4,297 research outputs found
SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images
No full textHigh computational cost associated with digital pathology image analysis approaches is a challenge towards their translation in routine pathology clinic. Here, we propose a computationally efficient framework (SuperHistopath), designed to map global context features reflecting the rich tumor morphological heterogeneity. SuperHistopath efficiently combines i) a segmentation approach using the linear iterative clustering (SLIC) superpixels algorithm applied directly on the whole-slide images at low resolution (5x magnification) to adhere to region boundaries and form homogeneous spatial units at tissue-level, followed by ii) classification of superpixels using a convolution neural network (CNN). To demonstrate how versatile SuperHistopath was in accomplishing histopathology tasks, we classified tumor tissue, stroma, necrosis, lymphocytes clusters, differentiating regions, fat, hemorrhage and normal tissue, in 127 melanomas, 23 triple-negative breast cancers, and 73 samples from transgenic mouse models of high-risk childhood neuroblastoma with high accuracy (98.8%, 93.1% and 98.3% respectively). Furthermore, SuperHistopath enabled discovery of significant differences in tumor phenotype of neuroblastoma mouse models emulating genomic variants of high-risk disease, and stratification of melanoma patients (high ratio of lymphocyte-to-tumor superpixels (p = 0.015) and low stroma-to-tumor ratio (p = 0.028) were associated with a favorable prognosis). Finally, SuperHistopath is efficient for annotation of ground-truth datasets (as there is no need of boundary delineation), training and application (~5 min for classifying a whole-slide image and as low as ~30 min for network training). These attributes make SuperHistopath particularly attractive for research in rich datasets and could also facilitate its adoption in the clinic to accelerate pathologist workflow with the quantification of phenotypes, predictive/prognosis markers
Computational science-enabled radiological pathology for the non-invasive mapping of tumour heterogeneity in childhood neuroblastoma
No full textNeuroblastoma is a common childhood solid tumour that accounts for 15% of all cancer paediatric deaths. This thesis addresses key deficiencies in our ability to define, monitor and predict neuroblastoma heterogeneity for precision medicine. I used computational science to integrate the spatially-encoded phenotypic information provided by multi-parametric magnetic resonance imaging (MRI) with digital histopathology, demonstrating that MRI can provide non-invasive pathology to characterise neuroblastoma heterogeneity and provide biomarkers of response in clinically-relevant transgenic mouse models of high-risk disease. I first developed and demonstrated the application of novel computational pathology methodologies to enhance the quantitative assessment of tumour components from H&E-stained whole-slide images (WSI). These include two frameworks: SuperCRF, which fuses traditional machine learning with deep learning to model the way pathologists incorporate large-scale tissue architecture and context across spatial spaces to significantly improve single-cell classification and, SuperHistopath, which combines the application of the SLIC superpixels algorithm on low-magnification WSIs (5x) with a convolutional neural network (CNN) for superpixels classification to accurately map tumour heterogeneity from low-resolution histology. I then developed an MRI-histopathology cross-validation pipeline which provides the rigorous validation needed to support the deployment of novel MRI scans in the neuroblastoma clinic. Using this platform, I demonstrated the sensitivity of susceptibility-, T1-Mapping- and diffusion-weighted-MRI to the cellular and microenvironmental hallmarks of high-risk neuroblastoma and their modulation by either vascular- or MYCN-targeted therapies. Finally, I used supervised machine learning classification- and regression-based approaches to show proof-of-concept that habitat imaging derived from these three scans can non-invasively provide quantitative data typically acquired from histological analysis, such as densities of specific cell populations. This thesis demonstrates the potential of multi-parametric MRI to deliver non-invasive "virtual" biopsies to enhance diagnostic and treatment monitoring for children with neuroblastoma and pave new ways in studying tumour as an evolving ecosystem
Predicting fraud in mobile money transfer using case-based reasoning
No full textThis paper proposes an improved CBR approach for the identification of money transfer fraud in Mobile Money Transfer (MMT) environments. Standard CBR capability is augmented by machine learning techniques to assign parameter weights in the sample dataset and automate k-value random selection in k-NN classification to improve CBR performance. The CBR system observes users’ transaction behaviour within the MMT service and tries to detect abnormal patterns in the transaction flows. To capture user behaviour effectively, the CBR system classifies the log information into five contexts and then combines them into a single dimension, instead of using the conventional approach where the transaction amount, time dimensions or features dimension are used individually. The applicability of the proposed augmented CBR system is evaluated using simulation data. From the results, both dimensions show good performance with the context of information weighted CBR system outperforming the individual features approach
Editorial Comment: Integrating Morphomics in Clinical Practice for Personalized Medicine: A Paradigm Shift Toward Holistic Care
No full textn/
Radiology and multi-scale data integration for precision oncology
No full textIn this Perspective paper we explore the potential of integrating radiological imaging with other data types, a critical yet underdeveloped area in comparison to the fusion of other multi-omic data. Radiological images provide a comprehensive, three-dimensional view of cancer, capturing features that would be missed by biopsies or other data modalities. This paper explores the complexities and challenges of incorporating medical imaging into data integration models, in the context of precision oncology. We present the different categories of imaging-omics integration and discuss recent progress, highlighting the opportunities that arise from bringing together spatial data on different scales
Investigating the contribution of hyaluronan to the breast tumour microenvironment using multiparametric MRI and MR elastography
No full textHyaluronan (HA) is a key component of the dense extracellular matrix in breast cancer, and its accumulation is associated with poor prognosis and metastasis. Pegvorhyaluronidase alfa (PEGPH20) enzymatically degrades HA and can enhance drug delivery and treatment response in preclinical tumour models. Clinical development of stromal-targeted therapies would be accelerated by imaging biomarkers that inform on therapeutic efficacy in vivo. Here, PEGPH20 response was assessed by multiparametric magnetic resonance imaging (MRI) in three orthotopic breast tumour models. Treatment of 4T1/HAS3 tumours, the model with the highest HA accumulation, reduced T1 and T2 relaxation times and the apparent diffusion coefficient (ADC), and increased the magnetisation transfer ratio, consistent with lower tissue water content and collapse of the extracellular space. The transverse relaxation rate R2* increased, consistent with greater erythrocyte accessibility following vascular decompression. Treatment of MDA-MB-231 LM2-4 tumours reduced ADC and dramatically increased tumour viscoelasticity measured by MR elastography. Correlation matrix analyses of data from all models identified ADC as having the strongest correlation with HA accumulation, suggesting that ADC is the most sensitive imaging biomarker of tumour response to PEGPH20
Accelerating Whole-Body Diffusion-weighted MRI with Deep Learning-based Denoising Image Filters
No full textPurpose: To use deep learning to improve the image quality of subsampled images (number of acquisitions = 1 [NOA 1]) to reduce whole-body diffusion-weighted MRI (WBDWI) acquisition times.Materials and Methods: Both retrospective and prospective patient groups were used to develop a deep learning-based denoising image filter (DNIF) model. For initial model training and validation, 17 patients with metastatic prostate cancer with acquired WBDWI NOA 1 and NOA 9 images (acquisition period, 2015-2017) were retrospectively included. An additional 22 prospective patients with advanced prostate cancer, myeloma, and advanced breast cancer were used for model testing (2019), and the radiologic quality of DNIF-processed NOA 1 (NOA 1-DNIF) images were compared with NOA 1 images and clinical NOA 16 images by using a three-point Likert scale (good, average, or poor; statistical significance was calculated by using a Wilcoxon signed ranked test). The model was also retrained and tested in 28 patients with malignant pleural mesothelioma (MPM) who underwent lung MRI (2015-2017) to demonstrate feasibility in other body regions.Results: The model visually improved the quality of NOA 1 images in all test patients, with the majority of NOA 1-DNIF and NOA 16 images being graded as either "average" or "good" across all image-quality criteria. From validation data, the mean apparent diffusion coefficient (ADC) values within NOA 1-DNIF images of bone disease deviated from those within NOA 9 images by an average of 1.9% (range, 1.1%-2.6%). The model was also successfully applied in the context of MPM; the mean ADCs from NOA 1-DNIF images of MPM deviated from those measured by using clinical-standard images (NOA 12) by 3.7% (range, 0.2%-10.6%).Conclusion: Clinical-standard images were generated from subsampled images by using a DNIF. Supplemental material is available for this article. Published under a CC BY 4.0 license
First observation of the decay Bs0→K*0K*0
No full textThe first observation of the decay B0s→K∗0K∗0 is reported using 35 pb−1 of data collected by LHCb in proton–proton collisions at a centre-of-mass energy of 7 TeV. A total of 49.8±7.5 B0s→(K+π−)(K−π+) events are observed within ±50 MeV/c2 of the B0s mass and 746 MeV/c2 < mKπ < 1046 MeV/c2, mostly coming from a resonant B0s→K∗0K∗0 signal. The branching fraction and the CP-averaged K∗0 longitudinal polarization fraction are measured to be B(B0s→K∗0K∗0)=(2.81±0.46(stat.)±0.45(syst.)±0.34(fs/ fd))×10−5 and fL =0.31±0.12(stat.)±0.04(syst.)
Effective lifetime measurements in the B-s(0) -> K+K-, B-0 -> K+pi(-) and B-s(0) -> pi K-+(-) decays
No full textMeasurements of the effective lifetimes in the View the MathML source, B0→K+π− and View the MathML source decays are presented using 1.0 fb−1 of pp collision data collected at a centre-of-mass energy of 7 TeV by the LHCb experiment. The analysis uses a data-driven approach to correct for the decay time acceptance.
This is the most precise determination to date of the effective lifetime in the View the MathML source decay and provides constraints on contributions from physics beyond the Standard Model to the View the MathML source mixing phase and the width difference ΔΓs
- …
