Rapid diagnosis and treatment of acute neurological illnesses such as stroke, hemorrhage, and hydrocephalus are critical to achieving positive outcomes and preserving neurologic function-'time is brain'. Although these disorders are often recognizable by their symptoms, the critical means of their diagnosis is rapid imaging. Computer-aided surveillance of acute neurologic events in cranial imaging has the potential to triage radiology workflow, thus decreasing time to treatment and improving outcomes. Substantial clinical work has focused on computer-assisted diagnosis (CAD), whereas technical work in volumetric image analysis has focused primarily on segmentation. 3D convolutional neural networks (3D-CNNs) have primarily been used for supervised classification on 3D modeling and light detection and ranging (LiDAR) data. Here, we demonstrate a 3D-CNN architecture that performs weakly supervised classification to screen head CT images for acute neurologic events. Features were automatically learned from a clinical radiology dataset comprising 37,236 head CTs and were annotated with a semisupervised natural-language processing (NLP) framework. We demonstrate the effectiveness of our approach to triage radiology workflow and accelerate the time to diagnosis from minutes to seconds through a randomized, double-blinded, prospective trial in a simulated clinical environment.
Purpose To compare different methods for generating features from radiology reports and to develop a method to automatically identify findings in these reports. Materials and Methods In this study, 96 303 head computed tomography (CT) reports were obtained. The linguistic complexity of these reports was compared with that of alternative corpora. Head CT reports were preprocessed, and machine-analyzable features were constructed by using bag-of-words (BOW), word embedding, and Latent Dirichlet allocation-based approaches. Ultimately, 1004 head CT reports were manually labeled for findings of interest by physicians, and a subset of these were deemed critical findings. Lasso logistic regression was used to train models for physician-assigned labels on 602 of 1004 head CT reports (60%) using the constructed features, and the performance of these models was validated on a held-out 402 of 1004 reports (40%). Models were scored by area under the receiver operating characteristic curve (AUC), and aggregate AUC statistics were reported for (a) all labels, (b) critical labels, and (c) the presence of any critical finding in a report. Sensitivity, specificity, accuracy, and F1 score were reported for the best performing model's (a) predictions of all labels and (b) identification of reports containing critical findings. Results The best-performing model (BOW with unigrams, bigrams, and trigrams plus average word embeddings vector) had a held-out AUC of 0.966 for identifying the presence of any critical head CT finding and an average 0.957 AUC across all head CT findings. Sensitivity and specificity for identifying the presence of any critical finding were 92.59% (175 of 189) and 89.67% (191 of 213), respectively. Average sensitivity and specificity across all findings were 90.25% (1898 of 2103) and 91.72% (18 351 of 20 007), respectively. Simpler BOW methods achieved results competitive with those of more sophisticated approaches, with an average AUC for presence of any critical finding of 0.951 for unigram BOW versus 0.966 for the best-performing model. The Yule I of the head CT corpus was 34, markedly lower than that of the Reuters corpus (at 103) or I2B2 discharge summaries (at 271), indicating lower linguistic complexity. Conclusion Automated methods can be used to identify findings in radiology reports. The success of this approach benefits from the standardized language of these reports. With this method, a large labeled corpus can be generated for applications such as deep learning. RSNA, 2018 Online supplemental material is available for this article.
The plasmodial surface anion channel (PSAC) is an unusual small-conductance ion channel induced on erythrocytes infected with plasmodia, including parasites responsible for human malaria. Although broadly available inhibitors produce microscopic clearance of parasite cultures at high concentrations and suggest that PSAC is an antimalarial target, they have low affinity for the channel and may interfere with other parasite activities. To address these concerns, we developed a miniaturized assay for PSAC activity and carried out a high-throughput inhibitor screen. Approximately 70,000 compounds from synthetic and natural product libraries were screened, revealing inhibitors from multiple structural classes including two novel and potent heterocyclic scaffolds. Single-channel patch-clamp studies indicated that these compounds act directly on PSAC, further implicating a proposed role in transport of diverse solutes. A statistically significant correlation between channel inhibition and in vitro parasite killing by a family of compounds provided chemical validation of PSAC as a drug target. These new inhibitors should be important research tools and may be starting points for much-needed antimalarial drugs.
Cysteine protease inhibitors kill malaria parasites and are being pursued for development as antimalarial agents. Because they have multiple targets within bloodstream-stage parasites, workers have assumed that resistance to these inhibitors would not be acquired easily. In the present study, we used in vitro selection to generate a parasite resistant to growth inhibition by leupeptin, a broad-profile cysteine and serine protease inhibitor. Resistance was not associated with upregulation of cysteine protease activity, reduced leupeptin sensitivity of this activity, or expression level changes for putative cysteine or serine proteases in the parasite genome. Instead, it was associated with marked changes in the plasmodial surface anion channel (PSAC), an ion channel on infected erythrocytes that functions in nutrient and bulky organic solute uptake. Osmotic fragility measurements, electrophysiological recordings, and leupeptin uptake studies revealed selective reductions in organic solute permeability via PSAC, altered single-channel gating, and reduced inhibitor affinity. These changes yielded significantly reduced leupeptin uptake and could fully account for the acquired resistance. PSAC represents a novel route for the uptake of bulky hydrophilic compounds acting against intraerythrocytic parasite targets. Drug development based on such compounds should proceed cautiously in light of possible resistance development though the selection of PSAC mutants.
Tumor consistency is a critical factor that influences operative strategy and patient counseling. Magnetic resonance imaging (MRI) describes the concentration of water within living tissues and as such, is hypothesized to predict aspects of their biomechanical behavior. In meningiomas, MRI signal intensity has been used to predict the consistency of the tumor and its histopathological subtype, though its predictive capacity is debated in the literature. We performed a systematic review of the PubMed database since 1990 concerning MRI appearance and tumor consistency to assess whether or not MRI can be used reliably to predict tumor firmness. The inclusion criteria were case series and clinical studies that described attempts to correlate preoperative MRI findings with tumor consistency. The relationship between the pre-operative imaging characteristics, intraoperative findings, and World Health Organization (WHO) histopathological subtype is described. While T2 signal intensity and MR elastography provide a useful predictive measure of tumor consistency, other techniques have not been validated. T1-weighted imaging was not found to offer any diagnostic or predictive value. A quantitative assessment of T2 signal intensity more reliably predicts consistency than inherently variable qualitative analyses. Preoperative knowledge of tumor firmness affords the neurosurgeon substantial benefit when planning surgical techniques. Based upon our review of the literature, we currently recommend the use of T2-weighted MRI for predicting consistency, which has been shown to correlate well with analysis of tumor histological subtype. Development of standard measures of tumor consistency, standard MRI quantification metrics, and further exploration of MRI technique may improve the predictive ability of neuroimaging for meningiomas.
Glioblastoma multiforme (GBM) remains a mainly incurable disease in desperate need of more effective treatments. In this study, we develop evidence that the mitotic spindle checkpoint molecule BUB1B may offer a predictive marker for aggressiveness and effective drug response. A subset of GBM tumor isolates require BUB1B to suppress lethal kinetochore-microtubule attachment defects. Using gene expression data from GBM stem-like cells, astrocytes and neural progenitor cells that are sensitive or resistant to BUB1B inhibition, we created a computational framework to predict sensitivity to BUB1B inhibition. Applying this framework to tumor expression data from patients, we stratified tumors into BUB1B sensitive (BUB1BS) or BUB1B resistant (BUB1BR) subtypes. Through this effort, we found that BUB1BS patients have a significantly worse prognosis regardless of tumor development subtype (i.e., classical, mesenchymal, neural, proneural). Functional genomic profiling of BUB1BR versus BUB1BS isolates revealed a differential reliance of genes enriched in the BUB1BS classifier, including those involved in mitotic cell cycle, microtubule organization and chromosome segregation. By comparing drug sensitivity profiles, we predicted BUB1BS cells to be more sensitive to type I and II topoisomerase inhibitors, Raf inhibitors and other drugs, and experimentally validated some of these predictions. Taken together, the results show that our BUB1BR/S classification of GBM tumors can predict clinical course and sensitivity to drug treatment.
Erythrocytes infected with malaria parasites have increased permeability to various solutes. These changes may be mediated by an unusual small conductance ion channel known as the plasmodial surface anion channel (PSAC). While channel activity benefits the parasite by permitting nutrient acquisition, it can also be detrimental because water-soluble antimalarials may more readily access their parasite targets via this channel. Recently, two such toxins, blasticidin S and leupeptin, were used to select mutant parasites with altered PSAC activities, suggesting acquired resistance via reduced channel-mediated toxin uptake. Surprisingly, although these toxins have similar structures and charge, we now show that reduced permeability of one does not protect the intracellular parasite from the other. Leupeptin accumulation in the blasticidin S-resistant mutant was relatively preserved, consistent with retained in vitro susceptibility to leupeptin. Subsequent in vitro selection with both toxins generated a double mutant parasite having additional changes in PSAC, implicating an antimalarial resistance mechanism for water-soluble drugs requiring channel-mediated uptake at the erythrocyte membrane. Characterization of these mutants revealed a single conserved channel on each mutant, albeit with distinct gating properties. These findings are consistent with a shared channel that mediates uptake of ions, nutrients and toxins. This channel's gating and selectivity properties can be modified in response to in vitro selective pressure.
Preoperative PTE may represent a significant marker of poor functional outcome risk in older adults and provides a quantitative measurement to incorporate into surgical decision-making.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.