Khandelwal, Ashish

Abstract Renal tumors are highly heterogeneous, ranging from benign lesions and indolent renal cell carcinoma (RCC) to highly aggressive phenotypes. Accurately determining tumor aggressiveness before treatment remains a major clinical challenge. Conventional MR imaging lacks sensitivity to microarchitectural differences underlying tumor biology, and biopsy is limited by sampling error and tumor heterogeneity. Radiomics offers a noninvasive approach to extract high dimensional features that may capture biologically relevant patterns. In this IRB-approved retrospective study, we evaluated MR-based radiomics combined with machine learning (ML) to differentiate indolent from aggressive tumors. Pre-operative clinically acquired MR images obtained from eighty-two RCC patients (aggressive, n = 56; indolent, n = 26) who underwent nephrectomy were included for the analysis. Regions of interest (ROIs) of the entire tumor were manually drawn using 3D Slicer on the morphological T2-weighted images and four phases (pre-contrast [PRE], corticomedullary [CM], nephrographic [NG], and delayed [DEL]) from the contrast-enhanced MR images, normalized, and used for radiomic feature extraction (PyRadiomics, v3.1.0). Independently, tumors were grouped into aggressive and indolent phenotypes based on the established histological classification of Mayo Clinic. Statistical analysis used two-sided t-test. Features selected based on mutual information were used for ML classification (Random Under-Sampling Boosting (RUSBoost)) and performance assessed using accuracy, sensitivity, precision, specificity, F1-score, and area under the curve (AUC). Of 107 radiomics features extracted, the following numbers showed statistically significant differences between aggressive and indolent tumors (p < 0.05): CM phase (n = 19), NG phase (n = 24), DEL phase (n = 22), and T2-weighted images (n = 29). Several features consistently differed among contrast-enhanced images and included first-order (length, surface area, volume), GLCM (correlation, IDM, IMC1, IMC2), GLDM (dependence entropy, dependence non-uniformity, dependence variance), GLRLM (gray-level non-uniformity, run entropy, run-length non-uniformity), GLSZM (high gray-level emphasis, zone entropy), and NGTDM (coarseness). Using the 15 features with highest mutual information across 50 patients (aggressive, n = 31; indolent, n = 19), a five-fold cross-validation RUSBoost classifier achieved accuracy 0.81, sensitivity 0.84, precision 0.87, specificity 0.77, F1-score 0.85, and AUC 0.80 for identifying the aggressive phenotype. MRI radiomics features show potential to differentiate aggressive from indolent renal tumors. ML-based classification using these features demonstrates promising accuracy. Further optimization and validation in larger cohorts, may help guide individualized care, including consideration of active surveillance for indolent renal tumors. Citation Format: Huan Lu, Salim Rukhsar, Xueqing Yin, Garima Suman, Ashish Khandelwal, Ananth J. Madhuranthakam, Durga Udayakumar. MRI radiomic features to differentiate aggressive and indolent renal tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 2142.

Alcohol use disorder (AUD) is a preventable non-communicable disease that affects multiple organs and organ systems across all age groups, including the fetus and is a risk factor for developing certain cancers. Furthermore, alcohol intoxication can result in physical trauma to oneself and others, and is a contributing factor in road accidents. Early recognition of AUD is critical for improving diagnosis, management, and outcomes. Accurate diagnosis relies on comprehensive clinical evaluation and patient history. However, denial of AUD, inebriation, and lack of awareness of problems associated with AUD, can prevent early identification of the disease. AUD-associated organ damage manifests in several ways and can be recognized on imaging modalities including ultrasound, CT, and MRI. Detection of these imaging features is useful in raising suspicion of AUD or diagnosing chronic alcohol use. Radiologists should be aware of the manifestations of alcohol's effects across various organ systems and aid in the early detection and treatment of AUD. In this two-part review, the authors present a comprehensive image-based review illustrating the effects of AUD on different organ systems at various stages. This second part focuses on the imaging manifestations in the central nervous system, fetal health, cardiovascular system, and musculoskeletal system. Additionally, a brief overview of secondary imaging manifestations of alcohol use, associated with trauma and cancers, will be presented.

Alcohol use disorder (AUD) is a significant public health challenge, affecting multiple organs and organ systems, and fetal health. Additionally, AUD also significantly contributes to self-harm and road accidents. Beyond its health effects, AUD creates economic and political challenges, including escalating treatment costs and the complex alcohol regulation policies. Despite global impact, AUD remains under-addressed in countries like India due to cultural norms and limited resources. Early recognition of AUD is vital for better outcomes, relying on thorough clinical evaluation and patient history. However, denial, inebriation, or lack of awareness often delays diagnosis. Imaging techniques like ultrasound, CT, and MRI effectively depict AUD-related organ damage and aid in detecting chronic alcohol use. Radiologists play a crucial role in identifying these manifestations, contributing to its early detection and treatment. This review article highlights the imaging of alcohol use related disorders and diseases affecting different organs and organ systems at various stages. The review is presented in two parts: the first focuses on alcohol burden, alcohol metabolism and toxicity, and imaging findings of AUD-related abdominal diseases and disorders.

This review examines the applications and challenges of large language models (LLMs), like OpenAI’s ChatGPT, in radiology research. ChatGPT can assist radiology researchers in generating new ideas, finding and summarizing research papers, designing studies, analyzing data, and facilitating manuscript writing. LLMs are powerful tools with numerous applications in radiology research. However, users should be mindful of potential pitfalls, such as producing incorrect or biased outputs and inconsistent responses, along with ethical and privacy concerns. We discuss approaches to optimize models and address these issues, including prompting techniques like chain-of-thought prompting, retrieval-augmented generation, and fine-tuning. For researchers, prompt engineering can be particularly effective. This review seeks to demonstrate how researchers can utilize ChatGPT for radiology research while offering strategies to mitigate associated risks. We aim to help researchers harness these potent tools to safely boost their productivity.

Abstract Incidental findings in diagnostic imaging are common, but follow-up recommendations often lack consistency. The Society of Radiologists in Ultrasound (SRU) issued guidelines in 2021 for managing incidentally detected gallbladder polyps, aiming to balance follow-up with avoiding overtreatment. There is variable adherence to these guidelines in radiology reports, however, which makes it difficult for the clinician to pursue appropriate follow-up for the patient. The purpose of this project is to test the feasibility of a Large Language Model (LLM)–based tool to incorporate SRU guidelines into radiology reports. Additionally, we propose a framework for closely integrating societal follow-up recommendations into radiology reports, using this tool as an example. Following institutional review board approval, we retrospectively reviewed gallbladder ultrasound examinations performed on adult ED patients in 2022. Data on patient demographics and radiology report content were collected. Using the 2021 SRU guidelines, we developed an interactive tool employing a retriever-augmented generator (RAG) and prompt engineering. A board-certified radiologist tested the accuracy, whereas a board-certified emergency medicine physician assessed the clarity and consistency of the recommendations. The interactive tool, GB-PRL, outperformed leading closed-source and open-source LLMs, achieving 100% accuracy in risk categorization and follow-up recommendations on hypothetical user queries (P < 0.001). The tool also showed superior accuracy compared to radiology reports on retrospective data (P = 0.04). Although GB-PRL demonstrated greater clarity and consistency, the improvement from the radiology reports was not statistically significant (P = 0.22). Further work is needed for prospective testing of GB-PRL before integrating it into clinical practice.

To retrospectively evaluate the trends in utilization and results of computed tomography pulmonary angiography (CTPA study) for detection of acute pulmonary embolism (PE) in the hospital inpatients during different phases of COVID-19 public health emergency. We conducted an Institutional Review Board (IRB)-approved retrospective review of CTPA studies for our hospital inpatients in the years from 2019 to 2023, ranging from the prepandemic year (2019) to the year coinciding with the end of public health declarations (2023). Collected characteristics included patient age, patient sex, and result of the study. The utilization of CTPA studies for inpatients was higher in 2020 to 2023, compared to 2019 (3.8% in 2023 compared to 2.4% in 2019, P < .001). The increase in utilization was also statistically significant in each group, when stratified by age and sex (OR = 1.46 for female, OR = 1.71 for male, OR = 1.93 for elderly, and OR = 1.29 for non-elderly inpatients in 2023, compared to 2019). The positivity rate of acute PE in the inpatients was overall higher in 2021, 2022, and 2023, compared to 2019 (for example, 18.5% in 2023 compared to 14.3% in 2019, P = .01). When stratified by age and sex, only the non-elderly patients continued to have a significantly higher rate of acute PE in 2023, compared to 2019 (OR = 1.39). While studies spanning longer time frames and involving multiple institutions are needed to understand and generalize this conclusion, we conclude that the utilization and positivity rates of CTPA studies in inpatients remains high at the end of the COVID-19 pandemic public health emergency.

Background Dual-energy virtual monoenergetic images can increase iodine signal, potentially increasing the conspicuity of hepatic masses. Purpose To determine if dual-energy 50-keV virtual monoenergetic images improve visualization of key imaging findings or diagnostic confidence for small (≤2 cm) hepatocellular carcinomas (HCC) at multiphase, contrast-enhanced liver computed tomography (CT). Material and Methods Patients with chronic liver disease underwent multiphase dual-energy CT imaging for HCC, with late arterial and delayed phase dual-energy 50-keV images reconstructed. Two non-reader subspecialized gastrointestinal (GI) radiologists established the reference standard, determining the location and diagnosis of all hepatic lesions using predetermined criteria. Three GI radiologists interpreted mixed kV CT images without or with dual-energy 50-keV images. Radiologists identified potential HCCs and rated their confidence (0–100 scales) in imaging findings of arterial enhancement, enhancing capsule, tumor washout, and LI-RADS 5 (2018) category. Results In total, 45 patients (14 women; mean age = 59.5 ± 10.9 years) with chronic liver disease were included. Of them, 19 patients had 25 HCCs ≤2 cm (mean size = 1.5 ± 0.4 cm). There were 17 LI-RADS 3 and 4 lesions and 19 benign lesions. Reader confidence in imaging findings of arterial enhancement, enhancing capsule, and non-peripheral washout significantly increased with dual-energy images ( P ≤ 0.022). Overall confidence in HCC diagnosis increased significantly with dual-energy 50-keV images (52.4 vs. 68.8; P = 0.001). Dual-energy images demonstrated a slight but significant decrease in overall image quality. Conclusion Radiologist confidence in key imaging features of small HCCs and confidence in imaging diagnosis increases with use of dual-energy 50-keV images at multiphase, contrast-enhanced liver CT.

Background Low tube potential-high tube current computed tomography (CT) imaging allows reduction in iodine-based contrast dose and may extend the benefit of routine contrast-enhanced CT exams to patients at risk of nephrotoxicity. Purpose To determine the ability of an iodine contrast reduction algorithm to maintain diagnostic image quality for contrast-enhanced abdominal CT. Material and Methods CT exams with iodine contrast reduction were prescribed for patients at risk for renal dysfunction. The iodine contrast reduction algorithm combines weight-based contrast volume reduction with patient width-based low tube potential selection and bolus-tracking. Control exams with routine iodine dose were selected based on weight, width, and scan protocol. Three radiologists evaluated image quality and diagnostic confidence using a 4-point scale (<2 acceptable). Another radiologist assessed contrast reduction indications and measured portal vein and liver contrast-to-noise ratios. Results Forty-six contrast reduction algorithm and control exams were compared (mean creatinine 1.6 vs. 1.2 mg/dL, P ≤ 0.0001). Thirty-nine contrast reduction patients had an eGFR <60 mL/min/1.73m 2 and 15 had single or transplanted kidney. Mean iodine contrast dose was lower in the contrast reduction group (20.9 vs. 39.4 g/mL, P < 0.0001). Diagnostic confidence was rated as acceptable in 95% (131/138) of contrast reduction and 100% of control exams (1.18–1.28 vs. 1.02–1.13, respectively; P > 0.06). Liver attenuation and contrast-to-noise ratio (CNR) were similar ( P = 0.08), but portal vein attenuation and CNR were lower with contrast-reduction (mean 176 vs. 198 HU, P = 0.02; 13 vs. 16, P = 0.0002). Conclusion This size-based contrast reduction algorithm using low kV and bolus tracking reduced iodine contrast dose by 50%, while achieving acceptable image quality in 95% of exams.