Towards effective machine learning in medical imaging analysis: A novel approach and expert evaluation of high-grade glioma ‘ground truth’ simulation on MRI

2021 ◽  
Vol 146 ◽  
pp. 104348
Author(s):  
K. Sepehri ◽  
X. Song ◽  
R. Proulx ◽  
S. Ghosh Hajra ◽  
B. Dobberthien ◽  
...  
Keyword(s):  
Machine Learning ◽  
Medical Imaging ◽  
Ground Truth ◽  
High Grade Glioma ◽  
High Grade ◽  
Expert Evaluation ◽  
Imaging Analysis ◽  
Novel Approach

scholarly journals A Comparative Assessment of Ensemble-Based Machine Learning and Maximum Likelihood Methods for Mapping Seagrass Using Sentinel-2 Imagery in Tauranga Harbor, New Zealand

2020 ◽  
Vol 12 (3) ◽  
pp. 355 ◽  
Author(s):  
Nam Thang Ha ◽  
Merilyn Manley-Harris ◽  
Tien Dat Pham ◽  
Ian Hawes
Keyword(s):  
Machine Learning ◽  
New Zealand ◽  
Maximum Likelihood ◽  
Ground Truth ◽  
Machine Learning Techniques ◽  
Ground Truth Data ◽  
Seagrass Meadows ◽  
Ensemble Machine Learning ◽  
Novel Approach ◽  
Sentinel 2

Seagrass has been acknowledged as a productive blue carbon ecosystem that is in significant decline across much of the world. A first step toward conservation is the mapping and monitoring of extant seagrass meadows. Several methods are currently in use, but mapping the resource from satellite images using machine learning is not widely applied, despite its successful use in various comparable applications. This research aimed to develop a novel approach for seagrass monitoring using state-of-the-art machine learning with data from Sentinel–2 imagery. We used Tauranga Harbor, New Zealand as a validation site for which extensive ground truth data are available to compare ensemble machine learning methods involving random forests (RF), rotation forests (RoF), and canonical correlation forests (CCF) with the more traditional maximum likelihood classifier (MLC) technique. Using a group of validation metrics including F1, precision, recall, accuracy, and the McNemar test, our results indicated that machine learning techniques outperformed the MLC with RoF as the best performer (F1 scores ranging from 0.75–0.91 for sparse and dense seagrass meadows, respectively). Our study is the first comparison of various ensemble-based methods for seagrass mapping of which we are aware, and promises to be an effective approach to enhance the accuracy of seagrass monitoring.

scholarly journals Detecting Depression and Predicting its Onset Using Longitudinal Symptoms Captured by Passive Sensing

2021 ◽  
Vol 28 (1) ◽  
pp. 1-41
Author(s):  
Prerna Chikersal ◽  
Afsaneh Doryab ◽  
Michael Tumminia ◽  
Daniella K. Villalba ◽  
Janine M. Dutcher ◽  
...  
Keyword(s):  
Machine Learning ◽  
Depressive Symptoms ◽  
Symptom Severity ◽  
Ground Truth ◽  
Learning Approach ◽  
Novel Approach ◽  
Passive Sensing ◽  
Machine Learning Approach ◽  
Fitness Trackers ◽  
Feature Extraction Technique

We present a machine learning approach that uses data from smartphones and fitness trackers of 138 college students to identify students that experienced depressive symptoms at the end of the semester and students whose depressive symptoms worsened over the semester. Our novel approach is a feature extraction technique that allows us to select meaningful features indicative of depressive symptoms from longitudinal data. It allows us to detect the presence of post-semester depressive symptoms with an accuracy of 85.7% and change in symptom severity with an accuracy of 85.4%. It also predicts these outcomes with an accuracy of >80%, 11–15 weeks before the end of the semester, allowing ample time for pre-emptive interventions. Our work has significant implications for the detection of health outcomes using longitudinal behavioral data and limited ground truth. By detecting change and predicting symptoms several weeks before their onset, our work also has implications for preventing depression.

scholarly journals Targeting Glucose Metabolism of Cancer Cells with Dichloroacetate to Radiosensitize High-Grade Gliomas

2021 ◽  
Vol 22 (14) ◽  
pp. 7265
Author(s):  
Kristina M. Cook ◽  
Han Shen ◽  
Kelly J. McKelvey ◽  
Harriet E. Gee ◽  
Eric Hau
Keyword(s):  
Glucose Metabolism ◽  
Warburg Effect ◽  
High Grade Glioma ◽  
Glycolytic Flux ◽  
High Grade ◽  
Dna Breaks ◽  
Novel Approach ◽  
Altered Glucose ◽  
Altered Metabolism ◽  
The Warburg Effect

As the cornerstone of high-grade glioma (HGG) treatment, radiotherapy temporarily controls tumor cells via inducing oxidative stress and subsequent DNA breaks. However, almost all HGGs recur within months. Therefore, it is important to understand the underlying mechanisms of radioresistance, so that novel strategies can be developed to improve the effectiveness of radiotherapy. While currently poorly understood, radioresistance appears to be predominantly driven by altered metabolism and hypoxia. Glucose is a central macronutrient, and its metabolism is rewired in HGG cells, increasing glycolytic flux to produce energy and essential metabolic intermediates, known as the Warburg effect. This altered metabolism in HGG cells not only supports cell proliferation and invasiveness, but it also contributes significantly to radioresistance. Several metabolic drugs have been used as a novel approach to improve the radiosensitivity of HGGs, including dichloroacetate (DCA), a small molecule used to treat children with congenital mitochondrial disorders. DCA reverses the Warburg effect by inhibiting pyruvate dehydrogenase kinases, which subsequently activates mitochondrial oxidative phosphorylation at the expense of glycolysis. This effect is thought to block the growth advantage of HGGs and improve the radiosensitivity of HGG cells. This review highlights the main features of altered glucose metabolism in HGG cells as a contributor to radioresistance and describes the mechanism of action of DCA. Furthermore, we will summarize recent advances in DCA’s pre-clinical and clinical studies as a radiosensitizer and address how these scientific findings can be translated into clinical practice to improve the management of HGG patients.

Combined structural and perfusion MRI enhanced by machine learning may outperform standalone modalities and radiological expertise in high-grade glioma surveillance: A proof-of-concept study.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e14528-e14528
Author(s):  
Diana Roettger ◽  
Loizos Siakallis ◽  
Carole Sudre ◽  
Jasmina Panovska-Griffiths ◽  
Paul Mulholland ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Grade Glioma ◽  
Treatment Monitoring ◽  
Perfusion Mri ◽  
Svm Classifier ◽  
High Grade ◽  
Time Points ◽  
Group I ◽  
Sensitivity Specificity ◽  
Time Point

e14528 Background: Treatment monitoring in patients with High-Grade Glioma (HGG) and identification of disease progression, remains a major challenge in clinical neurooncology. We aimed to develop a support vector machine (SVM) classifier utilising combined longitudinal conventional and Dynamic Susceptibility Contrast (DSC) perfusion MRI to classify between Stable Disease (SD), Pseudoprogression (PsP) and Progressive Disease (PD) in glioma patients under surveillance. Methods: Conventional (269) and perfusion (62) MRI studies of HGG patients acquired between 2012 and 2018 were prospectively analysed. Study participants were separated into two groups: Group I with a single DSC time point (64 participants) and Group II with multiple DSC time points (19 participants). The SVM classifier was trained using all available MRI for each group. Classification accuracy was assessed for the use of features extracted from different feature dataset and time point combinations and compared to the experienced radiologists’ predictions. Results: The study included 64 participants (mean age: 48.5 ± 12.8 yrs [standard deviation], 24 female). SVM classification based on combined perfusion and structural features outperformed standalone datasets across all groups. For the clinically relevant classification step (SD/PSP vs PD), both feature combination as well as the addition of multiple DSC time points, improved classification performance (lowest median error rate: 0.016). The SVM algorithm outperformed radiologists in predicting lesion destiny in both groups. Optimal performance was observed in Group II, in which SVM sensitivity/specificity/accuracy was 100/91.67/94.7% for analysis based on the first time point and 85.71/100/ 94.7% based on multiple time points compared to 60/78/68% and 70/90/84.2% for the respective radiologist classifications. In Group I, the SVM also exceeded radiologist predictions, albeit by a smaller margin and resulted in sensitivity/specificity of 86.49/75.00/81.53% (SVM) compared to 75.7/68.9/73.84% (radiologists). Conclusions: Our results indicate that the addition of multiple longitudinal perfusion time points as well as the combination of structural and perfusion features significantly enhance classification outcome in treatment monitoring of HGGs and machine-learning-assisted diagnosis has potentially superior accuracy than the radiologist's visual evaluation and expertise.

scholarly journals OS6.3 Radiomics and machine learning on [18F]FET PET and T1ce MRI discriminate between low-grade and high-grade glioma

2018 ◽  
Vol 20 (suppl_3) ◽  
pp. iii226-iii226
Author(s):  
S Bonte ◽  
S Donche ◽  
M Henrotte ◽  
R van Holen ◽  
I Goethals
Keyword(s):  
Machine Learning ◽  
High Grade Glioma ◽  
Low Grade ◽  
High Grade ◽  
Fet Pet

scholarly journals NI-07 VALIDATION OF MACHINE LEARNING BASED HIGH GRADE GLIOMA MR SEGMENTATION VIA METHIONINE PET

2019 ◽  
Vol 1 (Supplement_2) ◽  
pp. ii27-ii27
Author(s):  
Manabu Kinoshita ◽  
Tomohiko Ozaki ◽  
Hideyuki Arita ◽  
Naoki Kagawa ◽  
Yonehiro Kanemura ◽  
...  
Keyword(s):  
Machine Learning ◽  
Brain Tumor ◽  
Treatment Planning ◽  
Radiation Treatment ◽  
Ground Truth ◽  
Tumor Segmentation ◽  
High Grade ◽  
Lesion Segmentation ◽  
Brain Tumor Segmentation ◽  
Negative Error

Abstract Treatment planning and lesion-follow up are generally conducted by contrast-enhanced MRI in glioma patient care. On the other hand, there are, however, substantial concerns whether MRI actually reflects the extension or activity of this neoplasm, which information should be fundamentally important at every step when treating this disease. As a matter of fact, the authors of this investigation have already shown that there is no difference in tumor cell density within areas with and without contrast enhancement (J Neurosurg. 2016,125(5):1136–1142.) and furthermore that the geometry of MRI based-radiation treatment planning is significantly altered when methionine PET is integrated for this purpose (J Neurosurg. 2018 published on-line). Regardless of these concerns, there is great interest in the research community to construct a machine learning based fully automated brain tumor segmentation tool specific for gliomas using MRI. The authors attempted to validate this method by comparing MRI-based automated brain tumor segmentation and methionine PET. Consecutively collected 45 high-grade gliomas (GBM-26, grade3-19) were analyzed. BraTumIA, an automated brain tumor segmentation tool, was used for machine learning based lesion segmentation. At the same time, lesions were segmented using various thresholds on methionine PET. The authors observed 40% of pseudo-positive and 90% of pseudo-negative error on BraTumIA based lesion segmentation when methionine PET was considered as ground truth with a cut-off of 1.3 in T/N ratio. Pseudo-negative error was as high as 60% even if the threshold was elevated to 2.0. Although machine learning based glioma segmentation is expected to expand in both research and clinical use, the observed results caution the use of MRI as ground truth of spatial extension of glioma and researchers should be reminded that this imaging modality may obscure the true behavior of the disease within the patient in some cases.

Sign in / Sign up

Export Citation Format

Share Document