Browsing by Author "Prabhu, A."

Now showing 1 - 11 of 11

An Efficient Parallel Branch Network for Multi-Class Classification of Prostate Cancer From Histopathological Images
(John Wiley and Sons Inc, 2025) Srivastava, V.; Prabhu, A.; Sravya, S.; Vibha Damodara, K.; Lal, S.; Kini, J.
Prostate cancer is one of the prevalent forms of cancer, posing a significant health concern for men. Accurate detection and classification of prostate cancer are crucial for effective diagnosis and treatment planning. Histopathological images play a pivotal role in identifying prostate cancer by enabling pathologists to identify cellular abnormalities and tumor characteristics. With the rapid advancements in deep learning, Convolutional Neural Networks (CNNs) have emerged as a powerful tool for tackling complex computer vision tasks, including object detection, classification, and segmentation. This paper proposes a Parallel Branch Network (PBN), a CNN architecture specifically designed for the automatic classification of prostate cancer into its subtypes from histopathological images. The paper introduces a novel Efficient Residual (ER) block that enhances feature representation using residual learning and multi-scale feature extraction. By utilizing multiple branches with different filter reduction ratios and dense attention mechanisms, the block captures diverse features while preserving essential information. The proposed PBN model achieved a classification accuracy of 93.16% on the Prostate Gleason dataset, outperforming all other comparison models. © 2025 Wiley Periodicals LLC.
Bio-corrosion impacts on mechanical integrity of ZM21 Mg for orthopaedic implant application processed by equal channel angular pressing
(Springer, 2021) Sekar, P.; Nyahale, M.B.; Naik, G.M.; Narendranath, N.; Prabhu, A.; Rekha, P.D.
The mechanical integrity of rolled ZM21 Mg was improved by equal channel angular pressing (ECAP) to function as a potential biodegradable bone screw implant. Electron backscattered diffraction (EBSD) revealed deformed grains of 45 µm observed in rolled ZM21 Mg. They were transformed to equiaxed fine grains of 5.4 µm after 4th pass ECAP. The yield strength of rolled and ECAPed ZM21 Mg alloys were comparable. In contrast, 4th pass ZM21 Mg exhibited relatively higher elongation when compared to rolled sample. The mechanical properties of rolled and ECAPed ZM21 Mg were dependant on both grain refinement and crystallographic texture. The rolled and 4th pass ECAPed tensile samples exhibited nonlinear deterioration of mechanical properties when tested after 7, 14, 21 and 28 days immersion in Hank’s solution. The evaluation signifies that regardless their processing condition, ZM21 Mg alloys are suitable for surgical areas that requires high mechanical strength. In addition, the 4th pass ECAP samples were viable to MG-63 cells proving themselves to be promising candidates for future in vivo studies. [Figure not available: see fulltext.] © 2021, The Author(s).
Enhancing the functionality of biodegradable Mg–Zn–Mn alloys using poly(lactic) acid (PLA) coating for temporary implants
(Springer, 2024) Kumar, P.; Anne, G.; Ramesh, M.R.; Doddamani, M.; Prabhu, A.
Polylactic acid (PLA) was coated on biodegradable Mg–Zn–Mn alloys using a sol–gel coating technique for temporary implant applications. The presence of smooth, dense, crack-free PLA coating was evidenced using Fourier transform infrared spectroscopy (FTIR) and a scanning electronic microscope (SEM) equipped with an energy-dispersive X-ray spectroscopy (EDX) module. The strength of the bond between PLA and the Mg–Zn–Mn alloys was investigated as per ASTM D3359 and found to be 4B. The degradation behavior was evaluated using potentiodynamic polarization and electrochemical impedance spectroscopy in a simulated body fluid (SBF) solution. The corrosion rate of the PLA–Mg–Zn–Mn sample was found to be 0.00363 mm/y, which is 73% better than the bare Mg–Zn–Mn sample (0.00493 mm/y). In addition, the results of the cytotoxicity assay indicated the cytocompatibility of the implant material on MG-63 osteoblast-like cells, confirming its safety on the bone cells. The efficacy of the use of PLA coating on the biodegradable Mg–Zn–Mn is due to the synergistic effect of both physical and chemical interactions between the PLA layer and the substrate. © American Coatings Association 2024.
High-pressure torsion of biodegradable Mg?Zn?Mn alloy and investigate mechanical and corrosion behaviour
(Nature Research, 2025) Kumar, P.; Anne, G.; Ramesh, S.; Kudva, S.A.; Ramesh, M.R.; Doddamani, M.; Prabhu, A.; Sahu, S.
Considering their biodegradability in physiological environments and similar elastic modulus to natural bone, magnesium alloys have generated a lot of interest as biodegradable implant materials. Their poor corrosion resistance is primarily a result of the inhomogeneous distribution of their second phase, which limits their clinical application. High pressure torsion (HPT) one of the severe plastic deformation techniques which provides an opportunity to process materials with low formability such as magnesium at room temperature. The present study HPT is conducted for Mg-Zn-Mn alloy up to ten revolutions at room temperature. Optical, scanning, and transmission electron microscopes were used to examine the microstructures of base material (BM) and ten revolution HPT samples. Significant microhardness improvement was observed in HPT N10 samples (222 Hv) as compared to BM samples (68 Hv). It was determined that the improvement in microhardness was primarily due to dislocation strengthening, fine grain strengthening, and second phase strengthening. Potentiodynamic polarisation and electrochemical impedance spectroscopy (EIS) were used in a simulated body fluid (SBF) solution to assess the corrosion behaviour. When compared to the BM sample (0.0243 mm/y), the corrosion resistance of the HPT N10 sample (0.0012 mm/y) increased significantly. This was mostly due to the smaller grain size and uniform dispersion of the secondary phases, which result in a uniform corrosion. Further, obtained data from the cytotoxicity assay carried out using the MTT method indicated the compatibility of the Mg-Zn-Mn alloy on MG-63 osteoblast-like cells, further substantiating its safety on the bone cells. © The Author(s) 2025.
Investigating the role of WEDM surface texturing in the degradation and biocompatibility of Mg–Zn–Ca alloy
(KeAi Publishing Communications Ltd., 2025) Aswith Babu, I.; Sekar, P.; Prabhu, A.; Narendranath, S.; Balan, A.S.S.
Magnesium (Mg) alloy-based biodegradable implants are gaining popularity for their low density, high strength, and biocompatibility. The corrosion and wear performance of Mg is poor in physiological environments, leading to premature failure. Surface modification, particularly through surface texturing, reduces the effective contact area of Mg–Zn–Ca alloy with corrosive media and tribological partners, potentially optimizing its degradation kinetics and cytocompatibility. Wire Electric Discharge Machining (WEDM) offers a stable oxide layer on the surface, unlike laser surface texturing, which may thermally damage the Mg alloy. In this study, three types of textures, mainly Wavy Texture (WT), microchannels (MC), and micropillars (MP), were created using WEDM on the Mg–Zn–Ca samples, and their corrosion, wear, cytotoxicity, and cell adhesion performance were evaluated. Texturing on the surface of the samples enhanced the corrosion performance, from 3.14 mm/year for the untextured sample to 0.98 mm/year for the micropillar textured sample, representing a 68.8 % reduction. This improvement after texturing is attributed to the superior surface finish (1.049 ?m) and increased hydrophobicity (130.3°), equating to a 50.8 % improvement. The coefficient of friction (COF) value decreased from 0.364 for an untextured sample to 0.208 for microchannels, a 42.9 % reduction, due to the entrapment of debris in the textures and effective heat transfer. The samples' cell adhesion and cell viability have been improved after texturing. The combination of cytocompatibility, appropriate mechanical properties, and a reduced bio-corrosion rate highlights the potential of this surface texturing method, utilizing WEDM, as a promising approach to enhance biodegradable implant materials. © 2025 The Authors. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co. Ltdé This is an open access article under the CC BY license. http://creativecommons.org/licenses/by/4.0/
Petri Net-Based Verification of Adaptive Traffic Light Control with AIMD Algorithm
(Institute of Electrical and Electronics Engineers Inc., 2024) Prasanna, S.; Gulati, A.; Anagha, H.C.; Prabhu, A.; Das, M.; Mohan, B.R.
This paper introduces and analyses the performance of the Petri net model created to simulate a traffic control system using the Additive Increase Multiplicative Decrease (AIMD) algorithm. The Petri net model was designed using TimeNET [1] tool. The model was evaluated by analysing the Reachability Graph generated by a Depth First Search (DFS) and Backtracking based algorithm. Several criteria such as Stability, Boundedness, Deadlock, etc. were verified by our proposed algorithm. The model was then validated through a C++ code to ensure it performs correctly under different situations. All the related code, images, and tables used in this paper can be found at GitHub 1 Â© 2024 IEEE.
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
Synthesis and characteristics of Fe/Ni/Cr oxide nanoparticles/PLA hybrid composite coatings on Mg–Zn–Ca alloy
(Elsevier Editora Ltda, 2025) Kumar, P.; Kudva S, A.; T, A.; S, R.; Ramesh, M.R.; Prabhu, A.; Anne, G.
Biodegradable materials research is dominated by magnesium and alloys thereof due to their excellent compatibility with biological barriers and biomechanical strength. Despite this, the rapid degradation of these materials in the physiological environment is the primary obstacle hindering their utilization in biomedical applications. This issue must be resolved before considering their use in clinical applications. To improve resistance towards corrosion and enhance biological efficacy and compatibility, the surfaces were coated with polylactic acid (PLA) using dip-coating. In this study, iron (Fe), nickel (Ni), and chromium (Cr) oxide nanoparticles from the Coleus amboinicus extract are synthesized and mixed with PLA to develop hybrid composite coatings, which are then applied onto the Mg–4Zn–1Ca alloy. Coleus amboinicus is known for its various medicinal properties, including immunoregulatory effects, antimicrobial activity, anti-inflammatory properties, and potential use in treating sepsis and other ailments. The extracted FeNiCr was used the develop composite coatings on Mg–4Zn–1Ca alloy. The coating improves biocompatibility, antibacterial properties, and overall performance of biomedical implants. These composite coatings were evaluated for their morphological and optical characteristics using a scanning electron microscope (SEM), 3-D non-contact profilometer, Fourier transform infrared spectroscopy (FTIR), and X-ray diffraction (XRD). The corrosion characteristics of developed samples were measured by electrochemical corrosion in standard simulation body fluid (SBF) at 37 °C. Furthermore, cytocompatibility of the PLA hybrid composites on osteoblast cells and apoptosis detection using acridine orange-ethidium bromide. Our developed coating showed ratings of 5B and 4B were obtained for FeNiCr/PLA NC- ball burnished (BB) Mg and FeNiCr/PLA nano composite (NC)–Mg samples, respectively, demonstrating the exceptional coating strength and the substrate. The corrosion rate of the FeNiCr/PLA NC-BB-Mg sample (0.02890 mm/y) is two-fold times increased against comparison with the H Mg sample (0.00012 mm/y). Cytocompatibility indicates their cytocompatibility for bone implant applications. © 2025 The Authors
Synthesis, Molecular Docking, MD Simulation and Evaluation of Anticancer Activity of Novel 1,3,4-Oxadiazole Derivatives against Ehrlich Ascites Carcinoma (EAC) Cell Lines
(World Scientific, 2024) Deshpande, N.S.; Naik, S.; Udayakumar, U.; Prabhu, A.; Rani, V.; Dixit, S.R.; Singh, D.; Revanasiddappa, B.C.
In this study, a new series of 1,3,4-oxadiazole derivatives (3a- 3h) was synthesized, characterized using various analytical techniques (FT-IR, 1H- and 13C-NMR, mass spectrometry), and tested for their effectiveness against Ehrlich's Ascites Carcinoma (EAC) cell lines in vitro. After 48 h of exposure to these test compounds, the EAC cells exhibited a dose-dependent reduction in their viability. Among the tested compounds, 3b and 3e demonstrated the most potent anticancer effects, with IC50 values of 352.69 μM and 177.44 μ M, respectively. Consequently, these compounds were chosen for further investigation into their mechanisms of action on EAC cell lines. The assessment included the induction of apoptosis and the analysis of DNA damage, which were evaluated using fluorescence staining and the comet assay. These assessments revealed distinctive apoptotic characteristics such as nuclear fragmentation, cytoplasmic shrinkage and DNA damage. As a result, these compounds hold promise as potential anticancer agents. The study also delved into the binding affinities of these compounds through molecular docking analysis, and the findings showed that compounds 3b and 3e exhibited a strong binding affinity with the receptor Transforming Growth Factor-Beta Receptor I (TGF-βRI) kinase (PDB ID: 1PY5), surpassing the reference compound 5-fluorouracil. Additionally, calculations related to Molecular Mechanics Generalized Born Surface Area (MM-GBSA) indicated favorable free binding energy. The compounds also displayed acceptable ADMET properties. To validate the stability of the bond between compounds 3b and 3e with the 1PY5 receptor, a molecular dynamics simulation lasting 100 ns was carried out. © 2024 World Scientific Publishing Company.
Vision based laser controlled keyboard system for the disabled
(2014) Ahsan, H.; Prabhu, A.; Deeksha, S.D.; Domanal, S.G.; Ashwin, T.S.; Ram Mohana Reddy, Guddeti
In this paper, we have proposed a novel design for a vision based unistroke keyboard system for the disabled. The keyboard layout considers the commonly used character patterns, which makes it convenient for the user to type. In addition to this, Shift functionality is provided to accommodate a larger set of characters. A webcam is positioned so as to monitor the keyboard and the characters are identified based on the laser pointer which the user can control by minor head movements. Experimental results demonstrate that the design achieves very promising results, thus establishing a baseline for such models in this domain. Copyright 2014 ACM.
Vision based laser controlled keyboard system for the disabled
(Association for Computing Machinery, 2014) Ahsan, H.; Prabhu, A.; Deeksha, S.D.; Domanal, S.G.; Ashwin, T.S.; Guddeti, G.R.M.
In this paper, we have proposed a novel design for a vision based unistroke keyboard system for the disabled. The keyboard layout considers the commonly used character patterns, which makes it convenient for the user to type. In addition to this, Shift functionality is provided to accommodate a larger set of characters. A webcam is positioned so as to monitor the keyboard and the characters are identified based on the laser pointer which the user can control by minor head movements. Experimental results demonstrate that the design achieves very promising results, thus establishing a baseline for such models in this domain. Â© 2014 ACM.