CSChigurupati Ravi Swaroop

Chigurupati Ravi Swaroop

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Chigurupati Ravi Swaroop has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A unified imaging-to-pharmacology AI framework for pulmonary nodule detection, malignancy classification, and mutation-stratified drug validation from low-dose CT scans

    by Reddy Shiva Shankar, Nakka Deshai, Chigurupati Ravi Swaroop, Kankanala Amrutha

    Background: Low-dose computed tomography (CT) screening for lung cancer can impose a substantial and clinically under-recognised psychosocial burden, with published studies reporting clinically significant anxiety among 30%–45% of screen-positive individuals, driven by a 96.4% benign false-positive rate and prolonged diagnostic uncertainty. Chronic distress may activate the hypothalamic–pituitary–adrenal axis and contribute to catecholamine-driven β2-adrenergic–epidermal growth factor receptor transactivation. Methods: We present PulmoNet-X, a unified deep learning framework that integrates a six-module imaging backbone with three psychosomatic burden-reduction mechanisms: false-positive reduction module (FPRM), uncertainty-calibrated risk stratification (UCRS), and integrated drug validation and therapeutic drug recommendation (IDVTRM). The framework was evaluated on the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) benchmark comprising 888 CT scans and 1,004 annotated nodules using 10-fold cross-validation. Results: PulmoNet-X achieved 98.1% nodule-detection sensitivity at one false-positive/scan (competition performance metric = 93.7%), malignancy classification area under the curve (AUC) = 97.8%, segmentation Dice similarity coefficient (DSC) = 84.6%, and Lung Imaging Reporting and Data System agreement κ = 0.87 on LIDC-IDRI. FPRM reduced false-positive detections from 4.8 to 1.0 per scan, corresponding to a modelled estimate of approximately 380 fewer unnecessary recall investigations per 1,000 patients screened. UCRS achieved a calibration error of 0.016 (expected calibration error). IDVTRM attained a mutation-stratified drug-response AUC of 0.918 and lung-tissue penetration prediction (R2 = 0.986), with 94.2% concordance with independent expert oncologist assessment. All primary pairwise comparisons were statistically significant (two-sided Wilcoxon signed-rank test, p < 0.001, Bonferroni-corrected for six comparisons). Conclusion: External validation on 150 independent National Institutes of Health Chest CT scans provided preliminary evidence supporting generalisability beyond LIDC-IDRI (sensitivity = 98.1%, AUC = 99.3%, DSC = 95.8%, κ = 0.94). Reported psychosomatic benefits remain mechanistically grounded hypotheses; validated psychometric instruments, including the Generalised Anxiety Disorder 7-item scale, Patient Health Questionnaire-9, and Hospital Anxiety and Depression Scale, were not administered. The pharmacological prediction component remains exploratory, and the incremental contribution of imaging features to drug-response prediction has not been established. Prospective, multi-centre validation is required before clinical translation. PulmoNet-X demonstrates the feasibility of incorporating psychosomatic burden reduction as an explicit architectural objective alongside imaging and pharmacological modelling. Relevance for patients: PulmoNet-X is designed to reduce unnecessary recalls, screening anxiety, and diagnostic uncertainty by providing calibrated cancer risk estimates and personalised treatment guidance.

  • Open Access

    Methodology for eliminating plain regions from captured images

    by Shiva Shankar Reddy, Vuddagiri Mnssvkr. Gupta, Lokavarapu V. Srinivas, Chigurupati Ravi Swaroop

    Finding relevant content and extracting information from images is highly significant. Still, it may be challenging to do so because of changes within the textual contents, such as typefaces, size, line orientation, sophisticated backgrounds in images, and non-uniform illuminations. Despite these challenges, extracting content from captured images is still very important. Proficient textual content image recognition abilities extract text from the images to get over these issues. Despite the availability of several optical character recognition (OCR) techniques, this issue has yet to be resolved. Captured images with text are a rich source of information that should be presented so that viewers may make informed decisions. Because of this, it has become a complicated process to extract the text from an image because the text might be of poor quality, has a variety of fonts and styles, and occasionally have a complicated backdrop, among other things. Several approaches have been tried. However, finding a solution remains challenging. The maximally stable external regions (MSER) approach is developed to identify the text region in a picture. MSER is utilized to elevate the plain regions outside the text and non-text areas using geometric features and stroke width variation qualities.


  • Open Access

    Evaluation of deep learning models for melanoma image classification

    by Shiva Shankar Reddy, Vetukuri Venkata Siva Rama Raju, Chigurupati Ravi Swaroop, Neelima Pilli

    Melanin-producing cells are the origin of melanoma, the worst form of skin cancer (Melanocytes). If this cancer is not caught early, it might spread to other organs. With automated diagnostic technologies, clinicians and non- professionals may better diagnose diseases. Dermoscopic analysis, biopsy, and histological tests may be needed starting with a clinical assessment. Photo-based skin lesion categorization is challenging due to the fine-grained variability of skin lesions. We provide a more reliable melanoma detection model for each suspicious lesion in this paper. A set of characteristics characterizing a skin lesion's borders, texture, and coloursis used to educate convolutional neural networks. The deep learning models were generated using a standard dataset. To know the model's performance, consider the metrics like accuracy, sensitivity, specificity, Jaccard index and Dice coefficient. Transfer learning is used to categorize normal and diseased skin pictures automatically. This model-driven design helps doctors swiftly assess lesions.


  • Open Access

    An extensible framework for recurrent breast cancer prognosis using deep learning techniques

    by Reddy Shiva Shankar, Ravi Swaroop Chigurupati, Priyadarshini Voosala, Neelima Pilli

    Due to population growth, early illness detection is getting more challenging. Breast cancer is the second-deadliest malignancy. An estimated one million people are newly diagnosed with the disease annually in India. Most cases are never diagnosed because they are either ignored or not reported. Also, secondary malignancies may develop after a breast cancer recurrence, including those of the brain, lungs, and bones. Early detection and treatment of people with recurring breast cancer may help prevent secondary cancers and other disorders. By examining cell and tumour data as well as data from other diseases, this project hopes to overcome this obstacle and more accurately diagnose breast cancer. Accurate diagnosis of breast cancer may be achieved with the use of machine learning techniques. The effort focuses on recurring breast cancer and aims to efficiently identify it. In ensemble learning, decision trees filter out non-essential qualities. Cancer recurrences and non-recurrences are distinguished using voting classifiers. The soft voting classifier classifies a variety of data sets with 98.24% accuracy. The proposed model has an accuracy of 0.97, a recall of 0.97, an F1-Score of 0.969, and a Choen kappa score of 0.9655, as stated by the recommended model.


  • Open Access

    An approach to classify distraction driver detection system by using mining techniques

    by Reddy Shiva Shankar, Pilli Neelima, Voosala Priyadarshini, Swaroop Ravi Chigurupati

    According to the motor vehicle safety division, over the past 5-10 years, usage of motor vehicles has rapidly increased, in that specifical usage of cars has grown tremendously. The major contribution of this paper is a systematic evaluation of the scholarly literature on driver distraction detection techniques. Our driver distraction detection framework offers a systematic overview of evaluated methodologies for detecting driver attention. So, we need to develop a model that classifies each driver's behaviour and determines its corresponding class name. To overcome this dispute, we have attained an appreciable number of deep learning algorithms on the dataset like convolutional neural network (CNN) and VGG16 to detect what the driver is doing in the car as given in the driver images. This process can be done by predicting the likelihood of the driver's actions in each picture. Of all models, we distinguished that the VGG16 Algorithm has conquered CNN with a loss of 0.298 and an Accuracy of 91.7%.


  • Open Access

    A comparative study to predict breast cancer using machine learning techniques

    by Shiva Shankar Reddy, Neelima Pilli, Priyadarshini Voosala, Swaroop Ravi Chigurupati

    Detection of disease at the starting stage is a very crucial problem. As the population growth increases, the risk of death incurred by breast cancer rises exponentially. Breast cancer is the most common cancer in women, and it is also the most dangerous of all cancers. Deaths because of breast cancer have b een increasing in recent times. Earlier detection of the disease followed by treatment can reduce the risk and increase survival chances. There will be cases where even medical professionals can make mistakes in identifying the disease. This project deals with the detection of Breast cancer using the cell data of the tumor present in the breast. So, with the help of technologies in machine learning and artificial intelligence can substantially improve the diagnosis accuracy. The development of this project is beneficial in medical decision support systems. Several machine learning techniques, namely Adaboost, multi-layer perceptron (MLP) and stacking classifier; were used, and among all the algorithms, the stacking classifier results in the best accuracy. The accuracies 95.6%, 97.1%, and 99.2% respectively.