Computable Guidelines and Clinical Decision Support for Cervical Cancer Screening and Management to Improve Outcomes and Health Equity.

Cervical cancer is highly preventable when precancerous lesions are detected early and appropriately managed. However, the complexity of and frequent updates to existing evidence-based clinical guidelines make it challenging for clinicians to stay abreast of the latest recommendations. In addition, limited availability and accessibility to information technology (IT) decision supports make it difficult for groups who are medically underserved to receive screening or receive the appropriate follow-up care. The Centers for Disease Control and Prevention (CDC), Division of Cancer Prevention and Control (DCPC), is leading a multiyear initiative to develop computer-interpretable ("computable") version of already existing evidence-based guidelines to support clinician awareness and adoption of the most up-to-date cervical cancer screening and management guidelines. DCPC is collaborating with the MITRE Corporation, leading scientists from the National Cancer Institute, and other CDC subject matter experts to translate existing narrative guidelines into computable format and develop clinical decision support tools for integration into health IT systems such as electronic health records with the ultimate goal of improving patient outcomes and decreasing disparities in cervical cancer outcomes among populations that are medically underserved. This initiative meets the challenges and opportunities highlighted by the President's Cancer Panel and the President's Cancer Moonshot 2.0 to nearly eliminate cervical cancer.

A Sparsity Regularization Approach to the Electromagnetic Inverse Scattering Problem.

We investigate solving the electromagnetic inverse scattering problem using the distorted Born iterative method (DBIM) in conjunction with a variable-selection approach known as the elastic net. The elastic net applies both ℓ1 and ℓ2 penalties to regularize the system of linear equations that result at each iteration of the DBIM. The elastic net thus incorporates both the stabilizing effect of the ℓ2 penalty with the sparsity encouraging effect of the ℓ1 penalty. The DBIM with the elastic net outperforms the commonly used ℓ2 regularizer when the unknown distribution of dielectric properties is sparse in a known set of basis functions. We consider two very different 3-D examples to demonstrate the efficacy and applicability of our approach. For both examples, we use a scalar approximation in the inverse solution. In the first example the actual distribution of dielectric properties is exactly sparse in a set of 3-D wavelets. The performances of the elastic net and ℓ2 approaches are compared to the ideal case where it is known a priori which wavelets are involved in the true solution. The second example comes from the area of microwave imaging for breast cancer detection. For a given set of 3-D Gaussian basis functions, we show that the elastic net approach can produce a more accurate estimate of the distribution of dielectric properties (in particular, the effective conductivity) within an anatomically realistic 3-D numerical breast phantom. In contrast, the DBIM with an ℓ2 penalty produces an estimate which suffers from multiple artifacts.

Three-dimensional microwave breast imaging: dispersive dielectric properties estimation using patient-specific basis functions.

Breast imaging via microwave tomography involves estimating the distribution of dielectric properties within the patient's breast on a discrete mesh. The number of unknowns in the discrete mesh can be very large for 3-D imaging, and this results in computational challenges. We propose a new approach where the discrete mesh is replaced with a relatively small number of smooth basis functions. The dimension of the tomography problem is reduced by estimating the coefficients of the basis functions instead of the dielectric properties at each element in the discrete mesh. The basis functions are constructed using knowledge of the location of the breast surface. The number of functions used in the basis can be varied to balance resolution and computational complexity. The reduced dimension of the inverse problem enables application of a computationally efficient, multiple-frequency inverse scattering algorithm in 3-D. The efficacy of the proposed approach is verified using two 3-D anatomically realistic numerical breast phantoms. It is shown for the case of single-frequency microwave tomography that the imaging accuracy is comparable to that obtained when the original discrete mesh is used, despite the reduction of the dimension of the inverse problem. Results are also shown for a multiple-frequency algorithm where it is computationally challenging to use the original discrete mesh.

Estimating the breast surface using UWB microwave monostatic backscatter measurements.

This paper presents an algorithm for estimating the location of the breast surface from scattered ultrawideband (UWB) microwave signals recorded across an antenna array. Knowing the location of the breast surface can improve imaging performance if incorporated as a priori information into recently proposed microwave imaging algorithms. These techniques transmit low-power microwaves into the breast using an antenna array, which in turn measures the scattered microwave signals for the purpose of detecting anomalies or changes in the dielectric properties of breast tissue. Our proposed surface identification algorithm consists of three procedures, the first of which estimates M points on the breast surface given M channels of measured microwave backscatter data. The second procedure applies interpolation and extrapolation to these M points to generate N > M points that are approximately uniformly distributed over the breast surface, while the third procedure uses these N points to generate a 3-D estimated breast surface. Numerical as well as experimental tests indicate that the maximum absolute error in the estimated surface generated by the algorithm is on the order of several millimeters. An error analysis conducted for a basic microwave radar imaging algorithm (least-squares narrowband beamforming) indicates that this level of error is acceptable. A key advantage of the algorithm is that it uses the same measured signals that are used for UWB microwave imaging, thereby minimizing patient scan time and avoiding the need for additional hardware.