RESUMEN
Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.
RESUMEN
Automated brain tumor segmentation methods have become well-established and reached performance levels offering clear clinical utility. These methods typically rely on four input magnetic resonance imaging (MRI) modalities: T1-weighted images with and without contrast enhancement, T2-weighted images, and FLAIR images. However, some sequences are often missing in clinical practice due to time constraints or image artifacts, such as patient motion. Consequently, the ability to substitute missing modalities and gain segmentation performance is highly desirable and necessary for the broader adoption of these algorithms in the clinical routine. In this work, we present the establishment of the Brain MR Image Synthesis Benchmark (BraSyn) in conjunction with the Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2023. The primary objective of this challenge is to evaluate image synthesis methods that can realistically generate missing MRI modalities when multiple available images are provided. The ultimate aim is to facilitate automated brain tumor segmentation pipelines. The image dataset used in the benchmark is diverse and multi-modal, created through collaboration with various hospitals and research institutions.
RESUMEN
Meningiomas are the most common primary intracranial tumor in adults and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on multiparametric MRI (mpMRI) for diagnosis, treatment planning, and longitudinal treatment monitoring; yet automated, objective, and quantitative tools for non-invasive assessment of meningiomas on mpMRI are lacking. The BraTS meningioma 2023 challenge will provide a community standard and benchmark for state-of-the-art automated intracranial meningioma segmentation models based on the largest expert annotated multilabel meningioma mpMRI dataset to date. Challenge competitors will develop automated segmentation models to predict three distinct meningioma sub-regions on MRI including enhancing tumor, non-enhancing tumor core, and surrounding nonenhancing T2/FLAIR hyperintensity. Models will be evaluated on separate validation and held-out test datasets using standardized metrics utilized across the BraTS 2023 series of challenges including the Dice similarity coefficient and Hausdorff distance. The models developed during the course of this challenge will aid in incorporation of automated meningioma MRI segmentation into clinical practice, which will ultimately improve care of patients with meningioma.
RESUMEN
Clinical monitoring of metastatic disease to the brain can be a laborious and timeconsuming process, especially in cases involving multiple metastases when the assessment is performed manually. The Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) guideline, which utilizes the unidimensional longest diameter, is commonly used in clinical and research settings to evaluate response to therapy in patients with brain metastases. However, accurate volumetric assessment of the lesion and surrounding peri-lesional edema holds significant importance in clinical decision-making and can greatly enhance outcome prediction. The unique challenge in performing segmentations of brain metastases lies in their common occurrence as small lesions. Detection and segmentation of lesions that are smaller than 10 mm in size has not demonstrated high accuracy in prior publications. The brain metastases challenge sets itself apart from previously conducted MICCAI challenges on glioma segmentation due to the significant variability in lesion size. Unlike gliomas, which tend to be larger on presentation scans, brain metastases exhibit a wide range of sizes and tend to include small lesions. We hope that the BraTS-METS dataset and challenge will advance the field of automated brain metastasis detection and segmentation.
RESUMEN
Deep learning (DL) has been proposed to automate image segmentation and provide accuracy, consistency, and efficiency. Accurate segmentation of lipomatous tumors (LTs) is critical for correct tumor radiomics analysis and localization. The major challenge of this task is data heterogeneity, including tumor morphological characteristics and multicenter scanning protocols. To mitigate the issue, we aimed to develop a DL-based Super Learner (SL) ensemble framework with different data correction and normalization methods. Pathologically proven LTs on pre-operative T1-weighted/proton-density MR images of 185 patients were manually segmented. The LTs were categorized by tumor locations as distal upper limb (DUL), distal lower limb (DLL), proximal upper limb (PUL), proximal lower limb (PLL), or Trunk (T) and grouped by 80%/9%/11% for training, validation and testing. Six configurations of correction/normalization were applied to data for fivefold-cross-validation trainings, resulting in 30 base learners (BLs). A SL was obtained from the BLs by optimizing SL weights. The performance was evaluated by dice-similarity-coefficient (DSC), sensitivity, specificity, and Hausdorff distance (HD95). For predictions of the BLs, the average DSC, sensitivity, and specificity from the testing data were 0.72 [Formula: see text] 0.16, 0.73 [Formula: see text] 0.168, and 0.99 [Formula: see text] 0.012, respectively, while for SL predictions were 0.80 [Formula: see text] 0.184, 0.78 [Formula: see text] 0.193, and 1.00 [Formula: see text] 0.010. The average HD95 of the BLs were 11.5 (DUL), 23.2 (DLL), 25.9 (PUL), 32.1 (PLL), and 47.9 (T) mm, whereas of SL were 1.7, 8.4, 15.9, 2.2, and 36.6 mm, respectively. The proposed method could improve the segmentation accuracy and mitigate the performance instability and data heterogeneity aiding the differential diagnosis of LTs in real clinical situations.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Imagen por Resonancia Magnética , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Inteligencia ArtificialRESUMEN
Hepatocellular carcinoma (HCC) is the most common primary liver neoplasm, and its incidence has doubled over the past two decades owing to increasing risk factors. Despite surveillance, most HCC cases are diagnosed at advanced stages and can only be treated using transarterial chemo-embolization (TACE) or systemic therapy. TACE failure may occur with incidence reaching up to 60% of cases, leaving patients with a financial and emotional burden. Radiomics has emerged as a new tool capable of predicting tumor response to TACE from pre-procedural computed tomography (CT) studies. This data report defines the HCC-TACE data collection of confirmed HCC patients who underwent TACE and have pre- and post-procedure CT imaging studies and available treatment outcomes (time-to-progression and overall survival). Clinically curated segmentation of pre-procedural CT studies was done for the purpose of algorithm training for prediction and automatic liver tumor segmentation.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/diagnóstico por imagen , Carcinoma Hepatocelular/terapia , Quimioembolización Terapéutica/efectos adversos , Quimioembolización Terapéutica/métodos , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/terapia , Resultado del TratamientoRESUMEN
Background: The increasing use of computed tomography (CT) has identified many patients with incidental adrenal lesions. Further evaluation of these lesions is often dependent on the language used in the radiology report. Compared to the general population, patients with cancer have a higher risk for adrenal abnormalities, yet data on the prevalence and type of incidental adrenal lesions reported on radiologic reports in cancer patients is limited. In this study, we aimed to determine the prevalence and nature of adrenal abnormalities as an incidental finding reported on radiology reports of cancer patients evaluated for reasons other than suspected adrenal pathology. Methods: Radiology reports of patients who underwent abdominal CT within 30 days of presentation to a tertiary cancer center were reviewed and analyzed. We used natural language processing to perform a multi-class text classification of the adrenal reports. Patients who had CT for suspected adrenal mass including adrenal protocol CT were excluded. Three independent abstractors manually reviewed abnormal and questionable results, and we measured the interobserver agreement. Results: From June 1, 2006, to October 1, 2017, a total of 600,399 abdominal CT scans were performed including 66,478 scans obtained within 30 days of the patient's first presentation. Of these, 58,512 were eligible after applying the exclusion criteria. Adrenal abnormalities were identified in 7,817 (13.4%) reports, with adrenal nodularity (3,401 [43.5%]), adenomas (1,733 [22.2%]), and metastases (1,337 [17.1%]) being the most reported categories. Only 10 cases (0.1%) were reported as primary adrenal carcinomas and 2 as pheochromocytoma. Interobserver agreement using 300 reports yielded a Fleiss kappa of 0.893, implying almost perfect agreement between the abstractors. Conclusions: Incidental adrenal abnormalities are commonly reported in abdominal CT reports of cancer patients. As the terminology used by radiologists to describe these findings greatly determine the subsequent management plans, further studies are needed to correlate some of these findings to the actual confirmed diagnosis based on hormonal, histological and follow-up data and ascertain the impact of such reported findings on patients' outcomes.
Asunto(s)
Neoplasias de las Glándulas Suprarrenales , Feocromocitoma , Humanos , Prevalencia , Tomografía Computarizada por Rayos X , Feocromocitoma/diagnóstico por imagen , Feocromocitoma/epidemiología , Neoplasias de las Glándulas Suprarrenales/diagnóstico por imagen , Neoplasias de las Glándulas Suprarrenales/epidemiologíaRESUMEN
ABSTRACT: Artificial intelligence (AI) is the most revolutionizing development in the health care industry in the current decade, with diagnostic imaging having the greatest share in such development. Machine learning and deep learning (DL) are subclasses of AI that show breakthrough performance in image analysis. They have become the state of the art in the field of image classification and recognition. Machine learning deals with the extraction of the important characteristic features from images, whereas DL uses neural networks to solve such problems with better performance. In this review, we discuss the current applications of machine learning and DL in the field of diagnostic radiology.Deep learning applications can be divided into medical imaging analysis and applications beyond analysis. In the field of medical imaging analysis, deep convolutional neural networks are used for image classification, lesion detection, and segmentation. Also used are recurrent neural networks when extracting information from electronic medical records and to augment the use of convolutional neural networks in the field of image classification. Generative adversarial networks have been explicitly used in generating high-resolution computed tomography and magnetic resonance images and to map computed tomography images from the corresponding magnetic resonance imaging. Beyond image analysis, DL can be used for quality control, workflow organization, and reporting.In this article, we review the most current AI models used in medical imaging research, providing a brief explanation of the various models described in the literature within the past 5 years. Emphasis is placed on the various DL models, as they are the most state-of-art in imaging analysis.
Asunto(s)
Inteligencia Artificial , Interpretación de Imagen Radiográfica Asistida por Computador , Tomografía Computarizada por Rayos X , Algoritmos , Humanos , Aprendizaje Automático , Neoplasias/diagnóstico por imagen , Redes Neurales de la Computación , Control de Calidad , Flujo de TrabajoRESUMEN
The Peutz-Jeghers Syndrome (PJS) is an autosomal dominant neoplastic syndrome defined by hamartomatous polyps through the gastrointestinal tract, development of characteristic mucocutaneous pigmentations, and an elevated lifetime cancer risk. The majority of cases are due to a mutation in the STK11 gene located at 19p13.3. The estimated incidence of PJS ranges from 1:50,000 to 1:200,000. PJS carries an elevated risk of malignancies including gastrointestinal, breast, lung, and genitourinary (GU) neoplasms. Patients with PJS are at a 15- to 18-fold increased malignancy risk relative to the general population. Radiologists have an integral role in the diagnosis of these patients. Various imaging modalities are used to screen for malignancies and complications associated with PJS. Awareness of various PJS imaging patterns, associated malignancies, and their complications is crucial for accurate imaging interpretation and patient management. In this manuscript, we provide a comprehensive overview of PJS, associated malignancies, and surveillance protocols.
RESUMEN
The lymphatic system is an anatomically complex vascular network that is responsible for interstitial fluid homeostasis, transport of large interstitial particles and cells, immunity, and lipid absorption in the gastrointestinal tract. This network of specially adapted vessels and lymphoid tissue provides a major pathway for metastatic spread. Many malignancies produce vascular endothelial factors that induce tumoral and peritumoral lymphangiogenesis, increasing the likelihood for lymphatic spread. Radiologic evaluation for disease staging is the cornerstone of oncologic patient treatment and management. Multiple imaging modalities are available to access both local and distant metastasis. In this manuscript, we review the anatomy, physiology, and imaging of the lymphatic system.
RESUMEN
Here we review artificial intelligence (AI) models which aim to assess various aspects of chronic liver disease. Despite the clinical importance of hepatocellular carcinoma in the setting of chronic liver disease, we focus this review on AI models which are not lesion-specific and instead review models developed for liver parenchyma segmentation, evaluation of portal circulation, assessment of hepatic fibrosis, and identification of hepatic steatosis. Optimization of these models offers the opportunity to potentially reduce the need for invasive procedures such as catheterization to measure hepatic venous pressure gradient or biopsy to assess fibrosis and steatosis. We compare the performance of these AI models amongst themselves as well as to radiomics approaches and alternate modality assessments. We conclude that these models show promising performance and merit larger-scale evaluation. We review artificial intelligence models that aim to assess various aspects of chronic liver disease aside from hepatocellular carcinoma. We focus this review on models for liver parenchyma segmentation, evaluation of portal circulation, assessment of hepatic fibrosis, and identification of hepatic steatosis. We conclude that these models show promising performance and merit a larger scale evaluation.
Asunto(s)
Inteligencia Artificial , Hepatopatías , Humanos , Cirrosis Hepática/diagnóstico por imagen , Hepatopatías/diagnóstico por imagen , Imagen por Resonancia MagnéticaRESUMEN
GOAL: To evaluate the ability of radiomic feature extraction and a machine learning algorithm to differentiate between benign and malignant indeterminate adrenal lesions on contrast-enhanced computed tomography (CT) studies. BACKGROUND: Adrenal "incidentalomas" are adrenal lesions that are accidentally discovered during workup not related to the adrenal glands; they have an incidence as high as 5%. Small adrenal incidentalomas (< 4 cm) with high attenuation values on pre-contrast CT(> 10 HU) need further evaluation to calculate the absolute percentage of washout (APW). If the APW is < 60%, these lesions are considered non-adenomas and commonly classified as indeterminate adrenal lesions. Further workup for indeterminate lesions includes more complicated and expensive radiological studies or invasive procedures like biopsy or surgical resection. METHODS: We searched our institutional database for indeterminate adrenal lesions with the following characteristics: < 4 cm, pre-attenuation value > 10 HU, and APW < 60%. Exclusion criteria included pheochromocytoma and no histopathological examination. CT images were converted to Nifti format, and adrenal tumors were segmented using Amira software. Radiomic features from the adrenal mask were extracted using PyRadiomics software after removing redundant features (highly pairwise correlated features and low-variance features) using recursive feature extraction to select the final discriminative set of features. Lastly, the final features were used to build a binary classification model using a random forest algorithm, which was validated and tested using leave-one-out cross-validation, confusion matrix, and receiver operating characteristic curve. RESULTS: We found 40 indeterminate adrenal lesions (21 benign and 19 malignant). Feature extraction resulted in 3947 features, which reduced down to 62 features after removing redundancies. Recursive feature elimination resulted in the following top 4 discriminative features: gray-level size zone matrix-derived size zone non-uniformity from pre-contrast and delayed phases, gray-level dependency matrix-derived large dependence high gray-level emphasis from venous-phase, and gray-level co-occurrence matrix-derived cluster shade from delayed-phase. A binary classification model with leave-one-out cross-validation showed AUC = 0.85, sensitivity = 84.2%, and specificity = 71.4%. CONCLUSION: Machine learning and radiomic features extraction can differentiate between benign and malignant indeterminate adrenal tumors and can be used to direct further workup with high sensitivity and specificity.
Asunto(s)
Neoplasias de las Glándulas Suprarrenales , Neoplasias de las Glándulas Suprarrenales/diagnóstico por imagen , Algoritmos , Humanos , Aprendizaje Automático , Estudios Retrospectivos , Tomografía Computarizada por Rayos XRESUMEN
Artificial Intelligence (AI) continues to shape the practice of radiology, with imaging of hepatocellular carcinoma (HCC) being of no exception. This article prepared by members of the LI-RADS Treatment Response (TR LI-RADS) work group and associates, presents recent trends in the utility of AI applications for the volumetric evaluation and assessment of HCC treatment response. Various topics including radiomics, prognostic imaging findings, and locoregional therapy (LRT) specific issues will be discussed in the framework of HCC treatment response classification systems with focus on the Liver Reporting and Data System treatment response algorithm (LI-RADS TRA).
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Inteligencia Artificial , Carcinoma Hepatocelular/diagnóstico por imagen , Carcinoma Hepatocelular/terapia , Humanos , Hígado , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/terapia , Imagen por Resonancia Magnética , Estudios RetrospectivosRESUMEN
PURPOSE: In the clinical workflow of radiology services, a critical connection exists between technologists and radiologists, yet there is often limited communication between this key link in the chain of patient imaging. Our aim was to quantify and detail the communication between CT technologists and radiologists in our tertiary oncology practice. METHODS: Using the note function in our EMR, as standard operating procedure, CT technologists are instructed to place pertinent notes for the radiologist relevant to any portion of the patient encounter. Note categories pertain to quality and/or safety: patient limitations (e.g., patient unable to raise arm), protocol confirmation (e.g., rectal contrast given), critical finding communication, scan range considerations, IV issues, reduction in eGFR, oral contrast issues, allergy information, general feedback, equipment malfunction, and radiologist approval information. The percentage of notes within each category were recorded upon review of contiguous abdominal CT scans in July 2018 with the primary outcome measure of overall note volume compared to baseline in July 2016 after which time technologists were educated on the importance of notes and were requested to increase use of this tool. Notes were regularly reviewed to identify practice improvement opportunities. RESULTS: Compared to baseline 2 years earlier (8860 CT scans, 812 technologist notes), there was a 32% increase in technologist note volume (10,948 CT scans, 1330 technologist notes), representing an increase of notes from 9.2% of exams to 12.1% of exams (p < .001) and there were 14 related practice improvements. CONCLUSION: After communicating the importance of CT technologist notes and requesting increased notation frequency, technologist note volume significantly increased and 14 specific case examples of related practice improvement demonstrate the electronic medical record note function to be a robust tool in the management of patient imaging.
Asunto(s)
Radiólogos , Tomografía Computarizada por Rayos X , Abdomen , Comunicación , Registros Electrónicos de Salud , HumanosRESUMEN
There have been rapid advancements in cancer treatment in recent years, including targeted molecular therapy and the emergence of anti-angiogenic agents, which necessitate the need to quickly and accurately assess treatment response. The ideal tool is robust and non-invasive so that the treatment can be rapidly adjusted or discontinued based on efficacy. Since targeted therapies primarily affect tumor angiogenesis, morphological assessment based on tumor size alone may be insufficient, and other imaging modalities and features may be more helpful in assessing response. This review aims to discuss the biological principles of tumor angiogenesis and the multi-modality imaging evaluation of anti-angiogenic therapeutic responses.
RESUMEN
PURPOSE: To evaluate the value of follow-up chest CT in the surveillance of HCC patients. BACKGROUND: Imaging guidelines for the surveillance of hepatocellular carcinoma (HCC) patients recommend multiple follow-up computed tomography (CT) examinations of the chest, abdomen, and pelvis. Imaging studies are a major driver of rising healthcare costs. The appropriate use of imaging studies must be evaluated to provide valued health care. METHODS: We reviewed the radiology reports of baseline and follow-up chest, abdominal, and pelvic CT examinations of HCC patients. We categorized the incidence of malignancy in the chest and abdomen for the baseline and follow-up examinations. We also categorized the follow-up examinations as showing improved disease, stable disease, or disease progression. We correlated any progression of disease in the chest with progression of disease in the abdomen. We determined the extent to which disease progression in the chest occurred alongside that in the abdomen. Descriptive statistical analysis was carried out using R (version 3.5.2, R Development Core Team). RESULTS: Of the 226 patients included in our study, only 7 (3%) had disease progression in the chest without corresponding disease progression in the abdomen and pelvis on follow-up CT. Only 1.8% of patients with disease progression in the chest had a negative CT chest at baseline. CONCLUSION: Follow-up chest CT has limited benefit in the surveillance of HCC patients, especially those with negative baseline chest CT findings.
RESUMEN
Hepatocellular carcinoma (HCC) is one of the most common tumors worldwide, usually occurring on a background of liver cirrhosis. HCC is a highly vascular tumor in which angiogenesis plays a major role in tumor growth and spread. Tumor-induced angiogenesis is usually related to a complex interplay between multiple factors and pathways, with vascular endothelial growth factor being a major player in angiogenesis. In the past decade, understanding of tumor-induced angiogenesis has led to the emergence of novel anti-angiogenic therapies, which act by reducing neo-angiogenesis, and improving patient survival. Currently, Sorafenib and Lenvatinib are being used as the first-line treatment for advanced unresectable HCC. However, a disadvantage of these agents is the presence of numerous side effects. A major challenge in the management of HCC patients being treated with anti-angiogenic therapy is effective monitoring of treatment response, which decides whether to continue treatment or to seek second-line treatment. Several criteria can be used to assess response to treatment, such as quantitative perfusion on cross-sectional imaging and novel/emerging MRI techniques, including a host of known and emerging biomarkers and radiogenomics. This review addresses the pathophysiology of angiogenesis in HCC, accurate imaging assessment of angiogenesis, monitoring effects of anti-angiogenic therapy to guide future treatment and assessing prognosis.
RESUMEN
Background: Hepatocellular carcinoma (HCC) is the most common liver malignancy and the leading cause of death in patients with cirrhosis. Various treatments for HCC are available, including transarterial chemoembolization (TACE), which is the commonest intervention performed in HCC. Radiologic tumor response following TACE is an important prognostic factor for patients with HCC. We hypothesized that, for large HCC tumors, assessment of treatment response made with automated volumetric response evaluation criteria in solid tumors (RECIST) might correlate with the assessment made with the more time- and labor-intensive unidimensional modified RECIST (mRECIST) and manual volumetric RECIST (M-vRECIST) criteria. Accordingly, we undertook this retrospective study to compare automated volumetric RECIST (A-vRECIST) with M-vRECIST and mRESIST for the assessment of large HCC tumors' responses to TACE. Methods:We selected 42 pairs of contrast-enhanced computed tomography (CT) images of large HCCs. Images were taken before and after TACE, and in each of the images, the HCC was segmented using both a manual contouring tool and a convolutional neural network. Three experienced radiologists assessed tumor response to TACE using mRECIST criteria. The intra-class correlation coefficient was used to assess inter-reader reliability in the mRECIST measurements, while the Pearson correlation coefficient was used to assess correlation between the volumetric and mRECIST measurements. Results:Volumetric tumor assessment using automated and manual segmentation tools showed good correlation with mRECIST measurements. For A-vRECIST and M-vRECIST, respectively, r = 0.597 vs. 0.622 in the baseline studies; 0.648 vs. 0.748 in the follow-up studies; and 0.774 vs. 0.766 in the response assessment (P < 0.001 for all). The A-vRECIST evaluation showed high correlation with the M-vRECIST evaluation (r = 0.967, 0.937, and 0.826 in baseline studies, follow-up studies, and response assessment, respectively, P < 0.001 for all). Conclusion:Volumetric RECIST measurements are likely to provide an early marker for TACE monitoring, and automated measurements made with a convolutional neural network may be good substitutes for manual volumetric measurements.
RESUMEN
OBJECTIVES: The objectives of the study are (1) to distinguish lipoma (L) from atypical lipomatous tumor (ALT) using MRI qualitative features, (2) to assess the value of contrast enhancement, and (3) to evaluate the reproducibility and confidence level of radiological readings. MATERIALS AND METHODS: Patients with pathologically proven L or ALT, who underwent MRI within 3 months from surgical excision were included in this retrospective multicenter international study. Two radiologists independently reviewed MRI centrally. Impressions were recorded as L or ALT. A third radiologist was consulted for discordant readings. The two radiologists re-read all non-contrast sequences; impression was recorded; then post-contrast images were reviewed and any changes were recorded. RESULTS: A total of 246 patients (135 females; median age, 59 years) were included. ALT was histopathologically confirmed in 70/246 patients. In multivariable analysis, in addition to the lesion size, deep location, proximal lower limb lesions, demonstrating incomplete fat suppression, or increased architectural complexity were the independent predictive features of ALT; but not the contrast enhancement. Post-contrast MRI changed the impression in a total of 5 studies (3 for R1 and 4 for R2; 2 studies are common); all of them were incorrectly changed from Ls to ALTs. Overall, inter-reader kappa agreement was 0.42 (95% CI 0.39-0.56). Discordance between the two readers was statistically significant for both pathologically proven L (p < 0.001) and ALT (p = 0.003). CONCLUSION: Most qualitative MR imaging features can help distinguish ALTs from BLs. However, contrast enhancement may be limited and occasionally misleading. Substantial discordance on MRI readings exists between radiologists with a relatively high false positive and negative rates.