Image fusion can be performed on images either in spatial domain or frequency domain methods. Frequency domain methods will be most preferred because these methods can improve the quality of edges in an image. In image fusion, the resultant fused images will be more informative than individual input images, thus more suitable for classification problems. Artificial intelligence (AI) algorithms play a significant role in improving patient's treatment in the health care industry and thus improving personalized medicine. This research work analyses the role of image fusion in an improved brain tumour classification model, and this novel fusion-based cancer classification model can be used for personalized medicine more effectively. Image fusion can improve the quality of resultant images and thus improve the result of classifiers. Instead of using individual input images, the high-quality fused images will provide better classification results. Initially, the contrast limited adaptive histogram equalization technique preprocess input images such as MRI and SPECT images. Benign and malignant class brain tumor images are applied with discrete cosine transform-based fusion method to obtain fused images. AI algorithms such as support vector machine classifier, KNN classifier, and decision tree classifiers are tested with features obtained from fused images and compared with the result obtained from individual input images. Performances of classifiers are measured using the parameters accuracy, precision, recall, specificity, and F1 score. SVM classifier provided the maximum accuracy of 96.8%, precision of 95%, recall of 94%, specificity of 93%, F1 score of 91%, and performed better than KNN and decision tree classifiers when extracted features from fused images are used. The proposed method results are compared with existing methods and provide satisfactory results.

Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine

Automated detection of glaucoma using optical coherence tomography angiogram images

Diabetic retinopathy (DR) is one of the severe eye conditions due to diabetes complication which can lead to vision loss if left untreated. In this paper, a computationally simple, yet very effective, DR detection method is proposed. First, a segmentation independent two-stage preprocessing based technique is proposed which can effectively extract DR pathognomonic signs; both bright and red lesions, and blood vessels from the eye fundus image. Then, the performance of Local Binary Patterns (LBP), Local Ternary Patterns (LTP), Dense Scale-Invariant Feature Transform (DSIFT) and Histogram of Oriented Gradients (HOG) as a feature descriptor for fundus images, is thoroughly analyzed. SVM kernel-based classifiers are trained and tested, using a 5-fold cross-validation scheme, on both newly acquired fundus image database from the local hospital and combined database created from the open-sourced available databases. The classification accuracy of 96.6% with 0.964 sensitivity and 0.969 specificity is achieved using a Cubic SVM classifier with LBP and LTP fused features for the local database. More importantly, in out-of-sample testing on the combined database, the model gives an accuracy of 95.21% with a sensitivity of 0.970 and specificity of 0.932. This indicates the proposed model is very well-fitted and generalized which is further corroborated by the presented train-test curves.

Automated detection of diabetic retinopathy in fundus images using fused features

The use of biometrics provides a more reliable security layer in identification and user authentication in many fields of commercial and institutional transactions. Vascular vein patterns from the hand have recently been explored as another approach to the biometric modality because these innate patterns are constant, remains distinct lifelong; relatively stable, cannot be forged, tampered nor copied. This study proposes the use of a rotation invariant algorithm like ORB for a bimodal approach in the vein recognition from the palm and dorsal vein patterns of the hand. Using near-infrared LEDs, Raspberry Pi with NOIR camera module, a portable, real time hand vein pattern recognition device was developed. Image pre-processing, feature extraction, feature matching, database of user information and GUI are implemented in Raspberry Pi, Python and OpenCV Libraries. ORB was used for generating feature descriptors and BruteForce Matcher for feature matching. Match scores generated by the classifier from dorsal and palm vein were combined using sum-rule in score level fusion to generate the final recognition results. After experimental tests conducted, system performance resulted to 95.00% accuracy level and overall response time of 2. 76secs. The developed architecture can be integrated with other systems like attendance monitoring, access control, identity authentication for financial transactions, forensic investigation, and fraud detection.

A Rotation Invariant Algorithm for Bimodal Hand Vein Recognition System

In preoperative imaging, the demarcation of rectal cancer with magnetic resonance images provides an important basis for cancer staging and treatment planning. Recently, deep learning has greatly improved the state-of-the-art method in automatic segmentation. However, limitations in data availability in the medical field can cause large variance and consequent overfitting to medical image segmentation networks. In this study, we propose methods to reduce the model variance of a rectal cancer segmentation network by adding a rectum segmentation task and performing data augmentation; the geometric correlation between the rectum and rectal cancer motivated the former approach. Moreover, we propose a method to perform a bias-variance analysis within an arbitrary region-of-interest (ROI) of a segmentation network, which we applied to assess the efficacy of our approaches in reducing model variance. As a result, adding a rectum segmentation task reduced the model variance of the rectal cancer segmentation network within tumor regions by a factor of 0.90; data augmentation further reduced the variance by a factor of 0.89. These approaches also reduced the training duration by a factor of 0.96 and a further factor of 0.78, respectively. Our approaches will improve the quality of rectal cancer staging by increasing the accuracy of its automatic demarcation and by providing rectum boundary information since rectal cancer staging requires the demarcation of both rectum and rectal cancer. Besides such clinical benefits, our method also enables segmentation networks to be assessed with bias-variance analysis within an arbitrary ROI, such as a cancerous region.

/pdf/reducing-the-model-variance-of-a-rectal-cancer-segmentation-49azu3gidv.pdf

Reducing the Model Variance of a Rectal Cancer Segmentation Network

Medical image processing is a challenging field of research since the captured images suffers from the noise and poor contrast. The efficiency of the medical image processing depends on the quality of the captured medical images. Major factors for the low contrast medical images are age of capturing equipments, poor illumination conditions and inexperience of medical staff. Thus, contrast enhancement methods are used for improving the contrast of medical images before being used. In this paper an combination of the contrast limited adaptive histogram equalization (CLAHE) method and the wavelet based Fusion techniques are used for designing the efficient medical image enhancement method. Method is capable of adapting the Fusion rules adaptively for best enhancement results. First CLAHE image enhancement is used for improving the contrast of the medical images. then in second stage 2D Discrete wavelet transformation based adaptive image fusion is used for fusing the original and CLAHE output images. For testing the performance SNR and entropy are calculated and used as parameters. It is found that based on adaptive Fusion the visual content of the medical images are efficiently improved under all kind of capturing environments.

/pdf/efficient-medical-image-enhancement-using-clahe-enhancement-1iszx4y7dr.pdf

Shailendra Patel

Papers

Efficient Medical Image Enhancement using CLAHE Enhancement and Wavelet Fusion