Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item Adversarial Learning Based Semi-supervised Semantic Segmentation of Low Resolution Gram Stained Microscopic Images(Springer Science and Business Media Deutschland GmbH, 2024) Singh, H.; Kanabur, V.R.; Sumam David, S.; Vijayasenan, D.; Govindan, S.Urinary tract infections (UTIs) are infections that affect the urinary system. It is usually caused by bacteria and pus cells. Analyzing urine samples, including examining pus cells, is a standard method for diagnosing and monitoring UTIs. However, manually detecting bacteria or pus cells in microscopic urine images is a time-consuming and labour-intensive task for microbiologists. Therefore, the segmentation of microscopic pus cell images will ease the process of detecting UTI. Especially low resolution microscopic images are hard to annotate; therefore, in this study, we propose an adversarial learning based semi-supervised segmentation method for segmentation of pus cell images at low resolution i.e. 40× using labeled high resolution images i.e. 100×. The proposed methodology aims to ease the process of UTI detection by automating the segmentation of pus cell images. The results of the proposed methodology demonstrate an increase in the Dice coefficient score percentage by 1%, 1.6% and 2.4% on 40× images when compared to fully supervised segmentation model trained on only 100× data using three different architectures- Unet, ResUnet++, and PSPnet, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.Item An Enhancer-Driven Stem Cell–Like Program Mediated by SOX9 Blocks Intestinal Differentiation in Colorectal Cancer(W.B. Saunders, 2022) Liang, X.; Duronio, G.N.; Yang, Y.; Bala, P.; Hebbar, P.; Spisák, S.; Sahgal, P.; Singh, H.; Zhang, Y.; Xie, Y.; Cejas, P.; Long, H.W.; Bass, A.J.; Sethi, N.S.Background and Aims: Genomic alterations that encourage stem cell activity and hinder proper maturation are central to the development of colorectal cancer (CRC). Key molecular mediators that promote these malignant properties require further elucidation to galvanize translational advances. We therefore aimed to characterize a key factor that blocks intestinal differentiation, define its transcriptional and epigenetic program, and provide preclinical evidence for therapeutic targeting in CRC. Methods: Intestinal tissue from transgenic mice and patients were analyzed by means of histopathology and immunostaining. Human CRC cells and neoplastic murine organoids were genetically manipulated for functional studies. Gene expression profiling was obtained through RNA sequencing. Histone modifications and transcription factor binding were determined with the use of chromatin immunoprecipitation sequencing. Results: We demonstrate that SRY-box transcription factor 9 (SOX9) promotes CRC by activating a stem cell–like program that hinders intestinal differentiation. Intestinal adenomas and colorectal adenocarcinomas from mouse models and patients demonstrate ectopic and elevated expression of SOX9. Functional experiments indicate a requirement for SOX9 in human CRC cell lines and engineered neoplastic organoids. Disrupting SOX9 activity impairs primary CRC tumor growth by inducing intestinal differentiation. By binding to genome wide enhancers, SOX9 directly activates genes associated with Paneth and stem cell activity, including prominin 1 (PROM1). SOX9 up-regulates PROM1 via a Wnt-responsive intronic enhancer. A pentaspan transmembrane protein, PROM1 uses its first intracellular domain to support stem cell signaling, at least in part through SOX9, reinforcing a PROM1-SOX9 positive feedback loop. Conclusions: These studies establish SOX9 as a central regulator of an enhancer-driven stem cell–like program and carry important implications for developing therapeutics directed at overcoming differentiation defects in CRC. © 2022Item Adaptive conductance function based improved diffusion filtering and bi-dimensional empirical mode decomposition based image denoising(Springer, 2023) Gupta, H.; Singh, H.; Kumar, A.; Vishwakarma, A.This paper presents a new method for image denoising based on a two-dimensional empirical mode decomposition algorithm and semi-adaptive diffusion coefficient in anisotropic diffusion filter. The proposed model uses a local difference value method to compare and replace some pixels of the noisy image with a pre-processed image that has been passed through a Gaussian filter. A bi-dimensional empirical mode decomposition algorithm is then employed to decompose the noise-contaminated image into its intrinsic mode functions in which high-frequency and low-frequency noise components are removed by applying a diffusion filter. The filter has a semi-adaptive threshold in the diffusion coefficient with parameters like connectivity, conductance function, number of iterations, and gradient threshold. The semi-adaptive threshold for each diffusion is implemented by introducing gradient values in the threshold of the corrupted image. The image is then reconstructed from these denoised intrinsic mode functions. The performance of the proposed method is assessed in terms of peak signal-to-noise ratio, mean square error, and structural similarity index and is compared with the existing methodologies. The results obtained from experimentation indicate that the proposed method is efficient in both feature retention and noise suppression. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item Variational mode decomposition based image denoising using semi-adaptive conductance function inspired diffusion filtering(Springer, 2024) Gupta, H.; Singh, H.; Kumar, A.; Vishwakarma, A.; Singh, G.K.In day-to-day life, images are the most frequent and casual way of information sharing. These images are susceptible to external disturbances or noise. Thus, to curb noise, image denoising algorithms are utilized. In this paper, the variational mode decomposition, with its concurrent and a non-recursive process for determining the mode functions that also provides a robust method for image denoising, has been introduced. This decomposition process divides the whole spectrum of the signal into a number of sub-bands or mode functions, centered around their respective center frequencies. To these mode functions, spatial filters such as bilateral filter, wiener filter, and modified anisotropic diffusion filter are employed. These filters help in enhancing the yield of the quality assessment metrics; such as mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM), together with the semi-adaptive conductance function in the diffusion filter. The parameters of these respective spatial filters are calibrated, and then selected in order to get the best possible metric scores. The applicability and ability of the algorithm to suppress noise are compared visually and quantitatively for the noisy image using modified variational mode decomposition and other denoising algorithms in both low and high noise levels. The algorithm provides an average decrease of 62% in case of MSE, 28% increase in PSNR, and 110% increase in SSIM when compared with other denoising techniques. The estimated metric score values signify that the proposed method has a better prospect as a denoising algorithm. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item Amidated pectin and gum Arabic aldehyde-based pH-sensitive hydrogel for targeted colonic treatment(Elsevier B.V., 2025) Singh, H.; JagadeeshBabu, J.; Mohan Balakrishnan, R.In this study, a novel pH-responsive hydrogel was developed by crosslinking amidated pectin(AmPec) with oxidised gum Arabic(GAA) by hydrogen and hemiacetal bonding without the need for toxic crosslinkers for oral delivery of doxorubicin to treat colon cancer. FTIR and NMR confirmed the amidation of pectin and oxidation of Gum Arabic. FTIR confirmed the formation of hydrogen and hemiacetal bonds in the hydrogel. X-ray diffraction(XRD) spectra showed the amorphous characteristic of AmPec-GAA hydrogels compared to their polymer precursors, confirming the formation of a crosslinked hydrogel. AmPec-GAA15 hydrogel swelled around 655 %±39.90 at pH 7.4 compared to 181 %±7.94 swelling at pH 1.2 after 72 h. The release of doxorubicin also followed the same trend, with only 4.48 % ±0.89 doxorubicin release at pH 1.2, while the drug release increased to 68.10 %±3.73 at pH 7.4 after 48 h. SEM micrographs revealed the macroporous and interconnected hydrogel structure with fewer pores in the hydrogel swelled in pH 1.2 compared with pH 7.4, where more visible pores were observed, indicating the pH-sensitive behaviour of the hydrogel. Hydrogel possessed excellent thermal and mechanical stability as revealed by TGA and rheology study, which can also be explored for tissue engineering applications. MTT assay on L929 cells showed cell viability above 95.1 %±,0.0074, demonstrating hydrogels' non-toxic and biocompatible behaviour. Meanwhile, Dox-loaded hydrogel induced higher cytotoxicity against HT-29 cells than free Dox in a dose-dependent manner. Therefore, the developed hydrogel can be used as an effective oral carrier to deliver doxorubicin to colon cancer while hindering its release in the stomach and thus preventing associated toxicity. © 2025 Elsevier B.V.