Motivation: The price of medical treatment continues to rise due to (i) an increasing population; (ii) an aging human growth; (iii) disease prevalence; (iv) a rise in the frequency of patients that utilize health care services; and (v) increase in the price. Objective: Artificial Intelligence (AI) is already well-known for its superiority in various healthcare applications, including the segmentation of lesions in images, speech recognition, smartphone personal assistants, navigation, ride-sharing apps, and many more. Our study is based on two hypotheses: (i) AI offers more economic solutions compared to conventional methods; (ii) AI treatment offers stronger economics compared to AI diagnosis. This novel study aims to evaluate AI technology in the context of healthcare costs, namely in the areas of diagnosis and treatment, and then compare it to the traditional or non-AI-based approaches. Methodology: PRISMA was used to select the best 200 studies for AI in healthcare with a primary focus on cost reduction, especially towards diagnosis and treatment. We defined the diagnosis and treatment architectures, investigated their characteristics, and categorized the roles that AI plays in the diagnostic and therapeutic paradigms. We experimented with various combinations of different assumptions by integrating AI and then comparing it against conventional costs. Lastly, we dwell on three powerful future concepts of AI, namely, pruning, bias, explainability, and regulatory approvals of AI systems. Conclusions: The model shows tremendous cost savings using AI tools in diagnosis and treatment. The economics of AI can be improved by incorporating pruning, reduction in AI bias, explainability, and regulatory approvals.

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13–55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm.

Shear wave elastography is emerging as a clinically valuable diagnostic tool to differentiate between benign and malignant breast masses. Elastography techniques assume that soft tissue can be modelled as a purely elastic medium. However, this assumption is often violated as soft tissue exhibits viscoelastic properties. In order to explore the role of viscoelastic parameters in suspicious breast masses, a study was conducted on a group of patients using shear wave dispersion ultrasound vibrometry in the frequency range of 50–400 Hz. A total of 43 female patients with suspicious breast masses were recruited before their scheduled biopsy. Of those, 15 patients did not meet the data selection criteria. Voigt model based shear elasticity showed a significantly (p = 7.88x10^-6) higher median value for the 13 malignant masses (16.76±13.10 kPa) compared to 15 benign masses (1.40±1.12 kPa). Voigt model based shear viscosity was significantly different (p = 4.13x10^-5) between malignant (8.22±3.36 Pa-s) and benign masses (2.83±1.47 Pa-s). Moreover, the estimated time constant from the Voigt model, which is dependent on both shear elasticity and viscosity, differed significantly (p = 6.13x10^-5) between malignant (0.68±0.33 ms) and benign masses (3.05±1.95 ms). Results suggest that besides elasticity, viscosity based parameters like shear viscosity and time constant can also be used to differentiate between malignant and benign breast masses.

Sonographic features associated with margins, shape, size, and volume of thyroid nodules are used to assess their risk of malignancy. Automatically segmenting nodules from normal thyroid gland would enable an automated estimation of these features. A novel multi-output convolutional neural network algorithm with dilated convolutional layers is presented to segment thyroid nodules, cystic components inside the nodules, and normal thyroid gland from clinical ultrasound B-mode scans. A prospective study was conducted, collecting data from 234 patients undergoing a thyroid ultrasound exam before biopsy. The training and validation sets encompassed 188 patients total; the testing set consisted of 48 patients. The algorithm effectively segmented thyroid anatomy into nodules, normal gland, and cystic components. The algorithm achieved a mean Dice coefficient of 0.76, a mean true positive fraction of 0.90, and a mean false positive fraction of 1.61 × 10 ^-6 . The values are on par with a conventional seeded algorithm. The proposed algorithm eliminates the need for a seed in the segmentation process, thus automatically detecting and segmenting the thyroid nodules and cystic components. The detection rate for thyroid nodules and cystic components was 82% and 44%, respectively. The inference time per image, per fold was 107ms. The mean error in volume estimation of thyroid nodules for five select cases was 7.47%. The algorithm can be used for detection, segmentation, size estimation, volume estimation, and generating thyroid maps for thyroid nodules. The algorithm has applications in point of care, mobile health monitoring, improving workflow, reducing localization time, and assisting sonographers with limited expertise.

Objective: Recent advances in ultrasound Doppler imaging have made it possible to visualize small vessels with diameters near the imaging resolution limits using spatiotemporal singular value thresholding of long ensembles of ultrasound data. However, vessel images derived based on this method present severe intensity variations and additional background noise that limits visibility and subsequent processing such as centerline extraction and morphological analysis. The goal of this paper is to devise a method to enhance vessel-background separation directly on the power Doppler images by exploiting blood echo-noise independence. Method: We present a two-step algorithm to mitigate these adverse effects when using singular value thresholding for obtaining gross vasculature images. Our method comprises a morphological-based filtering for removing global and local background signals and a multiscale Hessian-based vessel enhancement filtering to further improve the vascular structures. We applied our method for in vivo imaging of the microvasculature of kidney in one healthy subject, liver in five healthy subjects, thyroid nodules in five patients, and breast tumors in five patients. Results: Singular value thresholding, top-hat filtering, and Hessian-based vessel enhancement filtering each provided an average peak-to-side level gain of 1.11, 18.55, and 2.26 dB, respectively, resulting in an overall gain of 21.92 dB when compared to the conventional power Doppler imaging using infinite impulse response filtering. Conclusion: Singular value thresholding combined with morphological and Hessian-based vessel enhancement filtering provides a powerful tool for visualization of the deep-seated small vessels using long ultrasound echo ensembles without requiring any type of contrast enhancing agents. Significance: This method provides a fast and cost-effective modality for in vivo assessment of the microvasculature suitable for both clinical and preclinical applications.

SARS-CoV-2 has infected over ∼165 million people worldwide causing Acute Respiratory Distress Syndrome (ARDS) and has killed ∼3.4 million people. Artificial Intelligence (AI) has shown to benefit in the biomedical image such as X-ray/Computed Tomography in diagnosis of ARDS, but there are limited AI-based systematic reviews (aiSR). The purpose of this study is to understand the Risk-of-Bias (RoB) in a non-randomized AI trial for handling ARDS using novel AtheroPoint-AI-Bias (AP(ai)Bias). Our hypothesis for acceptance of a study to be in low RoB must have a mean score of 80% in a study. Using the PRISMA model, 42 best AI studies were analyzed to understand the RoB. Using the AP(ai)Bias paradigm, the top 19 studies were then chosen using the raw-cutoff of 1.9. This was obtained using the intersection of the cumulative plot of “mean score vs. study” and score distribution. Finally, these studies were benchmarked against ROBINS-I and PROBAST paradigm. Our observation showed that AP(ai)Bias, ROBINS-I, and PROBAST had only 32%, 16%, and 26% studies, respectively in low-moderate RoB (cutoff>2.5), however none of them met the RoB hypothesis. Further, the aiSR analysis recommends six primary and six secondary recommendations for the non-randomized AI for ARDS. The primary recommendations for improvement in AI-based ARDS design inclusive of (i) comorbidity, (ii) inter-and intra-observer variability studies, (iii) large data size, (iv) clinical validation, (v) granularity of COVID-19 risk, and (vi) cross-modality scientific validation. The AI is an important component for diagnosis of ARDS and the recommendations must be followed to lower the RoB.