A Guideline for Open-Source Tools to Make Medical Imaging Data Ready for Artificial Intelligence Applications: A Society of Imaging Informatics in Medicine (SIIM) Survey.

In recent years, the role of Artificial Intelligence (AI) in medical imaging has become increasingly prominent, with the majority of AI applications approved by the FDA being in imaging and radiology in 2023. The surge in AI model development to tackle clinical challenges underscores the necessity for preparing high-quality medical imaging data. Proper data preparation is crucial as it fosters the creation of standardized and reproducible AI models while minimizing biases. Data curation transforms raw data into a valuable, organized, and dependable resource and is a fundamental process to the success of machine learning and analytical projects. Considering the plethora of available tools for data curation in different stages, it is crucial to stay informed about the most relevant tools within specific research areas. In the current work, we propose a descriptive outline for different steps of data curation while we furnish compilations of tools collected from a survey applied among members of the Society of Imaging Informatics (SIIM) for each of these stages. This collection has the potential to enhance the decision-making process for researchers as they select the most appropriate tool for their specific tasks.

Translation of AI into oncology clinical practice.

Artificial intelligence (AI) is a transformative technology that is capturing popular imagination and can revolutionize biomedicine. AI and machine learning (ML) algorithms have the potential to break through existing barriers in oncology research and practice such as automating workflow processes, personalizing care, and reducing healthcare disparities. Emerging applications of AI/ML in the literature include screening and early detection of cancer, disease diagnosis, response prediction, prognosis, and accelerated drug discovery. Despite this excitement, only few AI/ML models have been properly validated and fewer have become regulated products for routine clinical use. In this review, we highlight the main challenges impeding AI/ML clinical translation. We present different clinical use cases from the domains of radiology, radiation oncology, immunotherapy, and drug discovery in oncology. We dissect the unique challenges and opportunities associated with each of these cases. Finally, we summarize the general requirements for successful AI/ML implementation in the clinic, highlighting specific examples and points of emphasis including the importance of multidisciplinary collaboration of stakeholders, role of domain experts in AI augmentation, transparency of AI/ML models, and the establishment of a comprehensive quality assurance program to mitigate risks of training bias and data drifts, all culminating toward safer and more beneficial AI/ML applications in oncology labs and clinics.

A pilot study of volumetric and density tumor analysis of ACC patients treated with vorinostat in a phase II clinical trial.

Rationale and objectives: Adenoid cystic carcinoma (ACC) is a rare salivary gland cancer. The vast majority of clinical trials evaluating systemic therapy efficacy in solid tumors use the Response Evaluation Criteria in Solid Tumors (RECIST) to measure response that is limited to 2 dimensional only evaluations, not taking volume or density into account. The indolent behavior ACC represents a challenge toward an appropriate evaluation of therapy response. Objectives: 1) To describe and contrast volumetric and density changes at each time-point, including changes noted from baseline to best response, to currently used 2 dimensional-only criteria (RECIST) and 2) To report the coefficient of variation in volume measurement among three reviewers on a subset of ACC patients. Materials and methods: We retrospectively assessed a cohort of 18 prospectively treated patients with ACC in a phase 2 trial with vorinostat using a volumetric (viable tumor volume, VTV) and density criteria. Three independent and blinded observers segmented target lesions across a sample of randomly selected computed tomography (CT) exams to examine inter-observer variation. Results: We found that the average coefficient of variation among observers for all target lesions was 16.1%, with lung lesions displaying a smaller variation at 14.0% (p-value >0.17). We describe examples of decrease in volume and density in several lesions despite stable disease by RECIST. Conclusion: This pilot study demonstrates that two-dimensional criteria such as RECIST may not be the best criteria to assess response to therapy, especially with evolving tools within picture archiving and communication system (PACS) that can assess volumetric size, density and texture, however, this should be prospectively studied.

Annotations of Lung Abnormalities in Shenzhen Chest X-ray Dataset for Computer-Aided Screening of Pulmonary Diseases.

Developments in deep learning techniques have led to significant advances in automated abnormality detection in radiological images and paved the way for their potential use in computer-aided diagnosis (CAD) systems. However, the development of CAD systems for pulmonary tuberculosis (TB) diagnosis is hampered by the lack of training data that is of good visual and diagnostic quality, of sufficient size, variety, and, where relevant, containing fine region annotations. This study presents a collection of annotations/segmentations of pulmonary radiological manifestations that are consistent with TB in the publicly available and widely used Shenzhen chest X-ray (CXR) dataset made available by the U.S. National Library of Medicine and obtained via a research collaboration with No. 3. People's Hospital Shenzhen, China. The goal of releasing these annotations is to advance the state-of-the-art for image segmentation methods toward improving the performance of fine-grained segmentation of TB-consistent findings in digital Chest X-ray images. The annotation collection comprises the following: 1) annotation files in JSON (JavaScript Object Notation) format that indicate locations and shapes of 19 lung pattern abnormalities for 336 TB patients; 2) mask files saved in PNG format for each abnormality per TB patient; 3) a CSV (comma-separated values) file that summarizes lung abnormality types and numbers per TB patient. To the best of our knowledge, this is the first collection of pixel-level annotations of TB-consistent findings in CXRs. Dataset: https://data.lhncbc.nlm.nih.gov/public/Tuberculosis-Chest-X-ray-Datasets/Shenzhen-Hospital-CXR-Set/Annotations/index.html.

CT organ dose calculator size adaptive for pediatric and adult patients.

Background. Although computed tomography (CT) has played a critical role in medical care since its introduction in the 1970s, its potential long-term risk of adverse health effects has been of concern. It is crucial to accurately estimate the radiation dose delivered to the patient's critical organs to ensure the dose is As Low As Reasonably Achievable. However, organ-level dose calculation tools for pediatric and adult patients with various body sizes are rare. We extended the existing CT organ dose calculator, NCICT 1.0, which is based on reference-size phantoms, to include body size-specific pediatric and adult phantoms.Methods. We calculated body size-specific organ doses normalized to CTDIvolby using a library of 158 pediatric and 193 adult computational human phantoms with various body sizes combined with a Monte Carlo radiation transport code, MCNP6. We also created a library of generic tube current modulation (TCM) profiles for the phantom library using a ray-tracing algorithm and implemented them into organ dose calculations. We validated organ doses for the body size-specific phantoms using those calculated from ten abdominal CT patients. We also evaluated potential dosimetric errors caused by only using reference phantoms for patients with different body sizes.Results. Organ dose coefficients and TCM profiles for 351 pediatric and adult body size-specific phantoms were implemented into NCICT 2.0. The dose coefficients from the ten abdominal CT patients agreed with those from the program within 13%. The organ doses for the overweight phantoms were overestimated by over 80% when only reference size phantoms were used.Conclusion. We confirmed that the upgraded dose calculator NCICT 2.0 could substantially reduce potential dosimetric errors caused by using only reference size phantoms. The program should be useful for the radiology community to accurately monitor organ doses for pediatric and adult CT patients with various body sizes.

Interactive Multimedia Reporting Technical Considerations: HIMSS-SIIM Collaborative White Paper.

Despite technological advances in the analysis of digital images for medical consultations, many health information systems lack the ability to correlate textual descriptions of image findings linked to the actual images. Images and reports often reside in separate silos in the medical record throughout the process of image viewing, report authoring, and report consumption. Forward-thinking centers and early adopters have created interactive reports with multimedia elements and embedded hyperlinks in reports that connect the narrative text with the related source images and measurements. Most of these solutions rely on proprietary single-vendor systems for viewing and reporting in the absence of any encompassing industry standards to facilitate interoperability with the electronic health record (EHR) and other systems. International standards have enabled the digitization of image acquisition, storage, viewing, and structured reporting. These provide the foundation to discuss enhanced reporting. Lessons learned in the digital transformation of radiology and pathology can serve as a basis for interactive multimedia reporting (IMR) across image-centric medical specialties. This paper describes the standard-based infrastructure and communications to fulfill recently defined clinical requirements through a consensus from an international workgroup of multidisciplinary medical specialists, informaticists, and industry participants. These efforts have led toward the development of an Integrating the Healthcare Enterprise (IHE) profile that will serve as a foundation for interoperable interactive multimedia reporting.

GIMAP6 regulates autophagy, immune competence, and inflammation in mice and humans.

Inborn errors of immunity (IEIs) unveil regulatory pathways of human immunity. We describe a new IEI caused by mutations in the GTPase of the immune-associated protein 6 (GIMAP6) gene in patients with infections, lymphoproliferation, autoimmunity, and multiorgan vasculitis. Patients and Gimap6-/- mice show defects in autophagy, redox regulation, and polyunsaturated fatty acid (PUFA)-containing lipids. We find that GIMAP6 complexes with GABARAPL2 and GIMAP7 to regulate GTPase activity. Also, GIMAP6 is induced by IFN-γ and plays a critical role in antibacterial immunity. Finally, we observed that Gimap6-/- mice died prematurely from microangiopathic glomerulosclerosis most likely due to GIMAP6 deficiency in kidney endothelial cells.

DeBoNet: A deep bone suppression model ensemble to improve disease detection in chest radiographs.

Automatic detection of some pulmonary abnormalities using chest X-rays may be impacted adversely due to obscuring by bony structures like the ribs and the clavicles. Automated bone suppression methods would increase soft tissue visibility and enhance automated disease detection. We evaluate this hypothesis using a custom ensemble of convolutional neural network models, which we call DeBoNet, that suppresses bones in frontal CXRs. First, we train and evaluate variants of U-Nets, Feature Pyramid Networks, and other proposed custom models using a private collection of CXR images and their bone-suppressed counterparts. The DeBoNet, constructed using the top-3 performing models, outperformed the individual models in terms of peak signal-to-noise ratio (PSNR) (36.7977±1.6207), multi-scale structural similarity index measure (MS-SSIM) (0.9848±0.0073), and other metrics. Next, the best-performing bone-suppression model is applied to CXR images that are pooled from several sources, showing no abnormality and other findings consistent with COVID-19. The impact of bone suppression is demonstrated by evaluating the gain in performance in detecting pulmonary abnormality consistent with COVID-19 disease. We observe that the model trained on bone-suppressed CXRs (MCC: 0.9645, 95% confidence interval (0.9510, 0.9780)) significantly outperformed (p < 0.05) the model trained on non-bone-suppressed images (MCC: 0.7961, 95% confidence interval (0.7667, 0.8255)) in detecting findings consistent with COVID-19 indicating benefits derived from automatic bone suppression on disease classification. The code is available at https://github.com/sivaramakrishnan-rajaraman/Bone-Suppresion-Ensemble.

Detecting Tuberculosis-Consistent Findings in Lateral Chest X-Rays Using an Ensemble of CNNs and Vision Transformers.

Research on detecting Tuberculosis (TB) findings on chest radiographs (or Chest X-rays: CXR) using convolutional neural networks (CNNs) has demonstrated superior performance due to the emergence of publicly available, large-scale datasets with expert annotations and availability of scalable computational resources. However, these studies use only the frontal CXR projections, i.e., the posterior-anterior (PA), and the anterior-posterior (AP) views for analysis and decision-making. Lateral CXRs which are heretofore not studied help detect clinically suspected pulmonary TB, particularly in children. Further, Vision Transformers (ViTs) with built-in self-attention mechanisms have recently emerged as a viable alternative to the traditional CNNs. Although ViTs demonstrated notable performance in several medical image analysis tasks, potential limitations exist in terms of performance and computational efficiency, between the CNN and ViT models, necessitating a comprehensive analysis to select appropriate models for the problem under study. This study aims to detect TB-consistent findings in lateral CXRs by constructing an ensemble of the CNN and ViT models. Several models are trained on lateral CXR data extracted from two large public collections to transfer modality-specific knowledge and fine-tune them for detecting findings consistent with TB. We observed that the weighted averaging ensemble of the predictions of CNN and ViT models using the optimal weights computed with the Sequential Least-Squares Quadratic Programming method delivered significantly superior performance (MCC: 0.8136, 95% confidence intervals (CI): 0.7394, 0.8878, p < 0.05) compared to the individual models and other ensembles. We also interpreted the decisions of CNN and ViT models using class-selective relevance maps and attention maps, respectively, and combined them to highlight the discriminative image regions contributing to the final output. We observed that (i) the model accuracy is not related to disease region of interest (ROI) localization and (ii) the bitwise-AND of the heatmaps of the top-2-performing models delivered significantly superior ROI localization performance in terms of mean average precision [mAP@(0.1 0.6) = 0.1820, 95% CI: 0.0771,0.2869, p < 0.05], compared to other individual models and ensembles. The code is available at https://github.com/sivaramakrishnan-rajaraman/Ensemble-of-CNN-and-ViT-for-TB-detection-in-lateral-CXR.

Rethinking Clinical Trial Radiology Workflows and Student Training: Integrated Virtual Student Shadowing Experience, Education, and Evaluation.

There is consistent demand for clinical exposure from students interested in radiology; however, the COVID-19 pandemic resulted in fewer available options and limited student access to radiology departments. Additionally, there is increased demand for radiologists to manage more complex quantification in reports on patients enrolled in clinical trials. We present an online educational curriculum that addresses both of these gaps by virtually immersing students (radiology preprocessors, or RPs) into radiologists' workflows where they identify and measure target lesions in advance of radiologists, streamlining report quantification. RPs switched to remote work at the beginning of the COVID-19 pandemic in our National Institutes of Health (NIH). We accommodated them by transitioning our curriculum on cross-sectional anatomy and advanced PACS tools to a publicly available online curriculum. We describe collaborations between multiple academic research centers and industry through contributions of academic content to this curriculum. Further, we describe how we objectively assess educational effectiveness with cross-sectional anatomical quizzes and decreasing RP miss rates as they gain experience. Our RP curriculum generated significant interest evidenced by a dozen academic and research institutes providing online presentations including radiology modality basics and quantification in clinical trials. We report a decrease in RP miss rate percentage, including one virtual RP over a period of 1 year. Results reflect training effectiveness through decreased discrepancies with radiologist reports and improved tumor identification over time. We present our RP curriculum and multicenter experience as a pilot experience in a clinical trial research setting. Students are able to obtain useful clinical radiology experience in a virtual learning environment by immersing themselves into a clinical radiologist's workflow. At the same time, they help radiologists improve patient care with more valuable quantitative reports, previously shown to improve radiologist efficiency. Students identify and measure lesions in clinical trials before radiologists, and then review their reports for self-evaluation based on included measurements from the radiologists. We consider our virtual approach as a supplement to student education while providing a model for how artificial intelligence will improve patient care with more consistent quantification while improving radiologist efficiency.

Gamification in Radiology Training Module Developed During the Society for Imaging Informatics in Medicine Annual Meeting Hackathon.

The purpose of this manuscript is to report our experience in the 2021 SIIM Virtual Hackathon, where we developed a proof-of-concept of a radiology training module with elements of gamification. In the 50 h allotted in the hackathon, we proposed an idea, connected with colleagues from five different countries, and completed an operational proof-of-concept, which was demonstrated live at the hackathon showcase, competing with eight other teams. Our prototype involved participants annotating publicly available chest radiographs of patients with tuberculosis. We showed how we could give experience points to trainees based on annotation precision compared to ground truth radiologists' annotation, ranked in a live leaderboard. We believe that gamification elements could provide an engaging solution for radiology education. Our project was awarded first place out of eight participating hackathon teams.

Training Strategies for Radiology Deep Learning Models in Data-limited Scenarios.

Data-driven approaches have great potential to shape future practices in radiology. The most straightforward strategy to obtain clinically accurate models is to use large, well-curated and annotated datasets. However, patient privacy constraints, tedious annotation processes, and the limited availability of radiologists pose challenges to building such datasets. This review details model training strategies in scenarios with limited data, insufficiently labeled data, and/or limited expert resources. This review discusses strategies to enlarge the data sample, decrease the time burden of manual supervised labeling, adjust the neural network architecture to improve model performance, apply semisupervised approaches, and leverage efficiencies from pretrained models. Keywords: Computer-aided Detection/Diagnosis, Transfer Learning, Limited Annotated Data, Augmentation, Synthetic Data, Semisupervised Learning, Federated Learning, Few-Shot Learning, Class Imbalance.

Fatal autoimmune pneumonitis requiring bilobectomy and omental flap repair in a patient with autoimmune polyendocrinopathy-candidiasis-ectodermal dystrophy (APECED).

We present a severe case of progressive autoimmune pneumonitis requiring surgical intervention in a patient with the monogenic syndrome, autoimmune polyendocrinopathy-candidiasis-ectodermal dystrophy (APECED). APECED is caused by loss-of-function mutations in the autoimmune regulator (AIRE) gene, which lead to impaired central immune tolerance and autoimmune organ destruction including pneumonitis, an underrecognized, life-threatening complication. When clinicians evaluate patients with pneumonitis, recurrent mucosal candidiasis, and autoimmunity, APECED should be considered in the differential. Additionally, in patients with established APECED, a chest computed tomography is preferred to identify pneumonitis early on and to promptly initiate lymphocyte-directed immunomodulatory treatment, which can prevent irreversible lung destruction.

Collaborative Writing Projects: Set Yourself up for Success.

ABSTRACT: This article will review critical components for the successful completion of a multi-institution, multiauthor collaborative paper. Best practices for the creation and publication of a collaborative paper will be addressed.

Chest X-ray Bone Suppression for Improving Classification of Tuberculosis-Consistent Findings.

Chest X-rays (CXRs) are the most commonly performed diagnostic examination to detect cardiopulmonary abnormalities. However, the presence of bony structures such as ribs and clavicles can obscure subtle abnormalities, resulting in diagnostic errors. This study aims to build a deep learning (DL)-based bone suppression model that identifies and removes these occluding bony structures in frontal CXRs to assist in reducing errors in radiological interpretation, including DL workflows, related to detecting manifestations consistent with tuberculosis (TB). Several bone suppression models with various deep architectures are trained and optimized using the proposed combined loss function and their performances are evaluated in a cross-institutional test setting using several metrics such as mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and multiscale structural similarity measure (MS-SSIM). The best-performing model (ResNet-BS) (PSNR = 34.0678; MS-SSIM = 0.9828) is used to suppress bones in the publicly available Shenzhen and Montgomery TB CXR collections. A VGG-16 model is pretrained on a large collection of publicly available CXRs. The CXR-pretrained model is then fine-tuned individually on the non-bone-suppressed and bone-suppressed CXRs of Shenzhen and Montgomery TB CXR collections to classify them as showing normal lungs or TB manifestations. The performances of these models are compared using several performance metrics such as accuracy, the area under the curve (AUC), sensitivity, specificity, precision, F-score, and Matthews correlation coefficient (MCC), analyzed for statistical significance, and their predictions are qualitatively interpreted through class-selective relevance maps (CRMs). It is observed that the models trained on bone-suppressed CXRs (Shenzhen: AUC = 0.9535 ± 0.0186; Montgomery: AUC = 0.9635 ± 0.0106) significantly outperformed (p < 0.05) the models trained on the non-bone-suppressed CXRs (Shenzhen: AUC = 0.8991 ± 0.0268; Montgomery: AUC = 0.8567 ± 0.0870).. Models trained on bone-suppressed CXRs improved detection of TB-consistent findings and resulted in compact clustering of the data points in the feature space signifying that bone suppression improved the model sensitivity toward TB classification.

Multispecialty Enterprise Imaging Workgroup Consensus on Interactive Multimedia Reporting Current State and Road to the Future: HIMSS-SIIM Collaborative White Paper.

Diagnostic and evidential static image, video clip, and sound multimedia are captured during routine clinical care in cardiology, dermatology, ophthalmology, pathology, physiatry, radiation oncology, radiology, endoscopic procedural specialties, and other medical disciplines. Providers typically describe the multimedia findings in contemporaneous electronic health record clinical notes or associate a textual interpretative report. Visual communication aids commonly used to connect, synthesize, and supplement multimedia and descriptive text outside medicine remain technically challenging to integrate into patient care. Such beneficial interactive elements may include hyperlinks between text, multimedia elements, alphanumeric and geometric annotations, tables, graphs, timelines, diagrams, anatomic maps, and hyperlinks to external educational references that patients or provider consumers may find valuable. This HIMSS-SIIM Enterprise Imaging Community workgroup white paper outlines the current and desired clinical future state of interactive multimedia reporting (IMR). The workgroup adopted a consensus definition of IMR as "interactive medical documentation that combines clinical images, videos, sound, imaging metadata, and/or image annotations with text, typographic emphases, tables, graphs, event timelines, anatomic maps, hyperlinks, and/or educational resources to optimize communication between medical professionals, and between medical professionals and their patients." This white paper also serves as a precursor for future efforts toward solving technical issues impeding routine interactive multimedia report creation and ingestion into electronic health records.

Pulmonary Manifestations of GATA2 Deficiency.

BACKGROUND: GATA2 deficiency is a genetic disorder of hematopoiesis, lymphatics, and immunity caused by autosomal dominant or sporadic mutations in GATA2. The disease has a broad phenotype encompassing immunodeficiency, myelodysplasia, leukemia, and vascular or lymphatic dysfunction as well as prominent pulmonary manifestations. RESEARCH QUESTION: What are the pulmonary manifestations of GATA2 deficiency? STUDY DESIGN AND METHODS: A retrospective review was conducted of clinical medical records, diagnostic imaging, pulmonary pathologic specimens, and tests of pulmonary function. RESULTS: Of 124 patients (95 probands and 29 ascertained), the lung was affected in 56%. In addition to chronic infections, pulmonary alveolar proteinosis (11 probands) and pulmonary arterial hypertension (nine probands) were present. Thoracic CT imaging found small nodules in 54% (54 probands and 12 relatives), reticular infiltrates in 40% (45 probands and four relatives), paraseptal emphysema in 25% (30 probands and one relative), ground-glass opacities in 35% (41 probands and two relatives), consolidation in 21% (23 probands and two relatives), and a typical crazy-paving pattern in 7% (eight probands and no relatives). Nontuberculous mycobacteria were the most frequent organisms associated with chronic infection. Allogeneic hematopoietic stem cell transplantation successfully reversed myelodysplasia and immune deficiency and also improved pulmonary hypertension and pulmonary alveolar proteinosis in most patients. INTERPRETATION: GATA2 deficiency has prominent pulmonary manifestations. These clinical observations confirm the essential role of hematopoietic cells in many aspects of pulmonary function, including infections, alveolar proteinosis, and pulmonary hypertension, many of which precede the formal diagnosis, and many of which respond to stem cell transplantation.

Improved Semantic Segmentation of Tuberculosis-Consistent Findings in Chest X-rays Using Augmented Training of Modality-Specific U-Net Models with Weak Localizations.

Deep learning (DL) has drawn tremendous attention for object localization and recognition in both natural and medical images. U-Net segmentation models have demonstrated superior performance compared to conventional hand-crafted feature-based methods. Medical image modality-specific DL models are better at transferring domain knowledge to a relevant target task than those pretrained on stock photography images. This character helps improve model adaptation, generalization, and class-specific region of interest (ROI) localization. In this study, we train chest X-ray (CXR) modality-specific U-Nets and other state-of-the-art U-Net models for semantic segmentation of tuberculosis (TB)-consistent findings. Automated segmentation of such manifestations could help radiologists reduce errors and supplement decision-making while improving patient care and productivity. Our approach uses the publicly available TBX11K CXR dataset with weak TB annotations, typically provided as bounding boxes, to train a set of U-Net models. Next, we improve the results by augmenting the training data with weak localization, postprocessed into an ROI mask, from a DL classifier trained to classify CXRs as showing normal lungs or suspected TB manifestations. Test data are individually derived from the TBX11K CXR training distribution and other cross-institutional collections, including the Shenzhen TB and Montgomery TB CXR datasets. We observe that our augmented training strategy helped the CXR modality-specific U-Net models achieve superior performance with test data derived from the TBX11K CXR training distribution and cross-institutional collections (p < 0.05). We believe that this is the first study to i) use CXR modality-specific U-Nets for semantic segmentation of TB-consistent ROIs and ii) evaluate the segmentation performance while augmenting the training data with weak TB-consistent localizations.

CT Evaluation of Lymph Nodes That Merge or Split during the Course of a Clinical Trial: Limitations of RECIST 1.1.

Purpose To compare Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 with volumetric measurement in the setting of target lymph nodes that split into two or more nodes or merge into one conglomerate node. Materials and Methods In this retrospective study, target lymph nodes were evaluated on CT scans from 166 patients with different types of cancer; 158 of the scans came from The Cancer Imaging Archive. Each target node was measured using RECIST 1.1 criteria before and after merging or splitting, followed by volumetric segmentation. To compare RECIST 1.1 with volume, a single-dimension hypothetical diameter (HD) was determined from the nodal volume. The nodes were divided into three groups: (a) one-target merged (one target node merged with other nodes); (b) two-target merged (two neighboring target nodes merged); and (c) split node (a conglomerate node cleaved into smaller fragments). Bland-Altman analysis and t test were applied to compare RECIST 1.1 with HD. On the basis of the RECIST 1.1 concept, we compared response category changes between RECIST 1.1 and HD. Results The data set consisted of 30 merged nodes (19 one-target merged and 11 two-target merged) and 20 split nodes (mean age for all 50 included patients, 50 years ± 7 [standard deviation]; 38 men). RECIST 1.1, volumetric, and HD measurements indicated an increase in size in all one-target merged nodes. While volume and HD indicated an increase in size for nodes in the two-target merged group, RECIST 1.1 showed a decrease in size in all two-target merged nodes. Although volume and HD demonstrated a decrease in size of all split nodes, RECIST 1.1 indicated an increase in size in 60% (12 of 20) of the nodes. Discrepancy of the response categories between RECIST 1.1 and HD was observed in 5% (one of 19) in one-target merged, 82% (nine of 11) in two-target merged, and 55% (11 of 20) in split nodes. Conclusion RECIST 1.1 does not optimally reflect size changes when lymph nodes merge or split. Keywords: CT, Lymphatic, Tumor Response Supplemental material is available for this article. © RSNA, 2021.