Developing a Novel Methodology by Integrating Deep Learning and HMM for Segmentation of Retinal Blood Vessels in Fundus Images.

Accurate segregation of retinal blood vessels network plays a crucial role in clinical assessments, treatments, and rehabilitation process. Owing to the presence of acquisition and instrumentation anomalies, precise tracking of vessels network is challenging. For this, a new fundus image segmentation framework is proposed by combining deep neural networks, and hidden Markov model. It has three main modules: the Atrous spatial pyramid pooling-based encoder, the decoder, and hidden Markov model vessel tracker. The encoder utilized modified ResNet18 deep neural networks model for low-and-high-levels features extraction. These features are concatenated in module-II by the decoder to perform convolution operations to obtain the initial segmentation. Previous modules detected the main vessel structure and overlooked some small capillaries. For improved segmentation, hidden Markov model vessel tracker is integrated with module-I and-II to detect overlooked small capillaries of the vessels network. In last module, final segmentation is obtained by combining multi-oriented sub-images using logical OR operation. This novel framework is validated experimentally using two standard DRIVE and STARE datasets. The developed model offers high average values of accuracy, area under the curve, and sensitivity of 99.8, 99.0, and 98.2%, respectively. Analysis of the results revealed that the developed approach offered enhanced performance in terms of sensitivity 18%, accuracy 3%, and specificity 1% over the state-of-the-art approaches. Owing to better learning and generalization capability, the developed approach tracked blood vessels network efficiently and automatically compared to other approaches. The proposed approach can be helpful for human eye assessment, disease diagnosis, and rehabilitation process.

Development of multivariate classification models for the diagnosis of dengue virus infection.

The dengue virus (DENV) infection is a worldwide cause of serious illness and death. Early and efficient prediction of disease may help in proper medical management to control disease. Keeping this in view, multivariate classification models by combining with Raman spectroscopy have been developed for the diagnosis of DENV infection in human blood sera. For study design, a statistical analysis is performed to select the sample size for training of models. Total 1240 Raman spectra have been acquired from 39 DENV infected and 23 healthy sera samples. Prior to model development, Raman spectra were examined using ANOVA test for significant differences present in the intensities of newly appeared Raman bands at 622, 645, 700, 746, 800, 814, 873, 890, 948, 1002, 1018, 1080, 1235, 1250, 1272, 1386, 1404, 1446, 1609 and 1645 cm-1. The significant differences and characteristic patterns of Raman bands induced by disease played decisive role and are exploited for development of multivariate model. Classification models are developed by utilizing principal component analysis (PCA) to extract discriminant features from multidimensional Raman spectral dataset and followed by support vector machines (SVM) with Polynomial of 5, RBF, and liner kernels. The proposed model for this study is built using 10-fold cross validation technique and evaluated on independent dataset to demonstrate its robustness. PCA-SVM (poly-5) model successfully yielded high diagnostic accuracy of 99.52%, sensitivity of 99.75%, specificity of 99.09% for classification of unknown suspected samples. For comparison, PCA discriminant analysis (PCA-DA), partial least squares regression (PLSR) are PLS-DA have been compared. It is found that PCA-SVM (poly-5) approach is more effective and robust compared to other state-of-the-art approaches and it can be used for clinical prediction of DENV infection in human blood sera.

Developing intelligent medical image modality classification system using deep transfer learning and LDA.

Rapid advancement in imaging technology generates an enormous amount of heterogeneous medical data for disease diagnosis and rehabilitation process. Radiologists may require related clinical cases from medical archives for analysis and disease diagnosis. It is challenging to retrieve the associated clinical cases automatically, efficiently and accurately from the substantial medical image archive due to diversity in diseases and imaging modalities. We proposed an efficient and accurate approach for medical image modality classification that can used for retrieval of clinical cases from large medical repositories. The proposed approach is developed using transfer learning concept with pre-trained ResNet50 Deep learning model for optimized features extraction followed by linear discriminant analysis classification (TLRN-LDA). Extensive experiments are performed on challenging standard benchmark ImageCLEF-2012 dataset of 31 classes. The developed approach yields improved average classification accuracy of 87.91%, which is higher up-to 10% compared to the state-of-the-art approaches on the same dataset. Moreover, hand-crafted features are extracted for comparison. Performance of TLRN-LDA system demonstrates the effectiveness over state-of-the-art systems. The developed approach may be deployed to diagnostic centers to assist the practitioners for accurate and efficient clinical case retrieval and disease diagnosis.