A convolutional neural network-based system to classify patients using FDG PET/CT examinations

Kawauchi, Keisuke; Furuya, Shinichi; Hirata, Kenji; Katoh, Chietsugu; Manabe, Osamu; Kobayashi, Kentaro; Watanabe, Shirô; Shiga, Tohru

doi:10.1186/s12885-020-6694-x

Cited by 58 publications

(30 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In radiomics, a large number of indicators are calculated [ 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 ]. Previously, when only SUVmax was utilized, univariate analysis and receiver operator curve analysis were enough to determine whether the particular indicator was a useful predictor for histological or genetic characteristics and prognosis [ 59 ].…”

Section: Basic Concepts For Quantitative Fdg Pet Assessmentmentioning

confidence: 99%

Quantitative FDG PET Assessment for Oncology Therapy

Hirata

Tamaki

2021

Cancers

Self Cite

View full text Add to dashboard Cite

Positron emission tomography (PET) has unique characteristics for quantitative assessment of tumour biology in vivo. Accumulation of F-18 fluorodeoxyglucose (FDG) may reflect tumour characteristics based on its metabolic activity. Quantitative assessment of FDG uptake can often be applied for treatment monitoring after chemotherapy or chemoradiotherapy. Numerous studies indicated biochemical change assessed by FDG PET as a more sensitive marker than morphological change estimated by CT or MRI. In addition, those with complete metabolic response after therapy may show better disease-free survival and overall survival than those with other responses. Assessment of metabolic change may be performed using absolute FDG uptake in the tumour (standardized uptake value: SUV). In addition, volumetric parameters such as metabolic tumour volume (MTV) have been introduced for quantitative assessment of FDG uptake in tumour. More recently, radiomics approaches that focus on image-based precision medicine have been applied to FDG PET, as well as other radiological imaging. Among these, texture analysis extracts intratumoral heterogeneity on a voxel-by-voxel basis. Combined with various machine learning techniques, these new quantitative parameters hold a promise for assessing tissue characterization and predicting treatment effect, and could also be used for future prognosis of various tumours, although multicentre clinical trials are needed before application in clinical settings.

show abstract

Section: Basic Concepts For Quantitative Fdg Pet Assessmentmentioning

confidence: 99%

Quantitative FDG PET Assessment for Oncology Therapy

Hirata

Tamaki

2021

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kawauchi et al introduced a CNN-based system to classify FDG PET MIP images of 3485 patients into 3 categories: benign, equivocal and malignant, with accuracy of 99.4, 87.5 and 99.4, respectively. The network architecture was ResNet-50 [26]. It allowed physicians checking their opinions doubly based on CNN system and personal experience.…”

Section: Least Absolute Shrinkage and Selection Operator (Lasso)mentioning

confidence: 99%

Artiﬁcial intelligence applications for oncological positron emission tomography imaging

Liu

Cheng

et al. 2021

European Journal of Radiology

View full text Add to dashboard Cite

Positron emission tomography (PET), a functional and dynamic molecular imaging technique, is generally used to reveal tumors' biological behavior. Radiomics allows a high-throughput extraction of multiple features from images with artificial intelligence (AI) approaches and develops rapidly worldwide. Quantitative and objective features of medical images have been explored to recognize reliable biomarkers, with the development of PET radiomics. This paper will review the current clinical exploration of PET-based classical machine learning and deep learning methods, including disease diagnosis, the prediction of histological subtype, gene mutation status, tumor metastasis, tumor relapse, therapeutic side effects, therapeutic intervention and evaluation of prognosis. The applications of AI in oncology will be mainly discussed. The image-guided biopsy or surgery assisted by PETbased AI will be introduced as well. This paper aims to present the applications and methods of AI for PET imaging, which may offer important details for further clinical studies. Relevant precautions are put forward and future research directions are suggested.

show abstract

“…This algorithm can learn by themselves and produce the output that is not limited to the input provided to them. Another fascinating feature is that, even if a neuron is not responding or a piece of information is missing, the network can detect the fault and still produce the output [36,37]. In addition, ANN can perform multiple tasks in parallel without affecting the system performance.…”

Section: Statistical Analysesmentioning

confidence: 99%

Predicting the Use Labor Induction Intervention: A Machine Learning Approach for the Birth-Cohort Registry at A Tertiary Hospital in North Tanzania.

Tarimo¹,

Bhuyan²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Introduction: Following an increased use of labor induction procedure to prevent adverse maternal and fetal outcomes in Sub-Saharan Africa, hitting the best algorithm that accurately classify subjects in need of the intervention is of paramount importance. This study aimed at comparing the potential benefits of applying machine learning (ML) algorithms over the conventional logistic regression model in predicting the use of labor induction intervention in pregnant women attending one of the tertiary hospitals in north Tanzania for delivery. Methods: We conducted a secondary data analysis of the Kilimanjaro Christian Medical Centre (KCMC) birth registry database for women with uncomplicated pregnancies from the year 2000 to 2015. We excluded observations with non-vertex presentation and those with missing information on labor induction status. Model accuracy and Area under the receiver operating characteristic curve (AUC - ROC) were used to assess the discriminative ability of the selected models. We plotted the decision curve analysis (DCA) to assess the clinical utility of the models under observation. Results: A total of 21,578 deliveries were analyzed. Among these, 8814 (41%) were induced during the study period. Among the selected machine learning models, Random forest algorithm exhibited the best performance in terms of accuracy [0.75; 95%CI (0.73 – 0.76)] and AUC-ROC [AUC-ROC: 0.75; 95% CI (0.74 – 0.76)] compared to other models including logistic regression. Among assessed maternal attributes, parity, maternal age, body mass index, gestational age and birthweight were deemed most important predictors for labor induction intervention. Conclusion: The selected machine learning methods offered better computational performance compared to the conventional logistic regression model in predicting the use of labor induction intervention. The current study lends substantial support to the use of machine learning models in predicting the use of labor induction intervention.

show abstract

A convolutional neural network-based system to classify patients using FDG PET/CT examinations

Cited by 58 publications

References 28 publications

Quantitative FDG PET Assessment for Oncology Therapy

Quantitative FDG PET Assessment for Oncology Therapy

Artiﬁcial intelligence applications for oncological positron emission tomography imaging

Predicting the Use Labor Induction Intervention: A Machine Learning Approach for the Birth-Cohort Registry at A Tertiary Hospital in North Tanzania.

Contact Info

Product

Resources

About