Publications
219 results found
Vameghestahbanati M, Kingdom L, Hoffman EA, et al., 2024, Airway tree caliber heterogeneity and airflow obstruction among older adults., J Appl Physiol (1985)
INTRODUCTION: Smaller mean airway tree caliber is associated with airflow obstruction and chronic obstructive pulmonary disease (COPD). We investigated whether airway tree caliber heterogeneity was associated with airflow obstruction and COPD. METHODS: Two community-based cohorts (MESA Lung, CanCOLD) and a longitudinal case-control study of COPD (SPIROMICS) performed spirometry and computed tomography measurements of airway lumen diameters at standard anatomic locations and total lung volume. Percent-predicted airway lumen diameters were calculated using sex-specific reference equations accounting for age, height and lung volume. The association of airway tree caliber heterogeneity, quantified as the standard deviation (SD) of percent-predicted airway lumen diameters, with baseline forced expired volume in 1-second (FEV1), FEV1/forced vital capacity (FEV1/FVC) and COPD, as well as longitudinal spirometry, were assessed using regression models adjusted for age, sex, height, race-ethnicity, and mean airway tree caliber. RESULTS: Among 2,505 MESA Lung participants (mean±SD age: 69±9 years; 53% female, mean airway tree caliber: 99±10% predicted, airway tree caliber heterogeneity: 14±5%; median follow-up: 6.1 years), participants in the highest quartile of airway tree caliber heterogeneity exhibited lower FEV1 (adjusted mean difference: -125 ml, 95%CI:-171,-79), lower FEV1/FVC (adjusted mean difference: -0.01, 95%CI:-0.02,-0.01), and higher odds of COPD (adjusted OR 1.42, 95%CI:1.01-2.02) when compared with the lowest quartile, whereas longitudinal changes in FEV1 and FEV1/FVC did not differ significantly. Observations in CanCOLD and SPIROMICS were consistent. CONCLUSION: Among older adults, airway tree caliber heterogeneity was associated with airflow obstruction and COPD at baseline but was not associated with longitudinal changes in spirometry.
Angelini ED, Yang J, Balte PP, et al., 2023, Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans, THORAX, ISSN: 0040-6376
- Author Web Link
- Cite
- Citations: 2
Huang Z, Gan Y, Lye T, et al., 2023, Cardiac Adipose Tissue Segmentation via Image-Level Annotations, IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, Vol: 27, Pages: 2932-2943, ISSN: 2168-2194
Vameghestahbanati M, Sack C, Wysoczanski A, et al., 2023, Association of dysanapsis with mortality among older adults., Eur Respir J, Vol: 61
Dysanapsis – an anthropometric mismatch between airway tree calibre and lung size that is common in the general population – is strongly associated with all-cause mortality and increases susceptibility to tobacco smoking-related diseases https://bit.ly/42oDe8J
Shen W, Zhang X, Sun Y, et al., 2023, Lung Microstructure and Regional Function of Quantitative Emphysema Subtypes on Coregistered Computed Tomography and Hyperpolarized Gas Magnetic Resonance Imaging Scans: The M E S A - C O P D Study, International Conference of the American-Thoracic-Society (ATS), Publisher: AMER THORACIC SOC, ISSN: 1073-449X
Dereure E, Kervazo C, Seguin J, et al., 2023, Sparse Non-Negative Matrix Factorization for Preclinical Bioluminescent Imaging, ISSN: 1945-7928
Bioluminescent imaging is used in oncology to measure tumoral size and activity via spatio-temporal photon emission counting. Bioluminescent signal analysis often requires delineating regions of interest around each tumor by hand, which complicates quantification in the case of mice bearing multiple tumors. In this work, we propose to use Non-Negative Matrix Factorization with data-adaptive sparsity constraints to enable automated separation of signals emitted from multiple tumors in mice. Results are presented on a set of 18 long-exposure acquisitions.
Reme R, Piriou V, Hanson A, et al., 2023, Tracking Intermittent Particles with Self-Learned Visual Features, ISSN: 1945-7928
In time-lapse fluorescence imaging, single-particle-tracking is a powerful tool to monitor the dynamics of objects of interest, and extract information about biological processes. However, tracked particles can be subject to occlusion and intermittent detectability. When these phenomena persist over a few frames, tracking algorithms tend to produce multiple tracklets for the same particle. In this work, we introduce self-supervised learning of visual features to compare tracked particles, and we exploit both visual and positional distances to robustly stitch tracklets representing the same particle. We demonstrate the performance of our stitching framework on time-lapse fluorescence sequences of Hydra Vulgaris neurons. Results show high stitching precision, and reduction of errors made by previous algorithms on the same data by a factor of two.
Wysoczanski A, Angelini ED, Sun Y, et al., 2023, Multi-View Cnn For Total Lung Volume Inference On Cardiac Computed Tomography, ISSN: 1945-7928
Total lung volume (TLV) at full inspiration is a parameter of significant interest in pulmonary physiology but requires computed tomography (CT) scanning of the full axial extent of the lung. There is a growing interest to infer TLV from cardiac CT scans, which are much more widely available in epidemiologic studies. In this study, we present an original approach to train a multi-view convolutional neural network (CNN) model to infer TLV from cardiac CT scans, which visualize about 2/3rd of the lung volume. Supervised learning is used, exploiting paired full-lung and cardiac CT scans in the Multi-Ethnic Study of Atherosclerosis (MESA). Our results show that our network outperforms existing regression models for TLV estimation, and achieves accuracy and reproducibility comparable to the scan-rescan reproducibility of TLV on full-lung CT.
Naik SN, Forlano R, Manousou P, et al., 2023, Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning, Biological Imaging, Vol: 3, ISSN: 2633-903X
Non-alcoholic fatty liver disease (NAFLD) is now the leading cause of chronic liver disease, affecting approximately 30% of people worldwide. Histopathology reading of fibrosis patterns is crucial to diagnosing NAFLD. In particular, separating mild from severe stages corresponds to a critical transition as it correlates with clinical outcomes. Deep Learning for digitized histopathology whole-slide images (WSIs) can reduce high inter- and intra-rater variability. We demonstrate a novel solution to score fibrosis severity on a retrospective cohort of 152 Sirius-Red WSIs, with fibrosis stage annotated at slide level by an expert pathologist. We exploit multiple instance learning and multiple-inferences to address the sparsity of pathological signs. We achieved an accuracy of 78:98 ± 5:86%, an F1 score of 77:99 ± 5:64%, and an AUC of 0:87 ± 0:06. These results set new state-of-the-art benchmarks for this application.
Zhang X, Angelini ED, Haghpanah FS, et al., 2022, Quantification of lung ventilation defects on hyperpolarized MRI: The Multi-Ethnic Study of Atherosclerosis (MESA) COPD study., Magn Reson Imaging, Vol: 92, Pages: 140-149
PURPOSE: To develop an end-to-end deep learning (DL) framework to segment ventilation defects on pulmonary hyperpolarized MRI. MATERIALS AND METHODS: The Multi-Ethnic Study of Atherosclerosis Chronic Obstructive Pulmonary Disease (COPD) study is a nested longitudinal case-control study in older smokers. Between February 2016 and July 2017, 56 participants (age, mean ± SD, 74 ± 8 years; 34 men) underwent same breath-hold proton (1H) and helium (3He) MRI, which were annotated for non-ventilated, hypo-ventilated, and normal-ventilated lungs. In this retrospective DL study, 820 1H and 3He slices from 42/56 (75%) participants were randomly selected for training, with the remaining 14/56 (25%) for test. Full lung masks were segmented using a traditional U-Net on 1H MRI and were imported into a cascaded U-Net, which were used to segment ventilation defects on 3He MRI. Models were trained with conventional data augmentation (DA) and generative adversarial networks (GAN)-DA. RESULTS: Conventional-DA improved 1H and 3He MRI segmentation over the non-DA model (P = 0.007 to 0.03) but GAN-DA did not yield further improvement. The cascaded U-Net improved non-ventilated lung segmentation (P < 0.005). Dice similarity coefficients (DSC) between manually and DL-segmented full lung, non-ventilated, hypo-ventilated, and normal-ventilated regions were 0.965 ± 0.010, 0.840 ± 0.057, 0.715 ± 0.175, and 0.883 ± 0.060, respectively. We observed no statistically significant difference in DCSs between participants with and without COPD (P = 0.41, 0.06, and 0.18 for non-ventilated, hypo-ventilated, and normal-ventilated regions, respectively). CONCLUSION: The proposed cascaded U-Net framework generated fully-automated segmentation of ventilation defects on 3He MRI among older smokers with and without COPD that is consistent with our reference method.
Mehta R, Filos A, Baid U, et al., 2022, QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results., J Mach Learn Biomed Imaging, Vol: 2022
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.
Greenbury SF, Angelini DE, Ougham K, et al., 2022, Post-natal growth of very preterm neonates, The Lancet Child & Adolescent Health, Vol: 6, Pages: E11-E11, ISSN: 2352-4642
Dai C, Wang S, Mo Y, et al., 2022, Suggestive annotation of brain MR images with gradient-guided sampling, Medical Image Analysis, Vol: 77, Pages: 1-12, ISSN: 1361-8415
Machine learning has been widely adopted for medical image analysis in recent years given its promising performance in image segmentation and classification tasks. The success of machine learning, in particular supervised learning, depends on the availability of manually annotated datasets. For medical imaging applications, such annotated datasets are not easy to acquire, it takes a substantial amount of time and resource to curate an annotated medical image set. In this paper, we propose an efficient annotation framework for brain MR images that can suggest informative sample images for human experts to annotate. We evaluate the framework on two different brain image analysis tasks, namely brain tumour segmentation and whole brain segmentation. Experiments show that for brain tumour segmentation task on the BraTS 2019 dataset, training a segmentation model with only 7% suggestively annotated image samples can achieve a performance comparable to that of training on the full dataset. For whole brain segmentation on the MALC dataset, training with 42% suggestively annotated image samples can achieve a comparable performance to training on the full dataset. The proposed framework demonstrates a promising way to save manual annotation cost and improve data efficiency in medical imaging applications.
Habis A, Meas-Yedid V, Obando DFG, et al., 2022, SMART LEARNING OF CLICK AND REFINE FOR NUCLEI SEGMENTATION ON HISTOLOGY IMAGES, Pages: 2281-2285, ISSN: 1522-4880
Deep learning has proven to be a very efficient tool to help pathologists analyze Whole Slide Images (WSI) toward automated classification or segmentation of detailed structures such as nuclei, glands or glomeruli. These objects are particularly relevant for disease diagnosis and staging. Many deep learning methods have shown impressive performance but are still imperfect, while manual segmentation has poor inter-rater agreement. In this paper, we propose a patch-level automated correction of a given baseline initial segmentation, based on deep-learning of segmentation errors and downstream local refinements. Results on the MoNuSeg and PanNuke test datasets show significant improvement of nuclei segmentation quality.
Zang M, Wysoczanski A, Angelini E, et al., 2022, 3D U-Net Based Semantic Segmentation of Kidneys and Renal Masses on Contrast-Enhanced CT, Pages: 143-150, ISSN: 0302-9743
The accurate, automated detection and segmentation of renal tumors is of great interest for the imaging-based diagnosis, histologic subtyping, and management of suspected renal malignancy. The KiTS21 Grand Challenge provides 300 contrast enhanced CT images with kidney, tumors and cysts with corresponding manual annotation, to facilitate the development of robust segmentation algorithms for this task. In this work, we present an adaptation of the historically-successful 3D U-Net architecture, combined with deep supervision, foreground oversampling and large-scale image context, and trained on the majority-prediction segmentation masks. Our model achieved test-set performance of 97.0%, 85.1%, and 81.9% volumetric Dice score, and 93.7%, 72.0%, and 70.0% surface Dice score, on combined foreground, renal masses, and renal tumors, respectively, which tied for sixth place among challenge participants.
Yang J, Angelini ED, Balte PP, et al., 2021, Novel subtypes of pulmonary emphysema based on spatially-informed lung texture learning: the multi-ethnic study of atherosclerosis (MESA) COPD study., IEEE Transactions on Medical Imaging, Vol: 40, Pages: 3652-3662, ISSN: 0278-0062
Pulmonary emphysema overlaps considerably with chronic obstructive pulmonary disease (COPD), and is traditionally subcategorized into three subtypes previously identified on autopsy. Unsupervised learning of emphysema subtypes on computed tomography (CT) opens the way to new definitions of emphysema subtypes and eliminates the need of thorough manual labeling. However, CT-based emphysema subtypes have been limited to texture-based patterns without considering spatial location. In this work, we introduce a standardized spatial mapping of the lung for quantitative study of lung texture location and propose a novel framework for combining spatial and texture information to discover spatially-informed lung texture patterns (sLTPs) that represent novel emphysema subtype candidates. Exploiting two cohorts of full-lung CT scans from the MESA COPD (n=317) and EMCAP (n=22) studies, we first show that our spatial mapping enables population-wide study of emphysema spatial location. We then evaluate the characteristics of the sLTPs discovered on MESA COPD, and show that they are reproducible, able to encode standard emphysema subtypes, and associated with physiological symptoms.
Greenbury SF, Longford N, Ougham K, et al., 2021, Changes in neonatal admissions, care processes and outcomes in England and Wales during the COVID-19 pandemic: a whole population cohort study, BMJ Open, Vol: 11, ISSN: 2044-6055
Objectives: The COVID-19 pandemic instigated multiple societal and healthcare interventions with potential to affect perinatal practice. We evaluated population-level changes in preterm and full-term admissions to neonatal units, care processes and outcomes.Design: Observational cohort study using the UK National Neonatal Research Database.Setting: England and Wales.Participants: Admissions to National Health Service neonatal units from 2012 to 2020.Main outcome measures: Admissions by gestational age, ethnicity and Index of Multiple Deprivation, and key care processes and outcomes.Methods: We calculated differences in numbers and rates between April and June 2020 (spring), the first 3 months of national lockdown (COVID-19 period), and December 2019–February 2020 (winter), prior to introduction of mitigation measures, and compared them with the corresponding differences in the previous 7 years. We considered the COVID-19 period highly unusual if the spring–winter difference was smaller or larger than all previous corresponding differences, and calculated the level of confidence in this conclusion.Results: Marked fluctuations occurred in all measures over the 8 years with several highly unusual changes during the COVID-19 period. Total admissions fell, having risen over all previous years (COVID-19 difference: −1492; previous 7-year difference range: +100, +1617; p<0.001); full-term black admissions rose (+66; −64, +35; p<0.001) whereas Asian (−137; −14, +101; p<0.001) and white (−319; −235, +643: p<0.001) admissions fell. Transfers to higher and lower designation neonatal units increased (+129; −4, +88; p<0.001) and decreased (−47; −25, +12; p<0.001), respectively. Total preterm admissions decreased (−350; −26, +479; p<0.001). The fall in extremely preterm admissions was most marked in the two lowest socioeconomic quintiles.Conclusions: Our findings indicate substantia
Greenbury SF, Angelini ED, Ougham K, et al., 2021, Birthweight and patterns of postnatal weight gain in very and extremely preterm babies in England and Wales, 2008-19: a cohort study, The Lancet Child & Adolescent Health, Vol: 5, Pages: 719-728, ISSN: 2352-4642
BACKGROUND: Intrauterine and postnatal weight are widely regarded as biomarkers of fetal and neonatal wellbeing, but optimal weight gain following preterm birth is unknown. We aimed to describe changes over time in birthweight and postnatal weight gain in very and extremely preterm babies, in relation to major morbidity and healthy survival. METHODS: In this cohort study, we used whole-population data from the UK National Neonatal Research Database for infants below 32 weeks gestation admitted to neonatal units in England and Wales between Jan 1, 2008, and Dec 31, 2019. We used non-linear Gaussian process to estimate monthly trends, and Bayesian multilevel regression to estimate unadjusted and adjusted coefficients. We evaluated birthweight; weight change from birth to 14 days; weight at 36 weeks postmenstrual age; associated Z scores; and longitudinal weights for babies surviving to 36 weeks postmenstrual age with and without major morbidities. We adjusted birthweight for antenatal, perinatal, and demographic variables. We additionally adjusted change in weight at 14 days and weight at 36 weeks postmenstrual age, and their Z scores, for postnatal variables. FINDINGS: The cohort comprised 90 817 infants. Over the 12-year period, mean differences adjusted for antenatal, perinatal, demographic, and postnatal variables were 0 g (95% compatibility interval -7 to 7) for birthweight (-0·01 [-0·05 to 0·03] for change in associated Z score); 39 g (26 to 51) for change in weight from birth to 14 days (0·14 [0·08 to 0·19] for change in associated Z score); and 105 g (81 to 128) for weight at 36 weeks postmenstrual age (0·27 [0·21 to 0·33] for change in associated Z score). Greater weight at 36 weeks postmenstrual age was robust to additional adjustment for enteral nutritional intake. In babies surviving without major morbidity, weight velocity in all gestational age groups stabilised at around 34 weeks post
Vameghestahbanati M, Kingdom L, Anacleto-Dabarno M, et al., 2021, Airway tree caliber heterogeneity and airflow obstruction, Publisher: EUROPEAN RESPIRATORY SOC JOURNALS LTD, ISSN: 0903-1936
Greenbury SF, Angelini ED, Ougham K, et al., 2021, Birthweight and Patterns of Postnatal Weight Gain in Very and Extremely Preterm Babies: A 12 Year, Whole Population Study, The Lancet Child & Adolescent Health, ISSN: 2352-4642
Angelini E, Shah A, 2021, Using artificial intelligence in fungal lung disease: CPA CT imaging as an example, Mycopathologia, Vol: 186, Pages: 733-737, ISSN: 0301-486X
This positioning paper aims to discuss current challenges and opportunities for artificial intelligence (AI) in fungal lung disease, with a focus on chronic pulmonary aspergillosis and some supporting proof-of-concept results using lung imaging. Given the high uncertainty in fungal infection diagnosis and analyzing treatment response, AI could potentially have an impactful role; however, developing imaging-based machine learning raises several specific challenges. We discuss recommendations to engage the medical community in essential first steps towards fungal infection AI with gathering dedicated imaging registries, linking with non-imaging data and harmonizing image-finding annotations.
Greenbury SF, Ougham K, Wu J, et al., 2021, Identification of variation in nutritional practice in neonatal units in England and association with clinical outcomes using agnostic machine learning, Scientific Reports, Vol: 11, ISSN: 2045-2322
We used agnostic, unsupervised machine learning to cluster a large clinical database of information on infants admitted to neonatal units in England. Our aim was to obtain insights into nutritional practice, an area of central importance in newborn care, utilising the UK National Neonatal Research Database (NNRD). We performed clustering on time-series data of daily nutritional intakes for very preterm infants born at a gestational age less than 32 weeks (n = 45,679) over a six-year period. This revealed 46 nutritional clusters heterogeneous in size, showing common interpretable clinical practices alongside rarer approaches. Nutritional clusters with similar admission profiles revealed associations between nutritional practice, geographical location and outcomes. We show how nutritional subgroups may be regarded as distinct interventions and tested for associations with measurable outcomes. We illustrate the potential for identifying relationships between nutritional practice and outcomes with two examples, discharge weight and bronchopulmonary dysplasia (BPD). We identify the well-known effect of formula milk on greater discharge weight as well as support for the plausible, but insufficiently evidenced view that human milk is protective against BPD. Our framework highlights the potential of agnostic machine learning approaches to deliver clinical practice insights and generate hypotheses using routine data.
Greenbury SF, Longford NT, Ougham K, et al., 2021, Changes in Neonatal Admissions, Care Processes and Outcomes in England and Wales During the COVID-19 Pandemic, SSRN Electronic Journal
Jammes-Floreani M, Laine AF, Angelini ED, 2021, ENHANCED-QUALITY GAN (EQ-GAN) ON LUNG CT SCANS: TOWARD TRUTH AND POTENTIAL HALLUCINATIONS, 18th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 20-23, ISSN: 1945-7928
Wysoczanski A, Angelini ED, Smith BM, et al., 2021, UNSUPERVISED CLUSTERING OF AIRWAY TREE STRUCTURES ON HIGH-RESOLUTION CT: THE MESA LUNG STUDY, 18th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 1568-1572, ISSN: 1945-7928
Nunes A, Desai SR, Semple T, et al., 2021, 3D PATHOLOGICAL SIGNS DETECTION AND SCORING ON CPA CT LUNG SCANS, 18th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 82-85, ISSN: 1945-7928
Dai C, Wang S, Raynaud H, et al., 2021, Self-training for Brain Tumour Segmentation with Uncertainty Estimation and Biophysics-Guided Survival Prediction, 6th International MICCAI Brain-Lesion Workshop (BrainLes), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 514-523, ISSN: 0302-9743
- Author Web Link
- Cite
- Citations: 3
Huang Z, Zhang H, Laine A, et al., 2021, CO-SEG: AN IMAGE SEGMENTATION FRAMEWORK AGAINST LABEL CORRUPTION, 18th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 550-553, ISSN: 1945-7928
- Author Web Link
- Cite
- Citations: 1
Huang Z, Gan Y, Lye T, et al., 2020, Heterogeneity Measurement of Cardiac Tissues Leveraging Uncertainty Information from Image Segmentation., Pages: 782-791
Identifying arrhythmia substrates and quantifying their heterogeneity has great potential to provide critical guidance for radio frequency ablation. However, quantitative analysis of heterogeneity on cardiac optical coherence tomography (OCT) images is lacking. In this paper, we conduct the first study on quantifying cardiac tissue heterogeneity from human OCT images. Our proposed method applies a dropout-based Monte Carlo sampling technique to measure the model uncertainty. The heterogeneity information is extracted by decoupling the intra/inter-tissue heterogeneity and tissue boundary uncertainty from the uncertainty measurement. We empirically demonstrate that our model can highlight the subtle features from OCT images, and the heterogeneity information extracted is positively correlated with the tissue heterogeneity information from corresponding histology images.
Dai C, Wang S, Mo Y, et al., 2020, Suggestive annotation of brain tumour images with gradient-guided sampling, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Publisher: Springer International Publishing, Pages: 156-165, ISSN: 0302-9743
Machine learning has been widely adopted for medical image analysis in recent years given its promising performance in image segmentation and classification tasks. As a data-driven science, the success of machine learning, in particular supervised learning, largely depends on the availability of manually annotated datasets. For medical imaging applications, such annotated datasets are not easy to acquire. It takes a substantial amount of time and resource to curate an annotated medical image set. In this paper, we propose an efficient annotation framework for brain tumour images that is able to suggest informative sample images for human experts to annotate. Our experiments show that training a segmentation model with only 19% suggestively annotated patient scans from BraTS 2019 dataset can achieve a comparable performance to training a model on the full dataset for whole tumour segmentation task. It demonstrates a promising way to save manual annotation cost and improve data efficiency in medical imaging applications.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.