Abstract
In Medicine Deep Learning has become an essential tool to achieve outstanding diagnosis on image data. However, one critical problem is that Deep Learning comes with complicated, black-box models so it is not possible to analyze their trust level directly. So, Explainable Artificial Intelligence (XAI) methods are used to build additional interfaces for explaining how the model has reached the outputs by moving from the input data. Of course, that's again another competitive problem to analyze if such methods are successful according to the human view. So, this paper comes with two important research efforts: (1) to build an explainable deep learning model targeting medical image analysis, and (2) to evaluate the trust level of this model via several evaluation works including human contribution. The target problem was selected as the brain tumor classification, which is a remarkable, competitive medical image-based problem for Deep Learning. In the study, MR-based pre-processed brain images were received by the Subtractive Spatial Lightweight Convolutional Neural Network (SSLW-CNN) model, which includes additional operators to reduce the complexity of classification. In order to ensure the explainable background, the model also included Class Activation Mapping (CAM). It is important to evaluate the trust level of a successful model. So, numerical success rates of the SSLW-CNN were evaluated based on the peak signal-to-noise ratio (PSNR), computational time, computational overhead, and brain tumor classification accuracy. The objective of the proposed SSLW-CNN model is to obtain faster and good tumor classification with lesser time. The results illustrate that the SSLW-CNN model provides better performance of PSNR which is enhanced by 8%, classification accuracy is improved by 33%, computation time is reduced by 19%, computation overhead is decreased by 23%, and classification time is minimized by 13%, as compared to state-of-the-art works. Because the model provided good numerical results, it was then evaluated in terms of XAI perspective by including doctor-model based evaluations such as feedback CAM visualizations, usability, expert surveys, comparisons of CAM with other XAI methods, and manual diagnosis comparison. The results show that the SSLW-CNN provides good performance on brain tumor diagnosis and ensures a trustworthy solution for the doctors.
- [1] . 2020. Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion 58, 82–115.Google ScholarDigital Library
- [2] , (Eds.). 2019. Explainable AI: Interpreting, explaining and visualizing deep learning, Vol. 11700. Springer Nature. Google ScholarDigital Library
- [3] . 2019. Review of deep learning algorithms and architectures. IEEE Access 7 (2019), 53040–53065.Google ScholarCross Ref
- [4] . 2019. Introduction to Deep Learning. The MIT Press. Google ScholarDigital Library
- [5] . 2019. A state-of-the-art survey on deep learning theory and architectures. Electronics 8, 3 (2019), 292.Google ScholarCross Ref
- [6] . 2019. History and future of human-automation interaction. International Journal of Human-Computer Studies 131, 99–107.Google ScholarDigital Library
- [7] . 2020. Future trends in I&M: Human-machine co-creation in the rise of AI. IEEE Instrumentation & Meas. Magazine 23, 2 (2020), 71–73.Google ScholarCross Ref
- [8] . 2018. Peeking inside the black-box: A survey on explainable artificial int. (XAI). IEEE Access 6, 52138–52160.Google ScholarCross Ref
- [9] . 2017. Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296.Google Scholar
- [10] . 2020. Explainable artificial intelligence (xAI) approaches and deep meta-learning models. In Adv. in Deep Learning. IntechOpen.Google ScholarCross Ref
- [11] . 2018. Automatically designing CNN architectures for medical image segmentation. In International Workshop on Machine Learning in Medical Imaging. Springer, Cham, 98–106.Google Scholar
- [12] . 2018. SD-CNN: A shallow-deep CNN for improved breast cancer diagnosis. Computerized Medical Imaging and Graphics 70, 53–62.Google ScholarCross Ref
- [13] . 2017. 3D CNN based automatic diagnosis of attention deficit hyperactivity disorder using functional and structural MRI. IEEE Access 5 (2017), 23626–23636.Google ScholarCross Ref
- [14] . 2020. PROMETEO: A CNN-based computer-aided diagnosis system for WSI prostate cancer detection. IEEE Access 8 (2020), 128613–128628.Google ScholarCross Ref
- [15] . 2020. Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network. Information Fusion 67 (2020), 208–229.Google ScholarCross Ref
- [16] . 2020. COVID-19 classification by CCSHNet with deep fusion using transfer learning and discriminant correlation analysis. Information Fusion 68 (2020), 131–148.Google ScholarCross Ref
- [17] . 2021. Improved breast cancer classification through combining graph convolutional network and convolutional neural network. Information Processing & Management 58, 2 (2021), 102439.Google ScholarCross Ref
- [18] . 2019. Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach. Artificial Intelligence in Medicine 94, 42–53.Google ScholarDigital Library
- [19] . 2020. Explainable AI for medical imaging: Deep-learning CNN ensemble for classification of estrogen receptor status from breast MRI. In Medical Imaging 2020: Computer-Aided Diagnosis, Vol. 11314. International Society for Optics and Photonics, p. 113140Z.Google ScholarCross Ref
- [20] . 2020. Encoding visual attributes in capsules for explainable medical diagnoses. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 294–304.Google ScholarDigital Library
- [21] . 2018. Classification using deep learning neural networks for brain tumors. Future Computing and Informatics Journal 3, 1 (2018), 68–71.Google ScholarCross Ref
- [22] . 2019. Multi-grade brain tumor classification using deep CNN with extensive data augmentation. Journal of Computational Science 30, 174–182.Google ScholarCross Ref
- [23] . 2019. Clinical support system for brain tumor classification using soft computing techniques. Journal of Medical Systems 43, 5 (2019), 144. Google ScholarDigital Library
- [24] . 2018. Deep learning based brain tumor classification and detection system. Turkish Journal of Electrical Engineering & Computer Sciences 26, 5 (2018), 2275–2286.Google ScholarCross Ref
- [25] . 2018. Brain tumor classification using convolutional neural networks. Biomedical & Pharmacology Jour 11, 3 (2018), 1457.Google ScholarCross Ref
- [26] . 2019. Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI. European Radiology 29, 1 (2019), 124–132.Google ScholarCross Ref
- [27] . 2017. Image analysis for MRI based brain tumor detection and feature extraction using biologically inspired BWT and SVM. Hindawi, International Journal of Biomedical Imaging 2017, 1–12.Google ScholarDigital Library
- [28] . 2015. Brain tumor segmentation based on a hybrid clustering technique. Egyptian Informatics Journal 16, 1 (2015), 71–81.Google ScholarCross Ref
- [29] . 2018. Nifty net: A deep-learning platform for medical imaging. Computer Methods and Programs in Biomedicine 158, 113–122.Google ScholarCross Ref
- [30] . 2019. A deep neural network based classifier for brain tumor diagnosis. Applied Soft Computing 82, 105528.Google ScholarDigital Library
- [31] . 2017. Computer aided diagnosis system - A decision support system for clinical diagnosis of brain tumors. International Journal of Computational Intelligence Systems 10, 1 (2017), 104–119.Google ScholarCross Ref
- [32] . 2017. Tumor classification and segmentation of MR brain images. ArXiv preprint arXiv: 1710.11309, 1–20.Google Scholar
- [33] . 2019. An overview of deep learning in medical imaging focusing on MRI. Zeitschrift für Medizinische Physik 29, 2 (2019), 102–127.Google ScholarCross Ref
- [34] . 2018. Automatic semantic segmentation of brain gliomas from MRI images using a deep cascaded neural network. Hindawi, Journal of Healthcare Engineering 2018, 1–14.Google Scholar
- [35] . 2019. Neural network based brain tumor detection using wireless infrared imaging sensor. IEEE Access 7, 5577–5588.Google ScholarCross Ref
- [36] . 2019. Brain tumor segmentation based on hybrid clustering and morphological operations. Hindawi, International Journal of Biomedical Imaging (2019), 1–11.Google Scholar
- [37] . 2018. Identification and classification of brain tumor MRI images with feature extraction using DWT and probabilistic neural network. Springer, Brain Informatics 5, 1 (2018), 23–30.Google ScholarCross Ref
- [38] . 2019. Automated brain tumor segmentation on multi-modal MR image using SegNet. Springer, Computational Visual Media 5, 2 (2019), 209–219.Google ScholarCross Ref
- [39] . 2018. Two-phase multi-model automatic brain tumour diagnosis system from magnetic resonance images using convolutional neural networks. Springer, EURASIP Jour. on Image and Video Processing 1, 97 (2018), 1–10.Google Scholar
- [40] . 2017. Application of deep learning in automated analysis of molecular images in cancer: A survey. Hindawi, Contrast Media & Molecular Imaging 2017, 1–10.Google Scholar
- [41] . 2018. Identification and classification of brain tumor MRI images with feature extraction using DWT and probabilistic neural network. Springer, Brain Informatics 5, 1 (2018), 23–30.Google ScholarCross Ref
- [42] . 2020. An IoT platform for the analysis of brain CT images based on Parzen analysis. Elsevier, Future Generation Computer Systems 105, 135–147.Google ScholarCross Ref
- [43] . 2020. Artificial intelligence techniques empowered edge-cloud architecture for brain CT image analysis. Elsevier, Engineering Applications of Artificial Intelligence 91, 1–13 (2020), 103585.Google ScholarCross Ref
- [44] . 2016. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2921–2929.Google ScholarCross Ref
- [45] . 2019. Class activation maps. Medium Blog, Online: https://medium.com/@GaganaB/class-activation-maps-551477720679 (Retrieved 2 November 2020).Google Scholar
- [46] . 2019. Nutrition labeling schemes and the time and effort of consumer processing. Sustainability 11, 4 (2019), 1079.Google ScholarCross Ref
- [47] . 2016. A comparative study of user experience in online social media branding web pages using eye tracker. In 2016 International Conference on Advances in Human Machine Interaction (HMI). IEEE, 1–8.Google ScholarCross Ref
- [48] . 2020. Areas of interest on destination websites: A generation Y's perspective. In Eye Tracking in Tourism. Springer, Cham, 85–99.Google ScholarCross Ref
- [49] . 2005. Attention when?: An investigation of the ordering effect of input and interaction. Studies in Second Language Acquisition 27, 1 (2005), 1–31.Google ScholarCross Ref
- [50] . 2011. Menu design for computers and cell phones: Review and reappraisal. Intl. Journal of Human–Computer Interaction 27, 4 (2011), 383–404.Google ScholarCross Ref
- [51] . 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision 618–626.Google ScholarCross Ref
- [52] . 2020. Axiom-based grad-cam: Towards accurate visualization and explanation of cnns. arXiv preprint arXiv:2008.02312.Google Scholar
- [53] . 2019. Attention branch network: Learning of attention mechanism for visual explanation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 10705–10714.Google ScholarCross Ref
- [54] . 2017. Residual and plain convolutional neural networks for 3D brain MRI classification. In 2017 IEEE 14th International Symposium on Biomedical Imaging (2017), 835–838.Google ScholarCross Ref
- [55] . 2018. Voxel deconvolutional networks for 3D brain image labeling. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1226–1234. Google ScholarDigital Library
- [56] . 2019. 3D unsupervised modified spatial fuzzy c-means method for segmentation of 3D brain MR image. Pattern Analysis and Applications 22, 4 (2019), 1561–1571.Google ScholarDigital Library
- [57] . 2019. Effective diagnosis of Alzheimer's disease via multimodal fusion analysis framework. Frontiers in Genetics 10, 976.Google ScholarCross Ref
- [58] . 2020. Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation. Information Fusion 64, 149–187.Google ScholarCross Ref
- [59] . 2020. A survey on deep learning for multimodal data fusion. Neural Computation 32, 5 (2020), 829–864.Google ScholarDigital Library
- [60] . 2019. Pathological brain detection based on AlexNet and Transfer Learning. Journal of Computational Science 30, 41–47.Google ScholarCross Ref
- [61] . 2020. Detection of abnormal brain in MRI via improved AlexNet and ELM optimized by chaotic bat algorithm. Neural Computing and Applications 1 (2020), 1–13.Google Scholar
- [62] . 2018. Fully automatic model-based segmentation and classification approach for MRI brain tumor using artificial neural networks. Concurrency and Computation: Practice and Experience 22.Google Scholar
- [63] . 2018. K-Means clustering and neural network for object detecting and identifying abnormality of brain tumor. Soft Computing 23, 9083–9096.Google ScholarDigital Library
- [64] . 2020. Decision-level fusion scheme for nasopharyngeal carcinoma identification using machine learning techniques. Neural Computing and Applications 32, 625–638.Google ScholarDigital Library
- [65] . 2020. U-Net and its variants for medical image segmentation: Theory and applications. Image and Video Processing 1–12.Google Scholar
- [66] . 2021. A new approach for classifying coronavirus COVID-19 based on its manifestation on chest X-rays using texture features and neural networks. Elsevier Public Health Emergency Collection 545, 403–414.Google Scholar
- [67] . 2020. Optimal recognition model based on convolutional neural networks and fuzzy gravitational search algorithm method. 2020. Journal of Automation Mobile Robotics & Intelligent Systems 14, 1 (2020), 109–120.Google Scholar
Index Terms
- Doctor's Dilemma: Evaluating an Explainable Subtractive Spatial Lightweight Convolutional Neural Network for Brain Tumor Diagnosis
Recommendations
Brain tumor classification using deep convolutional autoencoder-based neural network: multi-task approach
AbstractDiagnosis, detection and classification of tumors, in the brain MRI images, are important because misdiagnosis can lead to death. This paper proposes a method that can diagnose brain tumors in the MRI images and classify them into 5 categories ...
Brain Tumor Segmentation with Cascaded Deep Convolutional Neural Network
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain InjuriesAbstractCancer is the second leading cause of death globally and is responsible for an estimated 9.6 million deaths in 2018. Approximately 70% of deaths from cancer occur in low and middle-income countries. One defining feature of cancer is the rapid ...
Dual feature extraction based convolutional neural network classifier for magnetic resonance imaging tumor detection using U-Net and three-dimensional convolutional neural network
Highlights- Gray-Level Co-occurrence matrix and vantage point tree were used which has excellent performance and classifier.
AbstractAnalysis and monitoring of disease development rely heavily on automated segmentation of brain tumors using MRI data. Because gliomas are aggressive and diverse, effective and precise segmentation techniques are utilized to divide ...
Graphical abstractDisplay Omitted
Comments