Emerging uses of artificial intelligence in breast and axillary ultrasound.

Breast ultrasound is a valuable adjunctive tool to mammography in detecting breast cancer, especially in women with dense breasts. Ultrasound also plays an important role in staging breast cancer by assessing axillary lymph nodes. However, its utility is limited by operator dependence, high recall rate, low positive predictive value and low specificity. These limitations present an opportunity for artificial intelligence (AI) to improve diagnostic performance and pioneer novel uses of ultrasound. Research in developing AI for radiology has flourished over the past few years. A subset of AI, deep learning, uses interconnected computational nodes to form a neural network, which extracts complex visual features from image data to train itself into a predictive model. This review summarizes several key studies evaluating AI programs' performance in predicting breast cancer and demonstrates that AI can assist radiologists and address limitations of ultrasound by acting as a decision support tool. This review also touches on how AI programs allow for novel predictive uses of ultrasound, particularly predicting molecular subtypes of breast cancer and response to neoadjuvant chemotherapy, which have the potential to change how breast cancer is managed by providing non-invasive prognostic and treatment data from ultrasound images. Lastly, this review explores how AI programs demonstrate improved diagnostic accuracy in predicting axillary lymph node metastasis. The limitations and future challenges in developing and implementing AI for breast and axillary ultrasound will also be discussed.

Image-Guided Precision Medicine in the Diagnosis and Treatment of Pheochromocytomas and Paragangliomas.

In this comprehensive review, we aimed to discuss the current state-of-the-art medical imaging for pheochromocytomas and paragangliomas (PPGLs) diagnosis and treatment. Despite major medical improvements, PPGLs, as with other neuroendocrine tumors (NETs), leave clinicians facing several challenges; their inherent particularities and their diagnosis and treatment pose several challenges for clinicians due to their inherent complexity, and they require management by multidisciplinary teams. The conventional concepts of medical imaging are currently undergoing a paradigm shift, thanks to developments in radiomic and metabolic imaging. However, despite active research, clinical relevance of these new parameters remains unclear, and further multicentric studies are needed in order to validate and increase widespread use and integration in clinical routine. Use of AI in PPGLs may detect changes in tumor phenotype that precede classical medical imaging biomarkers, such as shape, texture, and size. Since PPGLs are rare, slow-growing, and heterogeneous, multicentric collaboration will be necessary to have enough data in order to develop new PPGL biomarkers. In this nonsystematic review, our aim is to present an exhaustive pedagogical tool based on real-world cases, dedicated to physicians dealing with PPGLs, augmented by perspectives of artificial intelligence and big data.

Delays in imaging diagnosis of acute abdominal pain in the emergency setting.

Acute abdominal pain is a common cause of ED visits and often requires imaging to identify a specific diagnosis. Prompt and appropriate imaging plays a crucial role in patient management and leads to improved patient outcomes, decreased hospital stay, and improved ED workflow. There are many cases of abdominal pain in the ED with delayed diagnosis and management secondary to a combination of institutional policies and knowledge deficits in current imaging guidelines. Inappropriate use of abdominal radiographs, use of oral contrast for CT abdomen and pelvis, and concern for iodinated contrast-induced acute kidney injury are three of the more commonly encountered roadblocks to prompt imaging diagnosis of abdominal pain. The purpose of this review is to discuss why these potential causes of delayed diagnosis occur and how radiologists can help improve both imaging and ED workflow by utilizing the most up-to-date imaging guidelines such the American College of Radiology (ACR) Appropriateness Criteria and ACR Manual on Contrast Media to assist clinicians working in the emergency setting.

D-cis-Diltiazem Can Produce Oxidative Stress in Healthy Depolarized Rods In Vivo.

Purpose: New perspectives are needed to understand decades of contradictory reports on the neuroprotective effects of the Cav1.2 L-type calcium channel blocker d-cis-diltiazem in retinitis pigmentosa (RP) models. Here, we address, in vivo, the following two knowledge gaps regarding d-cis-diltiazem's actions in the murine outer retina: (1) do normal mouse rods contain d-cis-diltiazem-insensitive Cav1.2 L-type calcium channels? (2) Can d-cis-diltiazem modify the normal rod redox environment? Methods: First, transretinal Cav1.2 L-type calcium channels were noninvasively mapped with manganese-enhanced magnetic resonance imaging (MRI) following agonist Bay K 8644 in C57BL/6 (B6) and in Cav1.2 L-type calcium channel BAY K 8644-insensitive mutant B6 mice. Second, d-cis-diltiazem-treated oxidative stress-vulnerable (B6) or -resistant [129S6 (S6)] mice were examined in vivo (QUEnch-assiSTed [QUEST] MRI) and in whole retina ex vivo (lucigenin). Retinal thickness was measured using MRI. Results: The following results were observed: (1) manganese uptake patterns in BAY K 8644-treated controls and mutant mice identified in vivo Cav1.2 L-type calcium channels in inner and outer retina; and (2) d-cis-diltiazem induced rod oxidative stress in dark-adapted B6 mice but not in light-adapted B6 mice or dark-adapted S6 mice (QUEST MRI). Oxidative stress in vivo was limited to inferior outer retina in dark-adapted B6 mice approximately 1-hour post d-cis-diltiazem. By approximately 4 hours post, only superior outer retina oxidative stress was observed and whole retinal superoxide production was supernormal. All groups had unremarkable retinal thicknesses. Conclusions: D-cis-diltiazem's unexpectedly complex spatiotemporal outer retinal oxidative stress pattern in vivo was dependent on genetic background and rod membrane depolarization, but not apparently dependent on Cav1.2 L-type calcium channels, providing a potential rationale for contradictory results in different RP models.