNoising (SSWL-IDN), leveraging an innovative, task-relevant, simple, yet effective surrogate -- prediction of the window-leveled equivalent. SSWL-IDN leverages residual learning and a hybrid loss combining perceptual loss and MSE, all incorporated in a VAE framework. Our extensive (in- and cross-domain) experimentation demonstrates the effectiveness of SSWL-IDN in aggressive denoising of CT (abdomen and chest) images acquired at 5\% dose level only.
Semi-supervised learning via learning from limited quantities of labeled data has been investigated as an alternative to supervised counterparts. Maximizing knowledge gains from copious unlabeled data benefit semi-supervised learning settings. Moreover, learning multiple tasks within the same model further improves model generalizability. We propose a novel multitask learning model, namely MultiMix, which jointly learns disease classification and anatomical segmentation in a sparingly supervised manner, while preserving explainability through bridge saliency between the two tasks. Our extensive experimentation with varied quantities of labeled data in the training sets justify the effectiveness of our multitasking model for the classification of pneumonia and segmentation of lungs from chest X-ray images. Moreover, both in-domain and cross-domain evaluations across the tasks further showcase the potential of our model to adapt to challenging generalization scenarios.
Purpose: Developing photon-counting CT detectors requires understanding the impact of parameters such as converter material, absorption length and pixel size. We apply a novel linear-systems framework, incorporating spatial and energy resolution, to study realistic silicon (Si) and cadmium telluride (CdTe) detectors at low count rate. Approach: We compared CdTe detector designs with $0.5\times0.5\; \mathrm{mm}^2$ and $0.225\times0.225\; \mathrm{mm}^2$ pixels and Si detector designs with $0.5\times0.5\; \mathrm{mm}^2$ pixels of 30 and 60 mm active absorption length, with and without tungsten scatter blockers. Monte-Carlo simulations of photon transport were used together with Gaussian charge sharing models fitted to published data. Results: For detection in a 300 mm thick object at 120 kVp, the 0.5 mm and 0.225 mm pixel CdTe systems have 28-41 $\%$ and 5-29 $\%$ higher DQE, respectively, than the 60 mm Si system with tungsten, whereas the corresponding numbers for two-material decomposition are 2 $\%$ lower to 11 $\%$ higher DQE and 31-54 $\%$ lower DQE compared to Si. We also show that combining these detectors with dual-spectrum acquisition is beneficial. Conclusions: In the low-count-rate regime, CdTe detector systems outperform the Si systems for detection tasks, while silicon outperforms one or both of the CdTe systems for material decomposition.
Mobile applications and on-body devices are becoming increasingly ubiquitous tools for physical activity tracking. We propose utilizing a self-tracker's habits to support continuous prediction of whether they will reach their daily step goal, thus enabling a variety of potential persuasive interventions. Our aim is to improve the prediction by leveraging historical data and other qualitative (motivation for using the systems, location, gender) and, quantitative (age) features. We have collected datasets from two activity tracking platforms (Moves and Fitbit) and aim to check if the model we derive from one is generalizable over the other. In the following paper we establish a pipeline for extracting the data and formatting it for modeling. We discuss the approach we took and our findings while selecting the features and classification models for the dataset. We further discuss the notion of generalizability of the model across different types of dataset and the probable inclusion of non standard features to further improve the model's accuracy.