Model-based Image Reconstruction Research Articles

Comparison of model-based versus deep learning-based image reconstruction for thin-slice T2-weighted spin-echo prostate MRI.

To compare a previous model-based image reconstruction (MBIR) with a newly developed deep learning (DL)-based image reconstruction for providing improved signal-to-noise ratio (SNR) in high through-plane resolution (1mm) T2-weighted spin-echo (T2SE) prostate MRI. Large-area contrast and high-contrast spatial resolution of the reconstruction methods were assessed quantitatively in experimental phantom studies. The methods were next evaluated radiologically in 17 subjects at 3.0 Tesla for whom prostate MRI was clinically indicated. For each subject, the axial T2SE raw data were directed to MBIR and to the DL reconstruction at three vendor-provided levels: (L)ow, (M)edium, and (H)igh. Thin-slice images from the four reconstructions were compared using evaluation criteria related to SNR, sharpness, contrast fidelity, and reviewer preference. Results were compared using the Wilcoxon signed-rank test using Bonferroni correction, and inter-reader comparisons were done using the Cohen and Krippendorf tests. Baseline contrast and resolution in phantom studies were equivalent for all four reconstruction pathways as desired. In vivo, all three DL levels (L, M, H) provided improved SNR versus MBIR. For virtually, all other evaluation criteria DL L and M were superior to MBIR. DL L and M were evaluated as superior to DL H in fidelity of contrast. For 44 of the 51 evaluations, the DL M reconstruction was preferred. The deep learning reconstruction method provides significant SNR improvement in thin-slice (1mm) T2SE images of the prostate while retaining image contrast. However, if taken to too high a level (DL High), both radiological sharpness and fidelity of contrast diminish.

Model-based reconstruction for looping-star MRI.

The aim of this study was to develop a reconstruction method that more fully models the signals and reconstructs gradient echo (GRE) images without sacrificing the signal to noise ratio and spatial resolution, compared to conventional gridding and model-based image reconstruction method. By modeling the trajectories for every spoke and simplifying the scenario to only echo-in and echo-out mixture, the approach explicitly models the overlapping echoes. After modeling the overlapping echoes with two system matrices, we use the conjugate gradient algorithm (CG-SENSE) with the nonuniform FFT (NUFFT) to optimize the image reconstruction cost function. The proposed method is demonstrated in phantoms and in-vivo volunteer experiments for three-dimensional, high-resolution T2*-weighted imaging and functional MRI tasks. Compared to the gridding method, the high resolution protocol exhibits improved spatial resolution and reduced signal loss as a result of less intra-voxel dephasing. The fMRI task shows that the proposed model-based method produced images with reduced artifacts and blurring as well as more stable and prominent time courses. The proposed model-based reconstruction results shows improved spatial resolution and reduced artifacts. The fMRI task shows improved time series and activation map due to the reduced overlapping echoes and under-sampling artifacts.

Joint B0 and Image Reconstruction in Low-Field MRI by Physics-Informed Deep-Learning.

We present a model-based image reconstruction approach based on unrolled neural networks which corrects for image distortion and noise in low-field ( B0 ∼ 50mT) MRI. Utilising knowledge about the underlying physics, a novel network architecture (SH-Net) is introduced which involves the estimation of spherical harmonic coefficients to guarantee a spatially smooth field map estimate. The SH-Net is integrated in an end-to-end trainable model which jointly estimates the B0-field map as well as the image. Experiments were conducted on retrospectively simulated low-field data of human knees. We compare our model to different model-based approaches at distinct noise levels and various B0-field distributions. Our results show that our physics-informed neural network approach outperforms the purely model-based methods by improving the PSNR up to 11.7% and the RMSE up to 86.3%. Our end-to-end trained model-based approach outperforms existing methods in reconstructing image and B0-field maps in the low-field regime. low-field MRI is becoming increasingly more popular as it enables access to MR in challenging situations such as intensive care units or resource poor areas. Our method allows for fast and accurate image reconstruction in such low-field imaging with B0-inhomogeneity compensation under a wide range of various environmental conditions.

On the detection of upper mantle discontinuities with radon-transformed receiver functions (CRISP-RF)

SUMMARYSeismic interrogation of the upper mantle from the base of the crust to the top of the mantle transition zone has revealed discontinuities that are variable in space, depth, lateral extent, amplitude and lack a unified explanation for their origin. Improved constraints on the detectability and properties of mantle discontinuities can be obtained with P-to-S receiver function (Ps-RF) where energy scatters from P to S as seismic waves propagate across discontinuities of interest. However, due to the interference of crustal multiples, uppermost mantle discontinuities are more commonly imaged with lower resolution S-to-P receiver function (Sp-RF). In this study, a new method called CRISP-RF (Clean Receiver-function Imaging using SParse Radon Filters) is proposed, which incorporates ideas from compressive sensing and model-based image reconstruction. The central idea involves applying a sparse Radon transform to effectively decompose the Ps-RF into its underlying wavefield contributions, that is direct conversions, multiples, and noise, based on the phase moveout and coherence. A masking filter is then designed and applied to create a multiple-free and denoised Ps-RF. We demonstrate, using synthetic experiment, that our implementation of the Radon transform using a sparsity-promoting regularization outperforms the conventional least-squares methods and can effectively isolate direct Ps conversions. We further apply the CRISP-RF workflow on real data, including single station data on cratons, common-conversion-point stack at continental margins and seismic data from ocean islands. The application of CRISP-RF to global data sets will advance our understanding of the enigmatic origins of the upper mantle discontinuities like the ubiquitous mid-lithospheric discontinuity and the elusive X-discontinuity.

MMV-Net: A Multiple Measurement Vector Network for Multifrequency Electrical Impedance Tomography.

Multifrequency electrical impedance tomography (mfEIT) is an emerging biomedical imaging modality to reveal frequency-dependent conductivity distributions in biomedical applications. Conventional model-based image reconstruction methods suffer from low spatial resolution, unconstrained frequency correlation, and high computational cost. Deep learning has been extensively applied in solving the EIT inverse problem in biomedical and industrial process imaging. However, most existing learning-based approaches deal with the single-frequency setup, which is inefficient and ineffective when extended to the multifrequency setup. This article presents a multiple measurement vector (MMV) model-based learning algorithm named MMV-Net to solve the mfEIT image reconstruction problem. MMV-Net considers the correlations between mfEIT images and unfolds the update steps of the Alternating Direction Method of Multipliers for the MMV problem (MMV-ADMM). The nonlinear shrinkage operator associated with the weighted l2,1 regularization term of MMV-ADMM is generalized in MMV-Net with a cascade of a Spatial Self-Attention module and a Convolutional Long Short-Term Memory (ConvLSTM) module to better capture intrafrequency and interfrequency dependencies. The proposed MMV-Net was validated on our Edinburgh mfEIT Dataset and a series of comprehensive experiments. The results show superior image quality, convergence performance, noise robustness, and computational efficiency against the conventional MMV-ADMM and the state-of-the-art deep learning methods.

A frequency-domain model-based reconstruction method for transcranial photoacoustic imaging: A 2D numerical investigation

Phase aberration caused by the skull is a major barrier to achieving high quality photoacoustic images of human and non-human primates’ brains. To address this issue, time-reversal methods have been used but they are computationally demanding and slow due to relying on solving the full-wave equation. The proposed approach is based on model-based image reconstruction in the frequency-domain to achieve near real-time image reconstruction. The relationship between an imaging region and transducer array elements can be mathematically described as a model matrix and the image reconstruction can be performed by pseudo-inverse of the model matrix. The model matrix is numerically calculated due to the lack of analytical solutions for transcranial ultrasound. However, this calculation only needs to be performed once for a given experimental setup and the same acoustic medium, and is an offline process not affecting the actual image reconstruction time. This non-iterative mode-based method demonstrates a substantial improvement in image reconstruction time, being approximately 18 times faster than the time-reversal method, all while maintaining comparable image quality.

Mitigating the Limited View Problem in Photoacoustic Tomography for a Planar Detection Geometry by Regularized Iterative Reconstruction.

The use of a planar detection geometry in photoacoustic tomography results in the so- called limited-view problem due to the finite extent of the acoustic detection aperture. When images are reconstructed using one-step reconstruction algorithms, image quality is compromised by the presence of streaking artefacts, reduced contrast, image distortion and reduced signal-to-noise ratio. To mitigate this, model-based iterative reconstruction approaches based on least squares minimisation with and without total variation regularization were evaluated using in-silico, experimental phantom, ex vivo and in vivo data. Compared to one-step reconstruction methods, it has been shown that iterative methods provide better image quality in terms of enhanced signal-to-artefact ratio, signal-to-noise ratio, amplitude accuracy and spatial fidelity. For the total variation approaches, the impact of the regularization parameter on image feature scale and amplitude distribution was evaluated. In addition, the extent to which the use of Bregman iterations can compensate for the systematic amplitude bias introduced by total variation was studied. This investigation is expected to inform the practical application of model-based iterative image reconstruction approaches for improving photoacoustic image quality when using finite aperture planar detection geometries.

Motion-corrected model-based reconstruction for 2D myocardial T1 mapping.

To allow for T1 mapping of the myocardium within 2.3 s for a 2D slice utilizing cardiac motion-corrected, model-based image reconstruction. Golden radial data acquisition is continuously carried out for 2.3 s after an inversion pulse. In a first step, dynamic images are reconstructed which show both contrast changes due to T1 recovery and anatomical changes due to the heartbeat. An image registration algorithm with a signal model for T1 recovery is applied to estimate non-rigid cardiac motion. In a second step, estimated motion fields are applied during an iterative model-based T1 reconstruction. The approach was evaluated in numerical simulations, phantom experiments and in in-vivo scans in healthy volunteers. The accuracy of cardiac motion estimation was shown in numerical simulations with an average motion field error of 0.7 ± 0.6 mm for a motion amplitude of 5.1 mm. The accuracy of T1 estimation was demonstrated in phantom experiments, with no significant difference (p = 0.13) in T1 estimated by the proposed approach compared to an inversion-recovery reference method. In vivo, the proposed approach yielded 1.3 × 1.3 mm T1 maps with no significant difference (p = 0.77) in T1 and SDs in comparison to a cardiac-gated approach requiring 16 s scan time (i.e., seven times longer than the proposed approach). Cardiac motion correction improved the precision of T1 maps, shown by a 40% reduced SD. We have presented an approach that provides T1 maps of the myocardium in 2.3 s by utilizing both cardiac motion correction and model-based T1 reconstruction.

Joint radial trajectory correction for accelerated T2 * mapping on an MR-Linac.

T2 * mapping can characterize tumor hypoxia, which may be associated with resistance to therapy. Acquiring T2 * maps during MR-guided radiotherapy could inform treatment adaptation by, for example, escalating the dose to resistant sub-volumes. The purpose of this work is to demonstrate the feasibility of the accelerated T2 * mapping technique using model-based image reconstruction with integrated trajectory auto-correction (TrACR) for MR-guided radiotherapy on an MR-Linear accelerator (MR-Linac). The proposed method was validated in a numerical phantom, where two T2 * mapping approaches (sequential and joint) were compared for different noise levels (0,0.1,0.5,1) and gradient delays ([1, -1] and [1, -2] in units of dwell time for x- and y-axis, respectively). Fully sampled k-space was retrospectively undersampled using two different undersampling patterns. Root mean square errors (RMSEs) were calculated between reconstructed T2 * maps and ground truth. In vivo data was acquired twice weekly in one prostate and one head and neck cancer patient undergoing treatment on a 1.5 T MR-Linac. Data were retrospectively undersampled and T2 * maps reconstructed, with and without trajectory corrections were compared. Numerical simulations demonstrated that, for all noise levels, T2 * maps reconstructed with a joint approach demonstrated less error compared to an uncorrected and sequential approach. For a noise level of 0.1, uniform undersampling and gradient delay [1, -1] (in units of dwell time for x- and y-axis, respectively), RMSEs for sequential and joint approaches were 13.01 and 9.32ms, respectively, which reduced to 10.92 and 5.89ms for a gradient delay of [1, 2]. Similarly, for alternate undersampling and gradient delay [1, -1], RMSEs for sequential and joint approaches were 9.80 and 8.90ms, respectively, which reduced to 9.10 and 5.40ms for gradient delay [1, 2]. For in vivo data, T2 * maps reconstructed with our proposed approach resulted in less artifacts and improved visual appearance compared to the uncorrected approach. For both prostate and head and neck cancer patients, T2 * maps reconstructed from different treatment fractions showed changes within the planning target volume (PTV). Using the proposed approach, a retrospective data-driven gradient delay correction can be performed, which is particularly relevant for hybrid devices, where full information on the machine configuration is not available for image reconstruction. T2 * maps were acquired in under 5 min and can be integrated into MR-guided radiotherapy treatment workflows, which minimizes patient burden and leaves time for additional imaging for online adaptive radiotherapy on an MR-Linac.

Towards quantitative in vivo dosimetry using x-ray acoustic computed tomography.

Radiation dosimetry is essential for radiation therapy (RT) to ensure that radiation dose is accurately delivered to the tumor. Despite its wide use in clinical intervention, the delivered radiation dose can only be planned and verified via simulation. This makes precision radiotherapy challenging while in-line verification of the delivered dose is still absent in the clinic. X-ray-induced acoustic computed tomography (XACT) has recently been proposed as an imaging tool for in vivo dosimetry. Most of the XACT studies focus on localizing the radiation beam. However, it has not been studied for its potential for quantitative dosimetry. The aim of this study was to investigate the feasibility of using XACT for quantitative in vivo dose reconstruction during radiotherapy. Varian Eclipse system was used to generate simulated uniform and wedged 3D radiation field with a size of 4 cm 4 cm. In order to use XACT for quantitative dosimetry measurements, we have deconvoluted the effects of both the x-ray pulse shape and the finite frequency response of the ultrasound detector. We developed a model-based image reconstruction algorithm to quantify radiation dose in vivo using XACT imaging, and universal back-projection (UBP) reconstruction is used as comparison. The reconstructed dose was calibrated before comparing it to the percent depth dose (PDD) profile. Structural similarity index matrix (SSIM) and root mean squared error (RMSE) are used for numeric evaluation. Experimental signals were acquired from 4 cm 4 cm radiation field created by Linear Accelerator (LINAC) at depths of 6, 8, and 10 cm beneath the water surface. The acquired signals were processed before reconstruction to achieve accurate results. Applying model-based reconstruction algorithm with non-negative constraints successfully reconstructed accurate radiation dose in 3D simulation study. The reconstructed dose matches well with the PDD profile after calibration in experiments. The SSIMs between the model-based reconstructions and initial doses are over 85%, and the RMSEs of model-based reconstructions are eight times lower than the UBP reconstructions. We have also shown that XACT images can be displayed as pseudo-color maps of acoustic intensity, which correspond to different radiation doses in the clinic. Our results show that the XACT imaging by model-based reconstruction algorithm is considerably more accurate than the dose reconstructed by UBP algorithm. With proper calibration, XACT is potentially applicable to the clinic for quantitative in vivo dosimetry across a wide range of radiation modalities. In addition, XACT's capability of real-time, volumetric dose imaging seems well-suited for the emerging field of ultrahigh dose rate "FLASH" radiotherapy.

Compact breast shape acquisition system for improving diffuse optical tomography image reconstructions.

Diffuse optical tomography (DOT) has been investigated for diagnosing malignant breast lesions, but its accuracy relies on model-based image reconstructions, which in turn depends on the accuracy of breast shape acquisition. In this work, we have developed a dual-camera structured light imaging (SLI) breast shape acquisition system tailored for a mammography-like compression setting. Illumination pattern intensity is dynamically adjusted to account for skin tone differences, while thickness-informed pattern masking reduces artifacts due to specular reflections. This compact system is affixed to a rigid mount that can be installed into existing mammography or parallel-plate DOT systems without the need for camera-projector re-calibration. Our SLI system produces sub-millimeter resolution with a mean surface error of 0.26 mm. This breast shape acquisition system results in more accurate surface recovery, with an average 1.6-fold reduction in surface estimation errors over a reference method via contour extrusion. Such improvement translates to 25% to 50% reduction in mean squared error in the recovered absorption coefficient for a series of simulated tumors 1-2 cm below the skin.

Linearized Analysis of Noise and Resolution for DL-Based Image Generation.

Deep-learning (DL) based CT image generation methods are often evaluated using RMSE and SSIM. By contrast, conventional model-based image reconstruction (MBIR) methods are often evaluated using image properties such as resolution, noise, bias. Calculating such image properties requires time consuming Monte Carlo (MC) simulations. For MBIR, linearized analysis using first order Taylor expansion has been developed to characterize noise and resolution without MC simulations. This inspired us to investigate if linearization can be applied to DL networks to enable efficient characterization of resolution and noise. We used FBPConvNet as an example DL network and performed extensive numerical evaluations, including both computer simulations and real CT data. Our results showed that network linearization works well under normal exposure settings. For such applications, linearization can characterize image noise and resolutions without running MC simulations. We provide with this work the computational tools to implement network linearization. The efficiency and ease of implementation of network linearization can hopefully popularize the physics-related image quality measures for DL applications. Our methodology is general; it allows flexible compositions of DL nonlinear modules and linear operators such as filtered-backprojection (FBP). For the latter, we develop a generic method for computing the covariance images that is needed for network linearization.

A model-based image reconstruction algorithm for near real-time transcranial photoacoustic imaging

Photoacoustic imaging is a promising hybrid imaging modality that can visualize both microscopic and macroscopic structures and oxygenation changes in brain function. Phase aberration caused by the skull is a major barrier for high-quality photoacoustic imaging of the brain. Time-reversal methods have been used to address this issue, though they rely on solving the full-wave equation, and is therefore computationally heavy and slow. Herein, a near real-time model-based image reconstruction algorithm is proposed. The acoustic forward model is mathematically described as a model matrix and image reconstructions are performed by employing the pseudoinverse of the model matrix and calculating the initial pressure distribution. The pseudoinverse matrix only needs to be computed once for the same experimental setup and acoustic medium and is obtained offline prior to imaging. The proposed algorithm shows equivalent image quality but considerably faster reconstruction time (>40 times faster), compared to the time-reversal method and therefore could potentially enable near real-time photoacoustic imaging.

Efficient Approximation of Jacobian Matrices Involving a Non-Uniform Fast Fourier Transform (NUFFT).

There is growing interest in learning Fourier domain sampling strategies (particularly for magnetic resonance imaging, MRI) using optimization approaches. For non-Cartesian sampling, the system models typically involve non-uniform fast Fourier transform (NUFFT) operations. Commonly used NUFFT algorithms contain frequency domain interpolation, which is not differentiable with respect to the sampling pattern, complicating the use of gradient methods. This paper describes an efficient and accurate approach for computing approximate gradients involving NUFFTs. Multiple numerical experiments validate the improved accuracy and efficiency of the proposed approximation. As an application to computational imaging, the NUFFT Jacobians were used to optimize non-Cartesian MRI sampling trajectories via data-driven stochastic optimization. Specifically, the sampling patterns were learned with respect to various model-based image reconstruction (MBIR) algorithms. The proposed approach enables sampling optimization for image sizes that are infeasible with standard auto-differentiation methods due to memory limits. The synergistic acquisition and reconstruction design leads to remarkably improved image quality. In fact, we show that model-based image reconstruction methods with suitably optimized imaging parameters can perform nearly as well as CNN-based methods.

SPECT reconstruction with a trained regularizer using CT-side information: Application to 177Lu SPECT imaging.

Improving low-count SPECT can shorten scans and support pre-therapy theranostic imaging for dosimetry-based treatment planning, especially with radionuclides like 177Lu known for low photon yields. Conventional methods often underperform in low-count settings, highlighting the need for trained regularization in model-based image reconstruction. This paper introduces a trained regularizer for SPECT reconstruction that leverages segmentation based on CT imaging. The regularizer incorporates CT-side information via a segmentation mask from a pre-trained network (nnUNet). In this proof-of-concept study, we used patient studies with 177Lu DOTATATE to train and tested with phantom and patient datasets, simulating pre-therapy imaging conditions. Our results show that the proposed method outperforms both standard unregularized EM algorithms and conventional regularization with CT-side information. Specifically, our method achieved marked improvements in activity quantification, noise reduction, and root mean square error. The enhanced low-count SPECT approach has promising implications for theranostic imaging, post-therapy imaging, whole body SPECT, and reducing SPECT acquisition times.

RISING: A new framework for model-based few-view CT image reconstruction with deep learning.

Medical image reconstruction from low-dose tomographic data is an active research field, recently revolutionized by the advent of deep learning. In fact, deep learning typically yields superior results than classical optimization approaches, but unstable results have been reported both numerically and theoretically in the literature. This paper proposes RISING, a new framework for sparse-view tomographic image reconstruction combining an early-stopped Rapid Iterative Solver with a subsequent Iteration Network-based Gaining step. In our two-step approach, the first phase executes very few iterations of a regularized model-based algorithm, whereas the second step completes the missing iterations by means of a convolutional neural network. The proposed method is ground-truth free; it exploits the computational speed and flexibility of a data-driven approach, but it also imposes sparsity constraints to the solution as in the model-based setting. Experiments performed both on a digitally created and on a real abdomen data set confirm the numerical and visual accuracy of the reconstructed RISING images in short computational times. These features make the framework promising to be used on real systems for clinical exams.

OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing.

Non-mydriatic retinal color fundus photography (CFP) is widely available due to the advantage of not requiring pupillary dilation, however, is prone to poor quality due to operators, systemic imperfections, or patient-related causes. Optimal retinal image quality is mandated for accurate medical diagnoses and automated analyses. Herein, we leveraged the Optimal Transport (OT) theory to propose an unpaired image-to-image translation scheme for mapping low-quality retinal CFPs to high-quality counterparts. Furthermore, to improve the flexibility, robustness, and applicability of our image enhancement pipeline in the clinical practice, we generalized a state-of-the-art model-based image reconstruction method, regularization by denoising, by plugging in priors learned by our OT-guided image-to-image translation network. We named it as regularization by enhancing (RE). We validated the integrated framework, OTRE, on three publicly available retinal image datasets by assessing the quality after enhancement and their performance on various downstream tasks, including diabetic retinopathy grading, vessel segmentation, and diabetic lesion segmentation. The experimental results demonstrated the superiority of our proposed framework over some state-of-the-art unsupervised competitors and a state-of-the-art supervised method.

A graphical user interface (GUI) for model-based radiation-induced acoustic computed tomography

Radiation-induced acoustic computed tomography (RACT) is an evolving biomedical imaging modality that aims to reconstruct the radiation energy deposition in tissues. Traditional back-projection (BP) reconstructions carry noisy and limited-view artifacts. Model-based algorithms have been demonstrated to overcome the drawbacks of BPs. However, model-based algorithms are relatively more complex to develop and computationally demanding. Furthermore, while a plethora of novel algorithms has been developed over the past decade, most of these algorithms are either not accessible, readily available, or hard to implement for researchers who are not well versed in programming. We developed a user-friendly MATLAB-based graphical user interface (GUI; RACT2D) that facilitates back-projection and model-based image reconstructions for two-dimensional RACT problems. We included numerical and experimental X-ray-induced acoustic datasets to demonstrate the capabilities of the GUI. The developed algorithms support parallel computing for evaluating reconstructions using the cores of the computer, thus further accelerating the reconstruction speed. We also share the MATLAB-based codes for evaluating RACT reconstructions, which users with MATLAB programming expertise can further modify to suit their needs. The shared GUI and codes can be of interest to researchers across the globe and assist them in efficient evaluation of improved RACT reconstructions.

Joint Demosaicing and Fusion of Multiresolution Coded Acquisitions: A Unified Image Formation and Reconstruction Method

Novel optical imaging devices allow for hybrid acquisition modalities such as compressed acquisitions with locally different spatial and spectral resolutions captured by the same focal plane array. In this work, we propose to model a multiresolution coded acquisition (MRCA) in a generic framework, which natively includes acquisitions by conventional systems such as those based on spectral/color filter arrays, compressed coded apertures, and multiresolution sensing. We propose a model-based image reconstruction algorithm performing a joint demosaicing and fusion (JoDeFu) of any acquisition modeled in the MRCA framework. The JoDeFu reconstruction algorithm solves an inverse problem with a proximal splitting technique and is able to reconstruct an uncompressed image datacube at the highest available spatial and spectral resolution. An implementation of the code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/danaroth83/jodefu</uri> .

Diagnostic Evaluation of Rheumatoid Arthritis (RA) in Finger Joints Based on the Third-Order Simplified Spherical Harmonics (SP3) Light Propagation Model

This work focuses on the evaluation of third-order simplified spherical harmonics (SP3) model-based image reconstruction with respect to its clinical utility to diagnose rheumatoid arthritis (RA). The existing clinical data of 219 fingers was reconstructed for both absorption and scattering maps in fingers by using the reduced-Hessian sequential quadratic programming (rSQP) algorithm that employs the SP3 model of light propagation. The k-fold cross validation method was used for feature extraction and classification of SP3-based tomographic images. The performance of the SP3 model was compared to the DE and ERT models with respect to diagnostic accuracy and computational efficiency. The results presented here show that the SP3 model achieves clinically relevant sensitivity (88%) and specificity (93%) that compare favorably to the ERT while maintaining significant computational advantage over the ERT (i.e., the SP3 model is 100 times faster than the ERT). Furthermore, it is also shown that the SP3 is similar in speed but superior in diagnostic accuracy to the DE. Therefore, it is expected that the method presented here can greatly aid in the early diagnosis of RA with clinically relevant accuracy in near real-time at a clinical setting.