Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural Network
(1) Background: Lung cancers are the most common cancers worldwide, and prostate cancers are among the second in terms of the frequency of cancers diagnosed in men. Automatic ranking of the risk groups of such diseases is highly in demand, but the clinical practice has shown us that, for a sensitive...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/1/447 |
| _version_ | 1797359095355801600 |
|---|---|
| author | Darian M. Onchis Flavia Costi Codruta Istin Ciprian Cosmin Secasan Gabriel V. Cozma |
| author_facet | Darian M. Onchis Flavia Costi Codruta Istin Ciprian Cosmin Secasan Gabriel V. Cozma |
| author_sort | Darian M. Onchis |
| collection | DOAJ |
| description | (1) Background: Lung cancers are the most common cancers worldwide, and prostate cancers are among the second in terms of the frequency of cancers diagnosed in men. Automatic ranking of the risk groups of such diseases is highly in demand, but the clinical practice has shown us that, for a sensitive screening of the clinical parameters using an artificial intelligence system, a customarily defined deep neural network classifier is not sufficient given the usually small size of medical datasets. (2) Methods: In this paper, we propose a new management method of cancer risk groups based on a supervised neural network model that is further enhanced by using a features attention mechanism in order to boost its level of accuracy. For the analysis of each clinical parameter, we used local interpretable model-agnostic explanations, which is a post hoc model-agnostic technique that outlines feature importance. After that, we applied the feature-attention mechanism in order to obtain a higher weight after training. We tested the method on two datasets, one for binary-class in cases of thoracic cancer and one for multi-class classification in cases of urological cancer, to demonstrate the wide availability and versatility of the method. (3) Results: The accuracy levels of the models trained in this way reached values of more than 80% for both clinical tasks. (4) Conclusions: Our experiments demonstrate that, by using explainability results as feedback signals in conjunction with the attention mechanism, we were able to increase the accuracy of the base model by more than 20% on small medical datasets, reaching a critical threshold for providing recommendations based on the collected clinical parameters. |
| first_indexed | 2024-03-08T15:11:17Z |
| format | Article |
| id | doaj.art-b7c1f42186d340bd9de42278f089e2e0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T15:11:17Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b7c1f42186d340bd9de42278f089e2e02024-01-10T14:52:10ZengMDPI AGApplied Sciences2076-34172024-01-0114144710.3390/app14010447Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural NetworkDarian M. Onchis0Flavia Costi1Codruta Istin2Ciprian Cosmin Secasan3Gabriel V. Cozma4Computer Science Department, West University of Timisoara, 300223 Timisoara, RomaniaComputer Science Department, West University of Timisoara, 300223 Timisoara, RomaniaDepartment of Computer and Information Technology, Politehnica University, 300006 Timisoara, RomaniaUrology Clinic, Victor Babes University of Medicine and Pharmacy, 300041 Timisoara, RomaniaDepartment of Surgical Semiology I and Thoracic Surgery, Thoracic Surgery Research Center (CCCTTIM), “Victor Babes” University of Medicine and Pharmacy of Timisoara, 300041 Timisoara, Romania(1) Background: Lung cancers are the most common cancers worldwide, and prostate cancers are among the second in terms of the frequency of cancers diagnosed in men. Automatic ranking of the risk groups of such diseases is highly in demand, but the clinical practice has shown us that, for a sensitive screening of the clinical parameters using an artificial intelligence system, a customarily defined deep neural network classifier is not sufficient given the usually small size of medical datasets. (2) Methods: In this paper, we propose a new management method of cancer risk groups based on a supervised neural network model that is further enhanced by using a features attention mechanism in order to boost its level of accuracy. For the analysis of each clinical parameter, we used local interpretable model-agnostic explanations, which is a post hoc model-agnostic technique that outlines feature importance. After that, we applied the feature-attention mechanism in order to obtain a higher weight after training. We tested the method on two datasets, one for binary-class in cases of thoracic cancer and one for multi-class classification in cases of urological cancer, to demonstrate the wide availability and versatility of the method. (3) Results: The accuracy levels of the models trained in this way reached values of more than 80% for both clinical tasks. (4) Conclusions: Our experiments demonstrate that, by using explainability results as feedback signals in conjunction with the attention mechanism, we were able to increase the accuracy of the base model by more than 20% on small medical datasets, reaching a critical threshold for providing recommendations based on the collected clinical parameters.https://www.mdpi.com/2076-3417/14/1/447deep supervised learningthoracic dataseturology datasetexplainabilityattention mechanismcancer risk groups |
| spellingShingle | Darian M. Onchis Flavia Costi Codruta Istin Ciprian Cosmin Secasan Gabriel V. Cozma Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural Network Applied Sciences deep supervised learning thoracic dataset urology dataset explainability attention mechanism cancer risk groups |
| title | Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural Network |
| title_full | Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural Network |
| title_fullStr | Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural Network |
| title_full_unstemmed | Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural Network |
| title_short | Method of Improving the Management of Cancer Risk Groups by Coupling a Features-Attention Mechanism to a Deep Neural Network |
| title_sort | method of improving the management of cancer risk groups by coupling a features attention mechanism to a deep neural network |
| topic | deep supervised learning thoracic dataset urology dataset explainability attention mechanism cancer risk groups |
| url | https://www.mdpi.com/2076-3417/14/1/447 |
| work_keys_str_mv | AT darianmonchis methodofimprovingthemanagementofcancerriskgroupsbycouplingafeaturesattentionmechanismtoadeepneuralnetwork AT flaviacosti methodofimprovingthemanagementofcancerriskgroupsbycouplingafeaturesattentionmechanismtoadeepneuralnetwork AT codrutaistin methodofimprovingthemanagementofcancerriskgroupsbycouplingafeaturesattentionmechanismtoadeepneuralnetwork AT cipriancosminsecasan methodofimprovingthemanagementofcancerriskgroupsbycouplingafeaturesattentionmechanismtoadeepneuralnetwork AT gabrielvcozma methodofimprovingthemanagementofcancerriskgroupsbycouplingafeaturesattentionmechanismtoadeepneuralnetwork |