Lakshmi Devan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lakshmi Devan has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
M. Arunmozhi
Department of Information Technology St. Joseph's College of Engineering Chennai India
1 shared publication- Palani Thanaraj Krishnan
St. Joseph’s College of Engineering
1 shared publication - Palayanoor Seethapathy Ramapraba
Panimalar Engineering College
1 shared publication R. Niruban
St. Joseph’s College of Engineering
1 shared publicationRanganathan Hariharan
Principal, Rajiv Gandhi College of Engineering Chennai Tamil Nadu India
1 shared publicationRoy Santosham
Professor, Department of Radiology Sri Ramachandra Medical College, Consultant Radiologist, Santosham Chest Hospital Chennai Tamil Nadu India
1 shared publication
Latest Publications
- 19 February 2024
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 34 (2)
A customized ConvNeXt‐XL network with fusion of deep and handcrafted features for colposcopy image classification
Cervical cancer is the second most frequent cancer among women of all age groups worldwide. It occurs due to human papillomavirus. In the premature stages, the symptoms will not be predominant until they reach the final stage of cancer. Detection and classification of cervical cancer always demand gynecologists with the necessary skills and experience. The goal of the proposed work is to develop a deep learning framework to facilitate the automated classification of cervical cancer using colposcopy images. The following Deep Convolutional Neural Network (DCNN) models are proposed to detect cervical cancer and classify cervix‐type images. (i) the pre‐trained DCNNs, namely VGG16, ResNet50, InceptionV3, InceptionResNetV2, and ConvNeXtXLarge (ConvNeXt‐XL) using Softmax classifier based on deep features; (ii) the ConvNeXt‐XL model with classification using Support Vector Machine (SVM), K Nearest Neighbor (KNN) and Decision Tree (DT) based on deep features; (iii) a customized ConvNeXt‐XL network to enhance the classification accuracy using serially concatenated handcrafted and deep features. The research experiment was carried out separately using two datasets: the Cervix‐Type dataset (Type 1, Type 2, and Type 3) and the Real Time Cervical dataset (Normal and Abnormal). The simulation outcome confirms that the customized ConvNeXt‐XL helped to improve the classification accuracy with the Cervix‐Type dataset (>97%) and Real Time Cervical dataset (>98%).
- 19 February 2024
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 34 (2)
A customized ConvNeXt‐XL network with fusion of deep and handcrafted features for colposcopy image classification
Cervical cancer is the second most frequent cancer among women of all age groups worldwide. It occurs due to human papillomavirus. In the premature stages, the symptoms will not be predominant until they reach the final stage of cancer. Detection and classification of cervical cancer always demand gynecologists with the necessary skills and experience. The goal of the proposed work is to develop a deep learning framework to facilitate the automated classification of cervical cancer using colposcopy images. The following Deep Convolutional Neural Network (DCNN) models are proposed to detect cervical cancer and classify cervix‐type images. (i) the pre‐trained DCNNs, namely VGG16, ResNet50, InceptionV3, InceptionResNetV2, and ConvNeXtXLarge (ConvNeXt‐XL) using Softmax classifier based on deep features; (ii) the ConvNeXt‐XL model with classification using Support Vector Machine (SVM), K Nearest Neighbor (KNN) and Decision Tree (DT) based on deep features; (iii) a customized ConvNeXt‐XL network to enhance the classification accuracy using serially concatenated handcrafted and deep features. The research experiment was carried out separately using two datasets: the Cervix‐Type dataset (Type 1, Type 2, and Type 3) and the Real Time Cervical dataset (Normal and Abnormal). The simulation outcome confirms that the customized ConvNeXt‐XL helped to improve the classification accuracy with the Cervix‐Type dataset (>97%) and Real Time Cervical dataset (>98%).
- 28 December 2019
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 30 (2) , 445-454
Convolutional neural network in the detection of lung carcinoma using transfer learning approach
Background: Lung carcinoma is the leading cause of 1.76 million deaths worldwide. GLOBOCAN 2018 report says lung cancer occupies the first position in terms of incidence and mortality rate. Reasons include limited access to timely diagnosis and treatment.Objective: This research work presents the viability of using convolutional neural network (CNN) for lung carcinoma detection. The proposed network automatically detects the lung carcinomas tissues through transfer learning without the difficulty of specifying features for image classification.Subjects and methods: The study involves lung CT images of 12 male and 4 female subjects, aging between 35 and 77 years. These images are obtained in Bitmap image format with a resolution of 512 × 512. Two cases namely healthy and carcinoma are taken for study. Carcinoma cases include poorly differentiated carcinoma, moderately differentiated carcinoma. The training data consists of 800 lung CT slices, validation set consists of 100 CT images, and test data consist of 100 images, respectively.Results: Experimental results demonstrate the VGG16 and VGG 19 network implementation with the area under the receiver operating characteristics of 0.930 and 0.90, respectively. VGG19 compete well with a sensitivity and specificity of 80% and 100% compared to VGG16 with 98% and 88%, respectively.Conclusion: Hence, the implementation of VGG16 and VGG19 with good accuracy proves that CNN used for lung carcinoma detection leading to timely diagnosis and treatment may decrease the mortality rate.
- 28 December 2019
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 30 (2) , 445-454
Convolutional neural network in the detection of lung carcinoma using transfer learning approach
Background: Lung carcinoma is the leading cause of 1.76 million deaths worldwide. GLOBOCAN 2018 report says lung cancer occupies the first position in terms of incidence and mortality rate. Reasons include limited access to timely diagnosis and treatment.Objective: This research work presents the viability of using convolutional neural network (CNN) for lung carcinoma detection. The proposed network automatically detects the lung carcinomas tissues through transfer learning without the difficulty of specifying features for image classification.Subjects and methods: The study involves lung CT images of 12 male and 4 female subjects, aging between 35 and 77 years. These images are obtained in Bitmap image format with a resolution of 512 × 512. Two cases namely healthy and carcinoma are taken for study. Carcinoma cases include poorly differentiated carcinoma, moderately differentiated carcinoma. The training data consists of 800 lung CT slices, validation set consists of 100 CT images, and test data consist of 100 images, respectively.Results: Experimental results demonstrate the VGG16 and VGG 19 network implementation with the area under the receiver operating characteristics of 0.930 and 0.90, respectively. VGG19 compete well with a sensitivity and specificity of 80% and 100% compared to VGG16 with 98% and 88%, respectively.Conclusion: Hence, the implementation of VGG16 and VGG19 with good accuracy proves that CNN used for lung carcinoma detection leading to timely diagnosis and treatment may decrease the mortality rate.
- 22 August 2018
- Published by Springer Nature
- p. 117-123
Mathematical Model for Characterization of Lung Tissues Using Multiple Regression Analysis
- 22 August 2018
- Published by Springer Nature
- p. 117-123
Mathematical Model for Characterization of Lung Tissues Using Multiple Regression Analysis
- 10 February 2014
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 24 (1) , 39-44
Automated texture‐based characterization of fibrosis and carcinoma using low‐dose lung CT images
Lung cancer is the most common cause of cancer deaths worldwide and account for 1.38 million deaths per year. Patients with lung cancer are often misdiagnosed as pulmonary tuberculosis (TB) leading to delay in the correct diagnosis as well as exposure to inappropriate medication. The diagnosis of TB and lung cancer can be difficult as symptoms of both diseases are similar in computed tomography (CT) images. However, treating TB leads to inflammatory fibrosis in some of the patients. There comes the need of an efficient computer aided diagnosis (CAD) of the fibrosis and carcinoma diseases. To design a fully automated CAD for characterizing fibrous and carcinoma tissues without human intervention using lung CT images. The 18 subjects in this study include seven healthy, two fibrosis and eight carcinoma, and one necrosis cases. The dataset is built by CT cuts representing healthy is 113, fibrosis is 103, necrosis is 39, and carcinoma is 185 totalling 440 images. The gray‐level spatial dependence matrix and gray level run length matrix approach are used for extracting texture‐based features. These features are given to neural network classifier and statistical classifier. These classifier performances are evaluated using receiver‐operating characteristics (ROC). The proposed method characterizes these tissues without human intervention. Sensitivity, specificity, precision, and accuracy followed by ROC curves were obtained and also studied. Thus, the proposed automated image‐based classifier could act as a precursor to histopathological analysis, thereby creating a way to class specific treatment procedures.
- 10 February 2014
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 24 (1) , 39-44
Automated texture‐based characterization of fibrosis and carcinoma using low‐dose lung CT images
Lung cancer is the most common cause of cancer deaths worldwide and account for 1.38 million deaths per year. Patients with lung cancer are often misdiagnosed as pulmonary tuberculosis (TB) leading to delay in the correct diagnosis as well as exposure to inappropriate medication. The diagnosis of TB and lung cancer can be difficult as symptoms of both diseases are similar in computed tomography (CT) images. However, treating TB leads to inflammatory fibrosis in some of the patients. There comes the need of an efficient computer aided diagnosis (CAD) of the fibrosis and carcinoma diseases. To design a fully automated CAD for characterizing fibrous and carcinoma tissues without human intervention using lung CT images. The 18 subjects in this study include seven healthy, two fibrosis and eight carcinoma, and one necrosis cases. The dataset is built by CT cuts representing healthy is 113, fibrosis is 103, necrosis is 39, and carcinoma is 185 totalling 440 images. The gray‐level spatial dependence matrix and gray level run length matrix approach are used for extracting texture‐based features. These features are given to neural network classifier and statistical classifier. These classifier performances are evaluated using receiver‐operating characteristics (ROC). The proposed method characterizes these tissues without human intervention. Sensitivity, specificity, precision, and accuracy followed by ROC curves were obtained and also studied. Thus, the proposed automated image‐based classifier could act as a precursor to histopathological analysis, thereby creating a way to class specific treatment procedures.