Understanding machine learning classifier decisions in automated radiotherapy quality assurance

2021 ◽  
Author(s):  
Yunsheng Chen ◽  
Dionne M Aleman ◽  
Thomas G Purdie ◽  
Chris McIntosh
Keyword(s):  
Machine Learning ◽  
Quality Assurance ◽  
Treatment Plan ◽  
Region Of Interest ◽  
Expert Assessment ◽  
Learning Approaches ◽  
Ensure Patient Safety ◽  
Shapley Values ◽  
Clinically Significant ◽  
Radiotherapy Treatment

Abstract The complexity of generating radiotherapy treatments demands a rigorous quality assurance (QA) process to ensure patient safety and to avoid clinically significant errors. Machine learning classifiers have been explored to augment the scope and efficiency of the traditional radiotherapy treatment planning QA process. However, one important gap in relying on classifiers for QA of radiotherapy treatment plans is the lack of understanding behind a specific classifier prediction. We develop explanation methods to understand the decisions of two automated QA classifiers: (1) a region of interest (ROI) segmentation/labeling classifier, and (2) a treatment plan acceptance classifier. For each classifier, a local interpretable model-agnostic explanation (LIME) framework and a novel adaption of team-based Shapley values framework are constructed. We test these methods in datasets for two radiotherapy treatment sites (prostate and breast), and demonstrate the importance of evaluating QA classifiers using interpretable machine learning approaches. We additionally develop a notion of explanation consistency to assess classifier performance. Our explanation method allows for easy visualization and human expert assessment of classifier decisions in radiotherapy QA. Notably, we find that our team-based Shapley approach is more consistent than LIME. The ability to explain and validate automated decision-making is critical in medical treatments. This analysis allows us to conclude that both QA classifiers are moderately trustworthy and can be used to confirm expert decisions, though the current QA classifiers should not be viewed as a replacement for the human QA process.

scholarly journals Predicting clinically significant motor function improvement after contemporary task-oriented interventions using machine learning approaches

2020 ◽  
Vol 17 (1) ◽  
Author(s):  
Hiren Kumar Thakkar ◽  
Wan-wen Liao ◽  
Ching-yi Wu ◽  
Yu-Wei Hsieh ◽  
Tsong-Hai Lee
Keyword(s):  
Machine Learning ◽  
Motor Function ◽  
Chronic Stroke ◽  
Learning Approaches ◽  
Stroke Patients ◽  
Training Set ◽  
Data Set ◽  
Clinically Significant ◽  
Task Oriented ◽  
Significant Motor

Abstract Background Accurate prediction of motor recovery after stroke is critical for treatment decisions and planning. Machine learning has been proposed to be a promising technique for outcome prediction because of its high accuracy and ability to process large volumes of data. It has been used to predict acute stroke recovery; however, whether machine learning would be effective for predicting rehabilitation outcomes in chronic stroke patients for common contemporary task-oriented interventions remains largely unexplored. This study aimed to determine the accuracy and performance of machine learning to predict clinically significant motor function improvements after contemporary task-oriented intervention in chronic stroke patients and identify important predictors for building machine learning prediction models. Methods This study was a secondary analysis of data using two common machine learning approaches, which were the k-nearest neighbor (KNN) and artificial neural network (ANN). Chronic stroke patients (N = 239) that received 30 h of task-oriented training including the constraint-induced movement therapy, bilateral arm training, robot-assisted therapy and mirror therapy were included. The Fugl-Meyer assessment scale (FMA) was the main outcome. Potential predictors include age, gender, side of lesion, time since stroke, baseline functional status, motor function and quality of life. We divided the data set into a training set and a test set and used the cross-validation procedure to construct machine learning models based on the training set. After the models were built, we used the test data set to evaluate the accuracy and prediction performance of the models. Results Three important predictors were identified, which were time since stroke, baseline functional independence measure (FIM) and baseline FMA scores. Models for predicting motor function improvements were accurate. The prediction accuracy of the KNN model was 85.42% and area under the receiver operating characteristic curve (AUC-ROC) was 0.89. The prediction accuracy of the ANN model was 81.25% and the AUC-ROC was 0.77. Conclusions Incorporating machine learning into clinical outcome prediction using three key predictors including time since stroke, baseline functional and motor ability may help clinicians/therapists to identify patients that are most likely to benefit from contemporary task-oriented interventions. The KNN and ANN models may be potentially useful for predicting clinically significant motor recovery in chronic stroke.

Patient-specific quality assurance measurements for VMAT treatments: Do we really catch errors?

2013 ◽  
Vol 31 (31_suppl) ◽  
pp. 81-81 ◽  
Author(s):  
Wolfram Laub ◽  
Charles R. Thomas
Keyword(s):  
Quality Assurance ◽  
Head And Neck ◽  
Treatment Plan ◽  
Patient Specific ◽  
Imrt Qa ◽  
Passing Rates ◽  
Passing Rate ◽  
Gamma Index ◽  
Clinically Significant ◽  
Alignment Errors

81 Background: Patient-specific quality assurance measurements are time consuming and Gamma pass/fail criteria are often picked based on typical criteria used for IMRT QA measurements in the past. The questions needs to be asked if with these criteria QA plans could still show clinically significant deviations from the treatment plan calculated and how we should be doing QA for treatment delivery of complex treatment plans. In our study DICOM files of clinical Rapidarc plans were modified with in-house developed software to mimic leaf alignment errors and gravitation shifts. The Octavius 2D-ARRAY (PTW-Freiburg) and the Delta4 device (Scandidos) were used to investigate the effect of the simulated errors on the passing rate of quality assurance results. The manipulated Rapidarc plans were recalculated on patient CT scans in Eclipse. Methods: Three different types of errors were simulated and applied to five prostate (two arcs), three 2-arc head and neck cases and three 3-arc head and neck cases. The MLC modifications were: (1) both MLC banks are opened by 0.25mm, 0.50mm and 1.00mm in opposing directions resulting in larger fields, (2) both MLC banks are closed by 0.10mm, 0.25mm and 0.50mm, (3) both MLC banks are shifted in the same direction for lateral gantry angles to simulate effects of gravitational forces onto the leaves by 1mm, 2mm and 3mm, (4) 25%, 50% 70% and 100% of all active leaves are shifted by 3mm as in (3). QA evaluations were performed according to a gamma-index criterion of 3mm and 3% as well as 2mm and 2%. Results: All unmodified plans and the majority of the plans with the smallest modification pass the gamma-index criterion of 2%/2mm with >90%. After that the passing rate drops below 90%. For the largest modifications passing rates were typically below 85%. The Delta4 is generally more sensitive and the passing rate for modified plans drops below 90% earlier and more drastically. With the standard criteria (3mm, 3%) even the largest modifications would satisfy a >90% passing rate. Conclusions: A stricter gamma-index (2mm, 2%) is necessary in order to detect MLC positional errors and a passing rate of >90% should be expected. Clinical pass/fail criteria need to be developed.

scholarly journals Deep Learning of Histopathology Images at the Single Cell Level

2021 ◽  
Vol 4 ◽  
Author(s):  
Kyubum Lee ◽  
John H. Lockhart ◽  
Mengyu Xie ◽  
Ritu Chaudhary ◽  
Robbert J. C. Slebos ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Spatial Organization ◽  
Region Of Interest ◽  
Cell Types ◽  
Training Data ◽  
Omics Data ◽  
Learning Approaches ◽  
Cell Level ◽  
Histopathology Images

The tumor immune microenvironment (TIME) encompasses many heterogeneous cell types that engage in extensive crosstalk among the cancer, immune, and stromal components. The spatial organization of these different cell types in TIME could be used as biomarkers for predicting drug responses, prognosis and metastasis. Recently, deep learning approaches have been widely used for digital histopathology images for cancer diagnoses and prognoses. Furthermore, some recent approaches have attempted to integrate spatial and molecular omics data to better characterize the TIME. In this review we focus on machine learning-based digital histopathology image analysis methods for characterizing tumor ecosystem. In this review, we will consider three different scales of histopathological analyses that machine learning can operate within: whole slide image (WSI)-level, region of interest (ROI)-level, and cell-level. We will systematically review the various machine learning methods in these three scales with a focus on cell-level analysis. We will provide a perspective of workflow on generating cell-level training data sets using immunohistochemistry markers to “weakly-label” the cell types. We will describe some common steps in the workflow of preparing the data, as well as some limitations of this approach. Finally, we will discuss future opportunities of integrating molecular omics data with digital histopathology images for characterizing tumor ecosystem.

scholarly journals Machine Learning-based state-of-the-art methods for the classification of RNA-Seq data

2017 ◽  
Author(s):  
Almas Jabeen ◽  
Nadeem Ahmad ◽  
Khalid Raza
Keyword(s):  
Machine Learning ◽  
Region Of Interest ◽  
Disease Diagnosis ◽  
Learning Approaches ◽  
Rna Seq ◽  
Computational Tools ◽  
Disease Biomarkers ◽  
Diagnosis And Classification ◽  
Gene Exon

AbstractRNA-Seq measures expression levels of several transcripts simultaneously. The identified reads can be gene, exon, or other region of interest. Various computational tools have been developed for studying pathogen or virus from RNA-Seq data by classifying them according to the attributes in several predefined classes, but still computational tools and approaches to analyze complex datasets are still lacking. The development of classification models is highly recommended for disease diagnosis and classification, disease monitoring at molecular level as well as researching for potential disease biomarkers. In this chapter, we are going to discuss various machine learning approaches for RNA-Seq data classification and their implementation. Advancements in bioinformatics, along with developments in machine learning based classification, would provide powerful toolboxes for classifying transcriptome information available through RNA-Seq data.

Multiple vehicles detection and tracking for intelligent transport systems using machine learning approaches

2019 ◽  
Vol 70 (3) ◽  
pp. 214-224
Author(s):  
Bui Ngoc Dung ◽  
Manh Dzung Lai ◽  
Tran Vu Hieu ◽  
Nguyen Binh T. H.
Keyword(s):  
Machine Learning ◽  
Gaussian Mixture ◽  
Research Field ◽  
Transport Systems ◽  
Learning Approaches ◽  
Subtraction Method ◽  
Intelligent Transport Systems ◽  
Intelligent Transport ◽  
Detection And Tracking ◽  
Multiple Vehicles

Video surveillance is emerging research field of intelligent transport systems. This paper presents some techniques which use machine learning and computer vision in vehicles detection and tracking. Firstly the machine learning approaches using Haar-like features and Ada-Boost algorithm for vehicle detection are presented. Secondly approaches to detect vehicles using the background subtraction method based on Gaussian Mixture Model and to track vehicles using optical flow and multiple Kalman filters were given. The method takes advantages of distinguish and tracking multiple vehicles individually. The experimental results demonstrate high accurately of the method.

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

2017 ◽  
Author(s):  
Sabrina Jaeger ◽  
Simone Fulle ◽  
Samo Turk
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Learning Approaches ◽  
Unsupervised Machine Learning ◽  
Feature Representations ◽  
Machine Learning Approach ◽  
The Individual ◽  
Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

Sign in / Sign up

Export Citation Format

Share Document