Browsing by Author "Sumit Tripathi"

Now showing 1 - 7 of 7

Automatic segmentation of brain tumour in MR images using an enhanced deep learning approach
(Taylor and Francis Ltd., 2021) Sumit Tripathi; Ashish Verma; Neeraj Sharma
The presented manuscript proposes a fully automatic deep learning method to quantify the tumour region in brain Magnetic Resonance images as the accurate diagnosis of brain tumour region is necessary for the treatment of the patients. The irregular and confusing boundaries of tumours regions make it a challenging task to accurately figure out such regions. Another challenge with the segmentation task is of preserving the boundary details of the segmented tumour regions. The proposed network focuses on delineating the irregular tumour region as the best feature maps are learnt by the network, which is used for decoding; thus, it preserves the accurate boundary and pixel details. The proposed method incorporates internal residual connections in encoder and decoder to transfer feature maps directly to the successive layers to avoid loss of information contained in the images. The use of cross channel normalization (CCN) and parametric rectified linear unit (PRELU) gives a more balanced network output. The trained network produced remarkable results when tested on images of other datasets. Further, external clinical validation was performed by comparison of the algorithmic segmented images with those generated by a manual segmentation done by an experienced radiologist. We have termed our network as CCN-PR-Seg-net. © 2020 Informa UK Limited, trading as Taylor & Francis Group.
Conservation Agriculture for Soil Health and Carbon Sequestration in the Indian Himalayan Region
(Springer Singapore, 2023) Ashish Rai; Sumit Tripathi; Ayush Bahuguna; Sumit Rai; Jitendra Rajput; Anshu Gangwar; Rajeev Kumar Srivastava; Arvind Kumar Singh; Satish Kumar Singh; Dibyanshu Shekhar; Rahul Mishra; Eetela Sathyanarayana; Supriya Pandey
Mountains the most significant agro-ecosystems that directly or indirectly support human life. The areas surrounding the hills are abundant in biodiversity and have enormous potential for sustaining Indian agriculture. It has been widely recognised that the ecological fragility and sensitivity of the Himalayas to climatic aberrations, topography, peculiar geographical features, and some of the particular identified problems, which may be soil loss, runoff, steep slopes, acidity of soils, and loss of soil nutrients, form it a very distinct region as opposed to plains in terms of socioeconomic situation. Conventional agriculture was one of the best aspects of food production during the green revolution and after India gained its independence for securing food and nutrition through intensive agricultural practices, but on the flip side, it has simultaneous effects on resource degradation and soil biodiversity. The need for food and fodder, an ever-growing population, the preservation of soil biodiversity, declining soil health, climate change, the use of unbalanced fertilisers, and decreased farm profitability all call for a paradigm shift in the agriculture sector. On the other hand, increasing the intensity of the hillside agriculture system without implementing any conservation measures greatly increases the likelihood of disastrous conditions. Conservation agriculture has long been known to improve soil health and sustain agricultural production systems by reducing environmental footprints. Between the atmosphere and the lithosphere, numerous biological and physical processes are regulated by soils. An integral aspect of soil that promotes agricultural sustainability is soil health. However, each measurement of a specific soil health parameter is always tied to a unique set of circumstances. A fundamental concern in maintaining soil health to feed an expanding population is resource conservation. Climate change is a topic of discussion on a worldwide scale in the current globalisation context. The greenhouse effect is best for life but only up to a point beyond which it becomes dangerous. Due to urbanisation, changes in land use, cropping patterns, and other factors, human influences on climate change go beyond the range of natural fluctuation. Climate change in the soil system is significantly influenced by carbon regulation in the soil. The rate of organic matter decomposition is accelerated by an increase in mean annual temperature, which affects aggregate stability, water storage capacity, and nutrient balance— all of which are crucial for healthy soil structure, soil fertility, productivity, and sustainability. In actuality, soil bacteria break down organic materials, but a change in temperature regime may change the microbial population. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.
DEEP ENSEMBLE METHODS for IDENTIFICATION of MALICIOUS TISSUES in NOISY BREAST HISTOPATHOLOGICAL IMAGES
(World Scientific, 2025) Sumit Tripathi; Neeraj Sharma
This work addresses the issues of noise and tissue appearance fluctuations in histopathology image classification by using a novel deep ensemble method. The experiment's images were inherently noisy; however, the proposed approach includes features that allow for noise to be effectively encountered while classification tasks are being completed. This integration streamlines the categorization process by eliminating the requirement for a separate denoising phase. This approach encompasses studies on two types of noise, namely Gaussian and Rician, both commonly encountered in histopathological images. Remarkably, our proposed model demonstrated effectiveness in handling both types of noise, yielding satisfactory performance across diverse noise conditions. The proposed ensemble model achieves an accuracy of 83.74%, an F1-score of 81.72%, an F2-score of 81.04%, and an MCC of 83.99% for the highest level of rician noise. The proposed approach improves classification resilience and accuracy by combining the output of several deep-learning models. It does this by increasing the F2-score for malignant classes by 3-5%, which helps to reduce False Negatives. This approach differs from current technology and has promising implications for the diagnosis and treatment of breast cancer. Compared to other approaches, our suggested model performs better at higher noise levels. LIME and saliency map integration improve the interpretability of model decisions, which in turn improves classification accuracy and decision clarity. These features emphasize the adaptability and resilience of the suggested method, highlighting it as a potential instrument for enhancing the results of breast cancer diagnosis and therapy in clinical settings. The workload for pathologists is lessened, and diagnostic consistency and accuracy are improved through automation of the classification process. © 2025 National Taiwan University.
DEEP ENSEMBLE METHODS for IDENTIFICATION of MALICIOUS TISSUES in NOISY BREAST HISTOPATHOLOGICAL IMAGES
(World Scientific, 2024) Sumit Tripathi; Neeraj Sharma
This work addresses the issues of noise and tissue appearance fluctuations in histopathology image classification by using a novel deep ensemble method. The experiment's images were inherently noisy; however, the proposed approach includes features that allow for noise to be effectively encountered while classification tasks are being completed. This integration streamlines the categorization process by eliminating the requirement for a separate denoising phase. This approach encompasses studies on two types of noise, namely Gaussian and Rician, both commonly encountered in histopathological images. Remarkably, our proposed model demonstrated effectiveness in handling both types of noise, yielding satisfactory performance across diverse noise conditions. The proposed ensemble model achieves an accuracy of 83.74%, an F1-score of 81.72%, an F2-score of 81.04%, and an MCC of 83.99% for the highest level of rician noise. The proposed approach improves classification resilience and accuracy by combining the output of several deep-learning models. It does this by increasing the F2-score for malignant classes by 3-5%, which helps to reduce False Negatives. This approach differs from current technology and has promising implications for the diagnosis and treatment of breast cancer. Compared to other approaches, our suggested model performs better at higher noise levels. LIME and saliency map integration improve the interpretability of model decisions, which in turn improves classification accuracy and decision clarity. These features emphasize the adaptability and resilience of the suggested method, highlighting it as a potential instrument for enhancing the results of breast cancer diagnosis and therapy in clinical settings. The workload for pathologists is lessened, and diagnostic consistency and accuracy are improved through automation of the classification process. © 2024 National Taiwan University.
Denoising of magnetic resonance images using discriminative learning-based deep convolutional neural network
(IOS Press BV, 2022) Sumit Tripathi; Neeraj Sharma
The noise in magnetic resonance (MR) images causes severe issues for medical diagnosis purposes. OBJECTIVE: In this paper, we propose a discriminative learning based convolutional neural network denoiser to denoise the MR image data contaminated with noise. METHODS: The proposed method incorporates the use of depthwise separable convolution along with local response normalization with modified hyperparameters and internal skip connections to denoise the contaminated MR images. Moreover, the addition of parametric RELU instead of normal conventional RELU in our proposed architecture gives more stable and fine results. The denoised images were further segmented to test the appropriateness of the results. The network is trained on one dataset and tested on other dataset produces remarkably good results. RESULTS: Our proposed network was used to denoise the images of different noise levels, and it yields better performance as compared with various networks. The SSIM and PSNR showed an average improvement of (7.2 ± 0.002) % and (8.5 ± 0.25) % respectively when tested on different datasets without retaining the network. An improvement of 5% and 6% was achieved in the values of mean intersection over union (mIoU) and BF score when the denoised images were segmented for testing the relevancy in biomedical imaging applications. The statistical test suggests that the obtained results are statistically significant as p< 0.05. CONCLUSION: The denoised images obtained are more clinically suitable for medical image diagnosis purposes, as depicted by the evaluation parameters. Further, external clinical validation was performed by an experienced radiologist for testing the validation of the resulting images. © 2022 - IOS Press. All rights reserved.
Detection of COVID-19 Infection in CT and X-ray images using transfer learning approach
(IOS Press BV, 2022) Alok Tiwari; Sumit Tripathi; Dinesh Chandra Pandey; Neeraj Sharma; Shiru Sharma
BACKGROUND: The infection caused by the SARS-CoV-2 (COVID-19) pandemic is a threat to human lives. An early and accurate diagnosis is necessary for treatment. OBJECTIVE: The study presents an efficient classification methodology for precise identification of infection caused by COVID-19 using CT and X-ray images. METHODS: The depthwise separable convolution-based model of MobileNet V2 was exploited for feature extraction. The features of infection were supplied to the SVM classifier for training which produced accurate classification results. RESULT: The accuracies for CT and X-ray images are 99.42% and 98.54% respectively. The MCC score was used to avoid any mislead caused by accuracy and F1 score as it is more mathematically balanced metric. The MCC scores obtained for CT and X-ray were 0.9852 and 0.9657, respectively. The Youden's index showed a significant improvement of more than 2% for both imaging techniques. CONCLUSION: The proposed transfer learning-based approach obtained the best results for all evaluation metrics and produced reliable results for the accurate identification of COVID-19 symptoms. This study can help in reducing the time in diagnosis of the infection. © 2022 - IOS Press. All rights reserved.
Effect of Ni and Fe Co-Application on the Soybean Crop Grown in Nickel and Iron Deficient Soils of Mirzapur District
(Taylor and Francis Ltd., 2024) Ayush Bahuguna; Satish Kumar Singh; Astha Pandey; Sachin Sharma; Surajyoti Pradhan; Arvind; Munesh Kumar Shukla; Prem Kumar Bharteey; Sayon Mukherjee; Sumit Tripathi; Pavan Singh
Considering the importance of nickel and iron nutrition for the soybean crop, their deficiency inhibits the yield drastically specially in the area where soybean crop is dominant. To encounter this problem, a pot experiment was conducted in glass house on low nickel and iron soil in Department of Soil Science and Agricultural Chemistry, Institute of Agricultural Sciences, Banaras Hindu University, Varanasi, during 2019–20 and 2021–22. The study was carried out to investigate the effect of Ni (nickel) and Fe (iron) on the post-harvest soil parameters, growth, yield, nutrient uptake and nutrient content of soybean crop. There were 10 treatments with two levels of Ni (5 and 10 mg kg −1) and Fe (10 and 20 mg kg−1) with recommended dosage of fertilizers nitrogen, phosphorus, potassium (8.93, 35.71, and 17.86 mg kg−1) applied to all treatments except control. The result of the experiment revealed that the co-application of nickel and iron@10 mg kg−1 and 20 mg kg−1 (RDF + Ni10Fe20), resulted in the increase in plant height, greeness index, no of seed per pod, no of pod per plant, seed yield, and stover yield. Similar, findings for the post- harvest soil parameter indicated that there was increase in pH, electrical conductivity, and organic carbon content of soil. DTPA (Diethylenetriaminepentaacetic acid) extractable Ni, Fe, Zn, and Cu, also found highest in treatment where nickel and iron@10 mg kg−1 and 20 mg kg−1 (RDF + Ni10Fe20) were applied in soil, but in case of DTPA extractable Mn, the highest amount was found in treatment where nickel and iron@10 mg kg−1 and 10 mg kg−1 (RDF + Ni10Fe10) was applied in soil. The soil microbial biomass carbon and urease activity was also found highest in the treatment where nickel and iron@10 and 20 mg kg−1 was applied in soil. The minimum plant height, greeness index, no of seed per pod, no of pod per plant, seed, and stover yield was recorded in treatment where only RDF(T1) was applied. Similar, result recorded for the post-harvest soil parameters. So, overall findings of the pot experiment revealed that the conjoint application of nickel and iron has resulted in better yield of soybean crop. © 2024 Taylor & Francis Group, LLC.