Dataset Information

Context aware decision support in neurosurgical oncology based on an efficient classification of endomicroscopic data.

ABSTRACT: PURPOSE:Probe-based confocal laser endomicroscopy (pCLE) enables in vivo, in situ tissue characterisation without changes in the surgical setting and simplifies the oncological surgical workflow. The potential of this technique in identifying residual cancer tissue and improving resection rates of brain tumours has been recently verified in pilot studies. The interpretation of endomicroscopic information is challenging, particularly for surgeons who do not themselves routinely review histopathology. Also, the diagnosis can be examiner-dependent, leading to considerable inter-observer variability. Therefore, automatic tissue characterisation with pCLE would support the surgeon in establishing diagnosis as well as guide robot-assisted intervention procedures. METHODS:The aim of this work is to propose a deep learning-based framework for brain tissue characterisation for context aware diagnosis support in neurosurgical oncology. An efficient representation of the context information of pCLE data is presented by exploring state-of-the-art CNN models with different tuning configurations. A novel video classification framework based on the combination of convolutional layers with long-range temporal recursion has been proposed to estimate the probability of each tumour class. The video classification accuracy is compared for different network architectures and data representation and video segmentation methods. RESULTS:We demonstrate the application of the proposed deep learning framework to classify Glioblastoma and Meningioma brain tumours based on endomicroscopic data. Results show significant improvement of our proposed image classification framework over state-of-the-art feature-based methods. The use of video data further improves the classification performance, achieving accuracy equal to 99.49%. CONCLUSIONS:This work demonstrates that deep learning can provide an efficient representation of pCLE data and accurately classify Glioblastoma and Meningioma tumours. The performance evaluation analysis shows the potential clinical value of the technique.

SUBMITTER: Li Y

PROVIDER: S-EPMC6096753 | biostudies-literature | 2018 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Context aware decision support in neurosurgical oncology based on an efficient classification of endomicroscopic data.

Li Yachun Y Charalampaki Patra P Liu Yong Y Yang Guang-Zhong GZ Giannarou Stamatia S

International journal of computer assisted radiology and surgery 20180613 8

<h4>Purpose</h4>Probe-based confocal laser endomicroscopy (pCLE) enables in vivo, in situ tissue characterisation without changes in the surgical setting and simplifies the oncological surgical workflow. The potential of this technique in identifying residual cancer tissue and improving resection rates of brain tumours has been recently verified in pilot studies. The interpretation of endomicroscopic information is challenging, particularly for surgeons who do not themselves routinely review his ...[more]

PMID: 29948845

Similar Datasets

Project description:PURPOSE:Precision oncology is hindered by the lack of decision support for determining the functional and therapeutic significance of genomic alterations in tumors and relevant clinically available options. To bridge this knowledge gap, we established a Precision Oncology Decision Support (PODS) team that provides annotations at the alteration-level and subsequently determined if clinical decision-making was influenced. METHODS:Genomic alterations were annotated to determine actionability based on a variant's known or potential functional and/or therapeutic significance. The medical records of a subset of patients annotated in 2015 were manually reviewed to assess trial enrollment. A web-based survey was implemented to capture the reasons why genotype-matched therapies were not pursued. RESULTS:PODS processed 1,669 requests for annotation of 4,084 alterations (2,254 unique) across 49 tumor types for 1,197 patients. 2,444 annotations for 669 patients included an actionable variant call: 32.5% actionable, 9.4% potentially, 29.7% unknown, 28.4% non-actionable. 66% of patients had at least one actionable/potentially actionable alteration. 20.6% (110/535) patients annotated enrolled on a genotype-matched trial. Trial enrolment was significantly higher for patients with actionable/potentially actionable alterations (92/333, 27.6%) than those with unknown (16/136, 11.8%) and non-actionable (2/66, 3%) alterations (p=0.00004). Actionable alterations in PTEN, PIK3CA, and ERBB2 most frequently led to enrollment on genotype-matched trials. Clinicians cited a variety of reasons why patients with actionable alterations did not enroll on trials. CONCLUSION:Over half of alterations annotated were of unknown significance or non-actionable. Physicians were more likely to enroll a patient on a genotype-matched trial when an annotation supported actionability. Future studies are needed to demonstrate the impact of decision support on trial enrollment and oncologic outcomes.

Project description:BackgroundDrug-laboratory (lab) interactions (DLIs) are a common source of preventable medication errors. Clinical decision support systems (CDSSs) are promising tools to decrease such errors by improving prescription quality in terms of lab values. However, alert fatigue counteracts their impact. We aimed to develop a novel user-friendly, evidence-based, clinical context-aware CDSS to alert nephrologists about DLIs clinically important lab values in prescriptions of kidney recipients.MethodsFor the most frequently prescribed medications identified by a prospective cross-sectional study in a kidney transplant clinic, DLI-rules were extracted using main pharmacology references and clinical inputs from clinicians. A CDSS was then developed linking a computerized prescription system and lab records. The system performance was tested using data of both fictitious and real patients. The "Questionnaire for User Interface Satisfaction" was used to measure user satisfaction of the human-computer interface.ResultsAmong 27 study medications, 17 needed adjustments regarding renal function, 15 required considerations based on hepatic function, 8 had drug-pregnancy interactions, and 13 required baselines or follow-up lab monitoring. Using IF & THEN rules and the contents of associated alert, a DLI-alerting CDSS was designed. To avoid alert fatigue, the alert appearance was considered as interruptive only when medications with serious risks were contraindicated or needed to be discontinued or adjusted. Other alerts appeared in a non-interruptive mode with visual clues on the prescription window for easy, intuitive notice. When the system was used for real 100 patients, it correctly detected 260 DLIs and displayed 249 monitoring, seven hepatic, four pregnancy, and none renal alerts. The system delivered patient-specific recommendations based on individual lab values in real-time. Clinicians were highly satisfied with the usability of the system.ConclusionsTo our knowledge, this is the first study of a comprehensive DLI-CDSS for kidney transplant care. By alerting on considerations in renal and hepatic dysfunctions, maternal and fetal toxicity, or required lab monitoring, this system can potentially improve medication safety in kidney recipients. Our experience provides a strong foundation for designing specialized systems to promote individualized transplant follow-up care.

Project description:The inference of cortical sulcal labels often focuses on deep (primary and secondary) sulcal regions, whereas shallow (tertiary) sulcal regions are largely overlooked in the literature due to the scarcity of manual/well-defined annotations and their large neuroanatomical variability. In this paper, we present an automated framework for regional labeling of both primary/secondary and tertiary sulci of the dorsal portion of lateral prefrontal cortex (LPFC) using spherical convolutional neural networks. We propose two core components that enhance the inference of sulcal labels to overcome such large neuroanatomical variability: (1) surface data augmentation and (2) context-aware training. (1) To take into account neuroanatomical variability, we synthesize training data from the proposed feature space that embeds intermediate deformation trajectories of spherical data in a rigid to non-rigid fashion, which bridges an augmentation gap in conventional rotation data augmentation. (2) Moreover, we design a two-stage training process to improve labeling accuracy of tertiary sulci by informing the biological associations in neuroanatomy: inference of primary/secondary sulci and then their spatial likelihood to guide the definition of tertiary sulci. In the experiments, we evaluate our method on 13 deep and shallow sulci of human LPFC in two independent data sets with different age ranges: pediatric (N=60) and adult (N=36) cohorts. We compare the proposed method with a conventional multi-atlas approach and spherical convolutional neural networks without/with rotation data augmentation. In both cohorts, the proposed data augmentation improves labeling accuracy of deep and shallow sulci over the baselines, and the proposed context-aware training offers further improvement in the labeling of shallow sulci over the proposed data augmentation. We share our tools with the field and discuss applications of our results for understanding neuroanatomical-functional organization of LPFC and the rest of cortex (https://github.com/ilwoolyu/SphericalLabeling).

Dataset Information

Context aware decision support in neurosurgical oncology based on an efficient classification of endomicroscopic data.

Publications

Context aware decision support in neurosurgical oncology based on an efficient classification of endomicroscopic data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets