Deep learning for liver tumour classification: enhanced loss function

Background and Aim: deep learning has not been successfully implemented in liver tumour feature extraction and classification using computer-aided diagnosis. This study aims to enhance classification accuracy and improves the processing time to better differentiate tumour types. Methodology: This study proposed a hybrid model, which combines the regularization function with the current loss function for the support vector machine (SVM) classifier. Regularization function is used for prioritizing image classes before feeding it to the linear mapping. The proposed model consists of the region growing algorithm to get the region-of-interest (ROI), and Weiner filtering algorithm for image enhancement and noise removal. The gray level co-occurrence matrix (GLCM) was performed to extract the feature from the image. The extracted feature then fed to SVM classifier using selected feature vectors to classify the affected region and neglecting the unwanted areas. Results: classification accuracy was calculated using probability score, and the processing time was calculated based on the total execution time. The proposed system was able to achieve an average classification accuracy of 98.9%, which is about 2–3% higher than the current system. The results showed that 12 ms reduced the processing time on average. Conclusion: The proposed system focused on improving feature extraction and classification for different types of tumours from the MRI images. The study solved the problem in linear mapping of support vector machine and enhanced the classification accuracy and the processing time of early diagnosis of three different types of tumours in liver MRI images.

[1]  Ehsan Golkar,et al.  An automated liver tumour segmentation from abdominal CT scans for hepatic surgical planning , 2018, International Journal of Computer Assisted Radiology and Surgery.

[2]  Kostas Marias,et al.  Extending 2-D Convolutional Neural Networks to 3-D for Advancing Deep Learning Cancer Classification With Application to MRI Liver Tumor Differentiation , 2019, IEEE Journal of Biomedical and Health Informatics.

[3]  Mingjie Sun,et al.  Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning , 2019, Pattern Recognit..

[4]  Seyed-Ahmad Ahmadi,et al.  Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields , 2016, MICCAI.

[5]  Aboul Ella Hassanien,et al.  Automatic computer aided segmentation for liver and hepatic lesions using hybrid segmentations techniques , 2013, 2013 Federated Conference on Computer Science and Information Systems.

[6]  Yu-Chen Chen,et al.  A Deep Learning-Based Radiomics Model for Differentiating Benign and Malignant Renal Tumors1 , 2018, Translational oncology.

[7]  Dhanasekaran Raghavan,et al.  Combining tissue segmentation and neural network for brain tumor detection , 2015, Int. Arab J. Inf. Technol..

[8]  Jong Chul Ye,et al.  Mumford–Shah Loss Functional for Image Segmentation With Deep Learning , 2019, IEEE Transactions on Image Processing.

[9]  Fucang Jia,et al.  Automatic Segmentation of Liver Tumor in CT Images with Deep Convolutional Neural Networks , 2015 .

[10]  Chi-Wing Fu,et al.  H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes , 2018, IEEE Transactions on Medical Imaging.

[11]  S. Saravanan,et al.  An Enhancement of Deep Learning Algorithm for Brain Tumor Segmentation Using Kernel Based CNN with M-SVM , 2019, Journal of Medical Systems.

[12]  D. Maintz,et al.  Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI , 2018, European Radiology.

[13]  Huiyan Jiang,et al.  AHCNet: An Application of Attention Mechanism and Hybrid Connection for Liver Tumor Segmentation in CT Volumes , 2019, IEEE Access.

[14]  U. Rajendra Acharya,et al.  Automated diagnosis of focal liver lesions using bidirectional empirical mode decomposition features , 2018, Comput. Biol. Medicine.

[15]  U. Rajendra Acharya,et al.  Deep learning based liver cancer detection using watershed transform and Gaussian mixture model techniques , 2019, Cognitive Systems Research.

[16]  Sébastien Ourselin,et al.  Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning , 2017, IEEE Transactions on Medical Imaging.

[17]  Lu Meng,et al.  Liver tumor segmentation based on 3D convolutional neural network with dual scale , 2019, Journal of applied clinical medical physics.

[18]  Holger Roth,et al.  Unsupervised segmentation of 3D medical images based on clustering and deep representation learning , 2018, Medical Imaging.

[19]  Ian D. Reid,et al.  SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Yading Yuan,et al.  Hierarchical Convolutional-Deconvolutional Neural Networks for Automatic Liver and Tumor Segmentation , 2017, ArXiv.

[21]  Yen-Wei Chen,et al.  Tensor-based sparse representations of multi-phase medical images for classification of focal liver lesions , 2020, Pattern Recognit. Lett..

[22]  Robertas Damasevicius,et al.  A neuro-heuristic approach for recognition of lung diseases from X-ray images , 2019, Expert Syst. Appl..

[23]  Gianpaolo Francesco Trotta,et al.  Computer-assisted frameworks for classification of liver, breast and blood neoplasias via neural networks: A survey based on medical images , 2019, Neurocomputing.

[24]  N. Santhiyakumari,et al.  An Enhancement of Computer Aided Approach for Colon Cancer Detection in WCE Images Using ROI Based Color Histogram and SVM2 , 2019, Journal of Medical Systems.

[25]  X. Qi,et al.  Digital and intelligent liver surgery in the new era: Prospects and dilemmas , 2019, EBioMedicine.

[26]  Daguang Xu,et al.  Automatic Liver Segmentation Using an Adversarial Image-to-Image Network , 2017, MICCAI.

[27]  David Dagan Feng,et al.  Automatic Liver Lesion Detection using Cascaded Deep Residual Networks , 2017, ArXiv.

[28]  Yang Hu,et al.  Dual‐modality endoscopic probe for tissue surface shape reconstruction and hyperspectral imaging enabled by deep neural networks , 2018, Medical Image Anal..

[29]  Sohrab Rohani,et al.  Image Analysis for In-line Measurement of Multidimensional Size, Shape, and Polymorphic Transformation of l-Glutamic Acid Using Deep Learning-Based Image Segmentation and Classification , 2018, Crystal Growth & Design.

[30]  Hans Meine,et al.  Neural Network-Based Automatic Liver Tumor Segmentation With Random Forest-Based Candidate Filtering , 2017, ArXiv.

[31]  Min-Ying Su,et al.  Differentiation of spinal metastases originated from lung and other cancers using radiomics and deep learning based on DCE-MRI. , 2019, Magnetic resonance imaging.

[32]  Abeer Alsadoon,et al.  A novel enhanced softmax loss function for brain tumour detection using deep learning , 2019, Journal of Neuroscience Methods.