Evaluation of a pipeline for simulation, reconstruction, and classification in ultrasound-aided diffuse optical tomography of breast tumors

Abstract

. Significance : Diffuse optical tomography is an ill-posed problem. Combination with ultrasound can improve the results of diffuse optical tomography applied to the diagnosis of breast cancer and allow for classification of lesions. Aim : To provide a simulation pipeline for the assessment of reconstruction and classification methods for diffuse optical tomography with concurrent ultrasound information. Approach : A set of breast digital phantoms with benign and malignant lesions was simulated building on the software VICTRE. Acoustic and optical properties were assigned to the phantoms for the generation of B-mode images and optical data. A reconstruction algorithm based on a two-region nonlinear fitting and incorporating the ultrasound information was tested. Machine learning classification methods were applied to the reconstructed values to discriminate lesions into benign and malignant after reconstruction. Results : The approach allowed us to generate realistic US and optical data and to test a two-region reconstruction method for a large number of realistic simulations. When information is extracted from ultrasound images, at least 75% of lesions are correctly classified. With ideal two-region separation, the accuracy is higher than 80%. Conclusions : A pipeline for the generation of realistic ultrasound and diffuse optics data was implemented. Machine learning methods applied to a optical reconstruction with a nonlinear optical model and morphological information permit to discriminate malignant lesions from benign ones.

Breast lesion classification based on absorption and composition parameters: a look at SOLUS first outcomes

“…In fact, from the US B-mode image, a lesion segmentation is obtained and extrapolated to 3D to be used as morphological prior for the optical reconstruction [3]. DOT reconstructions exploit the Born approximation of the heterogenous analytical solution of the diffusion equation to estimate the absorption coefficients of the investigated breast tissue at the 8 wavelengths [4]. The breast tissue composition (oxy-and deoxy-hemoglobin, water, lipids, and collagen concentrations) is later retrieved by applying the Lambert-Beer law.…”

Orthogonal Multi-frequency Fusion Based Image Reconstruction and Diagnosis in Diffuse Optical Tomography

“…A difference based approach reconstructed optical properties and estimated tissue composition for seven collected wavelengths (635-1060 nm) followed by a discrete AdaBoost classifier. Augmenting DOT with ultrasound is finding recent adoption as well, an example of multi-modal fusion [29], [30]. The aforementioned art is based on conventional reconstruction algorithms.…”

Real‐time breast lesion classification combining diffuse optical tomography frequency domain data and BI‐RADS assessment

“…In recent years, machine learning approaches have enhanced breast cancer diagnosis using DOT [10][11][12][13]. Di Sciacca et al [11] utilized traditional machine learning and a neural network to classify simulated breast lesions, achieving an accuracy of 78%.…”

“…In recent years, machine learning approaches have enhanced breast cancer diagnosis using DOT [10][11][12][13]. Di Sciacca et al [11] utilized traditional machine learning and a neural network to classify simulated breast lesions, achieving an accuracy of 78%. Xu et al [12] applied a convolutional neural network (CNN) to classify 2D optical tomographic images obtained from 63 patients and achieved an area under the receiver operating characteristic curve (AUC) of 0.95.…”