Development of a Ready-to-Use Graphical Tool Based on Artificial Neural Network Classification : Application for the Prediction of Late Fecal Incontinence After Prostate Cancer Radiation Therapy

Published on Dec 1, 2018in International Journal of Radiation Oncology Biology Physics5.859
· DOI :10.1016/J.IJROBP.2018.07.2014
Mauro Carrara16
Estimated H-index: 16
Eleonora Massari2
Estimated H-index: 2
+ 13 AuthorsRiccardo Valdagni51
Estimated H-index: 51
(University of Milan)
Purpose This study was designed to apply artificial neural network (ANN) classification methods for the prediction of late fecal incontinence (LFI) after high-dose prostate cancer radiation therapy and to develop a ready-to-use graphical tool. Materials and Methods In this study, 598 men recruited in 2 national multicenter trials were analyzed. Information was recorded on comorbidity, previous abdominal surgery, use of drugs, and dose distribution. Fecal incontinence was prospectively evaluated through self-reported questionnaires. To develop the ANN, the study population was randomly split into training (n = 300), validation (n = 149), and test (n = 149) sets. Mean grade of longitudinal LFI (ie, expressed as the average incontinence grade over the first 3 years after radiation therapy) ≥1 was considered the endpoint. A suitable subset of variables able to better predict LFI was selected by simulating 100,000 ANN configurations. The search for the definitive ANN was then performed by varying the number of inputs and hidden neurons from 4 to 5 and from 1 to 9, respectively. A final classification model was established as the average of the best 5 among 500 ANNs with the same architecture. An ANN-based graphical method to compute LFI prediction was developed to include one continuous and n dichotomous variables. Results An ANN architecture was selected, with 5 input variables (mean dose, previous abdominal surgery, use of anticoagulants, use of antihypertensive drugs, and use of neoadjuvant and adjuvant hormone therapy) and 4 hidden neurons. The developed classification model correctly identified patients with LFI with 80.8% sensitivity and 63.7% ± 1.0% specificity and an area under the curve of 0.78. The developed graphical tool may efficiently classify patients in low, intermediate, and high LFI risk classes. Conclusions An ANN-based model was developed to predict LFI. The model was translated in a ready-to-use graphical tool for LFI risk classification, with direct interpretation of the role of the predictors.
📖 Papers frequently viewed together
7 Authors (Ziyu Li, ..., Jiafu Ji)
1 Citations
6 Authors (Daniel D Cho, ..., J Chang)
#1Eta S. Berner (UAB: University of Alabama at Birmingham)H-Index: 26
#2Bunyamin Ozaydin (UAB: University of Alabama at Birmingham)H-Index: 6
5 CitationsSource
#1Federico Cabitza (University of Milano-Bicocca)H-Index: 22
#2Raffaele RasoiniH-Index: 5
Last. Gian Franco GensiniH-Index: 98
view all 3 authors...
273 CitationsSource
#1Bulat Ibragimov (Stanford University)H-Index: 19
#2Lei Xing (Stanford University)H-Index: 85
Purpose Accurate segmentation of organs-at-risks (OARs) is the key step for efficient planning of radiation therapy for head and neck (HaN) cancer treatment. In the work, we proposed the first deep learning-based algorithm, for segmentation of OARs in HaN CT images, and compared its performance against state-of-the-art automated segmentation algorithms, commercial software, and interobserver variability. Methods Convolutional neural networks (CNNs)—a concept from the field of deep learning—were ...
218 CitationsSource
#1Antonella Belfatto (Polytechnic University of Milan)H-Index: 5
#2Derek A. White (UTSW: University of Texas Southwestern Medical Center)H-Index: 5
Last. Pietro Cerveri (Polytechnic University of Milan)H-Index: 25
view all 7 authors...
Purpose: Radiation therapy is one of the most common treatments in the fight against prostate cancer, since it is used to control the tumor (early stages), to slow its progression, and even to control pain (metastasis). Although many factors (e.g., tumor oxygenation) are known to influence treatment efficacy, radiotherapy doses and fractionation schedules are often prescribed according to the principle “one-fits-all,” with little personalization. Therefore, the authors aim at predicting the outc...
5 CitationsSource
#1Satomi Shiraishi (UCSD: University of California, San Diego)H-Index: 5
#2Kevin L. Moore (UCSD: University of California, San Diego)H-Index: 44
Purpose: To demonstrate knowledge-based 3D dose prediction for external beam radiotherapy. Methods: Using previously treated plans as training data, an artificial neural network (ANN) was trained to predict a dose matrix based on patient-specific geometric and planning parameters, such as the closest distance (r) to planning target volume (PTV) and organ-at-risks (OARs). Twenty-three prostate and 43 stereotactic radiosurgery/radiotherapy (SRS/SRT) cases with at least one nearby OAR were studied....
123 CitationsSource
Artificial neural networks (ANNs) are usually considered as tools which can help to analyze cause-effect relationships in complex systems within a big-data framework. On the other hand, health sciences undergo complexity more than any other scientific discipline, and in this field large datasets are seldom available. In this situation, I show how a particular neural network tool, which is able to handle small datasets of experimental or observational data, can help in identifying the main causal...
75 CitationsSource
#1Arjien van der Schaaf (UMCG: University Medical Center Groningen)H-Index: 1
#2Johannes A. Langendijk (UMCG: University Medical Center Groningen)H-Index: 86
Last. Tiziana RancatiH-Index: 27
view all 4 authors...
20 CitationsSource
#1Peter Tino (University of Birmingham)H-Index: 25
#2Lubica Benuskova (University of Otago)H-Index: 19
Last. Alessandro Sperduti (UNIPD: University of Padua)H-Index: 34
view all 3 authors...
We outline the main models and developments in the broad field of artificial neural networks (ANN). A brief introduction to biological neurons motivates the initial formal neuron model – the perceptron. We then study how such formal neurons can be generalized and connected in network structures. Starting with the biologically motivated layered structure of ANN (feed-forward ANN), the networks are then generalized to include feedback loops (recurrent ANN) and even more abstract generalized forms ...
17 CitationsSource
Purpose To fit urinary toxicity data of patients treated with postprostatectomy radiation therapy with the linear quadratic (LQ) model with/without introducing a time factor. Methods and Materials Between 1993 and 2010, 1176 patients were treated with conventional fractionation (1.8 Gy per fraction, median 70.2 Gy, n=929) or hypofractionation (2.35-2.90 Gy per fraction, n=247). Data referred to 2004-2010 (when all schemes were in use, n=563; conventional fractionation: 316; hypofractionation: 24...
17 CitationsSource
#1Gianni FellinH-Index: 17
#2Tiziana Rancati (UniSR: Vita-Salute San Raffaele University)H-Index: 27
Last. Riccardo Valdagni (UniSR: Vita-Salute San Raffaele University)H-Index: 51
view all 18 authors...
Abstract Purpose To prospectively evaluate long-term late rectal bleeding (lrb) and faecal incontinence (linc) after high-dose radiotherapy (RT) for prostate cancer in the AIROPROS 0102 population, and to assess clinical/dosimetric risk factors. Materials and methods Questionnaires of 515 patients with G0 baseline incontinence and bleeding scores (follow-up ⩾6years) were analysed. Correlations between lrb/linc and many clinical and dosimetric parameters were investigated by univariate and multiv...
25 CitationsSource
Cited By4
#1V. Bourbonne (French Institute of Health and Medical Research)H-Index: 4
#2Ronrick Da-ano (French Institute of Health and Medical Research)H-Index: 3
Last. Ulrike Schick (French Institute of Health and Medical Research)H-Index: 23
view all 10 authors...
Abstract Purpose (Chemo)–radiotherapy (RT) is the gold standard treatment for patients with locally advanced lung cancer non accessible for surgery. However, current toxicity prediction models rely on clinical and dose volume histograms (DVHs) and remain unsufficient. The goal of this work is to investigate the added predictive value of the radiomics approach applied to dose maps regarding acute and late toxicities in both the lungs and esophagus. Methods Acute and late toxicities scored using t...
#1Lars J. Isaksson (IEO: European Institute of Oncology)H-Index: 2
#2Matteo Pepa (IEO: European Institute of Oncology)H-Index: 4
Last. Barbara Alicja Jereczek-Fossa (IEO: European Institute of Oncology)H-Index: 3
view all 12 authors...
In order to limit radiotherapy (RT)-related side effects, effective toxicity prediction schemes are essential. In recent years, the growing interest towards artificial intelligence (AI) and machine learning (ML) in science have led to the implementation of such innovative tools in RT. Several researchers have demonstrated the high performance of ML-based models in predicting toxicity, but the application of these approaches in clinics is still lagging, partly due to their low interpretability. H...
6 CitationsSource
view all 3 authors...