Radiomics and Machine Learning for Radiotherapy in Head and Neck Cancers

Published on Mar 27, 2019in Frontiers in Oncology4.848
· DOI :10.3389/FONC.2019.00174
Paul Giraud3
Estimated H-index: 3
(Paris V: Paris Descartes University),
Philippe Giraud29
Estimated H-index: 29
(Paris V: Paris Descartes University)
+ 7 AuthorsJean-Emmanuel Bibault19
Estimated H-index: 19
(Paris V: Paris Descartes University)
Introduction: An increasing number of parameters can be considered when making decisions in oncology. Tumor characteristics can also be extracted from imaging through the use of radiomics and add to this wealth of clinical data. Machine learning can encompass these parameters and thus enhance clinical decision as well as radiotherapy workflow. Methods: We performed a description of machine learning applications at each step of treatment by radiotherapy in head and neck cancers. We then performed a systematic review on radiomics and machine learning outcome prediction models in head and neck cancers. Results: Machine Learning has several promising applications in treatment planning with automatic organ at risk delineation improvements and adaptative radiotherapy workflow automation. It may also provide new approaches for Normal Tissue Complication Probability models. Radiomics may provide additional data on tumors for improved machine learning powered predictive models, not only on survival, but also on risk of distant metastasis, in field recurrence, HPV status and extra nodal spread. However, most studies provide preliminary data requiring further validation. Conclusion: Promising perspectives arise from machine learning applications and radiomics based models, yet further data are necessary for their implementation in daily care.
Figures & Tables
📖 Papers frequently viewed together
12 Citations
14 Citations
#1Yitan Zhu (NorthShore University HealthSystem)H-Index: 15
#2Abdallah S.R. Mohamed (Alexandria University)H-Index: 25
Last. Clifton D. Fuller (University of Texas MD Anderson Cancer Center)H-Index: 49
view all 19 authors...
PurposeRecent data suggest that imaging radiomic features of a tumor could be indicative of important genomic biomarkers. Understanding the relationship between radiomic and genomic features is important for basic cancer research and future patient care. We performed a comprehensive study to discover the imaginggenomic associations in head and neck squamous cell carcinoma (HNSCC) and explore the potential of predicting tumor genomic alternations using radiomic features.MethodsOur retrospective s...
8 CitationsSource
#1Lu Zhang (Southern Medical University)H-Index: 20
#2Di Dong (CAS: Chinese Academy of Sciences)H-Index: 30
Last. Shuixing Zhang (Academy of Medical Sciences, United Kingdom)H-Index: 11
view all 15 authors...
Abstract Background We aimed to identify a magnetic resonance imaging (MRI)-based model for assessment of the risk of individual distant metastasis (DM) before initial treatment of nasopharyngeal carcinoma (NPC). Methods This retrospective cohort analysis included 176 patients with NPC. Using the PyRadiomics platform, we extracted the imaging features of primary tumors in all patients who did not exhibit DM before treatment. Subsequently, we used minimum redundancy-maximum relevance and least ab...
27 CitationsSource
#1Shuangshuang Li (NU: Nanjing University)H-Index: 6
#1Shuangshuang Li (NU: Nanjing University)H-Index: 2
Last. Jing Yan (NU: Nanjing University)H-Index: 11
view all 11 authors...
Objective To analyze the recurrence patterns and reasons in patients with head and neck cancer(HNC) treated with intensity-modulated radiotherapy(IMRT) and to investigate the feasibility of radiomics for analysis of nasopharyngeal carcinoma(NPC) radioresistance. Methods We analyzed 504 HNC patients treated with IMRT from Jul-2009 to Aug-2016, 26 of whom developed with recurrence. For the HNCs with recurrence, CT, MR or PET/CT images of recurrent disease were registered with the primary planning ...
11 CitationsSource
#1Hesham Elhalawani (University of Texas MD Anderson Cancer Center)H-Index: 19
#2Aasheesh Kanwar (TTUHSC: Texas Tech University Health Sciences Center)H-Index: 6
Last. Clifton D. FullerH-Index: 49
view all 32 authors...
50 CitationsSource
#1Jennifer Y.Y. Kwan (Princess Margaret Cancer Centre)H-Index: 9
#2Jie Su (UHN: University Health Network)H-Index: 19
Last. Fei-Fei Liu (U of T: University of Toronto)H-Index: 73
view all 23 authors...
Purpose Distant metastasis (DM) is the main cause of death for patients with human papillomavirus (HPV)–related oropharyngeal cancers (OPCs); yet, there are few reliable predictors of DM in this disease. The role of quantitative imaging (ie, radiomic) analysis was examined to determine whether there are primary tumor features discernible on imaging studies that are associated with a higher risk of DM developing. Methods and Materials Radiation therapy planning computed tomography scans were retr...
20 CitationsSource
#1Benjamin H. Kann (Yale University)H-Index: 13
#2Sanjay Aneja (Yale University)H-Index: 12
Last. Zain A. Husain (Yale University)H-Index: 19
view all 12 authors...
Identification of nodal metastasis and tumor extranodal extension (ENE) is crucial for head and neck cancer management, but currently only can be diagnosed via postoperative pathology. Pretreatment, radiographic identification of ENE, in particular, has proven extremely difficult for clinicians, but would be greatly influential in guiding patient management. Here, we show that a deep learning convolutional neural network can be trained to identify nodal metastasis and ENE with excellent performa...
49 CitationsSource
Over half a million individuals are diagnosed with head and neck cancer each year worldwide. Radiotherapy is an important curative treatment for this disease, but it requires manually intensive delineation of radiosensitive organs at risk (OARs). This planning process can delay treatment commencement. While auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying and achieving expert performance remain. Adopting a deep learning approach, we d...
87 Citations
#1Rachel B. Ger (University of Texas Health Science Center at Houston)H-Index: 12
#2Shouhao Zhou (University of Texas MD Anderson Cancer Center)H-Index: 28
Last. Dennis Mackin (University of Texas MD Anderson Cancer Center)H-Index: 21
view all 13 authors...
Radiomics has shown promise in improving models for predicting patient outcomes. However, to maximize the information gain of the radiomics features, especially in larger patient cohorts, the variability in radiomics features owing to differences between scanners and scanning protocols must be accounted for. To this aim, the imaging variability of radiomics feature values was evaluated on 100 computed tomography scanners at 35 clinics by imaging a radiomics phantom using a controlled protocol an...
37 CitationsSource
#1Christophe Nioche (Université Paris-Saclay)H-Index: 15
#2Fanny Orlhac (Université Paris-Saclay)H-Index: 16
Last. Irène Buvat (Université Paris-Saclay)H-Index: 46
view all 10 authors...
Textural and shape analysis is gaining considerable interest in medical imaging, particularly to identify parameters characterizing tumor heterogeneity and to feed radiomic models. Here, we present a free, multiplatform, and easy-to-use freeware called LIFEx, which enables the calculation of conventional, histogram-based, textural, and shape features from PET, SPECT, MR, CT, and US images, or from any combination of imaging modalities. The application does not require any programming skills and ...
202 CitationsSource
#1R. BerenguerH-Index: 8
Last. Sebastià SabaterH-Index: 15
view all 7 authors...
The majority (94%) of the evaluated radiomics features for CT were not reproducible and were redundant. If all the CT parameters are held constant, then a smaller percentage (6%) of the radiomics f...
174 CitationsSource
Cited By31
#1Jung Hun Oh (MSK: Memorial Sloan Kettering Cancer Center)H-Index: 26
#2Aditya Apte (MSK: Memorial Sloan Kettering Cancer Center)H-Index: 19
Last. Joseph O. Deasy (MSK: Memorial Sloan Kettering Cancer Center)H-Index: 1
view all 14 authors...
Purpose: The goal of this study is to develop innovative methods for identifying radiomic features that are reproducible over varying image acquisition settings. Approach: We propose a regularized partial correlation network to identify reliable and reproducible radiomic features. This approach was tested on two radiomic feature sets generated using two different reconstruction methods on computed tomography (CT) scans from a cohort of 47 lung cancer patients. The largest common network componen...
#1Xinyan Wang (Capital Medical University)
Last. Junfang Xian (Capital Medical University)H-Index: 19
view all 5 authors...
PURPOSE To develop and validate an MRI-based radiomics model in differentiation between sinonasal primary lymphomas and squamous cell carcinomas (SCCs). MATERIALS AND METHODS One-hundred-and-fifty-four patients were enrolled (74 individuals with SCCs and 80 with lymphomas). After feature analysis and feature selection with variance threshold and least absolute shrinkage and selection operator (LASSO) methods, an MRI-based radiomics model with the support vector machine (SVM) classifier was const...
#1Shu-Ju Tu (CGU: Chang Gung University)
#2Wei-Yuan Chen (CGU: Chang Gung University)
Last. Chen-Te Wu (CGU: Chang Gung University)
view all 5 authors...
Quantum noise is a random process in X-ray-based imaging systems. We addressed and measured the uncertainty of radiomics features against this quantum noise in computed tomography (CT) images. A clinical multi-detector CT scanner, two homogeneous phantom sets, and four heterogeneous samples were used. A solid tumor tissue removed from a male BALB/c mouse was included. We the placed phantom sets on the CT scanning table and repeated 20 acquisitions with identical imaging settings. Regions of inte...
#1Archya Dasgupta (U of T: University of Toronto)H-Index: 7
#2Kashuf Fatima (Sunnybrook Research Institute)H-Index: 1
Last. Gregory J. Czarnota (U of T: University of Toronto)H-Index: 34
view all 12 authors...
This prospective study was conducted to investigate the role of quantitative ultrasound (QUS) radiomics in predicting recurrence for patients with node-positive head-neck squamous cell carcinoma (HNSCC) treated with radical radiotherapy (RT). The most prominent cervical lymph node (LN) was scanned with a clinical ultrasound device having central frequency of 6.5 MHz. Ultrasound radiofrequency data were processed to obtain 7 QUS parameters. Color-coded parametric maps were generated based on indi...
1 CitationsSource
#1Siye Liu (CSU: Central South University)H-Index: 3
#2Xiaoping Yu (CSU: Central South University)H-Index: 6
Last. Qiang Lu (CSU: Central South University)H-Index: 5
view all 10 authors...
Objective: To establish and validate a radiomics nomogram based on the features of the primary tumor for predicting preoperative pathological extramural venous invasion (EMVI) in rectal cancer using machine learning. Methods: The clinical and imaging data of 281 patients with primary rectal cancer from April 2012 to May 2018 were retrospectively analyzed. All the patients were divided into a training set (n = 198) and a test set (n = 83) respectively. The radiomics features of the primary tumor ...
#1Laurentius O. Osapoetra (Sunnybrook Health Sciences Centre)H-Index: 1
#1Laurentius O. Osapoetra (Sunnybrook Health Sciences Centre)H-Index: 4
Last. Gregory J. CzarnotaH-Index: 34
view all 12 authors...
To investigate the role of quantitative ultrasound (QUS) radiomics to predict treatment response in patients with head and neck squamous cell carcinoma (HNSCC) treated with radical radiotherapy (RT). Five spectral parameters, 20 texture, and 80 texture-derivative features were extracted from the index lymph node before treatment. Response was assessed initially at 3 months with complete responders labelled as early responders (ER). Patients with residual disease were followed to classify them as...
#1Kashuf Fatima (Sunnybrook Research Institute)H-Index: 3
#2Archya Dasgupta (U of T: University of Toronto)H-Index: 7
Last. Gregory J. CzarnotaH-Index: 34
view all 13 authors...
Abstract Purpose This study investigated the use of quantitative ultrasound (QUS) obtained during radical radiotherapy (RT) as a radiomics biomarker for predicting recurrence in patients with node-positive head-neck squamous cell carcinoma (HNSCC). Methods Fifty-one patients with HNSCC were treated with RT (70 Gy/33 fractions) (+/- concurrent chemotherapy) were included. QUS Data acquisition involved scanning an index neck node with a clinical ultrasound device. Radiofrequency data were collecte...
#1Ying Wang (Nanjing Medical University)
#2Feng Yang (Nanjing Medical University)
Last. Ming Yang (Nanjing Medical University)H-Index: 19
view all 4 authors...
In order to evaluate brain changes in young children with Pierre Robin sequence (PRs) using machine learning based on apparent diffusion coefficient (ADC) features, we retrospectively enrolled a total of 60 cases (42 in the training dataset and 18 in the testing dataset) which included 30 PRs and 30 controls from the Children's Hospital Affiliated to the Nanjing Medical University from January 2017-December 2019. There were 21 and nine PRs cases in each dataset, with the remainder belonging to t...
#1N. MaffeiH-Index: 5
#2Luigi MancoH-Index: 1
Last. Gabriele GuidiH-Index: 10
view all 9 authors...
Abstract Purpose 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 i...
Riassunto La radioterapia e da un secolo una parte imprescindibile dell’arsenale terapeutico contro i cancri oto-rino-laringoiatrici. Gli sviluppi tecnologici hanno permesso, negli ultimi 20 anni, di ottenere una precisione millimetrica nell’erogazione della dose, garantendo trattamenti meno tossici a breve e a lungo termine, con una migliore efficacia. La radioterapia conformazionale a intensita modulata e divenuta lo standard per l’irradiazione esterna e la brachiterapia mantiene alcune indica...