Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network Algorithms
In computed tomography, state-of-the-art reconstruction is based on neural network (NN) algorithms. However, NN reconstruction algorithms can be not robust to small noise-like perturbations in the input signal. A not robust NN algorithm can produce inaccurate reconstruction with plausible artifacts...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/22/4210 |
| _version_ | 1797464725284454400 |
|---|---|
| author | Aleksandr Smolin Andrei Yamaev Anastasia Ingacheva Tatyana Shevtsova Dmitriy Polevoy Marina Chukalina Dmitry Nikolaev Vladimir Arlazarov |
| author_facet | Aleksandr Smolin Andrei Yamaev Anastasia Ingacheva Tatyana Shevtsova Dmitriy Polevoy Marina Chukalina Dmitry Nikolaev Vladimir Arlazarov |
| author_sort | Aleksandr Smolin |
| collection | DOAJ |
| description | In computed tomography, state-of-the-art reconstruction is based on neural network (NN) algorithms. However, NN reconstruction algorithms can be not robust to small noise-like perturbations in the input signal. A not robust NN algorithm can produce inaccurate reconstruction with plausible artifacts that cannot be detected. Hence, the robustness of NN algorithms should be investigated and evaluated. There have been several attempts to construct the numerical metrics of the NN reconstruction algorithms’ robustness. However, these metrics estimate only the probability of the easily distinguishable artifacts occurring in the reconstruction. However, these methods measure only the probability of appearance of easily distinguishable artifacts on the reconstruction, which cannot lead to misdiagnosis in clinical applications. In this work, we propose a new method for numerical estimation of the robustness of the NN reconstruction algorithms. This method is based on the probability evaluation for NN to form such selected additional structures during reconstruction which may lead to an incorrect diagnosis. The method outputs a numerical score value from 0 to 1 that can be used when benchmarking the robustness of different reconstruction algorithms. We employed the proposed method to perform a comparative study of seven reconstruction algorithms, including five NN-based and two classical. The ResUNet network had the best robustness score (0.65) among the investigated NN algorithms, but its robustness score is still lower than that of the classical algorithm SIRT (0.989). The investigated NN models demonstrated a wide range of robustness scores (0.38–0.65). Thus, in this work, robustness of 7 reconstruction algorithms was measured using the new proposed score and it was shown that some of the neural algorithms are not robust. |
| first_indexed | 2024-03-09T18:11:17Z |
| format | Article |
| id | doaj.art-d94250ae716a4b5fa35ed9f511164791 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T18:11:17Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-d94250ae716a4b5fa35ed9f5111647912023-11-24T09:07:46ZengMDPI AGMathematics2227-73902022-11-011022421010.3390/math10224210Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network AlgorithmsAleksandr Smolin0Andrei Yamaev1Anastasia Ingacheva2Tatyana Shevtsova3Dmitriy Polevoy4Marina Chukalina5Dmitry Nikolaev6Vladimir Arlazarov7Smart Engines Service LLC, Moscow 121205, RussiaSmart Engines Service LLC, Moscow 121205, RussiaSmart Engines Service LLC, Moscow 121205, RussiaUniversity Clinical Hospital No. 3 of the Clinical Center, I.M. Sechenov First Moscow State Medical University (Sechenov University), Moscow 119991, RussiaSmart Engines Service LLC, Moscow 121205, RussiaSmart Engines Service LLC, Moscow 121205, RussiaSmart Engines Service LLC, Moscow 121205, RussiaSmart Engines Service LLC, Moscow 121205, RussiaIn computed tomography, state-of-the-art reconstruction is based on neural network (NN) algorithms. However, NN reconstruction algorithms can be not robust to small noise-like perturbations in the input signal. A not robust NN algorithm can produce inaccurate reconstruction with plausible artifacts that cannot be detected. Hence, the robustness of NN algorithms should be investigated and evaluated. There have been several attempts to construct the numerical metrics of the NN reconstruction algorithms’ robustness. However, these metrics estimate only the probability of the easily distinguishable artifacts occurring in the reconstruction. However, these methods measure only the probability of appearance of easily distinguishable artifacts on the reconstruction, which cannot lead to misdiagnosis in clinical applications. In this work, we propose a new method for numerical estimation of the robustness of the NN reconstruction algorithms. This method is based on the probability evaluation for NN to form such selected additional structures during reconstruction which may lead to an incorrect diagnosis. The method outputs a numerical score value from 0 to 1 that can be used when benchmarking the robustness of different reconstruction algorithms. We employed the proposed method to perform a comparative study of seven reconstruction algorithms, including five NN-based and two classical. The ResUNet network had the best robustness score (0.65) among the investigated NN algorithms, but its robustness score is still lower than that of the classical algorithm SIRT (0.989). The investigated NN models demonstrated a wide range of robustness scores (0.38–0.65). Thus, in this work, robustness of 7 reconstruction algorithms was measured using the new proposed score and it was shown that some of the neural algorithms are not robust.https://www.mdpi.com/2227-7390/10/22/4210robustnessneural networkcomputed tomography |
| spellingShingle | Aleksandr Smolin Andrei Yamaev Anastasia Ingacheva Tatyana Shevtsova Dmitriy Polevoy Marina Chukalina Dmitry Nikolaev Vladimir Arlazarov Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network Algorithms Mathematics robustness neural network computed tomography |
| title | Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network Algorithms |
| title_full | Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network Algorithms |
| title_fullStr | Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network Algorithms |
| title_full_unstemmed | Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network Algorithms |
| title_short | Reprojection-Based Numerical Measure of Robustness for CT Reconstruction Neural Network Algorithms |
| title_sort | reprojection based numerical measure of robustness for ct reconstruction neural network algorithms |
| topic | robustness neural network computed tomography |
| url | https://www.mdpi.com/2227-7390/10/22/4210 |
| work_keys_str_mv | AT aleksandrsmolin reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms AT andreiyamaev reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms AT anastasiaingacheva reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms AT tatyanashevtsova reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms AT dmitriypolevoy reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms AT marinachukalina reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms AT dmitrynikolaev reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms AT vladimirarlazarov reprojectionbasednumericalmeasureofrobustnessforctreconstructionneuralnetworkalgorithms |