scholarly journals Interactive Machine Learning-Based Multi-Label Segmentation of Solid Tumors and Organs

2021 ◽  
Vol 11 (16) ◽  
pp. 7488
Author(s):  
Dimitrios Bounias ◽  
Ashish Singh ◽  
Spyridon Bakas ◽  
Sarthak Pati ◽  
Saima Rathore ◽  
...  
Keyword(s):  
Machine Learning ◽  
Geodesic Distance ◽  
Ground Truth ◽  
Specific Model ◽  
General Purpose ◽  
Patient Specific ◽  
Manual Annotation ◽  
Interactive Machine Learning ◽  
Lung Cancer Patients ◽  
User Training

We seek the development and evaluation of a fast, accurate, and consistent method for general-purpose segmentation, based on interactive machine learning (IML). To validate our method, we identified retrospective cohorts of 20 brain, 50 breast, and 50 lung cancer patients, as well as 20 spleen scans, with corresponding ground truth annotations. Utilizing very brief user training annotations and the adaptive geodesic distance transform, an ensemble of SVMs is trained, providing a patient-specific model applied to the whole image. Two experts segmented each cohort twice with our method and twice manually. The IML method was faster than manual annotation by 53.1% on average. We found significant (p < 0.001) overlap difference for spleen (DiceIML/DiceManual = 0.91/0.87), breast tumors (DiceIML/DiceManual = 0.84/0.82), and lung nodules (DiceIML/DiceManual = 0.78/0.83). For intra-rater consistency, a significant (p = 0.003) difference was found for spleen (DiceIML/DiceManual = 0.91/0.89). For inter-rater consistency, significant (p < 0.045) differences were found for spleen (DiceIML/DiceManual = 0.91/0.87), breast (DiceIML/DiceManual = 0.86/0.81), lung (DiceIML/DiceManual = 0.85/0.89), the non-enhancing (DiceIML/DiceManual = 0.79/0.67) and the enhancing (DiceIML/DiceManual = 0.79/0.84) brain tumor sub-regions, which, in aggregation, favored our method. Quantitative evaluation for speed, spatial overlap, and consistency, reveals the benefits of our proposed method when compared with manual annotation, for several clinically relevant problems. We publicly release our implementation through CaPTk (Cancer Imaging Phenomics Toolkit) and as an MITK plugin.

scholarly journals Emulating complex simulations by machine learning methods

2021 ◽  
Vol 22 (S14) ◽  
Author(s):  
Paola Stolfi ◽  
Filippo Castiglione
Keyword(s):  
Machine Learning ◽  
Type 2 Diabetes ◽  
Mobile Devices ◽  
Learning Algorithm ◽  
Computational Cost ◽  
Specific Model ◽  
Patient Specific ◽  
Complex Biological System ◽  
Self Monitoring

Abstract Background The aim of the present paper is to construct an emulator of a complex biological system simulator using a machine learning approach. More specifically, the simulator is a patient-specific model that integrates metabolic, nutritional, and lifestyle data to predict the metabolic and inflammatory processes underlying the development of type-2 diabetes in absence of familiarity. Given the very high incidence of type-2 diabetes, the implementation of this predictive model on mobile devices could provide a useful instrument to assess the risk of the disease for aware individuals. The high computational cost of the developed model, being a mixture of agent-based and ordinary differential equations and providing a dynamic multivariate output, makes the simulator executable only on powerful workstations but not on mobile devices. Hence the need to implement an emulator with a reduced computational cost that can be executed on mobile devices to provide real-time self-monitoring. Results Similarly to our previous work, we propose an emulator based on a machine learning algorithm but here we consider a different approach which turn out to have better performances, indeed in terms of root mean square error we have an improvement of two order magnitude. We tested the proposed emulator on samples containing different number of simulated trajectories, and it turned out that the fitted trajectories are able to predict with high accuracy the entire dynamics of the simulator output variables. We apply the emulator to control the level of inflammation while leveraging on the nutritional input. Conclusion The proposed emulator can be implemented and executed on mobile health devices to perform quick-and-easy self-monitoring assessments.

Nanosecond Photodynamics Simulations of a Cis-Trans Isomerization Are Enabled by Machine Learning

2020 ◽  
Author(s):  
Jingbai Li ◽  
Patrick Reiser ◽  
André Eberhard ◽  
Pascal Friederich ◽  
Steven Lopez
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Excited State ◽  
Adaptive Sampling ◽  
Computational Cost ◽  
Ground Truth ◽  
Absolute Error ◽  
Photochemical Reactions ◽  
Computational Techniques ◽  
Full Potential

<p>Photochemical reactions are being increasingly used to construct complex molecular architectures with mild and straightforward reaction conditions. Computational techniques are increasingly important to understand the reactivities and chemoselectivities of photochemical isomerization reactions because they offer molecular bonding information along the excited-state(s) of photodynamics. These photodynamics simulations are resource-intensive and are typically limited to 1–10 picoseconds and 1,000 trajectories due to high computational cost. Most organic photochemical reactions have excited-state lifetimes exceeding 1 picosecond, which places them outside possible computational studies. Westermeyr <i>et al.</i> demonstrated that a machine learning approach could significantly lengthen photodynamics simulation times for a model system, methylenimmonium cation (CH<sub>2</sub>NH<sub>2</sub><sup>+</sup>).</p><p>We have developed a Python-based code, Python Rapid Artificial Intelligence <i>Ab Initio</i> Molecular Dynamics (PyRAI<sup>2</sup>MD), to accomplish the unprecedented 10 ns <i>cis-trans</i> photodynamics of <i>trans</i>-hexafluoro-2-butene (CF<sub>3</sub>–CH=CH–CF<sub>3</sub>) in 3.5 days. The same simulation would take approximately 58 years with ground-truth multiconfigurational dynamics. We proposed an innovative scheme combining Wigner sampling, geometrical interpolations, and short-time quantum chemical trajectories to effectively sample the initial data, facilitating the adaptive sampling to generate an informative and data-efficient training set with 6,232 data points. Our neural networks achieved chemical accuracy (mean absolute error of 0.032 eV). Our 4,814 trajectories reproduced the S<sub>1</sub> half-life (60.5 fs), the photochemical product ratio (<i>trans</i>: <i>cis</i> = 2.3: 1), and autonomously discovered a pathway towards a carbene. The neural networks have also shown the capability of generalizing the full potential energy surface with chemically incomplete data (<i>trans</i> → <i>cis</i> but not <i>cis</i> → <i>trans</i> pathways) that may offer future automated photochemical reaction discoveries.</p>

Dealing with Mislabeling via Interactive Machine Learning

2020 ◽  
Vol 34 (2) ◽  
pp. 271-278
Author(s):  
Wanyi Zhang ◽  
Andrea Passerini ◽  
Fausto Giunchiglia
Keyword(s):  
Machine Learning ◽  
Interactive Machine Learning

Patient-specific IMRT QA verification using machine learning and gamma radiomics

2021 ◽  
Vol 82 ◽  
pp. 100-108
Author(s):  
Jéssica Caroline Lizar ◽  
Carolina Cariolatto Yaly ◽  
Alexandre Colello Bruno ◽  
Gustavo Arruda Viani ◽  
Juliana Fernandes Pavoni
Keyword(s):  
Machine Learning ◽  
Patient Specific ◽  
Imrt Qa

scholarly journals A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

2021 ◽  
Vol 18 (4) ◽  
pp. 2121
Author(s):  
Mansoureh Maadi ◽  
Hadi Akbarzadeh Khorshidi ◽  
Uwe Aickelin
Keyword(s):  
Machine Learning ◽  
Future Research ◽  
Computational Power ◽  
Medical Field ◽  
Interactive Machine Learning ◽  
Human In The Loop ◽  
Human Interactions ◽  
Scoping Literature Review ◽  
Domain Expertise ◽  
Expertise Level

Objective: To provide a human–Artificial Intelligence (AI) interaction review for Machine Learning (ML) applications to inform how to best combine both human domain expertise and computational power of ML methods. The review focuses on the medical field, as the medical ML application literature highlights a special necessity of medical experts collaborating with ML approaches. Methods: A scoping literature review is performed on Scopus and Google Scholar using the terms “human in the loop”, “human in the loop machine learning”, and “interactive machine learning”. Peer-reviewed papers published from 2015 to 2020 are included in our review. Results: We design four questions to investigate and describe human–AI interaction in ML applications. These questions are “Why should humans be in the loop?”, “Where does human–AI interaction occur in the ML processes?”, “Who are the humans in the loop?”, and “How do humans interact with ML in Human-In-the-Loop ML (HILML)?”. To answer the first question, we describe three main reasons regarding the importance of human involvement in ML applications. To address the second question, human–AI interaction is investigated in three main algorithmic stages: 1. data producing and pre-processing; 2. ML modelling; and 3. ML evaluation and refinement. The importance of the expertise level of the humans in human–AI interaction is described to answer the third question. The number of human interactions in HILML is grouped into three categories to address the fourth question. We conclude the paper by offering a discussion on open opportunities for future research in HILML.

scholarly journals Patient-Specific Predictive Antibiogram in Decision Support for Empiric Antibiotic Treatment

2020 ◽  
Vol 41 (S1) ◽  
pp. s521-s522
Author(s):  
Debarka Sengupta ◽  
Vaibhav Singh ◽  
Seema Singh ◽  
Dinesh Tewari ◽  
Mudit Kapoor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Antimicrobial Resistance ◽  
Model Building ◽  
Medical Center ◽  
Bacterial Species ◽  
Model Performance ◽  
The United States ◽  
Patient Specific ◽  
Gradient Boosting ◽  
Comparative Performance

Background: The rising trend of antibiotic resistance imposes a heavy burden on healthcare both clinically and economically (US$55 billion), with 23,000 estimated annual deaths in the United States as well as increased length of stay and morbidity. Machine-learning–based methods have, of late, been used for leveraging patient’s clinical history and demographic information to predict antimicrobial resistance. We developed a machine-learning model ensemble that maximizes the accuracy of such a drug-sensitivity versus resistivity classification system compared to the existing best-practice methods. Methods: We first performed a comprehensive analysis of the association between infecting bacterial species and patient factors, including patient demographics, comorbidities, and certain healthcare-specific features. We leveraged the predictable nature of these complex associations to infer patient-specific antibiotic sensitivities. Various base-learners, including k-NN (k-nearest neighbors) and gradient boosting machine (GBM), were used to train an ensemble model for confident prediction of antimicrobial susceptibilities. Base learner selection and model performance evaluation was performed carefully using a variety of standard metrics, namely accuracy, precision, recall, F1 score, and Cohen &kappa;. Results: For validating the performance on MIMIC-III database harboring deidentified clinical data of 53,423 distinct patient admissions between 2001 and 2012, in the intensive care units (ICUs) of the Beth Israel Deaconess Medical Center in Boston, Massachusetts. From ~11,000 positive cultures, we used 4 major specimen types namely urine, sputum, blood, and pus swab for evaluation of the model performance. Figure 1 shows the receiver operating characteristic (ROC) curves obtained for bloodstream infection cases upon model building and prediction on 70:30 split of the data. We received area under the curve (AUC) values of 0.88, 0.92, 0.92, and 0.94 for urine, sputum, blood, and pus swab samples, respectively. Figure 2 shows the comparative performance of our proposed method as well as some off-the-shelf classification algorithms. Conclusions: Highly accurate, patient-specific predictive antibiogram (PSPA) data can aid clinicians significantly in antibiotic recommendation in ICU, thereby accelerating patient recovery and curbing antimicrobial resistance.Funding: This study was supported by Circle of Life Healthcare Pvt. Ltd.Disclosures: None

A NOVEL EXTENSIVE EX-VIVO OCT DATABASE FROM MURINE MODELS OF COLORECTAL CANCER

2021 ◽  
Vol 108 (Supplement_3) ◽  
Author(s):  
J Bote ◽  
J F Ortega-Morán ◽  
C L Saratxaga ◽  
B Pagador ◽  
A Picón ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Machine Learning ◽  
Structural Information ◽  
Ex Vivo ◽  
Ground Truth ◽  
Colon Polyps ◽  
Learning Methods ◽  
Non Invasive ◽  
Machine Learning Methods ◽  
In Situ Methods

Abstract INTRODUCTION New non-invasive technologies for improving early diagnosis of colorectal cancer (CRC) are demanded by clinicians. Optical Coherence Tomography (OCT) provides sub-surface structural information and offers diagnosis capabilities of colon polyps, further improved by machine learning methods. Databases of OCT images are necessary to facilitate algorithms development and testing. MATERIALS AND METHODS A database has been acquired from rat colonic samples with a Thorlabs OCT system with 930nm centre wavelength that provides 1.2KHz A-scan rate, 7μm axial resolution in air, 4μm lateral resolution, 1.7mm imaging depth in air, 6mm x 6mm FOV, and 107dB sensitivity. The colon from anaesthetised animals has been excised and samples have been extracted and preserved for ex-vivo analysis with the OCT equipment. RESULTS This database consists of OCT 3D volumes (C-scans) and 2D images (B-scans) of murine samples from: 1) healthy tissue, for ground-truth comparison (18 samples; 66 C-scans; 17,478 B-scans); 2) hyperplastic polyps, obtained from an induced colorectal hyperplastic murine model (47 samples; 153 C-scans; 42,450 B-scans); 3) neoplastic polyps (adenomatous and adenocarcinomatous), obtained from clinically validated Pirc F344/NTac-Apcam1137 rat model (232 samples; 564 C-scans; 158,557 B-scans); and 4) unknown tissue (polyp adjacent, presumably healthy) (98 samples; 157 C-scans; 42,070 B-scans). CONCLUSIONS A novel extensive ex-vivo OCT database of murine CRC model has been obtained and will be openly published for the research community. It can be used for classification/segmentation machine learning methods, for correlation between OCT features and histopathological structures, and for developing new non-invasive in-situ methods of diagnosis of colorectal cancer.

scholarly journals Prediction of 3D Cardiovascular hemodynamics before and after coronary artery bypass surgery via deep learning

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Gaoyang Li ◽  
Haoran Wang ◽  
Mingzi Zhang ◽  
Simon Tupin ◽  
Aike Qiao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Artery Bypass ◽  
Computational Cost ◽  
Specific Model ◽  
Arterial System ◽  
Patient Specific ◽  
Cardiovascular Hemodynamics ◽  
Before And After ◽  
Deep Learning Network ◽  
Cfd Method

AbstractThe clinical treatment planning of coronary heart disease requires hemodynamic parameters to provide proper guidance. Computational fluid dynamics (CFD) is gradually used in the simulation of cardiovascular hemodynamics. However, for the patient-specific model, the complex operation and high computational cost of CFD hinder its clinical application. To deal with these problems, we develop cardiovascular hemodynamic point datasets and a dual sampling channel deep learning network, which can analyze and reproduce the relationship between the cardiovascular geometry and internal hemodynamics. The statistical analysis shows that the hemodynamic prediction results of deep learning are in agreement with the conventional CFD method, but the calculation time is reduced 600-fold. In terms of over 2 million nodes, prediction accuracy of around 90%, computational efficiency to predict cardiovascular hemodynamics within 1 second, and universality for evaluating complex arterial system, our deep learning method can meet the needs of most situations.

Sign in / Sign up

Export Citation Format

Share Document