Ganapathy Krishnamurthi

Ganapathy Krishnamurthi

Auto-generated profile, based on publicly available information

Ganapathy Krishnamurthi

Indian Institute of Technology Madras

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

2 June 2021 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MKMahendra Khened
Mahendra Khened
AKAvinash Kori
Avinash Kori
HRHaran Rajkumar
Haran Rajkumar
GKGanapathy Krishnamurthi
Ganapathy Krishnamurthi
BSBalaji Srinivasan
Balaji Srinivasan
Histopathology tissue analysis is considered the gold standard in cancer diagnosis and prognosis. Whole-slide imaging (WSI), i.e., the scanning and digitization of entire histology slides, are now being adopted across the world in pathology labs. Trained histopathologists can provide an accurate diagnosis of biopsy specimens based on WSI data. Given the dimensionality of WSIs and the increase in the number of potential cancer cases, analyzing these images is a time-consuming process. Automated segmentation of tumorous tissue helps in elevating the precision, speed, and reproducibility of research. In the recent past, deep learning-based techniques have provided state-of-the-art results in a wide variety of image analysis tasks, including the analysis of digitized slides. However, deep learning-based solutions pose many technical challenges, including the large size of WSI data, heterogeneity in images, and complexity of features. In this study, we propose a generalized deep learning-based framework for histopathology tissue analysis to address these challenges. Our framework is, in essence, a sequence of individual techniques in the preprocessing-training-inference pipeline which, in conjunction, improve the efficiency and the generalizability of the analysis. The combination of techniques we have introduced includes an ensemble segmentation model, division of the WSI into smaller overlapping patches while addressing class imbalances, efficient techniques for inference, and an efficient, patch-based uncertainty estimation framework. Our ensemble consists of DenseNet-121, Inception-ResNet-V2, and DeeplabV3Plus, where all the networks were trained end to end for every task. We demonstrate the efficacy and improved generalizability of our framework by evaluating it on a variety of histopathology tasks including breast cancer metastases (CAMELYON), colon cancer (DigestPath), and liver cancer (PAIP). Our proposed framework has state-of-the-art performance across all these tasks and is ranked within the top 5 currently for the challenges based on these datasets. The entire framework along with the trained models and the related documentation are made freely available at GitHub and PyPi. Our framework is expected to aid histopathologists in accurate and efficient initial diagnosis. Moreover, the estimated uncertainty maps will help clinicians to make informed decisions and further treatment planning or analysis.

7 February 2020 in Frontiers in Computational Neuroscience
Verified
Journal Article
Open access
PDF file
PNParth Natekar
Parth Natekar
AKAvinash Kori
Avinash Kori
GKGanapathy Krishnamurthi
Ganapathy Krishnamurthi
The accurate automatic segmentation of gliomas and its intra-tumoral structures is important not only for treatment planning but also for follow-up evaluations. Several methods based on 2D and 3D Deep Neural Networks (DNN) have been developed to segment brain tumors and to classify different categories of tumors from different MRI modalities. However, these networks are often black-box models and do not provide any evidence regarding the process they take to perform this task. Increasing transparency and interpretability of such deep learning techniques is necessary for the complete integration of such methods into medical practice. In this paper, we explore various techniques to explain the functional organization of brain tumor segmentation models and to extract visualizations of internal concepts to understand how these networks achieve highly accurate tumor segmentations. We use the BraTS 2018 dataset to train three different networks with standard architectures and outline similarities and differences in the process that these networks take to segment brain tumors. We show that brain tumor segmentation networks learn certain human-understandable disentangled concepts on a filter level. We also show that they take a top-down or hierarchical approach to localizing the different parts of the tumor. We then extract visualizations of some internal feature maps and also provide a measure of uncertainty with regards to the outputs of the models to give additional qualitative evidence about the predictions of these networks. We believe that the emergence of such human-understandable organization and concepts might aid in the acceptance and integration of such methods in medical diagnosis.

14 December 2017 in Journal of Medical Imaging
Verified
Journal Article
Closed access
PDF file
VAVarghese Alex
Varghese Alex
KVKiran Vaidhya
Kiran Vaidhya
STSubramaniam Thirunavukkarasu
Subramaniam Thirunavukkarasu
CKChandrasekharan Kesavadas
Chandrasekharan Kesavadas
GKGanapathy Krishnamurthi
Ganapathy Krishnamurthi
The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patients ( n = 20 , 40, 65). The results show negligible loss in performance even when SDAE was fine-tuned using 20 labeled patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach in which a network pretrained with high grade glioma data was fine-tuned using LGG image patches. The networks were also shown to generalize well and provide good segmentation on unseen BraTS 2013 and BraTS 2015 test data. The manuscript also includes the use of a single layer DAE, referred to as novelty detector (ND). ND was trained to accurately reconstruct nonlesion patches. The reconstruction error maps of test data were used to localize lesions. The error maps were shown to assign unique error distributions to various constituents of the glioma, enabling localization. The ND learns the nonlesion brain accurately as it was also shown to provide good segmentation performance on ischemic brain lesions in images from a different database.

23 November 2017 in RSC Advances
Verified
Journal Article
Open access
PDF file
ANAshwin Kumar Narasimhan
Ashwin Kumar Narasimhan
SBSwathi Lakshmi B
Swathi Lakshmi B
Tuhin SantraTuhin Santra
Tuhin Santra
MRM S Ramachandra Rao
M S Ramachandra Rao
GKGanapathy Krishnamurthi
Ganapathy Krishnamurthi
Fluorescence probes are essential for in vivo molecular imaging as well as cell tracking applications. Probes that emit in the far red wavelength penetrate better through biological tissue and the autofluorescence background is reduced at higher wavelengths, making such probes highly desirable. We report the application of Graphene Quantum Dots (GQDs) as efficient fluorescence probes for single cell tracking using high-resolution confocal microscopy as well as a potential in vivo fluorescent imaging agent. High-quality water soluble GQDs were synthesized by ablating highly oriented pyrolytic graphite (HOPG) in liquid using a nanosecond pulsed laser. Refluxing GQDs at 200 °C for 20 minutes and 1 hour produces excitation independent broad emission peaking at 600 nm and excitation dependent color-tunable emission, respectively. These emission properties can be attributed to the functional groups such as carboxyl and hydroxyl groups on the surface or edges. MTT assays with the breast cancer (MCF-7) cell line suggest that 20 min and 1 h GQDs had 80% viability post incubation with concentrations as high as 2 mg mL−1. The paper also explores the molecular tracking functionality of GQDs. Fluorescence microscopy showed that MCF-7 cells incubated for up to 48 hours with GQDs, internalized the GQDs, by caveolae-mediated endocytosis without any targeting moiety. In addition, high-resolution Z stacking and 3D confocal microscopy of a single live MCF-7 cell confirm successful uptake of GQDs into the cytoplasm by endocytosis. Fluorescence imaging of GQDs loaded in polyacrylamide gel and subcutaneously implanted near the thoracic region of an euthanized mice was done to explore the feasibility of in vivo imaging using GQDs. Deep red fluorescence (610 nm emission filter) was observed from the implanted region with relatively low autofluorescence background.

15 March 2018 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
MKMahendra Khened
Mahendra Khened
VAVarghese Alex
Varghese Alex
GKGanapathy Krishnamurthi
Ganapathy Krishnamurthi