Basic of machine learning and deep learning in imaging for medical physicists

Manco, Luigi; Maffei, N.; Strolin, Silvia; Vichi, Sara; Bottazzi, Luca; Strigari, Lidia

doi:10.1016/j.ejmp.2021.03.026

Cited by 42 publications

(18 citation statements)

References 170 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since the beginning of the digital era, the amount of data produced has considerably increased, even in the field of medicine [5]. At the same time, the interest in the application of ML and DL approaches in medical data analysis has grown enormously [6][7][8][9]. A specific difficulty that is encountered in developing ML and DL analysis tools for medical applications is that the training processes often require large amounts of annotated data.…”

Section: Introductionmentioning

confidence: 99%

Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples

Ubaldi

Valenti²,

Borgese

et al. 2021

Physica Medica

View full text Add to dashboard Cite

Predictive models based on radiomics and machine-learning (ML) need large and annotated datasets for training, often difficult to collect. We designed an operative pipeline for model training to exploit data already available to the scientific community. The aim of this work was to explore the capability of radiomic features in predicting tumor histology and stage in patients with non-small cell lung cancer (NSCLC).We analyzed the radiotherapy planning thoracic CT scans of a proprietary sample of 47 subjects (L-RT) and integrated this dataset with a publicly available set of 130 patients from the MAASTRO NSCLC collection (Lung1). We implemented intra-and inter-sample cross-validation strategies (CV) for evaluating the ML predictive model performances with not so large datasets.We carried out two classification tasks: histology classification (3 classes) and overall stage classification (two classes: stage I and II). In the first task, the best performance was obtained by a Random Forest classifier, once the analysis has been restricted to stage I and II tumors of the Lung1 and L-RT merged dataset (AUC = 0.72 ± 0.11). For the overall stage classification, the best results were obtained when training on Lung1 and testing of L-RT dataset (AUC = 0.72 ± 0.04 for Random Forest and AUC = 0.84 ± 0.03 for linear-kernel Support Vector Machine).According to the classification task to be accomplished and to the heterogeneity of the available dataset(s), different CV strategies have to be explored and compared to make a robust assessment of the potential of a predictive model based on radiomics and ML.

show abstract

Section: Introductionmentioning

confidence: 99%

Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples

Ubaldi

Valenti²,

Borgese

et al. 2021

Physica Medica

View full text Add to dashboard Cite

show abstract

“…High quality auto-contouring is the single most important element to further accelerate the treatment planning workflow and to facilitate on-line adaptive radiotherapy (ART) strategies. Moreover, a recent review study focused on machine learning and deep learning in imaging highlighted a great interest on the possibility to extract useful features directly from raw images despite segmentation related challenges [41]. Identifying contouring methods that improve feature reliability, helps to reduce feature uncertainties caused by inconsistent contouring.…”

Section: Discussionmentioning

confidence: 99%

Radiomics classifier to quantify automatic segmentation quality of cardiac sub-structures for radiotherapy treatment planning

Maffei¹,

Manco²,

Aluisio³

et al. 2021

Physica Medica

Self Cite

View full text Add to dashboard Cite

A radiomics features classifier was implemented to evaluate segmentation quality of heart structures. A robust feature set sensitive to incorrect contouring would provide an ideal quantitative index to drive autocontouring optimization. Methods: Twenty-five cardiac sub-structures were contoured as regions of interest in 36 CTs. Radiomic features were extracted from manually-contoured (MC) and Hierarchical-Clustering automatic-contouring (AC) structures. A robust feature-set was identified from correctly contoured CT datasets. Features variation was analyzed over a MC/AC dataset. A supervised-learning approach was used to train an Artificial-Intelligence (AI) classifier; incorrect contouring cases were generated from the gold-standard MC datasets with translations, expansions and contractions. ROC curves and confusion matrices were used to evaluate the AI-classifier performance. Results: Twenty radiomics features, were found to be robust across structures, showing a good/excellent intraclass correlation coefficient (ICC) index comparing MC/AC. A significant correlation was obtained with quantitative indexes (Dice-Index, Hausdorff-distance). The trained AI-classifier detected correct contours (CC) and not correct contours (NCC) with an accuracy of 82.6% and AUC of 0.91. True positive rate (TPR) was 85.1% and 81.3% for CC and NCC. Detection of NCC at this point of the development still depended strongly on degree of contouring imperfection. Conclusions: A set of radiomics features, robust on "gold-standard" contour and sensitive to incorrect contouring was identified and implemented in an AI-workflow to quantify segmentation accuracy. This workflow permits an automatic assessment of segmentation quality and may accelerate expansion of an existing autocontouring atlas database as well as improve dosimetric analyses of large treatment plan databases.

show abstract

“…Interdisciplinary work between different professionals is necessary to reach the goal, and Medical Physicists can play an important role since they are a bridge between technology and medicine. Many reviews are available in literature describing the AI applications in Medical Imaging, Radiation Therapy (RT), Quality Assurance (QA) fields, also describing the role of Medical Physicists [1,[19][20][21][22].…”

Section: Ai Potential Impact On Medical Imaging Workflowsmentioning

confidence: 99%

Enhancing the impact of Artificial Intelligence in Medicine: A joint AIFM-INFN Italian initiative for a dedicated cloud-based computing infrastructure

et al. 2021

View full text Add to dashboard Cite

Basic of machine learning and deep learning in imaging for medical physicists

Cited by 42 publications

References 170 publications

Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples

Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples

Radiomics classifier to quantify automatic segmentation quality of cardiac sub-structures for radiotherapy treatment planning

Enhancing the impact of Artificial Intelligence in Medicine: A joint AIFM-INFN Italian initiative for a dedicated cloud-based computing infrastructure

Contact Info

Product

Resources

About