study inspired by the National Lung Screening Trial (NLST), illustrates the potential of VITs to expedite clinical trials, minimize risks to participants, and promote optimal use of imaging technologies in healthcare. This study aimed to show that a virtual imaging trial platform could investigate some key elements of a major clinical trial, specifically the NLST, which compared Computed tomography (CT) and chest radiography (CXR) for lung cancer screening. With simulated cancerous lung nodules, a virtual patient cohort of 294 subjects was created using XCAT human models. Each virtual patient underwent both CT and CXR imaging, with deep learning models, the AI CT-Reader and AI CXR-Reader, acting as virtual readers to perform recall patients with suspicion of lung cancer. The primary outcome was the difference in diagnostic performance between CT and CXR, measured by the Area Under the Curve (AUC). The AI CT-Reader showed superior diagnostic accuracy, achieving an AUC of 0.92 (95% CI: 0.90-0.95) compared to the AI CXR-Reader's AUC of 0.72 (95% CI: 0.67-0.77). Furthermore, at the same 94% CT sensitivity reported by the NLST, the VLST specificity of 73% was similar to the NLST specificity of 73.4%. This CT performance highlights the potential of VITs to replicate certain aspects of clinical trials effectively, paving the way toward a safe and efficient method for advancing imaging-based diagnostics.

Computer-aided detection (CAD) frameworks for breast cancer screening have been researched for several decades. Early adoption of deep-learning models in CAD frameworks has shown greatly improved detection performance compared to traditional CAD on single-view images. Recently, studies have improved performance by merging information from multiple views within each screening exam. Clinically, the integration of lesion correspondence during screening is a complicated decision process that depends on the correct execution of several referencing steps. However, most multi-view CAD frameworks are deep-learning-based black-box techniques. Fully end-to-end designs make it very difficult to analyze model behaviors and fine-tune performance. More importantly, the black-box nature of the techniques discourages clinical adoption due to the lack of explicit reasoning for each multi-view referencing step. Therefore, there is a need for a multi-view detection framework that can not only detect cancers accurately but also provide step-by-step, multi-view reasoning. In this work, we present Ipsilateral-Matching-Refinement Networks (IMR-Net) for digital breast tomosynthesis (DBT) lesion detection across multiple views. Our proposed framework adaptively refines the single-view detection scores based on explicit ipsilateral lesion matching. IMR-Net is built on a robust, single-view detection CAD pipeline with a commercial development DBT dataset of 24675 DBT volumetric views from 8034 exams. Performance is measured using location-based, case-level receiver operating characteristic (ROC) and case-level free-response ROC (FROC) analysis.

Most tissue collections of neoplasms are composed of formalin-fixed and paraffin-embedded (FFPE) excised tumor samples used for routine diagnostics. DNA sequencing is becoming increasingly important in cancer research and clinical management; however it is difficult to accurately sequence DNA from FFPE samples. We developed and validated a new bioinformatic pipeline to use existing variant-calling strategies to robustly identify somatic single nucleotide variants (SNVs) from whole exome sequencing using small amounts of DNA extracted from archival FFPE samples of breast cancers. We optimized this strategy using 28 pairs of technical replicates. After optimization, the mean similarity between replicates increased 5-fold, reaching 88% (range 0-100%), with a mean of 21.4 SNVs (range 1-68) per sample, representing a markedly superior performance to existing tools. We found that the SNV-identification accuracy declined when there was less than 40 ng of DNA available and that insertion-deletion variant calls are less reliable than single base substitutions. As the first application of the new algorithm, we compared samples of ductal carcinoma in situ of the breast to their adjacent invasive ductal carcinoma samples. We observed an increased number of mutations (paired-samples sign test, P < 0.05), and a higher genetic divergence in the invasive samples (paired-samples sign test, P < 0.01). Our method provides a significant improvement in detecting SNVs in FFPE samples over previous approaches.

OBJECTIVE: This study aims to develop and validate a novel framework, iPhantom, for automated creation of patient-specific phantoms or "digital-twins (DT)" using patient medical images. The framework is applied to assess radiation dose to radiosensitive organs in CT imaging of individual patients. METHOD: Given a volume of patient CT images, iPhantom segments selected anchor organs and structures (e.g., liver, bones, pancreas) using a learning-based model developed for multi-organ CT segmentation. Organs which are challenging to segment (e.g., intestines) are incorporated from a matched phantom template, using a diffeomorphic registration model developed for multi-organ phantom-voxels. The resulting digital-twin phantoms are used to assess organ doses during routine CT exams. RESULT: iPhantom was validated on both with a set of XCAT digital phantoms (n = 50) and an independent clinical dataset (n = 10) with similar accuracy. iPhantom precisely predicted all organ locations yielding Dice Similarity Coefficients (DSC) 0.6 - 1 for anchor organs and DSC of 0.3-0.9 for all other organs. iPhantom showed <10% errors in estimated radiation dose for the majority of organs, which was notably superior to the state-of-the-art baseline method (20-35% dose errors). CONCLUSION: iPhantom enables automated and accurate creation of patient-specific phantoms and, for the first time, provides sufficient and automated patient-specific dose estimates for CT dosimetry. SIGNIFICANCE: The new framework brings the creation and application of CHPs (computational human phantoms) to the level of individual CHPs through automation, achieving wide and precise organ localization, paving the way for clinical monitoring, personalized optimization, and large-scale research.

Mammography is currently the most widely utilized tool for detection and diagnosis of breast cancer. However, in women with dense breast tissue, tissue overlap may obscure lesions. Digital breast tomosynthesis can reduce tissue overlap. Furthermore, imaging with contrast enhancement can provide additional functional information about lesions, such as morphology and kinetics, which in turn may improve lesion identification and characterization. The performance of these imaging techniques is strongly dependent on the structural composition of the breast, which varies significantly among patients. Therefore, imaging system and imaging technique optimization should take patient variability into consideration. Furthermore, optimization of imaging techniques that employ contrast agents should include the temporally varying breast composition with respect to the contrast agent uptake kinetics. To these ends, we have developed a suite of 4-D virtual breast phantoms, which are incorporated with the kinetics of contrast agent propagation in different tissues and can realistically model normal breast parenchyma as well as benign and malignant lesions. This development presents a new approach in performing simulation studies using truly anthropomorphic models. To demonstrate the utility of the proposed 4-D phantoms, we present a simplified example study to compare the performance of 14 imaging paradigms qualitatively and quantitatively.

Super-resolution (SR) is the process of combining multiple aliased low-quality images to produce a high-resolution high-quality image. Aside from registration and fusion of low-resolution images, a key process in SR is the restoration and denoising of the fused images. We present a novel extension of the combined Fourier-wavelet deconvolution and denoising algorithm ForWarD to the multiframe SR application. Our method first uses a fast Fourier-base multiframe image restoration to produce a sharp, yet noisy estimate of the high-resolution image. Our method then applies a space-variant nonlinear wavelet thresholding that addresses the nonstationarity inherent in resolution-enhanced fused images. We describe a computationally efficient method for implementing this space-variant processing that leverages the efficiency of the fast Fourier transform (FFT) to minimize complexity. Finally, we demonstrate the effectiveness of this algorithm for regular imagery as well as in digital mammography.

Dedicated breast Computed Tomography (CT) is an emerging new technique for breast cancer imaging. Breast CT data can be acquired at a dose level as low as the conventional two-view mammography. Since the dose is equally split into hundreds of projection views, each projection image contains non-ignorable quantum noise. This study is aimed at investigating how volume noise removal affects the mass detectability in breast CT. A Partial Diffusion Equation (PDE) based denoising technique was applied before the reconstruction of either a simulated breast volume embedded with a contrast-detail mass phantom or a real human subject breast CT volume embedded with a simulated spherical mass. By applying a mathematical observer, it is found that the PDE volume noise removal technique improves the mass detectability in breast CT in a statistically significant sense.

Our previous work demonstrates the ability to reconstruct a single higher resolution image from fusing a collection of multiple extremely low-dosage aliased X-ray images. While this computationally efficient method eliminates aliasing artifacts associated with undersampling, it does not address the problem of deblurring the reconstructed image. In this paper, we present a fast nonlinear deblurring algorithm, specifically designed to address the nonstationary noise associated with multiframe reconstructed images. The algorithm uses a combination of Fourier sharpening and wavelet denoising similar to the ForWarD algorithm. Experimental results on enhancing digital mammogram images attest to the effectiveness of the presented method.

Digital breast tomosynthesis (DBT) is a three-dimensional imaging technique providing an arbitrary set of reconstruction planes in the breast with limited series of projection images. This paper describes a comparison between traditional shift-and-add (SAA) and point-by-point back projection (BP) algorithms by impulse response and modulation transfer function (MTF) analysis. Due to the partial isocentric motion of the x-ray tube in DBT, structures such as microcalcifications appear slightly blurred in traditional shift-and-add (SAA) images in the direction perpendicular to the direction of tube's motion. Point-by-point BP improved rendition of microcalcifications. The sharpness and morphology of calcifications were improved in a human subject images. A filtered back projection (FBP) deblurring approach was used to demonstrate deblurred point-by-point BP tomosynthesis images. The point-by-point BP rather than traditional SAA should be considered as the foundation of further deblurring algorithms for DBT reconstruction.

Current mammographic screening for breast cancer is less effective for younger women. To complement mammography for premenopausal women, we investigated the feasibility screening test using 98 blood serum proteins. Because the data set was very noisy and contained only weak features, we used a classifier designed for noisy data: decision fusion. Decision fusion outperformed both a support vector machine (SVM) and linear regression with forward stepwise feature selection on all three two-class classification tasks: normal tissue vs. cancer, normal tissue vs. benign lesions, and benign lesions vs. cancer. Decision fusion detected cancer moderately well (AUC=0.84 on normal vs. cancer), demonstrating promise as a screening tool. Decision fusion also detected benign lesions similarly well (AUC=0.83 on normal vs. benign lesions) and was the only classifier to achieve any success in separating benign from malignant lesions (AUC=0.64 on benign vs. cancer). The classification results suggest that the assayed proteins are more indicative of a secondary effect, such as immune response, rather than specific for breast cancer. In conclusion, the decision fusion classifier demonstrated some promise in detecting breast lesions and outperformed other classifiers, especially for the very noisy classification problem of distinguishing benign from malignant lesions.

This paper describes a breast cancer classification performance trade-off analysis using two computational intelligence paradigms. The first, an evolutionary programming (EP)/adaptive boosting (AB) based hybrid, intelligently combines the outputs from an iteratively "called" weak learning algorithm (one which performs at least slightly better than random guessing) in order to "boost" the performance of an EP-derived weak learner. The second paradigm is support vector machines (SVMs). SVMs are new and radically different types of classifiers and learning machines that use a hypothesis space of linear functions in a high dimensional feature space. The most important advantage of a SVM, unlike neural networks, is that SVM training always finds a global minimum. Furthermore, the SVM has inherent ability to solve pattern classification without incorporating any problem-domain knowledge. In this study, the both the EP/AB hybrid and SVM were employed as pattern classifiers, operating on mammography data used for breast cancer detection. The main focus of the study was to construct and seek the best EP/AB hybrid and SVM configurations for optimum specificity and positive predictive value at very high sensitivities. Using a mammogram database of 500 biopsy-proven samples, the best performing SVM, on average, was able to achieve (under statistical 5-fold cross-validation) a specificity of 45.0% and a positive predictive value (PPV) of 50.1% at 100% sensitivity. At 97% sensitivity, a specificity of 55.8% and a PPV of 55.2% were obtained. The best performing EP/AB hybrid obtained slightly lower, but comparable, results.

Mammography is the modality of choice for the early detection of breast cancer, primarily because of its sensitivity to the detection of breast cancer. However, because of its high rate of false positive predictions, a large number of biopsies of benign lesions result. The paper explores the use and evaluates the performance of two neural network hybrids as an aid to radiologists in avoiding biopsies of these benign lesions. These hybrids provide the potential to improve both the sensitivity and specificity of breast cancer diagnosis. The first hybrid, the Generalized Regression Neural Network (GRNN) Oracle, focuses on improving the performance output of a set of learning algorithms that operate and are accurate over the entire (defined) learning space. The second hybrid, an evolutionary programming (EP)/adaptive boosting (AB) based hybrid, intelligently combines the outputs from an iteratively called "weak" learning algorithm (one which performs at least slightly better than random guessing), in order to "boost" the performance of the weak learner. The second part of the paper discusses modifications to improve the EP/AB hybrid's performance, and further evaluates how the use of the EP/AB hybrid may obviate biopsies of benign lesions (as compared to an EP only classification system), given the requirement of missing few if any cancers.

A new evolutionary programming/adaptive boosting (EP/AB) neural network hybrid was investigated to measure the hybrid performance improvement as obtained when using an EP-only derived neural network as a baseline. By combining input variables consisting of mammography lesion descriptors and patient history data, the hybrid predicted whether the lesion was benign or malignant, which may aid in reducing the number of unnecessary biopsies and thus the cost of mammography screening of breast cancer. The EP process as well as the hybrid was optimized using a data set of 500 biopsy-proven cases from Duke University Medical Center (USA). Results showed that the hybrid provided a 15-20% classification performance improvement as measured by the ROC Az index when compared to a non-optimized EP derived architecture.

We review four current projects pertaining to artificial neural network (ANN) models that merge radiologist-extracted findings to perform computer aided diagnosis (CADx) of breast cancer. These projects are: (1) prediction of breast lesion malignancy using mammographic findings; (2) classification of malignant lesions as in situ vs. invasive cancer; (3) prediction of breast mass malignancy using ultrasound findings; and (4) the evaluation of CADx models in a cross-institution study. These projects share in common the use of feedforward error backpropagation ANNs. Inputs to the ANNs are medical findings such as mammographic or ultrasound lesion descriptors and patient history data. The output is the biopsy outcome (benign vs. malignant, or in situ vs. invasive cancer) which is being predicted. All ANNs undergo supervised training using actual patient data. These ANN decision models may assist in the management of patients with breast lesions, such as by reducing the number of unnecessary surgical procedures and their associated cost.

Two novel artificial neural network techniques, evolutionary programming (EP) and probabilistic neural networks (PNN), were applied to the problem of breast cancer diagnosis. The EP is a stochastic optimization technique with the ability to mutate both network connections and weight values. The PNN has the ability to produce optimal Bayesian decision making given sufficient training data. Both techniques offer potential improvements over the well-studied, classic backpropagation networks. Preliminary performances of these new techniques were comparable to but slightly worse than the classic networks. In on-going work, these new techniques will be optimized further and should produce results greater than or equal to the classic networks, but with more information content and confidence.

The objective of this study was to explore how a constraint satisfaction neural network (CSNN) can be used for medical diagnostic tasks. The study is based on a database of 500 patients who underwent breast biopsy at Duke University Medical Center due to suspicious mammographic findings. A CSNN was developed and evaluated to predict the biopsy result from the patient's mammographic findings. The diagnostic performance of the CSNN network was compared to a traditional backpropagation neural network and a case-based-reasoning algorithm by means of receiver operating characteristics analysis. The study demonstrates (i) how CSNNs can be applied to medical diagnostic tasks and, (ii) how they can be utilized to extract meaningful clinical information regarding underlying relationships among medical findings and associated diagnoses.