Progress in computing power and advances in medical imaging over recent decades have culminated in new opportunities for artificial intelligence (AI), computer vision, and using radiomics to facilitate clinical decision-making. These opportunities are growing in medical specialties, such as radiology, pathology, and oncology. As medical imaging and pathology are becoming increasingly digitized, it is recently recognized that harnessing data from digital images can yield parameters that reflect the underlying biology and physiology of various malignancies. This greater understanding of the behaviour of cancer can potentially improve on therapeutic strategies. In addition, the use of AI is particularly appealing in oncology to facilitate the detection of malignancies, to predict the likelihood of tumor response to treatments, and to prognosticate the patients' risk of cancer-related mortality. AI will be critical for identifying candidate biomarkers from digital imaging and developing robust and reliable predictive models. These models will be used to personalize oncologic treatment strategies, and identify confounding variables that are related to the complex biology of tumors and diversity of patient-related factors (ie, mining ''big data''). This commentary describes the growing body of work focussed on AI for precision oncology. Advances in AI-driven

Contrast-medium-enhanced digital mammography (CEDM) is an image subtraction technique which might help unmasking lesions embedded in very dense breasts. Previous works have stated the feasibility of CEDM and the imperative need of radiological optimization. This work presents an extension of a former analytical formalism to predict contrast-to-noise ratio (CNR) in subtracted mammograms. The goal is to optimize radiological parameters available in a clinical mammographic unit (x-ray tube anode/filter combination, voltage, and loading) by maximizing CNR and minimizing total mean glandular dose (D(gT)), simulating the experimental application of an iodine-based contrast medium and the image subtraction under dual-energy nontemporal, and single- or dual-energy temporal modalities. Total breast-entrance air kerma is limited to a fixed 8.76 mGy (1 R, similar to screening studies). Mathematical expressions obtained from the formalism are evaluated using computed mammographic x-ray spectra attenuated by an adipose/glandular breast containing an elongated structure filled with an iodinated solution in various concentrations. A systematic study of contrast, its associated variance, and CNR for different spectral combinations is performed, concluding in the proposal of optimum x-ray spectra. The linearity between contrast in subtracted images and iodine mass thickness is proven, including the determination of iodine visualization limits based on Rose's detection criterion. Finally, total breast-entrance air kerma is distributed between both images in various proportions in order to maximize the figure of merit CNR2/D(gT). Predicted results indicate the advantage of temporal subtraction (either single- or dual-energy modalities) with optimum parameters corresponding to high-voltage, strongly hardened Rh/Rh spectra. For temporal techniques, CNR was found to depend mostly on the energy of the iodinated image, and thus reduction in D(gT) could be achieved if the spectral energy of the noniodinated image is decreased and the breast-entrance air kerma is evenly distributed between both acquisitions. Predicted limits, in terms of iodine concentration, are found to guarantee the visualization of common clinical angiogenic concentrations in the breast.

No abstract

This manuscript reports preliminary results obtained by combining estimates of two or three (among seven) quantitative ultrasound (QUS) parameters in a model-free, multi-parameter classifier to differentiate breast carcinomas from fibroadenomas (the most common benign solid tumor). Forty-three subjects scheduled for core biopsy of a suspicious breast mass were recruited. Radiofrequency echo signal data were acquired using clinical breast ultrasound systems equipped with linear array transducers. The Reference Phantom Method was used to obtain systemindependent estimates of the specific attenuation (ATT), the average backscatter coefficients (ABSC), the effective scatterer diameter (ESD) and an effective scatterer diameter heterogeneity index (ESDHI) over regions of interest within each mass. In addition, the envelope amplitude signal-to-noise ratio (SNR), the Nakagami shape parameter, m, and the maximum collapsed average (maxCA) of the generalized spectrum were also computed. Classification was performed using the minimum Mahalanobis distance to the centroids of the training classes and tested against biopsy results. Classification performance was evaluated with the area under the receiver-operating characteristic (ROC) curve. The best performance with a two-parameter classifier used the ESD and ESDHI and resulted in an area under the ROC curve of 0.98 [0.95-1.00, 95% confidence interval]. Classification performance improved with three parameters (ATT, ESD, and ESDHI) yielding an area under the ROC curve of 0.999 [0.995-1.000].These results suggest that system independent QUS parameters, when combined in a model-free classifier, are a promising tool to characterize breast tumors. A larger study is needed to further test this idea.

One of the main limitations of ultrasound imaging is that image quality and interpretation depend on the skill of the user and the experience of the clinician. Quantitative ultrasound (QUS) methods provide objective, system-independent estimates of tissue properties, such as acoustic attenuation and backscattering properties of tissue, which are valuable as objective tools for both diagnosis and intervention. Accurate and precise estimation of these properties requires correct compensation for intervening tissue attenuation. Prior attempts to estimate intervening-tissue attenuation based on minimizing cost functions that compared backscattered echo data to models have resulted in limited precision and accuracy. To overcome these limitations, in this paper, we incorporate the prior information of piecewise continuity of QUS parameters as a regularization term into our cost function. We further propose to calculate this cost function using dynamic programming (DP), a computationally efficient optimization algorithm that finds the global optimum. Our results on tissue-mimicking phantoms show that DP substantially outperforms a published least squares method in terms of both estimation bias and variance.