Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item 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 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 Multilevel Multimodal Framework for Automatic Collateral Scoring in Brain Stroke(Institute of Electrical and Electronics Engineers Inc., 2024) Raj, R.; Dayananda, D.; Gupta, A.; Mathew, J.; Kannath, S.K.; Prakash, A.; Rajan, J.In patients with ischemic brain stroke, collateral circulation plays a crucial role in selecting patients suitable for endovascular therapy. The presence of well-developed collaterals improves the patient's chances of recovery. In clinical practice, the presence of collaterals is diagnosed on a Computed Tomography Angiography scan. The radiologist grades it on the basis of subjective visual assessment, which is prone to interobserver and intraobserver variability. Computer-based methods of collateral assessment face the challenge of non-uniform scan volume, leading to manual selection of slices, meaning that the most imperative slices have to be manually selected by the radiologist. This paper proposes a multilevel multimodal hierarchical framework for automated collateral scoring. Specifically, we propose deploying a Convolutional Neural Network for image selection based on the visibility of collaterals and a multimodal model for comparing the occluded and contralateral sides of the brain for collateral scoring. We also generate a patient-level prediction by integrating automated machine learning in the proposed framework. While the proposed multimodal predictor contributes to Artificial Intelligence, the proposed end-to-end framework is an application in engineering. The proposed framework has been trained and tested on 116 patients, with five-fold cross-validation, achieving an accuracy of 91.17% for multi-class collateral scores and 94.118% for binary class collateral scores. The proposed multimodal predictor achieved a weighted F1 score of 0.86 and 0.95 on multi-class and binary-class collateral scores, respectively. The proposed framework is fast, efficient, and scalable for real-world deployments. Automated evaluation of collaterals with attention maps for explainability would complement radiologists' efforts. Code for the proposed framework is available at: https://github.com/rishiraj-cs/collaterals_ML_MM. © 2013 IEEE.