Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Machine learning-based detection and classification of lung cancer(Elsevier, 2022) Dodia, S.; Annappa, A.Cancer is termed to be one of the life-threatening diseases in the world. Among various types of cancer, the highest mortality and morbidity rate recorded is from lung cancer. Computer-aided diagnosis (CAD) systems are used to identify lung cancer nodules. The development of reliable automated algorithms is important to provide doctors with a second opinion. A lung cancer diagnosis is performed in two steps: lung cancer nodule detection and classification. In nodule detection, from a given computed tomography (CT) scan, the nodules and nonnodules are identified. Once the nodules and nonnodules are identified, the next step is to classify the detected nodules as cancerous and noncancerous. This work explores various machine learning classifiers for lung cancer classification. A majority voting scheme is used to classify nodules. An in-depth analysis of different machine learning algorithms’ performance is presented in this work. © 2023 Elsevier Inc. All rights reserved.Item A Novel Artificial Intelligence-Based Lung Nodule Segmentation and Classification System on CT Scans(Springer Science and Business Media Deutschland GmbH, 2022) Dodia, S.; Annappa, A.; Mahesh, M.A.Major innovations in deep neural networks have helped optimize the functionality of tasks such as detection, classification, segmentation, etc., in medical imaging. Although Computer-Aided Diagnosis (CAD) systems created using classic deep architectures have significantly improved performance, the pipeline operation remains unclear. In this work, in comparison to the state-of-the-art deep learning architectures, we developed a novel pipeline for performing lung nodule detection and classification, resulting in fewer parameters, better analysis, and improved performance. Histogram equalization, an image enhancement technique, is used as an initial preprocessing step to improve the contrast of the lung CT scans. A novel Elagha initialization-based Fuzzy C-Means clustering (EFCM) is introduced in this work to perform nodule segmentation from the preprocessed CT scan. Following this, Convolutional Neural Network (CNN) is used for feature extraction to perform nodule classification instead of customary classification. Another set of features considered in this work is Bag-of-Visual-Words (BoVW). These features are encoded representations of the detected nodule images. This work also examines a blend of intermediate features extracted from CNN and BoVW characteristics, which resulted in higher performance than individual feature representation. A Support Vector Machine (SVM) is used to distinguish detected nodules into benign and malignant nodules. Achieved results clearly show improvement in the nodule detection and classification task performance compared to the state-of-the-art architectures. The model is evaluated on the popular publicly available LUNA16 dataset and verified by an expert pulmonologist. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item A Novel Bi-level Lung Cancer Classification System on CT Scans(Springer Science and Business Media Deutschland GmbH, 2022) Dodia, S.; Annappa, A.; Mahesh, M.A.Purpose: Lung cancer is a life-threatening disease that affects both men and women. Accurate identification of lung cancer has been a challenging task for decades. The aim of this work is to perform a bi-level classification of lung cancer nodules. In Level-1, candidates are classified into nodules and non-nodules, and in Level-2, the detected nodules are further classified into benign and malignant. Methods: A new preprocessing method, named, Boosted Bilateral Histogram Equalization (BBHE) is applied to the input scans prior to feeding the input to the neural networks. A novel Cauchy Black Widow Optimization-based Convolutional Neural Network (CBWO-CNN) is introduced for Level-1 classification. The weight updation in the CBWO-CNN is performed using Cauchy mutation, and the error rate is minimized, which in turn improved the accuracy with less computation time. A novel hybrid Convolutional Neural Network (CNN) model with shared parameters is introduced for performing Level-2 classification. The second model proposed in this work is a fusion of Squeeze-and-Excitation Network (SE-Net) and Xception, abbreviated as “SE-Xception†. The weight parameters are shared for the SE-Xception model trained from CBWO-CNN, i.e., a knowledge transfer approach is adapted. Results: The recognition accuracy obtained from CBWO-CNN for Level-1 classification is 96.37% with a reduced False Positive Rate (FPR) of 0.033. SE-Xception model achieved a sensitivity of 96.14%, an accuracy of 94.75%, and a specificity of 92.83%, respectively, for Level-2 classification. Conclusion: The proposed method’s performance is better than existing deep learning architectures and outperformed individual SE-Net and Xception with fewer parameters. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Development of Robust CNN Architecture for Grading and Classification of Renal Cell Carcinoma Histology Images(Institute of Electrical and Electronics Engineers Inc., 2025) Chanchal, C.A.; Lal, S.; Suresh, S.Kidney cancer is a commonly diagnosed cancer disease in recent years, and Renal Cell Carcinoma (RCC) is the most common kidney cancer responsible for 80% to 85% of all renal tumors. The diagnosis of kidney cancer requires manual examination and analysis of histopathological images of the affected tissue. This process is time-consuming, prone to human error, and highly depends on the expertise of a pathologist. Early detection and grading of kidney cancer tissues enable doctors and practitioners to decide the further course of treatment. Therefore, quick and precise analysis of kidney cancer tissue images is extremely important for proper diagnosis. Recently, deep learning algorithms have proved to be very efficient and accurate in histopathology image analysis. In this paper, we propose a computationally efficient deep-learning architecture based on convolutional neural networks (CNNs) to automate the grading and classification task for kidney cancer tissue. The proposed Robust CNN (RoCNN) architecture is capable of learning features at varying convolutional filter sizes because of the inception modules employed in it. Squeeze and Extract (SE) blocks are used to remove unnecessary contributions from noisy channels and improve model accuracy. Concatenating samples from three different parts of architecture allows for the encompassing of varied features, further improving grading and classification accuracy. To demonstrate that the proposed model is generalized and independent of the dataset, it has experimented on two well-known datasets, the KMC kidney dataset of five different grades and the TCGA dataset of four classes. Compared to the best-performing state-of-the-art model the accuracy of RoCNN shows a significant improvement of about 4.22% and 3.01% for both datasets respectively. © 2013 IEEE.Item Improving the performance of multi-stage HER2 breast cancer detection in hematoxylin-eosin images based on ensemble deep learning(Elsevier Ltd, 2025) Pateel, G.P.; Senapati, K.; Pandey, A.K.Background: Breast cancer is the most frequently diagnosed cancer among women worldwide, and histopathology is the gold standard in diagnosing the disease. Hematoxylin and Eosin (HE) staining, routinely employed to observe the overall tissue structure, is an affordable and commonly practiced cancer diagnosis. In contrast, Immunohistochemistry (IHC), which detects the increased presence of particular antigens linked to the mutation, can require multiple tests to conduct and is relatively costly. Generally, in computer-aided diagnosis, the conventional methods rely on a single network to extract features. However, these methods have significant limitations and fail to generalize. Methods: In this study, we propose an automated novel weighted average algorithm called HER2-ETNET, which ensembles the chosen three pre-trained deep learning models, DenseNet 201, GoogLeNet, and ResNet-50, to classify breast histopathology HE images into multi-class Human Epidermal Growth Factor Receptor-2 (HER2) status (HER2-0+, HER2-1+, HER2-2+, HER2-3+). The proposed method has the potential to bypass the IHC laboratory test. In this study, we form a weight matrix by fusing together, the scores of False Positive Rate (FPR) and False Negative Rate (FNR) of both training and validation sets, and the computed weights are assigned to the three base learners. This is in contrast to the previous works, in which the weights were generally assigned empirically to the chosen deep learning models, which might be erroneous. Result: The proposed approach is evaluated on the unseen test set, and it achieves accuracy, precision, recall and AUC of 97.44%, 97.32%, 97.39%, and 99.75% respectively. Conclusion: The proposed framework outperforms all the existing methods on the same dataset and is proven to be the reliable method in detecting the HER2 status (HER2-0+, HER2-1+, HER2-2+, HER2-3+) from HE images. This also proves that, HE stained images contain adequate information for efficiently detecting the HER2 status in breast cancer. © 2024 Elsevier LtdItem ProsGradNet: An effective and structured CNN approach for prostate cancer grading from histopathology images(Elsevier Ltd, 2025) Prabhu, A.; Sravya, N.; Lal, S.; Kini, J.Prostate cancer (PCa) is one of the most prevalent and potentially fatal malignancies affecting men globally. The incidence of prostate cancer is expected to double by 2040, posing significant health challenges. This anticipated increase underscores the urgent need for early and precise diagnosis to facilitate effective treatment and management. Histopathological analysis using Gleason grading system plays a pivotal role in clinical decision making by classifying cancer subtypes based on their cellular characteristics. This paper proposes a novel deep CNN model named as Prostate Grading Network (ProsGradNet), for the automatic grading of PCa from histopathological images. Central to the approach is the novel Context Guided Shared Channel Residual (CGSCR) block, that introduces structured methods for channel splitting and clustering, by varying group sizes. By grouping channels into 2, 4, and 8, it prioritizes deeper layer features, enhancing local semantic content and abstract feature representation. This methodological advancement significantly boosts classification accuracy, achieving an impressive 92.88% on Prostate Gleason dataset, outperforming other CNN models. To demonstrate the generalizability of ProsGradNet over different datasets, experiments are performed on Kasturba Medical College (KMC) Kidney dataset as well. The results further confirm the superiority of the proposed ProsGradNet model, with a classification accuracy of 92.68% on the KMC Kidney dataset. This demonstrates the model's potential to be applied effectively across various histopathological datasets, making it a valuable tool to fight against cancer. © 2025 Elsevier Ltd