Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
12 results
Search Results
Item Speckle reduction in medical ultrasound images using an unbiased non-local means method(Elsevier Ltd, 2016) Sudeep, P.V.; Ponnusamy, P.; Rajan, J.; Baradaran, H.; Saba, L.; Gupta, A.; Suri, J.S.Enhancement of ultrasound (US) images is required for proper visual inspection and further pre-processing since US images are generally corrupted with speckle. In this paper, a new approach based on non-local means (NLM) method is proposed to remove the speckle noise in the US images. Since the interpolated final Cartesian image produced from uncompressed ultrasound data contaminated with fully developed speckle can be represented by a Gamma distribution, a Gamma model is incorporated in the proposed denoising procedure. In addition, the scale and shape parameters of the Gamma distribution are estimated using the maximum likelihood (ML) method. Bias due to speckle noise is expressed using these parameters and is removed from the NLM filtered output. The experiments on phantom images and real 2D ultrasound datasets show that the proposed method outperforms other related well-accepted methods, both in terms of objective and subjective evaluations. The results demonstrate that the proposed method has a better performance in both speckle reduction and preservation of structural features. © 2016 Elsevier Ltd. All rights reserved.Item GPU implementation of non-local maximum likelihood estimation method for denoising magnetic resonance images(Springer Verlag service@springer.de, 2017) Upadhya, A.H.K.; Talawar, B.; Rajan, J.Magnetic resonance imaging (MRI) is a widely deployed medical imaging technique used for various applications such as neuroimaging, cardiovascular imaging and musculoskeletal imaging. However, MR images degrade in quality due to noise. The magnitude MRI data in the presence of noise generally follows a Rician distribution if acquired with single-coil systems. Several methods are proposed in the literature for denoising MR images corrupted with Rician noise. Amongst the methods proposed in literature for denoising MR images corrupted with Rician noise, the non-local maximum likelihood methods (NLML) and its variants are popular. In spite of the performance and denoising quality, NLML algorithm suffers from a tremendous time complexity O(m3N3) , where m3 and N3 represent the search window and image size, respectively, for a 3D image. This makes the algorithm challenging for deployment in the real-time applications where fast and prompt results are required. A viable solution to this shortcoming would be the application of a data parallel processing framework such as Nvidia CUDA so as to utilize the mutually exclusive and computationally intensive calculations to our advantage. The GPU-based implementation of NLML-based image denoising achieves significant speedup compared to the serial implementation. This research paper describes the first successful attempt to implement a GPU-accelerated version of the NLML algorithm. The main focus of the research was on the parallelization and acceleration of one computationally intensive section of the algorithm so as to demonstrate the execution time improvement through the application of parallel processing concepts on a GPU. Our results suggest the possibility of practical deployment of NLML and its variants for MRI denoising. © 2016, Springer-Verlag Berlin Heidelberg.Item A cascaded convolutional neural network architecture for despeckling OCT images(Elsevier Ltd, 2021) Anoop, B.N.; Kalmady, K.S.; Udathu, A.; Siddharth, V.; Girish, G.N.; Kothari, A.R.; Rajan, J.Optical Coherence Tomography (OCT) is an imaging technique widely used for medical imaging. Noise in an OCT image generally degrades its quality, thereby obscuring clinical features and making the automated segmentation task suboptimal. Obtaining higher quality images requires sophisticated equipment and technology, available only in selected research settings, and is expensive to acquire. Developing effective denoising methods to improve the quality of the images acquired on systems currently in use has potential for vastly improving image quality and automated quantitative analysis. Noise characteristics in images acquired from machines of different makes and models may vary. Our experiments show that any single state-of-the-art method for noise reduction fails to perform equally well on images from various sources. Therefore, detailed analysis is required to determine the exact noise type in images acquired using different OCT machines. In this work we studied noise characteristics in the publicly available DUKE and OPTIMA datasets to build a more efficient model for noise reduction. These datasets have OCT images acquired using machines of different manufacturers. We further propose a patch-wise training methodology to build a system to effectively denoise OCT images. We have performed an extensive range of experiments to show that the proposed method performs superior to other state-of-the-art-methods. © 2021 Elsevier LtdItem Crossover based technique for data augmentation(Elsevier Ireland Ltd, 2022) Raj, R.; Mathew, J.; Kannath, S.K.; Rajan, J.Background and Objective: Medical image classification problems are frequently constrained by the availability of datasets. “Data augmentation” has come as a data enhancement and data enrichment solution to the challenge of limited data. Traditionally data augmentation techniques are based on linear and label preserving transformations; however, recent works have demonstrated that even non-linear, non-label preserving techniques can be unexpectedly effective. This paper proposes a non-linear data augmentation technique for the medical domain and explores its results. Methods: This paper introduces “Crossover technique”, a new data augmentation technique for Convolutional Neural Networks in Medical Image Classification problems. Our technique synthesizes a pair of samples by applying two-point crossover on the already available training dataset. By this technique, we create N new samples from N training samples. The proposed crossover based data augmentation technique, although non-label preserving, has performed significantly better in terms of increased accuracy and reduced loss for all the tested datasets over varied architectures. Results: The proposed method was tested on three publicly available medical datasets with various network architectures. For the mini-MIAS database of mammograms, our method improved the accuracy by 1.47%, achieving 80.15% using VGG-16 architecture. Our method works fine for both gray-scale as well as RGB images, as on the PH2 database for Skin Cancer, it improved the accuracy by 3.57%, achieving 85.71% using VGG-19 architecture. In addition, our technique improved accuracy on the brain tumor dataset by 0.40%, achieving 97.97% using VGG-16 architecture. Conclusion: The proposed novel crossover technique for training the Convolutional Neural Network (CNN) is painless to implement by applying two-point crossover on two images to form new images. The method would go a long way in tackling the challenges of limited datasets and problems of class imbalances in medical image analysis. Our code is available at https://github.com/rishiraj-cs/Crossover-augmentation © 2022Item Deep learning-based automated mitosis detection in histopathology images for breast cancer grading(John Wiley and Sons Inc, 2022) Mathew, T.; Ajith, B.; Kini, J.; Rajan, J.Cancer grade is an indicator of the aggressiveness of cancer. It is used for prognosis and treatment decisions. Conventionally cancer grading is performed manually by experienced pathologists via microscopic examination of pathology slides. Among the three factors involved in breast cancer grading (mitosis count, nuclear atypia, and tubule formation), mitotic cell counting is the most challenging task for pathologists. It is possible to automate this task by applying computational algorithms on pathology slides images. Lack of sufficiently large datasets and class imbalance between mitotic and non-mitotic cells in slide images are the two major challenges in developing effective deep learning-based methods for mitosis detection. In this paper, we propose a new approach and a method based on that to address these challenges. The high training data requirement of the advanced deep neural network is met by combining two datasets from different sources after a color-normalization process. Class imbalance is addressed by the augmentation of the mitotic samples in a context-preserving manner. Finally, a customized convolutional neural network classifier is used to classify the candidate cells into the target classes. We have used the publicly available datasets MITOS-ATYPIA and MITOS for the experiments. Our method outperforms most of the recent methods that are based on independent datasets and at the same time offers adaptability to the combination of datasets from different sources. © 2022 Wiley Periodicals LLC.Item A novel deep classifier framework for automated molecular subtyping of breast carcinoma using immunohistochemistry image analysis(Elsevier Ltd, 2022) Mathew, T.; Niyas, S.; Johnpaul, C.I.; Kini, J.; Rajan, J.Breast carcinoma has various subtypes based on the genetic factors involved in the pathogenesis of the malignancy. Identifying the exact subtype and providing targeted treatment to the patient can improve the survival chances. Molecular subtyping through immunohistochemistry analysis is a pathology procedure to determine the subtype of breast cancer. The existing manual procedure is tedious and involves assessing the status of the four vital molecular biomarkers present in the tumor tissues. In this paper, a deep learning-based framework for automated molecular subtyping of breast cancer is proposed. Digital slide images of the four biomarkers are separately processed by the proposed framework. In the preprocessing stage, the non-informative background regions from the images are separated. The patches extracted from the foreground regions are classified into target classes using convolutional neural network models trained for this purpose. Classification results are post-processed to predict the status of all the four biomarkers. The predictions for the individual biomarkers are finally consolidated as per clinical guidelines to determine the subtype of the cancer. The proposed system is evaluated for the performance of individual biomarker status prediction and patient-level subtype classification.For patient-level evaluation of biomarkers ER, PR, K67, and HER2, the proposed method gives F1 Scores 1.00, 1.00, 0.90, and 0.94 respectively, whereas for molecular subtyping an F1 score of 0.89 is obtained. In both these aspects, the proposed framework has given significant results that show the effectiveness of our approach. © 2022 Elsevier LtdItem Automated Molecular Subtyping of Breast Carcinoma Using Deep Learning Techniques(Institute of Electrical and Electronics Engineers Inc., 2023) Niyas, S.; Bygari, R.; Naik, R.; Viswanath, B.; Ugwekar, D.; Mathew, T.; Kavya, J.; Kini, J.R.; Rajan, J.Objective: Molecular subtyping is an important procedure for prognosis and targeted therapy of breast carcinoma, the most common type of malignancy affecting women. Immunohistochemistry (IHC) analysis is the widely accepted method for molecular subtyping. It involves the assessment of the four molecular biomarkers namely estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and antigen Ki67 using appropriate antibody reagents. Conventionally, these biomarkers are assessed manually by a pathologist, who finally combines individual results to identify the molecular subtype. Molecular subtyping necessitates the status of all the four biomarkers together, and to the best of our knowledge, no such automated method exists. This paper proposes a novel deep learning framework for automatic molecular subtyping of breast cancer from IHC images. Methods and procedures: A modified LadderNet architecture is proposed to segment the immunopositive elements from ER, PR, HER2, and Ki67 biomarker slides. This architecture uses long skip connections to pass encoder feature space from different semantic levels to the decoder layers, allowing concurrent learning with multi-scale features. The entire architecture is an ensemble of multiple fully convolutional neural networks, and learning pathways are chosen adaptively based on input data. The segmentation stage is followed by a post-processing stage to quantify the extent of immunopositive elements to predict the final status for each biomarker. Results: The performance of segmentation models for each IHC biomarker is evaluated qualitatively and quantitatively. Furthermore, the biomarker prediction results are also evaluated. The results obtained by our method are highly in concordance with manual assessment by pathologists. Clinical impact: Accurate automated molecular subtyping can speed up this pathology procedure, reduce pathologists' workload and associated costs, and facilitate targeted treatment to obtain better outcomes. © 2013 IEEE.Item A Deep Ensemble Learning-Based CNN Architecture for Multiclass Retinal Fluid Segmentation in OCT Images(Institute of Electrical and Electronics Engineers Inc., 2023) Rahil, M.; Anoop, B.N.; Girish, G.N.; Kothari, A.R.; Koolagudi, S.G.; Rajan, J.Retinal Fluids (fluid collections) develop because of the accumulation of fluid in the retina, which may be caused by several retinal disorders, and can lead to loss of vision. Optical coherence tomography (OCT) provides non-invasive cross-sectional images of the retina and enables the visualization of different retinal abnormalities. The identification and segmentation of retinal cysts from OCT scans is gaining immense attention since the manual analysis of OCT data is time consuming and requires an experienced ophthalmologist. Identification and categorization of the retinal cysts aids in establishing the pathophysiology of various retinal diseases, such as macular edema, diabetic macular edema, and age-related macular degeneration. Hence, an automatic algorithm for the segmentation and detection of retinal cysts would be of great value to the ophthalmologists. In this study, we have proposed a convolutional neural network-based deep ensemble architecture that can segment the three different types of retinal cysts from the retinal OCT images. The quantitative and qualitative performance of the model was evaluated using the publicly available RETOUCH challenge dataset. The proposed model outperformed the state-of-the-art methods, with an overall improvement of 1.8%. © 2013 IEEE.Item StrokeViT with AutoML for brain stroke classification(Elsevier Ltd, 2023) Raj, R.; Mathew, J.; Kannath, S.K.; Rajan, J.Stroke, categorized under cardiovascular and circulatory diseases, is considered the second foremost cause of death worldwide, causing approximately 11% of deaths annually. Stroke diagnosis using a Computed Tomography (CT) scan is considered ideal for identifying whether the stroke is hemorrhagic or ischemic. However, most methods for stroke classification are based on a single slice-level prediction mechanism, meaning that the most imperative CT slice has to be manually selected by the radiologist from the original CT volume. This paper proposes an integration of Convolutional Neural Network (CNN), Vision Transformers (ViT), and AutoML to obtain slice-level predictions as well as patient-wise prediction results. While the CNN with inductive bias captures local features, the transformer captures long-range dependencies between sequences. This collaborative local-global feature extractor improves upon the slice-wise predictions of the CT volume. We propose stroke-specific feature extraction from each slice-wise prediction to obtain the patient-wise prediction using AutoML. While the slice-wise predictions helps the radiologist to verify close and corner cases, the patient-wise predictions makes the outcome clinically relevant and closer to real-world scenario. The proposed architecture has achieved an accuracy of 87% for single slice-level prediction and an accuracy of 92% for patient-wise prediction. For comparative analysis of slice-level predictions, standalone architectures of VGG-16, VGG-19, ResNet50, and ViT were considered. The proposed architecture has outperformed the standalone architectures by 9% in terms of accuracy. For patient-wise predictions, AutoML considers 13 different ML algorithms, of which 3 achieve an accuracy of more than 90%. The proposed architecture helps in reducing the manual effort by the radiologist to manually select the most imperative CT from the original CT volume and shows improvement over other standalone architectures for classification tasks. The proposed architecture can be generalized for volumetric scans aiding in the patient diagnosis of head and neck, lungs, diseases of hepatobiliary tract, genitourinary diseases, women's imaging including breast cancer and various musculoskeletal diseases. Code for proposed stroke-specific feature extraction with the pre-trained weights of the trained model is available at: https://github.com/rishiraj-cs/StrokeViT_With_AutoML. © 2022 Elsevier LtdItem A deep learning based classifier framework for automated nuclear atypia scoring of breast carcinoma(Elsevier Ltd, 2023) Mathew, T.; Johnpaul, C.I.; Ajith, B.; Kini, J.R.; Rajan, J.Nuclear atypia scoring is an essential procedure in the grading of breast carcinoma. Manual procedure of nuclear atypia scoring is error-prone, and marked by pathologists’ disagreement and low reproducibility. Automated methods are actively attempted by researchers to solve the problems of manual scoring. In this work, we propose a novel deep learning-based framework for automated nuclear atypia scoring of breast cancer from histopathology slide images. The framework consists of three major phases namely preprocessing, deep learning, and postprocessing. The original three-class problem of atypia scoring at slide level is not suitable for direct application of deep learning algorithms. This is due to the large dimensions and structural complexity of slide images, compounded by the small sample size of the available dataset. Redesign of this problem into a six-class nuclei classification problem through a set of preprocessing steps to facilitate effective use of deep learning algorithms, and the flexibility of the proposed three-phase framework to use different algorithms in each phase are the novel aspects of the proposed work. We used the publicly available slide image dataset MITOS-ATYPIA that contains 600 slide images of high spatial dimension for the experiments. A five-fold cross validation with the train-test sample ratio 80:20 in each fold is used for the performance evaluation. The performance of the method based on this framework exceeds the state-of-the-art with the results 0.8766, 0.8760, and 0.8745 for the metrics precision, recall, and F1 score respectively. © 2023 Elsevier Ltd