Browsing by Author "Sumam David S."

Now showing 1 - 6 of 6

An Approach for Diagnostically Lossless Coding of Volumetric Medical Data Based on Wavelet and Just-Noticeable-Distortion Model
(2020) Chandrika B.K.; Aparna P.; Sumam David S.
This paper explores a technique for visually/diagnostically lossless coding in the wavelet domain to effectively compress the three-dimensional medical image data. The quantisation module based on Just Noticeable Distortion (JND) for wavelets guarantees the visual quality in the reconstructed data. This method has been further extended to present the Volume of Interest (VOI) based technique that enables to preserve the quality of the diagnostically significant VOI region. The proposed method tested on several datasets outperforms the state-of-the-art methods. Apart from the conventional quality metric, Human Visual System (HVS) based quality metrics are also used to evaluate the visual quality of the reconstructed image. A subjective and objective evaluation carried out for VOI based coder shows that the quality-compression needs of the medical community are well addressed. © 2020 IETE.
Automatic Detection of Malignancy in Low-Magnification Effusion Cytology Images
(National Institute of Technology Karnataka, Surathkal, 2024) Aboobacker, Shajahan; Deepu, Vijayasenan; Sumam David S.
This thesis focuses on developing an integrated system for automatically detecting malignancy in effusion cytology images. Effusion cytology plays a crucial role in diagnosing various diseases, including cancer, by analyzing the cells present in body fluids. This study aims to develop an integrated system that can handle different resolutions of images and accurately detect malignant cases. Effusion cytology greatly benefits from the automatic detection of malignant cells, providing significant assistance to cytopathologists. However, conventional automation algorithms often rely on high-magnification images for analysis. In contrast, cytopathologists consider multiple magnifications when evaluating cytology images for malignancy. Lower magnification images capture a larger area in a single frame compared to high magnification images. This allows cytopathologists to identify regions of interest (ROI) using textural and morphological characteristics of cell clusters. Once identified, the ROIs are examined at a higher magnification for a closer evaluation at the cell level. Initially, we trained the existing state-of-the-art models with high magnification images for the semantic segmentation and classification of effusion cytology images. We obtained state-of-the-art results for the semantic segmentation task with a mean F-score of 0.82 and classification performance with a sensitivity value of 1, specificity of 0.85, and an area under the curve (AUC) of 0.98. However, using lower magnification images can be beneficial in identifying malignant areas, as it reduces memory requirements and scanning time by focusing only on the ROI at higher magnification. However, detecting malignancy in low-magnification images (4X) is challenging due to the blurring of features such as texture and nuclei. This blurring also makes it difficult to label the images accurately at low magnification levels. Therefore, an alternative method is needed that doesn’t rely on labels for the lowest magnification. We propose two methods for the semantic segmentation of low-magnification images. The first method is based on semi-supervised learning, and the second uses a combination of unsupervised, few-shot and weakly supervised learning. In the semi-supervised approach, we have extended the MixMatch and Fixi Match algorithms from the classification task to semantic segmentation. We used augmentation of the images and reverse augmentation of the predicted label to achieve this. The proposed methods allow using the 4X images without any labels along with the labelled 10X images to train the semantic segmentation model. The average F-score of benign and malignant pixels on the predictions of 4X images using the Extended FixMatch and Extended MixMatch has improved approximately by 9% compared with the predictions of 4X data on the semantic 10X model. The Extended MixMatch reduces the area to be scanned at a higher magnification by approximately 62%. Only 38% of sub-regions of low-magnification images have to be scanned at a higher magnification, thereby saving scanning time. In the context of semi-supervised learning for semantic segmentation of low-magnification images, it is worth noting that while we can reduce the reliance on pixel-wise labels for 4X magnification data, we still require labelled data at a higher magnification level, specifically at 10X. We propose WeakSegNet, a novel approach that combines unsupervised, few-shot and weakly supervised methods for the semantic segmentation of low-magnification effusion cytology images. By leveraging image-level labels and a small number of images with pixel-wise labels, our model achieves accurate and efficient detection of malignancy. Our approach utilizes unlabeled low-magnification images for training, reducing the need for manual annotations. The significant elimination (approximately 47%) achieved by our model in higher magnification scanning demonstrates its potential for time and resource savings. Overall, our approaches offer an effective solution for automating malignancy detection in low-magnification images, improving efficiency in cytology analysis.
Deep Learning Model based Ki-67 Index estimation with Automatically Labelled Data
(2020) Lakshmi S.; Sai Ritwik K.V.; Vijayasenan D.; Sumam David S.; Sreeram S.; Suresh P.K.
Ki-67 labelling index is a biomarker which is used across the world to predict the aggressiveness of cancer. To compute the Ki-67 index, pathologists normally count the tumour nuclei from the slide images manually; hence it is timeconsuming and is subject to inter pathologist variability. With the development of image processing and machine learning, many methods have been introduced for automatic Ki-67 estimation. But most of them require manual annotations and are restricted to one type of cancer. In this work, we propose a pooled Otsu's method to generate labels and train a semantic segmentation deep neural network (DNN). The output is postprocessed to find the Ki-67 index. Evaluation of two different types of cancer (bladder and breast cancer) results in a mean absolute error of 3.52%. The performance of the DNN trained with automatic labels is better than DNN trained with ground truth by an absolute value of 1.25%. © 2020 IEEE.
A Deep Learning Model for the Automatic Detection of Malignancy in Effusion Cytology
(2020) Aboobacker S.; Vijayasenan D.; Sumam David S.; Suresh P.K.; Sreeram S.
The excessive accumulation of fluid between layers of pleura covering lungs is known as pleural effusion. Pleural effusion may be due to various infections, inflammations or malignancy. The cytologists visually examine the microscopic slide to detect the malignant cells. The process is time-consuming, and interpretation of reactive cells and cells with ambiguous levels of atypia may differ between pathologists. Considerable research is happening towards the automation of fluid cytology reporting. We propose an integrated approach based on deep learning, where the network learns directly to detect the malignant cells in effusion cytology images. Architecture U-Net is used to learn the malignant and benign cells from the images and to detect the images that contain malignant cells. The model gives a precision of 0.96, recall of 0.96, and specificity of 0.97. The AUC of the ROC curve is 0.97. The model can be used as a screening tool and has a malignant cell detection rate of 0.96 with a low false alarm rate of 0.03. © 2020 IEEE.
Motion Deblurring of Faces
(2020) Anand P.; Sumam David S.; Sudeep K.S.
This paper evaluates learning-based data-driven models for deblurring of facial images. Existing algorithms for deblurring, when used for facial images, often fail to preserve the facial shape and identity information. The best available models, which are used for general-purpose image deblurring, are pre-trained using only facial images. The Peak Signal to Noise Ratio (PSNR) Structural Similarity Index Measure (SSIM) and Time to deblur single images are the key metrics used for evaluating the models and for finding the most efficient model for deblurring facial images. From the results, the observation is that even though the PSNR value for DeblurGANv2 model is the highest, the best trade off between PSNR, SSIM, Time to deblur and visual quality is seen in DeblurGAN model. © 2020 IEEE.
Non-intrusive methods to detect air-gap eccentricity faults in three-phase induction motor
(2020) Bindu S.; Sumam David S.; Thomas V.V.
The focus of this paper is model-based behavioural analysis for the diagnosis of the air-gap eccentricity fault condition in the three-phase induction machine. To facilitate reliable and sensitive diagnosis, an online condition monitoring system has to depend on multiple signals and signatures. Air-gap mixed eccentricity fault signatures derived from three non-invasive methods such as stator line current, instantaneous power, and estimated air-gap torque are presented. Modified winding function theory and multiple coupled circuit approaches are used to model the machine. The sidebands present around the fundamental frequency in the spectrum of stator current, and around double the supply frequency in the spectrum of instantaneous power indicate the presence of air-gap mixed eccentricity. The low frequencies which exist near the DC component in the spectra of the air-gap torque and instantaneous power also indicate the same. These specific components were also observed in the high-frequency spectra around the principal slot harmonics. The modelling approach, the torque estimation approach, the simulation results at different severity and load conditions, and the experimentation result in a motor with prefabricated eccentricity are presented. © 2020 Praise Worthy Prize S.r.l.-All rights reserved.