Krishna Juluru

• Research Director at Memorial Sloan Kettering Cancer Center

BACKGROUND: Imaging reports that consistently document all disease sites with potential to increase surgical complexity or morbidity can facilitate ovarian cancer treatment planning. OBJECTIVES: To compare simple structured reports and synoptic reports for pre-treatment CT examinations in patients with advanced ovarian cancer in terms of completene...

Objectives: While fully supervised learning can yield high-performing segmentation models, the effort required to manually segment large training sets limits practical utility. We investigate whether data mined line annotations can facilitate brain MRI tumor segmentation model development without requiring manually segmented training data. Method...

A vascular lab procedure culminates in a diagnostic report that is a combination of the data generated on the vascular lab equipment, physician interpretations, and recommendations. The transcription process can be error prone and inefficient. Computerized capture of data from the equipment and transmission into a reporting system is the definition...

Radiological reports are a valuable source of information used to guide clinical care and support research. Organizing and managing this content, however, frequently requires several manual curations due to the more common unstructured nature of the reports. However, manual review of these reports for clinical knowledge extraction is costly and tim...

Background Artificial intelligence (AI) applications for cancer imaging conceptually begin with automated tumor detection, which can provide the foundation for downstream AI tasks. However, supervised training requires many image annotations, and performing dedicated post hoc image labeling is burdensome and costly. Purpose To investigate whether c...

Purpose: To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI. Materials and methods: In this retrospective study, 38 229 examinations (composed of 64 063 individual breast scans from 14 475 patients) were performed in female patients (age range, 12-94 years; mean age,...

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predic...

Purpose: Automatic localization of pneumonia on chest X‐rays (CXRs) is highly desirable both as an interpretive aid to the radiologist and for timely diagnosis of the disease. However, pneumonia's amorphous appearance on CXRs and complexity of normal anatomy in the chest present key challenges that hinder accurate localization. Existing studies in...

Natural language processing (NLP) is a methodology designed to extract concepts and meaning from human-generated unstructured (free-form) text. It is intended to be implemented by using computer algorithms so that it can be run on a corpus of documents quickly and reliably. To enable machine learning (ML) techniques in NLP, free-form text must be c...

Integration of artificial intelligence (AI) applications within clinical workflows is an important step for leveraging developed AI algorithms. In this report, generalizable components for deploying AI systems into clinical practice are described that were implemented in a clinical pilot study using lymphoscintigraphy examinations as a prospective...

Purpose: Immune checkpoint inhibition (ICI) alone is not active in mismatch repair-proficient (MMR-P) metastatic colorectal cancer (mCRC), nor does radiotherapy (RT) alone result in objective systemic benefit. However, combined RT plus ICI can induce systemic anti-tumor immunity in pre-clinical and clinical models. Experimental design: In this s...

‘Federated Learning’ (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the data thus removing many barriers to data sharing. During the SARS-COV-2 pandemic, 20 institutes collaborated on a healthcare FL study to predict future oxygen requirements of infected patients using i...

Cancer-associated venous thromboembolism (CAT) is a well-described complication of cancer and a leading cause of death in cancer patients. The purpose of this study was to assess potential associations of molecular signatures with CAT, including tumor-specific mutations and the presence of clonal hematopoiesis. We analyzed deep-coverage targeted DN...

Purpose: The goal of this research was to develop a deep network architecture that achieves fully-automated radiologist-level segmentation of breast tumors in MRI. Materials and Methods: We leveraged 38,229 clinical MRI breast exams collected retrospectively from women aged 12-94 (mean age 54) who presented between 2002 and 2014 at a single clinica...

Cancer-associated venous thromboembolism (CAT) is a well-described complication of cancer and a leading cause of death in cancer patients. The purpose of this study was to assess potential associations of molecular signatures with CAT, including tumor-specific mutations and the presence of clonal hematopoiesis. We analyzed deep-coverage targeted DN...

Purpose Starting from a broad-based needs assessment and utilizing an image analysis algorithm (IAA) developed at our institution, the purpose of this study was to define generalizable building blocks necessary for the integration of any IAA into a clinical practice. Methods An IAA was developed in our institution to process lymphoscintigraphy exam...

Background: The intestinal microbiota contributes to the pathogenesis of obesity and metabolic disorders. People living with HIV (PLWH) have a higher risk for the development of visceral adiposity with accompanying worsened cardiovascular risk. Setting: Convenience sample from an HIV clinic and research unit. Methods: To understand the relatio...

Background: Cancer-associated thrombosis (CAT) is a leading cause of death in cancer patients after cancer itself. Risk factors for CAT include tumor type/stage, body mass index (BMI), blood cell counts and chemotherapy exposure. These factors form the basis of prediction algorithms for CAT risk, including most notably the Khorana Risk Score. Howev...

Background Low‐molecular‐weight heparin has been the preferred treatment of cancer‐associated thrombosis (CAT); however, emerging data support the use of direct oral anticoagulants (DOACs). Objectives The Memorial Sloan Kettering Cancer Center Clinical Pathway has served as the institutional guideline for the use of rivaroxaban to treat CAT since...

Categorization of radiological images according to characteristics such as modality, scanner parameters, body part etc, is important for quality control, clinical efficiency and research. The metadata associated with images stored in the DICOM format reliably captures scanner settings such as tube current in CT or echo time (TE) in MRI. Other param...

Objective: Long indwelling times for inferior vena cava (IVC) filters that are used to prevent venous thromboembolism can result in complications. To improve care for patients receiving retrievable IVC filters, we developed and evaluated an informatics-based initiative to facilitate patient tracking, clinical decision-making, and care coordination...

Patients with asymptomatic kidney stones have a high rate of progression to becoming symptomatic kidney stones when followed for several years. Small kidney stones are often found incidentally on imaging when evaluating patients for kidney donation, and there is a concern that after nephrectomy, the donor may become symptomatic and incur damage to...

Background and objectives Pre-operative kidney volume is an independent predictor of glomerular filtration rate in renal cell carcinoma patients. Compensatory renal growth (CRG) can ensue prior to nephrectomy in parallel to tumor growth and benign parenchyma loss. We aimed to test whether renal metabolite abundances significantly associate with CRG...

Purpose To investigate the associations between BRCA mutation status and computed tomography (CT) phenotypes of high-grade serous ovarian cancer (HGSOC) and to evaluate CT indicators of cytoreductive outcome and survival in patients with BRCA-mutant HGSOC and those with BRCA wild-type HGSOC. Materials and Methods This HIPAA-compliant, institutional...

Objective: We implemented an Image Quality Reporting and Tracking Solution (IQuaRTS), directly linked from the PACS, to improve communication between radiologists and technologists. Materials and methods: IQuaRTS launched in May 2015. We compared MRI issues filed in the period before IQuaRTS implementation (May-September 2014) using a manual sys...

446 Background: Pre-operative kidney volume is an independent predictor of glomerular filtration rate in renal cell carcinoma patients. Compensatory renal growth (CRG) can ensue prior to nephrectomy in parallel to tumor growth and benign parenchyma loss. We aimed to test whether renal metabolite abundances significantly associate with CRG, suggesti...

Purpose: To assess the diagnostic accuracy of intracellular uptake rates (Ki ), and other quantitative pharmacokinetic (PK) parameters, for hepatic fibrosis stage; to compare this accuracy with a previously published semiquantitative metric, contrast enhancement index (CEI); and to assess variability of these parameters between liver regions. Mat...

Rationale and objectives: We sought to determine if lung densities derived from computed tomography scans could be used to identify patients with pulmonary venous hypertension (Group II pulmonary hypertension [PH]), and to compare the performance of this metric with previously described metrics. Materials and methods: Patients were retrospective...

Pathologic evaluation of breast specimens requires a fixation and staining procedure of at least 12 hours duration, delaying diagnosis and post-operative planning. Here we introduce an MRI technique with a custom-designed radiofrequency resonator for imaging breast and lymph tissue with sufficient spatial resolution and speed to guide pathologic in...

Successful research results from the combination of multiple elements, including an appropriate research question, study design, research method, statistical analysis, and interpretation of results. One element of research that is easy to overlook is proper data collection and preparation for analysis. If data collection or preparation is inadequat...

The purpose of this study was to assess the use of semiautomated CT-based quantification of renal graft volume as a preoperative predictor of graft function. All transplants over a 3-year period in which donors underwent CT and for which recipient outcomes were available were included. Two blinded readers used a commercially available reconstructio...

Rationale and Objectives: The primary role of radiology in the preclinical setting is the use of imaging to improve students' understanding of anatomy. Many currently available Web-based anatomy programs include either suboptimal or overwhelming levels of detail for medical students. Our objective was to develop a user-friendly software program tha...

A radiology teaching file (TF) is a system containing a collection of cases with teaching value. Given the wide variety of TF solutions available, we conducted a national survey to better understand the need for TFs, TF features desired by users and their current implementation. A 28-question survey was created which explored TF implementation, uti...

The purpose of this study is to assess the variance and error in nodule diameter measurement associated with variations in nodule-slice position in cross-sectional imaging. A computer program utilizing a standard geometric model was used to simulate theoretical slices through a perfectly spherical nodule of known size, position, and density within...

To assess the correlation of quantitative ultrasound strain parameters with the severity of cortical edema in renal vein occlusion, we prospectively performed ultrasound strain elastography on a canine acute renal vein occlusion model prior to, and following 10, 20, and 40 minutes of renal vein ligation. Strain and strain relaxation time representi...

Objective: Three-dimensional and multiplanar reconstruction of CT images has become routine in diagnostic imaging. The technology also facilitates surface reconstruction, in which facial features and, as a result, patient identity may be recognized, leading to risk of violations of patient privacy rights. The purpose of this study was to assess wh...

Unlabelled: Substantial evidence has linked ionizing radiation exposure (RE) to oncogenesis. Patients evaluated for transplantation undergo extensive diagnostic imaging and have increased baseline cancer risk factors. The objective was to examine exposure in a cohort of patients undergoing evaluation and liver transplantation. Radiation exposure f...

LEARNING OBJECTIVES 1) Learn how easy it is to install the new and improved RSNA teaching file software with the one-click installer. 2) Learn how to create, organize, and share teaching files, create conference documents and save interesting cases for yourself, your group or your department.

LEARNING OBJECTIVES 1) Learn the features of the RSNA’s MIRC software for teaching files. 2) Learn how to download and install the software. 3) Learn to use the RSNA MIRC Wiki to obtain documentation on the software.

Objectives: To quantitatively assess the correlation between the corticomedullary strain ratio and cortical fibrosis in renal transplants. Methods: Using quasistatic ultrasound elasticity imaging, we prospectively assessed the corticomedullary strain ratio in renal allografts of 33 patients who underwent renal transplant sonography and biopsy. B...

Background and purpose: There is a desire within many institutions to reduce the radiation dose in CTP examinations. The purpose of this study was to simulate dose reduction through the addition of noise in brain CT perfusion examinations and to determine the subsequent effects on quality and quantitative interpretation. Materials and methods: A...

Current generations of graduate students have been immersed in technology from their early school years and have high expectations regarding digital resources. To better meet the expectations of Gross Anatomy students at our institution, electronic radiology teaching files for first-year coursework were organized into a web site. The web site was c...

LEARNING OBJECTIVES 1) Discuss key elements that should be present in any teaching file system. 2) Understand how RSNA's freely-available teaching file system, known as MIRC, can be used to create, store, present, and distribute educational content in use-cases such as day-to-day resident education and board review. ABSTRACT RSNA supports a freely...

LEARNING OBJECTIVES 1) Articulate the main objectives of each of the RSNA-sponsored informatics projects. 2) Identify the practical problems being addressed by each project. 3) Understand the relationships between these informatics projects. ABSTRACT The RSNA has created a library of consensus report templates that contain reusable structured data...

PURPOSE/AIM To present and review the creation and distribution of feature-rich educational content for radiology using a recently introduced publishing tool known as iBooks Author, by Apple, Inc. CONTENT ORGANIZATION iBooks Author is a free application created by Apple, Inc. that allows users to create multi-touch textbooks for the iPad that are...

BACKGROUND The Annotation and Image Mark-up (AIM) project is a National Cancer Institute initiative that provides a standardized, semantically interoperable information model for image annotation and markup. Using this model, characteristics of an image, such as the size of a lesion, are recorded in a standardized manner. A powerful aspect of AIM i...

PURPOSE The Apple iPAD is a tablet computing platform that combines a high-resolution screen, camera, microphone, wireless internet access, and powerful processor. Since its introduction, there has been much interest in the use of this technology for visualization of radiographic images. As the feature set of DICOM viewers available for iPAD mature...

Image de-identification has focused on the removal of textual protected health information (PHI). Surface reconstructions of the face have the potential to reveal a subject's identity even when textual PHI is absent. This study assessed the ability of a computer application to match research subjects' 3D facial reconstructions with conventional pho...

This paper presents an algorithm for the automatic detection of intravenous contrast in CT scans. This is useful e.g. for quality control, given the unreliability of the existing DICOM contrast metadata. The algorithm is based on a hybrid discriminative-generative probabilistic model. A discriminative detector localizes enhancing regions of intere...

When using a clinical outcome reference standards, angiography, VQ scan, non-multidetector computed tomography (MDCT) pulmonary angiography, MDCT pulmonary angiography, and electron beam computed tomography (EBCT), are all associated with negative predictive values of 94% or greater for diagnosing pulmonary embolism (PE). Differences in negative pr...

Post-processing of volumetric data sets lands in a fuzzy boundary between the technologist and the radiologist. Is this the role of the technologist as part of image preparation? Or is it the beginning of the diagnostic process by the radiologist? Technology advances in real-time server side rendering platforms is challenging the traditional role o...

PURPOSE Imaging research repositories exist both within an institution and nationally, such as the National Biomedical Imaging Archive (NBIA). To facilitate distribution of data, protected health information (PHI) must be removed. PHI embedded not within the metadata, but within the image itself, is a problem that is increasingly being recognized a...

LEARNING OBJECTIVES 1) Unique challenges in obtaining imaging data for research within a clinical environment. 2) Potential benefits and problems associated with establishing a dedicated research PACS. 3) Present some commercially available and home-grown tools that can be utilized to manage workflow. ABSTRACT Acquiring, storing, and distributing...

Gadolinium based contrast agents (GBCAs) have been linked to nephrogenic systemic fibrosis (NSF) in patients with severe renal dysfunction. This article reviews strategies to prevent this condition in patients at risk. These include administering only single dose GBCA, scheduling MRI for just before the next routine dialysis in dialysis patients, d...

onography is a widely used modality for the evaluation of transplanted kidneys. It is portable, fast, and noninvasive, and the superficial location of the renal transplant in the iliac fossa is ideal for sonographic imaging. Sonography can be used to evaluate the renal parenchyma, collecting system, and peritransplant regions as well as to guide pe...

The purpose of this study was to assess the implementation of a digital anatomy lecture series based largely on annotated, radiographic images and the utility of the Radiological Society of North America-developed Medical Imaging Resource Center (MIRC) for providing an online educational resource. A series of digital teaching images were collected...

BACKGROUND Research involving radiographic data must respect Protected Health Information (PHI), which includes patient name, medical record number, date of birth, and other items. There exist tools, such as RSNA's MIRC, that can be configured to accept DICOM data and anonymize metadata elements. These, however, do not remove PHI embedded within im...

LEARNING OBJECTIVES 1) Learn how to use the RSNA teaching file software to create, organize, and share teaching files, create conference documents and save interesting cases. SCHEDULE DATE TIME COURSE Tuesday, 12/1 12:30 PM - 2:00 PM IW32

PURPOSE The iPhone is a mobile communications device with a multi-touch display interface. There has been a steady growth in the number of applications available for download, including many relevant to medicine. There is a need and interest to explore these applications in aggregate. In this study, we perform a basic systematic review of all medic...

Hepatocellular carcinoma (liver tumor) is one of the most common malignancies causing an estimated one million deaths annually, and the fastest growing form of cancer in the United States. Dynamic Contrast Enhanced MRI (DCE-MRI) is a useful way to characterize tumor response to contrast agent uptake, but the method still lacks maturity in terms of...

Nephrogenic systemic fibrosis (NSF) is a rare but potentially debilitating or even fatal fibrosing condition that most often affects the skin but is now also recognized to involve multiple organs. The first report on NSF was published in 1997, and there is mounting evidence that this condition is associated with renal failure and the administration...

CONCLUSION The growing use of imaging data for research and the increasing size of imaging datasets presents a heightened risk for disclosure of PII. Our study demonstrates that an automatic computer tool can serve as an important check against the accidental disclosure of PII that is embedded in images. BACKGROUND Storage of imaging datasets in a...

LEARNING OBJECTIVES 1) To demonstrate the use of MIRC in various conference settings, including unknown case conference held by both residents and faculty. 2) To highlight the ability to index keywords for fast retrieval of related material, both documents and cases submitted by multiple users. 3) To review future directions in MIRC development for...

PURPOSE/AIM 1.To describe the history, clinical features, and pathophysiology of NSF 2.To outline the risk factors for development of NSF in the context of MRI 3.To present both contrast and non-contrast techniques to more safely obtain images of diagnostic quality 4. To review our institutional policies on obtaining MRI scans in high risk patients...

Knee-related injuries, including meniscal tears, are common in young athletes and require accurate diagnosis and appropriate surgical intervention. Although with proper technique and skill, confidence in the detection of meniscal tears should be high, this task continues to be a challenge for many inexperienced radiologists. The purpose of our stud...

3D and multi-planar reconstruction of CT images have become indispensable in the routine practice of diagnostic imaging. These tools cannot only enhance our ability to diagnose diseases, but can also assist in therapeutic planning as well. The technology utilized to create these can also render surface reconstructions, which may have the undesired...

Over the past decade, several computerized tools have been developed for detection of lung nodules and for providing volumetric analysis. Incidentally detected lung nodules have traditionally been followed over time by measurements of their axial dimensions on CT scans to ensure stability or document progression. A recently published article by the...

LEARNING OBJECTIVES 1) To demonstrate the use of MIRC in various conference settings,including unknown case conference held by both residents and faculty. 2) To highlight the ability to index keywords for fast retrieval of related material, both documents and cases submitted by multiple users. 3) To review future directions in MIRC development for...

PURPOSE To understand how handheld 3D navigation device (Teistler et al., infoRAD, 2004) is used differently than conventional mouse device during interpretation of routine thin slice multi-detector CT examinations METHOD AND MATERIALS Six radiologists alternatively interpreted 10 anonymized MDCT chest, abdomen and pelvis examinations using the ha...

Objective: Our aim was to develop a simple, low-cost, Internet-based application for radiology order-entry, reporting, and workflow management during off-hours. Conclusion: The system was quickly accepted by users both within and outside the radiology department, and it required very modest resources to develop, deploy, and support. In a busy on...

LEARNING OBJECTIVES 1.To describe the limitations of current imaging techniques in evaluating cardiac muscle viability2.To describe MR techniques and to assess the role of cardiac MRI in preoperative planning for Dor procedure3.To review MR findings and quantitative data on left ventricular structure and function to assess outcomes after coronary r...

Gastrointestinal stromal tumors (GISTs) are mesenchymal tumors that typically arise in association with the muscularis propria of gastrointestinal (GI) tract wall. They occur most frequently in the stomach (60%) but also can occur in the small bowel (30%) or elsewhere, including the colon and rectum (5%) and esophagus (<5%). In addition, a GIST may...

The purpose of this study was to determine whether transcatheter arterial chemoembolization (TACE) protocol affects the total volume of chemotherapy injected into the liver as well as subsequent arterial patency. A total of 160 patients with primary or secondary liver cancer were treated with 3 different chemoembolization protocols at a single inst...

The increased intra-abdominal pressure (IAP) commonly observed when the spine is loaded during physical activities is hypothesized to increase lumbar spine stability. The mechanical stability of the lumbar spine is an important consideration in low back injury prevention and rehabilitation strategies. This study examined the effects of raised IAP a...

Currently, intra-abdominal pressure (IAP) is thought to provide stability to the lumbar spine but the exact principles have yet to be specified. A simplified physical model was constructed and theoretical calculations performed to illustrate a possible intra-abdominal pressure mechanism for stabilizing the spine. The model consisted of an inverted...

PURPOSE/AIM For most medical students, their first exposure to Radiology occurs in Gross Anatomy. The primary goal in this setting is to use imaging to teach anatomy and normal studies with labels help achieve this goal. While multiple web-based anatomy programs exist, the level of detail is often beyond the appropriate scope for a medical student....

BACKGROUND The National Library of Medicine Insight Segmentation and Registration Toolkit (ITK) is an open-source software system developed in collaboration between industry and academia for support of the Visible Human Project. Broad goals include establishing a foundation for future research and instantiation of a platform for advanced product de...