Artificial intelligence-enhanced opportunistic screening of osteoporosis in CT scan: a scoping Review.

PURPOSE: This scoping review aimed to assess the current research on artificial intelligence (AI)--enhanced opportunistic screening approaches for stratifying osteoporosis and osteopenia risk by evaluating vertebral trabecular bone structure in CT scans. METHODS: PubMed, Scopus, and Web of Science databases were systematically searched for studies published between 2018 and December 2023. Inclusion criteria encompassed articles focusing on AI techniques for classifying osteoporosis/osteopenia or determining bone mineral density using CT scans of vertebral bodies. Data extraction included study characteristics, methodologies, and key findings. RESULTS: Fourteen studies met the inclusion criteria. Three main approaches were identified: fully automated deep learning solutions, hybrid approaches combining deep learning and conventional machine learning, and non-automated solutions using manual segmentation followed by AI analysis. Studies demonstrated high accuracy in bone mineral density prediction (86-96%) and classification of normal versus osteoporotic subjects (AUC 0.927-0.984). However, significant heterogeneity was observed in methodologies, workflows, and ground truth selection. CONCLUSIONS: The review highlights AI's promising potential in enhancing opportunistic screening for osteoporosis using CT scans. While the field is still in its early stages, with most solutions at the proof-of-concept phase, the evidence supports increased efforts to incorporate AI into radiologic workflows. Addressing knowledge gaps, such as standardizing benchmarks and increasing external validation, will be crucial for advancing the clinical application of these AI-enhanced screening methods. Integration of such technologies could lead to improved early detection of osteoporotic conditions at a low economic cost.

A systematic review of deep learning-based spinal bone lesion detection in medical images.

Spinal bone lesions encompass a wide array of pathologies, spanning from benign abnormalities to aggressive malignancies, such as diffusely localized metastases. Early detection and accurate differentiation of the underlying diseases is crucial for every patient's clinical treatment and outcome, with radiological imaging being a core element in the diagnostic pathway. Across numerous pathologies and imaging techniques, deep learning (DL) models are progressively considered a valuable resource in the clinical setting. This review describes not only the diagnostic performance of these models and the differing approaches in the field of spinal bone malignancy recognition, but also the lack of standardized methodology and reporting that we believe is currently hampering this newly founded area of research. In line with their established and reliable role in lesion detection, this publication focuses on both computed tomography and magnetic resonance imaging, as well as various derivative modalities (i.e. SPECT). After conducting a systematic literature search and subsequent analysis for applicability and quality using a modified QUADAS-2 scoring system, we confirmed that most of the 14 identified studies were plagued by major limitations, such as insufficient reporting of model statistics and data acquisition, a lacking external validation dataset, and potentially biased annotation. Although we experienced these limitations, we nonetheless conclude that the potential of these methods shines through in the presented results. These findings underline the need for more stringent quality controls in DL studies, as well as model development to afford increased insight and progress in this promising novel field.

Advancements in opportunistic intracranial aneurysm screening: The impact of a deep learning algorithm on radiologists' analysis of T2-weighted cranial MRI.

(1) Background: Unruptured Intracranial Aneurysms (UIAs) are common blood vessel malformations, occurring in up to 3 % of healthy adults. Magnetic Resonance Angiography (MRA) is frequently used for the screening of UIAs due to its high resolution in vascular anatomy. However, T2-Weighted Magnetic Resonance Imaging (T2WI) is a standard sequence utilized for the majority of outpatient head scans. By employing a sequence such as T2WI, there is a possible shift towards early detection of UIAs through opportunistic screening. Here, we assess a Deep Learning Algorithm (DLA) developed to assist radiologists in identifying and reporting UIAs on T2WI in a routine clinical setting. (2) Methods: A DLA was trained on a set of 110 patients undergoing an MR head scan with the gold standard set by two radiology experts. Eight radiologists were given a cohort of 50 cranial T2WI studies and asked for a routine report. After a 10-day washout period, they reviewed the same cases randomized and supported by the DLA predictions. We assessed changes in sensitivity, specificity, accuracy, and false positives. (3) Results: During routine reporting, the models' assistance improved the sensitivity of the eight participants by an average of 36.19 and the accuracy by 10.00 percentage points. (4) Conclusion: Our results indicate the potential benefit of deep learning to improve radiologists' detection of UIAs during routine reporting. From this, we can infer that the combination of T2WI with our DLA supports opportunistic screening, suggesting potential approaches for future research and application.

Selective multi-kinase inhibition sensitizes mesenchymal pancreatic cancer to immune checkpoint blockade by remodeling the tumor microenvironment.

KRAS-mutant pancreatic ductal adenocarcinoma (PDAC) is highly immunosuppressive and resistant to targeted and immunotherapies. Among the different PDAC subtypes, basal-like mesenchymal PDAC, which is driven by allelic imbalance, increased gene dosage and subsequent high expression levels of oncogenic KRAS, shows the most aggressive phenotype and strongest therapy resistance. In the present study, we performed a systematic high-throughput combination drug screen and identified a synergistic interaction between the MEK inhibitor trametinib and the multi-kinase inhibitor nintedanib, which targets KRAS-directed oncogenic signaling in mesenchymal PDAC. This combination treatment induces cell-cycle arrest and cell death, and initiates a context-dependent remodeling of the immunosuppressive cancer cell secretome. Using a combination of single-cell RNA-sequencing, CRISPR screens and immunophenotyping, we show that this combination therapy promotes intratumor infiltration of cytotoxic and effector T cells, which sensitizes mesenchymal PDAC to PD-L1 immune checkpoint inhibition. Overall, our results open new avenues to target this aggressive and therapy-refractory mesenchymal PDAC subtype.

Feasibility of electrospraying fully aqueous bovine serum albumin solutions.

Electrospraying or electrohydrodynamic atomisation, i.e. the formation of tiny droplets from a jet of conductive liquid under the influence of an electric field, has been gaining in popularity as a particle engineering technique in recent years. In addition to general benefits for particle engineering, e.g. the ability to generate nanometre sized particles with a very narrow size distribution, electrospraying also possesses a number of characteristics, like its applicability at ambient conditions, which could make it especially interesting for formulating therapeutic proteins. However, as fully aqueous solutions of proteins tend to have relatively high electrical conductivities and surface tensions, obtaining a stable Taylor cone-jet mode for these solutions is inherently challenging. This is why in the majority of studies reporting the successful electrospraying of proteins, either emulsions, aqueous suspensions or a mixture of water and one or more organic solvents were used instead of fully aqueous solutions. Therefore, an ab initio electrospraying formulation development study was conducted, using only fully aqueous feed solutions containing protein stabilising excipients commonly used in spray- and freeze-drying of therapeutic proteins. The study included bovine serum albumin (BSA) as a model protein and consisted out of two parts: (1) a one parameter at a time screening study, designed to improve the understanding of how various formulation components influence relevant physicochemical properties and the electrospraying process and (2) two subsequent mixture design of experiments (DoE) studies, designed to aid in the statistical description and prediction of the influence of different protein-excipient combinations on the electrospraying process. Additionally, the influence of physicochemical properties relevant to the electrospraying process, i.e. the volumetric mass density, electrical conductivity, kinematic viscosity and surface tension, was assessed for all feed solutions included in the study.

Formulating monoclonal antibodies as powders for reconstitution at high concentration using spray drying: Models and pitfalls.

In anticipation of non-invasive routes capable of delivering adequately high, systemic monoclonal antibody (mAb) concentrations, subcutaneous (SC) injection is arguably the most patient friendly alternative administration route available for this drug class. However, due to the limited volume that can be administered through this route and mAbs' relatively low therapeutic activity, solutions for subcutaneous injection often need to be highly concentrated, making them inherently more prone to potentially detrimental protein (self-) interaction, which is why mAb formulations for SC injection and other highly concentrated mAb solutions are often dried to increase their stability. In this work we investigated spray drying (SD) as a drying technique for formulating mAbs as powders for reconstitution, assessing the influence of SD process parameters, as well as excipients present in the feed solution on both mAb stability and relevant powder characteristics for reconstitution using a model mAb. By employing a design of experiments approach, we were able to provide statistically substantiated evidence for the reconstitution time reducing and stability improving properties of l-arginineHCl, l-histidineHCl, l-lysineHCl and polysorbate 20 when combined with a disaccharide in SD mAb powders for reconstitution. Additionally, the study yielded several statistical models describing process parameter influences on relevant powder and mAb stability characteristics.