RGRajesh Gupta

Rajesh Gupta

*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


Rajesh Gupta has a total of 254 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Machine Learning Models for Predicting Response to Percutaneous Transhepatic Biliary Drainage in Malignant Obstructive Jaundice: A Retrospective Cohort Study

    by Pankaj Gupta, Sonali Thakur, Abhinandan Kumar, Abhirup Chatterji, Anupam Kumar, Vaneet Jearth, Jimil Shah, Jayanta Samanta, Harshal Mandavdhare, Vishal Sharma, et al.

  • ConLymphNet: A Generalizable Region-Constrained Deep Learning Architecture for Precise Abdominal Lymph Node Segmentation Across Cancer Types.

    by Pankaj Gupta, Shubham Saini, Anjali Aggarwal, Ajay Gulati, Shraddha Patkar, Niharika Dutta, Sakshi Jeswani, Lovleen Kakkar, Kartik Bose, Gaurav Prakash, et al.

    Accurate identification and segmentation of abdominal lymph nodes on computed tomography (CT) is crucial for cancer staging and treatment planning but remains a challenging and time-consuming radiologic task. We developed and validated ConLymphNet, a deep learning-based approach for automated abdominal lymph node segmentation using vertebral landmarks as anatomic reference points to standardize the region of interest. We implemented a novel preprocessing pipeline incorporating vertebral landmark-based region selection followed by a 3D nnUNet segmentation model. The model was trained on 481 contrast-enhanced CT scans from patients with gallbladder cancer (GBC) and validated on external data sets including GBC (n = 54), public lymph node (n = 81), and multicancer data sets (n = 606). Performance was compared with three radiologists of varying experience levels. Interobserver agreement among radiologists and the incremental value of artificial intelligence (AI)-assisted reading were also assessed. To support reproducibility and future research, we also contribute 45 expert-verified lymph node segmentations for cases from public multicancer data sets. ConLymphNet achieved mean Dice coefficients of 0.696 ± 0.179, 0.631 ± 0.187, and 0.639 ± 0.176 and low false-positive rates of 0.78 ± 0.35, 0.81 ± 0.33, 0.93 ± 0.47/volume on internal cross-validation, external GBC, and public lymph node data sets, respectively. Performance varied by lymph node location (P = .0080) and size (P = .0444), with larger nodes yielding better results. The model's detection rate (89.6%) was comparable with experienced residents (89.2%) but with reduced processing time (28.7 ± 12.4s v 165.3 ± 47.8 s). AI assistance improved radiologists' performance significantly, particularly for less experienced readers (detection rate +20.2%, segmentation accuracy +13.0%, P < .001), while reducing false positives by 33.3%. ConLymphNet demonstrates reasonable performance across diverse cancer types and imaging protocols, offering segmentation accuracy comparable with radiologists with substantially faster processing times.

  • Prospective observational study on the impact of hepatic steatosis, hepatic fibrosis, and metabolic syndrome on the outcome of patients with acute pancreatitis

    by Abhirup Chatterjee, Surinder Singh Rana, Vaneet Jearth, Ajay Duseja, Jimil Shah, Mandeep Kang, Kamal Kishore, Rajesh Gupta

  • Pancreatic schwannoma: a diagnostic dilemma of pancreatic head tumour

    by Himanshu Gupta, Ds Darshanik, Pankaj Gupta, Ritambara Nada, Surinder S Rana, Rajesh Gupta

    Pancreatic schwannoma is usually a benign neoplasm presenting with non-specific symptoms, and preoperative diagnosis is often difficult to establish. The imaging features can overlap from benign cystic lesions to ductal adenocarcinomas. Diagnosis is mainly histological with characteristic microscopic appearance (aggregates of spindle-shaped cells) and immunostaining (positive for S100 and SOX-10) suggestive of a peripheral nerve sheath tumour. Due to diagnostic ambiguity, surgical resection is often mandated. We present a case of a female patient in her sixth decade of life presenting with symptoms pointing towards a malignant pancreatic head tumour. She underwent formal pancreatoduodenectomy, which on histopathological examination was diagnosed as a schwannoma.


  • CT-based multimodal prediction model for chemotherapy response in gallbladder cancer: integration of imaging and clinical biomarkers—a prospective pilot study

    by Kritika Sharma, Pankaj Gupta, Ajay Gulati, Niharika Dutta, Divya Khosla, Gaurav Prakash, Thakur Yadav, Lileswar Kaman, Santosh Irrinki, Harjeet Singh, et al.

    Background Gallbladder carcinoma (GBC) is an aggressive malignancy with poor prognosis, often diagnosed at advanced stages. While chemotherapy forms the cornerstone of treatment for locally advanced and metastatic disease, reliable predictors of response remain elusive. This exploratory pilot study aimed to develop a computed tomography (CT)-based prediction model incorporating clinical and biochemical parameters to identify patients likely to respond to chemotherapy. Methods This prospective study enrolled consecutive treatment-naïve patients with cytologically/histologically proven locally advanced or metastatic GBC scheduled for chemotherapy between July 2023 and March 2025. All patients underwent biphasic contrast-enhanced CT within 14 days prior to chemotherapy initiation. Demographic variables, biochemical parameters, and tumor markers (CA 19 − 9, CEA) were systematically recorded. CT-based response assessment was performed using RECIST 1.1 criteria after two cycles of chemotherapy. Three exploratory prediction models were developed using logistic regression with appropriate variable selection methods and penalized regression to address small sample size. Results Of 25 patients (18 females, mean age 50.0 ± 11.6), 11 (44%) achieved partial response while 14 (56%) were non-responders (stable or progressive disease). Univariate analysis identified calculus presence (p = 0.002), largest liver metastasis size (p = 0.001), ascites (p = 0.008), age (p = 0.128), ALT (p = 0.241), and CEA levels (p = 0.123) as potential predictors. After correction for optimism using bootstrap validation, the CT-only model achieved area under the receiver operating characteristic curve (AUC) of 0.82 (95% CI: 0.64–0.92) with 80.0% accuracy, 92.3% sensitivity, and 62.5% specificity (Nagelkerke R²=0.272). The clinical-only model yielded optimism-corrected AUC of 0.74 (95% CI: 0.51–0.88) with 68.0% accuracy, 71.4% sensitivity, and 63.6% specificity (Nagelkerke R²=0.424). The combined model showed better performance with optimism-corrected AUC of 0.85 (95% CI: 0.67–0.95), 84.0% accuracy, 85.7% sensitivity, 81.8% specificity, and highest explained variance (Nagelkerke R²=0.662). Gallstone presence emerged as a potential predictor associated with treatment response across models, while larger liver lesions and elevated CEA showed trends that may be associated with poor response. Conclusions This preliminary hypothesis-generating study suggests that integration of baseline CT imaging features with clinical parameters may potentially allow prediction of chemotherapy response in GBC patients. The identified factors require external validation in larger multi-institutional cohorts before clinical implementation can be considered.

  • Open Access

    Potential of circulating miR-6875 and miR-1307 as non-invasive diagnostic biomarkers for pancreatic cancer

    by Vinit Sharma, Ankita Semwal, Shivangani Lohani, Ankita Arora, Sakshi Bansal, Mayank Sharma, Rajesh Gupta, Harjeet Singh, Anjali Aggarwal

    Aim Pancreatic cancer (PC) is marked by high mortality and resistance to conventional therapies, largely due to a dense desmoplastic stroma that promotes drug resistance and metastasis. This highlights the need for specific non-invasive diagnostic markers. MicroRNAs (miRNAs), known for regulating gene expression and influencing tumor behavior, have emerged as promising biomarkers. This study aimed to evaluate the expression of circulating miR-6875 and miR-1307 in PC patients to explore their diagnostic potential. Methods Blood, urine, and saliva samples were collected from 20 PC patients and 12 healthy controls. RNA extraction and cDNA synthesis were performed following standard protocols, and quantitative real-time PCR assays were used to quantify miR-6875 and miR-1307 expression levels. Statistical analysis was performed to predict their diagnostic potential and association with clinical and biochemical parameters of PC patients. Results Our results revealed significantly elevated levels of miR-6875 and miR-1307 in plasma, urine samples, and saliva samples from PC patients compared to controls. Receiver operating characteristic (ROC) curve analysis demonstrated the potential of miR-6875 and miR-1307 in plasma as diagnostic biomarkers for PC, with AUC values of 0.79 and 0.83, respectively. Conclusion Plasma levels of miR-6875 and miR-1307 show potential as non-invasive diagnostic biomarkers for pancreatic cancer.

  • Gastric leiomyosarcoma mimicking hepatocellular carcinoma

    by Himanshu Gupta, Ds Darshanik, Ritambara Nada, Pankaj Gupta, Surinder S Rana, Rajesh Gupta

    Gastric leiomyosarcoma is an extremely rare malignancy with an aggressive course. Complete excision of the tumour with adjuvant therapy is a curative option. The patient presents with non-specific upper gastrointestinal symptoms. Preoperative biopsy and immunostaining with endoscopic ultrasound guidance is the most accurate tool for diagnosis. We present here a case of a middle-aged man, presenting with upper abdominal heaviness and a lump which progressed rapidly in size over a few weeks, associated with appetite and weight loss. Radiographic evaluation was suggestive of a large tumour of the left lobe of the liver, possibly hepatocellular carcinoma, due to raised protein induced by vitamin K absence-II levels. Intraoperatively, it turned out to be of gastric origin, in relation to the liver.

  • Nonsuperiority of Simultaneous Compared With Sequential Interventions in Infected Necrotic Collections at Multiple Sites in Acute Necrotizing Pancreatitis: A Randomized Trial

    by Bikkina Venkat Siddharda, Jimil Shah, Pankaj Gupta, Harish Bhujade, Sanish Ancil, Vaneet Jearth, Anupam K. Singh, Harshal S. Mandavdhare, Vishal Sharma, Yashwant Raj Sakaray, et al.

    Background: Patients with infected pancreatic necrosis (IPN) may need multiple interventions when the necrotic collection is multifocal. However, the efficacy of simultaneous interventions has not been compared with sequential interventions in this group of patients.Methods: We performed a single‐center, open‐label, superiority, randomized trial at a tertiary‐level hospital to compare simultaneous versus sequential intervention of infected necrotic collections involving at least two anatomical sites. In the simultaneous group (Group A), all sites were drained simultaneously. In the sequential group (Group B), only the largest site or the site with gas foci was drained initially. Additional interventions in either group were done based on predefined clinical criteria. The primary outcome was the Comprehensive Complication Index (CCI) until clinical success or death. Secondary outcomes were the number of interventions, major disease‐related complications, and mortality. An intention‐to‐treat analysis was performed.Results: We assessed 253 patients for eligibility, and 60 patients were enrolled (29 in Group A and 31 in Group B). The mean age was 36.9 ± 13.4 years. The mean CCI was similar among both groups (72.5 ± 28.3 vs. 64.4 ± 34.9; 95% CI, −24.59 to 8.39). The number of interventions in Group B was significantly lower (4.17 ± 2.00 vs. 2.97 ± 1.94; 95% CI, −0.18 to −2.22). Development of new‐onset organ failure (34.5% vs. 38.7%), need for surgical intervention (27.5% vs. 22.5%), and mortality (41.3% vs. 38.7%) were not significantly different between the groups.Conclusion: A simultaneous intervention approach aimed at draining multiple sites is not superior to a sequential intervention approach guided by clinical outcomes in patients with IPN involving multiple sites.Trial Registration: CTRI identifier: CTRI/2022/07/04387


  • Open Access

    Real-World Evidence of Porto-Mesenteric Vein Resections with Pancreatectomy and the Development of Predictive Clinical Nomograms for Postoperative Outcomes—An Analysis of 389 Cases: The “Porto-Mesenteric Vein Resection-Indian MulticentrE” (PRIME) Study

    by Deeksha Kapoor, Manish S. Bhandare, Agam Sharma, Raja Kalayarasan, Monish Karunakaran, Sree Kumar Balasubramanian, Aishwarya Pal, Nagaraj Palankar, D. S. Darshanik, Subhash Soni, et al.

    Background: With better surgery and chemotherapeutic agents, borderline resectable or locally advanced pancreatobiliary tumours are being treated with curative intent. This study presents real-world evidence of porto-mesenteric vein resections (PVR) with pancreatectomy and generates predictive nomograms for postoperative mortality (POM) and major complications (MC). Methods: A retrospective multicentre study, including 11 high-volume centres, evaluated patients undergoing PVR. Factors affecting 90-day POM and MC (Clavien-Dindo grades ≥ 3a) were assessed, and predictive nomograms were generated. Overall survival (OS) and disease-free survival (DFS) were estimated for patients with pancreatic ductal adenocarcinoma (PDAC). Cox regression analysis was performed to ascertain factors affecting OS and DFS. Results: Among 389 patients, POM was 6.4%, and MCs were 32.6%. Charlson comorbidity index > 4, preoperative biliary drainage, preoperative radiotherapy (PRT), segmental PVR, and additional organ resection (AOR) were predictive of POM. The independent predictors of MCs were American Society of Anesthesiologists status 3/4, PRT, and AOR. The generated model had an area under the curve (AUC) of 0.757, cutoff > 1.79 to predict POM, and AUC of 0.669, cutoff > 0.678 for MCs. In the 263 patients with PDAC, the median OS was 25.01 months (95% confidence interval [CI] 21.9–28.11), and DFS was 16.72 months (95% CI 14.56–18.89). Perineural invasion, segmental PVR, and margin positivity predicted worse survival, while completing multi-modality treatment was protective. Conclusions: The POM and MCs of PVR with pancreatectomy were at par with the world standards. The generated predictive nomograms for POM and MC revealed a good predictive potential. In patients with PDAC, completion of multimodality treatment offers better long-term survival.


  • Radiological signature of HER2-Positive gallbladder cancer: analysis of CT features

    by Pankaj Gupta, Niharika Dutta, Shravya Singh, Nikita Pradhan, Ruby Siddiqui, Ajay Gulati, Naveen Kalra, Gaurav Prakash, Thakur Yadav, Lileswar Kaman, et al.

    Objective This study aimed to identify distinctive computed tomography (CT) features associated with human epidermal growth factor receptor 2 (HER2) status in gallbladder cancer (GBC) that could serve as noninvasive imaging biomarkers. Materials and methods This study included 213 patients with pathologically confirmed GBCs with availability of HER2 status (171 HER2-negative, 42 HER2-positive). Pre-treatment contrast-enhanced CT scans were evaluated by two radiologists blinded to HER2 status. Multivariate analysis was performed using logistic regression with L2 regularization. Model discrimination was assessed using receiver operating characteristic (ROC) analysis, and internal validation was performed using bootstrap resampling (1,000 iterations) to correct for optimism. Results HER2-positive tumors exhibited larger lymph nodes (1.93 ± 0.79 cm vs. 1.61 ± 0.61 cm, p = 0.015), less frequent gallstones (14.3% vs. 35.7%, p = 0.013), arterial phase hyperenhancement (20.0% vs. 44.1%, p = 0.026), mass-like morphology (35.7% vs. 55.6%, p = 0.033), and more frequent biliary compression by lymph nodes (19.0% vs. 4.1%, p = 0.002). Multivariate analysis identified biliary compression by lymph nodes as the strongest positive predictor of HER2 positivity [odds ratio (OR) 2.99, 95% CI: 1.25–7.04], while arterial phase hyperenhancement (OR 0.40, 95% CI: 0.19–0.75), gallstone presence (OR 0.40, 95% CI: 0.18–0.75), and mass-like morphology (OR 0.54, 95% CI: 0.29–0.95) were significant negative predictors. The model demonstrated good discrimination (area under the ROC curve 0.782) with sensitivity 75%, specificity 79.4%, and negative predictive value 96.2%. Conclusion HER2-positive GBCs display characteristic CT findings that can be utilized for noninvasive diagnosis with robust predictive performance.