Supervised representation learning based on various levels of pediatric radiographic views for transfer learning.

Transfer learning plays a pivotal role in addressing the paucity of data, expediting training processes, and enhancing model performance. Nonetheless, the prevailing practice of transfer learning predominantly relies on pre-trained models designed for the natural image domain, which may not be well-suited for the medical image domain in grayscale. Recognizing the significance of leveraging transfer learning in medical research, we undertook the construction of class-balanced pediatric radiograph datasets collectively referred to as PedXnets, grounded in radiographic views using the pediatric radiographs collected over 24 years at Asan Medical Center. For PedXnets pre-training, approximately 70,000 X-ray images were utilized. Three different pre-training weights of PedXnet were constructed using Inception V3 for various radiation perspective classifications: Model-PedXnet-7C, Model-PedXnet-30C, and Model-PedXnet-68C. We validated the transferability and positive effects of transfer learning of PedXnets through pediatric downstream tasks including fracture classification and bone age assessment (BAA). The evaluation of transfer learning effects through classification and regression metrics showed superior performance of Model-PedXnets in quantitative assessments. Additionally, visual analyses confirmed that the Model-PedXnets were more focused on meaningful regions of interest.

Approximating Intermediate Feature Maps of Self-Supervised Convolution Neural Network to Learn Hard Positive Representations in Chest Radiography.

Recent advances in contrastive learning have significantly improved the performance of deep learning models. In contrastive learning of medical images, dealing with positive representation is sometimes difficult because some strong augmentation techniques can disrupt contrastive learning owing to the subtle differences between other standardized CXRs compared to augmented positive pairs; therefore, additional efforts are required. In this study, we propose intermediate feature approximation (IFA) loss, which improves the performance of contrastive convolutional neural networks by focusing more on positive representations of CXRs without additional augmentations. The IFA loss encourages the feature maps of a query image and its positive pair to resemble each other by maximizing the cosine similarity between the intermediate feature outputs of the original data and the positive pairs. Therefore, we used the InfoNCE loss, which is commonly used loss to address negative representations, and the IFA loss, which addresses positive representations, together to improve the contrastive network. We evaluated the performance of the network using various downstream tasks, including classification, object detection, and a generative adversarial network (GAN) inversion task. The downstream task results demonstrated that IFA loss can improve the performance of effectively overcoming data imbalance and data scarcity; furthermore, it can serve as a perceptual loss encoder for GAN inversion. In addition, we have made our model publicly available to facilitate access and encourage further research and collaboration in the field.

Updated Primer on Generative Artificial Intelligence and Large Language Models in Medical Imaging for Medical Professionals.

The emergence of Chat Generative Pre-trained Transformer (ChatGPT), a chatbot developed by OpenAI, has garnered interest in the application of generative artificial intelligence (AI) models in the medical field. This review summarizes different generative AI models and their potential applications in the field of medicine and explores the evolving landscape of Generative Adversarial Networks and diffusion models since the introduction of generative AI models. These models have made valuable contributions to the field of radiology. Furthermore, this review also explores the significance of synthetic data in addressing privacy concerns and augmenting data diversity and quality within the medical domain, in addition to emphasizing the role of inversion in the investigation of generative models and outlining an approach to replicate this process. We provide an overview of Large Language Models, such as GPTs and bidirectional encoder representations (BERTs), that focus on prominent representatives and discuss recent initiatives involving language-vision models in radiology, including innovative large language and vision assistant for biomedicine (LLaVa-Med), to illustrate their practical application. This comprehensive review offers insights into the wide-ranging applications of generative AI models in clinical research and emphasizes their transformative potential.

Overcoming the Challenges in the Development and Implementation of Artificial Intelligence in Radiology: A Comprehensive Review of Solutions Beyond Supervised Learning.

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

Screening of adolescent idiopathic scoliosis using generative adversarial network (GAN) inversion method in chest radiographs.

OBJECTIVE: Conventional computer-aided diagnosis using convolutional neural networks (CNN) has limitations in detecting sensitive changes and determining accurate decision boundaries in spectral and structural diseases such as scoliosis. We devised a new method to detect and diagnose adolescent idiopathic scoliosis in chest X-rays (CXRs) employing the latent space's discriminative ability in the generative adversarial network (GAN) and a simple multi-layer perceptron (MLP) to screen adolescent idiopathic scoliosis CXRs. MATERIALS AND METHODS: Our model was trained and validated in a two-step manner. First, we trained a GAN using CXRs with various scoliosis severities and utilized the trained network as a feature extractor using the GAN inversion method. Second, we classified each vector from the latent space using a simple MLP. RESULTS: The 2-layer MLP exhibited the best classification in the ablation study. With this model, the area under the receiver operating characteristic (AUROC) curves were 0.850 in the internal and 0.847 in the external datasets. Furthermore, when the sensitivity was fixed at 0.9, the model's specificity was 0.697 in the internal and 0.646 in the external datasets. CONCLUSION: We developed a classifier for Adolescent idiopathic scoliosis (AIS) through generative representation learning. Our model shows good AUROC under screening chest radiographs in both the internal and external datasets. Our model has learned the spectral severity of AIS, enabling it to generate normal images even when trained solely on scoliosis radiographs.

CheSS: Chest X-Ray Pre-trained Model via Self-supervised Contrastive Learning.

Training deep learning models on medical images heavily depends on experts' expensive and laborious manual labels. In addition, these images, labels, and even models themselves are not widely publicly accessible and suffer from various kinds of bias and imbalances. In this paper, chest X-ray pre-trained model via self-supervised contrastive learning (CheSS) was proposed to learn models with various representations in chest radiographs (CXRs). Our contribution is a publicly accessible pretrained model trained with a 4.8-M CXR dataset using self-supervised learning with a contrastive learning and its validation with various kinds of downstream tasks including classification on the 6-class diseases in internal dataset, diseases classification in CheXpert, bone suppression, and nodule generation. When compared to a scratch model, on the 6-class classification test dataset, we achieved 28.5% increase in accuracy. On the CheXpert dataset, we achieved 1.3% increase in mean area under the receiver operating characteristic curve on the full dataset and 11.4% increase only using 1% data in stress test manner. On bone suppression with perceptual loss, we achieved improvement in peak signal to noise ratio from 34.99 to 37.77, structural similarity index measure from 0.976 to 0.977, and root-square-mean error from 4.410 to 3.301 when compared to ImageNet pretrained model. Finally, on nodule generation, we achieved improvement in Fréchet inception distance from 24.06 to 17.07. Our study showed the decent transferability of CheSS weights. CheSS weights can help researchers overcome data imbalance, data shortage, and inaccessibility of medical image datasets. CheSS weight is available at https://github.com/mi2rl/CheSS .

Diagnosis of Scoliosis Using Chest Radiographs with a Semi-Supervised Generative Adversarial Network.

Purpose: To develop and validate a deep learning-based screening tool for the early diagnosis of scoliosis using chest radiographs with a semi-supervised generative adversarial network (GAN). Materials and Methods: Using a semi-supervised learning framework with a GAN, a screening tool for diagnosing scoliosis was developed and validated through the chest PA radiographs of patients at two different tertiary hospitals. Our proposed method used training GAN with mild to severe scoliosis only in a semi-supervised manner, as an upstream task to learn scoliosis representations and a downstream task to perform simple classification for differentiating between normal and scoliosis states sensitively. Results: The area under the receiver operating characteristic curve, negative predictive value (NPV), positive predictive value, sensitivity, and specificity were 0.856, 0.950, 0.579, 0.985, and 0.285, respectively. Conclusion: Our deep learning-based artificial intelligence software in a semi-supervised manner achieved excellent performance in diagnosing scoliosis using the chest PA radiographs of young individuals; thus, it could be used as a screening tool with high NPV and sensitivity and reduce the burden on radiologists for diagnosing scoliosis through health screening chest radiographs.

Clinical Impact of a Quality Improvement Program Including Dedicated Emergency Radiology Personnel on Emergency Surgical Management: A Propensity Score-Matching Study.

OBJECTIVE: To investigate the clinical impact of a quality improvement program including dedicated emergency radiology personnel (QIP-DERP) on the management of emergency surgical patients in the emergency department (ED). MATERIALS AND METHODS: This retrospective study identified all adult patients (n = 3667) who underwent preoperative body CT, for which written radiology reports were generated, and who subsequently underwent non-elective surgery between 2007 and 2018 in the ED of a single urban academic tertiary medical institution. The study cohort was divided into periods before and after the initiation of QIP-DERP. We matched the control group patients (i.e., before QIP-DERP) to the QIP-DERP group patients using propensity score (PS), with a 1:2 matching ratio for the main analysis and a 1:1 ratio for sub-analyses separately for daytime (8:00 AM to 5:00 PM on weekdays) and after-hours. The primary outcome was timing of emergency surgery (TES), which was defined as the time from ED arrival to surgical intervention. The secondary outcomes included ED length of stay (LOS) and intensive care unit (ICU) admission rate. RESULTS: According to the PS-matched analysis, compared with the control group, QIP-DERP significantly decreased the median TES from 16.7 hours (interquartile range, 9.4-27.5 hours) to 11.6 hours (6.6-21.9 hours) (p < 0.001) and the ICU admission rate from 33.3% (205/616) to 23.9% (295/1232) (p < 0.001). During after-hours, the QIP-DERP significantly reduced median TES from 19.9 hours (12.5-30.1 hours) to 9.6 hours (5.7-19.1 hours) (p < 0.001), median ED LOS from 9.1 hours (5.6-16.5 hours) to 6.7 hours (4.9-11.3 hours) (p < 0.001), and ICU admission rate from 35.5% (108/304) to 22.0% (67/304) (p < 0.001). CONCLUSION: QIP-DERP implementation improved the quality of emergency surgical management in the ED by reducing TES, ED LOS, and ICU admission rate, particularly during after-hours.

Emergency triage of brain computed tomography via anomaly detection with a deep generative model.

Triage is essential for the early diagnosis and reporting of neurologic emergencies. Herein, we report the development of an anomaly detection algorithm (ADA) with a deep generative model trained on brain computed tomography (CT) images of healthy individuals that reprioritizes radiology worklists and provides lesion attention maps for brain CT images with critical findings. In the internal and external validation datasets, the ADA achieved area under the curve values (95% confidence interval) of 0.85 (0.81-0.89) and 0.87 (0.85-0.89), respectively, for detecting emergency cases. In a clinical simulation test of an emergency cohort, the median wait time was significantly shorter post-ADA triage than pre-ADA triage by 294 s (422.5 s [interquartile range, IQR 299] to 70.5 s [IQR 168]), and the median radiology report turnaround time was significantly faster post-ADA triage than pre-ADA triage by 297.5 s (445.0 s [IQR 298] to 88.5 s [IQR 179]) (all p < 0.001).

Patient recalls associated with resident-to-attending radiology report discrepancies: predictive factors for risky discrepancies.

BACKGROUND: This study aimed to identify predictive factors for risky discrepancies in the emergency department (ED) by analyzing patient recalls associated with resident-to-attending radiology report discrepancies (RRDs). RESULTS: This retrospective study analyzed 759 RRDs in computed tomography (CT) and magnetic resonance imaging and their outcomes from 2013 to 2021. After excluding 73 patients lost to follow-up, we included 686 records in the final analysis. Risky discrepancies were defined as RRDs resulting in (1) inpatient management (hospitalization) and (2) adverse outcomes (delayed operations, 30-day in-hospital mortality, or intensive care unit admission). Predictors of risky discrepancies were assessed using multivariable logistic regression analysis. The overall RRD rate was 0.4% (759 of 171,419). Of 686 eligible patients, 21.4% (147 of 686) received inpatient management, and 6.0% (41 of 686) experienced adverse outcomes. RRDs with neurological diseases were associated with the highest ED revisit rate (79.4%, 81 of 102) but not with risky RRDs. Predictive factors of inpatient management were critical finding (odds ratio [OR], 5.60; p < 0.001), CT examination (OR, 3.93; p = 0.01), digestive diseases (OR, 2.54; p < 0.001), and late finalized report (OR, 1.65; p = 0.02). Digestive diseases (OR, 6.14; p = 0.006) were identified as the only significant predictor of adverse outcomes. CONCLUSIONS: Risky RRDs were associated with several factors, including CT examination, digestive diseases, and late finalized reports, as well as critical image findings. This knowledge could aid in determining the priority of discrepancies for the appropriate management of RRDs.

Bone suppression on pediatric chest radiographs via a deep learning-based cascade model.

BACKGROUND AND OBJECTIVE: Bone suppression images (BSIs) of chest radiographs (CXRs) have been proven to improve diagnosis of pulmonary diseases. To acquire BSIs, dual-energy subtraction (DES) or a deep-learning-based model trained with DES-based BSIs have been used. However, neither technique could be applied to pediatric patients owing to the harmful effects of DES. In this study, we developed a novel method for bone suppression in pediatric CXRs. METHODS: First, a model using digitally reconstructed radiographs (DRRs) of adults, which were used to generate pseudo-CXRs from computed tomography images, was developed by training a 2-channel contrastive-unpaired-image-translation network. Second, this model was applied to 129 pediatric DRRs to generate the paired training data of pseudo-pediatric CXRs. Finally, by training a U-Net with these paired data, a bone suppression model for pediatric CXRs was developed. RESULTS: The evaluation metrics were peak signal to noise ratio, root mean absolute error and structural similarity index measure at soft-tissue and bone region of the lung. In addition, an expert radiologist scored the effectiveness of BSIs on a scale of 1-5. The obtained result of 3.31 ± 0.48 indicates that the BSIs show homogeneous bone removal despite subtle residual bone shadow. CONCLUSION: Our method shows that the pixel intensity at soft-tissue regions was preserved, and bones were well subtracted; this can be useful for detecting early pulmonary disease in pediatric CXRs.

Impact of diagnostic errors on adverse outcomes: learning from emergency department revisits with repeat CT or MRI.

BACKGROUND: To investigate diagnostic errors and their association with adverse outcomes (AOs) during patient revisits with repeat imaging (RVRIs) in the emergency department (ED). RESULTS: Diagnostic errors stemming from index imaging studies and AOs within 30 days in 1054 RVRIs (≤ 7 days) from 2005 to 2015 were retrospectively analyzed according to revisit timing (early [≤ 72 h] or late [> 72 h to 7 days] RVRIs). Risk factors for AOs were assessed using multivariable logistic analysis. The AO rate in the diagnostic error group was significantly higher than that in the non-error group (33.3% [77 of 231] vs. 14.8% [122 of 823], p < .001). The AO rate was the highest in early revisits within 72 h if diagnostic errors occurred (36.2%, 54 of 149). The most common diseases associated with diagnostic errors were digestive diseases in the radiologic misdiagnosis category (47.5%, 28 of 59) and neurologic diseases in the delayed radiology reporting time (46.8%, 29 of 62) and clinician error (27.3%, 30 of 110) categories. In the matched set of the AO and non-AO groups, multivariable logistic regression analysis revealed that the following diagnostic errors contributed to AO occurrence: radiologic error (odds ratio [OR] 3.56; p < .001) in total RVRIs, radiologic error (OR 3.70; p = .001) and clinician error (OR 4.82; p = .03) in early RVRIs, and radiologic error (OR 3.36; p = .02) in late RVRIs. CONCLUSION: Diagnostic errors in index imaging studies are strongly associated with high AO rates in RVRIs in the ED.

Realistic High-Resolution Body Computed Tomography Image Synthesis by Using Progressive Growing Generative Adversarial Network: Visual Turing Test.

BACKGROUND: Generative adversarial network (GAN)-based synthetic images can be viable solutions to current supervised deep learning challenges. However, generating highly realistic images is a prerequisite for these approaches. OBJECTIVE: The aim of this study was to investigate and validate the unsupervised synthesis of highly realistic body computed tomography (CT) images by using a progressive growing GAN (PGGAN) trained to learn the probability distribution of normal data. METHODS: We trained the PGGAN by using 11,755 body CT scans. Ten radiologists (4 radiologists with <5 years of experience [Group I], 4 radiologists with 5-10 years of experience [Group II], and 2 radiologists with >10 years of experience [Group III]) evaluated the results in a binary approach by using an independent validation set of 300 images (150 real and 150 synthetic) to judge the authenticity of each image. RESULTS: The mean accuracy of the 10 readers in the entire image set was higher than random guessing (1781/3000, 59.4% vs 1500/3000, 50.0%, respectively; P<.001). However, in terms of identifying synthetic images as fake, there was no significant difference in the specificity between the visual Turing test and random guessing (779/1500, 51.9% vs 750/1500, 50.0%, respectively; P=.29). The accuracy between the 3 reader groups with different experience levels was not significantly different (Group I, 696/1200, 58.0%; Group II, 726/1200, 60.5%; and Group III, 359/600, 59.8%; P=.36). Interreader agreements were poor (κ=0.11) for the entire image set. In subgroup analysis, the discrepancies between real and synthetic CT images occurred mainly in the thoracoabdominal junction and in the anatomical details. CONCLUSIONS: The GAN can synthesize highly realistic high-resolution body CT images that are indistinguishable from real images; however, it has limitations in generating body images of the thoracoabdominal junction and lacks accuracy in the anatomical details.

Value of bone suppression software in chest radiographs for improving image quality and reducing radiation dose.

OBJECTIVES: To compare image quality and radiation dose between dual-energy subtraction (DES)-based bone suppression images (D-BSIs) and software-based bone suppression images (S-BSIs). METHODS: Chest radiographs (CXRs) of forty adult patients were obtained with the two X-ray devices, one with DES and one with bone suppression software. Three image quality metrics (relative mean absolute error (RMAE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM)) between original CXR and BSI for each of D-BSI and S-SBI groups were calculated for each bone and soft tissue areas. Two readers rated the visual image quality for original CXR and BSI for each of D-BSI and S-SBI groups. The dose area product (DAP) values were recorded. Paired t test was used to compare the image quality and DAP values between D-BSI and S-BSI groups. RESULTS: In bone areas, S-BSIs had better SSIM values than D-BSI (94.57 vs. 87.77) but worse RMAE and PSNR values (0.50 vs. 0.20; 20.93 vs. 34.37) (all p < 0.001). In soft tissue areas, S-BSIs had better SSIM values than D-BSI (97.56 vs. 91.42) but similar RMAE and PSNR values (0.29 vs. 0.27; 31.35 vs. 29.87) (all p < 0.001). Both readers gave S-BSIs significantly higher image quality scores than D-BSI (p < 0.001). The mean DAP in software-related images (0.98 dGy·cm2) was significantly lower than that in the DES-related images (1.48 dGy·cm2) (p < 0.001). CONCLUSION: Bone suppression software significantly improved the image quality of bone suppression images with a relatively lower radiation dose, compared with dual-energy subtraction technique. KEY POINTS: • Bone suppression software preserves structure similarity of soft tissues better than dual-energy subtraction technique in bone suppression images. • Bone suppression software achieves superior image quality for lung lesions than dual-energy subtraction technique in bone suppression images. • Bone suppression software can decrease the radiation dose over the hardware-based image processing technique.

Assessment of naive indolent lymphoma using whole-body diffusion-weighted imaging and T2-weighted MRI: results of a prospective study in 30 patients.

BACKGROUND: We prospectively evaluated the diagnostic utility of whole-body diffusion-weighted imaging with background body signal suppression and T2-weighted short-tau inversion recovery MRI (WB-DWIBS/STIR) for the pretherapeutic staging of indolent lymphoma in 30 patients. METHODS: This prospective study included 30 treatment-naive patients with indolent lymphomas who underwent WB-DWIBS/STIR and conventional imaging workup plus biopsy. The pretherapeutic staging agreement, sensitivity, and specificity of WB-DWIBS/STIR were investigated with reference to the multimodality and multidisciplinary consensus review for nodal and extranodal lesions excluding bone marrow. RESULTS: In the pretherapeutic staging, WB-DWIBS/STIR showed very good agreement (κ = 0.96; confidence interval [CI], 0.88-1.00), high sensitivity (93.4-95.1%), and high specificity (99.0-99.4%) for the whole-body regions. These results were similar to those of 18F-FDG-PET/CT, except for the sensitivity for extranodal lesions. For extranodal lesions, WB-DWIBS/STIR showed higher sensitivity compared to 18F-FDG-PET/CT for the whole-body regions (94.9-96.8% vs. 79.6-86.3%, P = 0.058). CONCLUSION: WB-DWIBS/STIR is an effective modality for the pretherapeutic staging of indolent lymphoma, and it has benefits when evaluating extranodal lesions, compared with 18F-FDG-PET/CT.

Ischemic colitis after enema administration: Incidence, timing, and clinical features.

BACKGROUND: Enema administration is a common procedure in the emergency department (ED). However, several published case reports on enema-related ischemic colitis (IC) have raised the concerns regarding the safety of enema agents. Nevertheless, information on its true incidence and characteristics are still lacking. AIM: To investigate the incidence, timing, and risk factors of IC in patients receiving enema. METHODS: We consecutively collected the data of all adult patients receiving various enema administrations in the ED from January 2010 to December 2018 and identified patients confirmed with IC following enema. Of 8320 patients receiving glycerin enema, 19 diagnosed of IC were compared with an age-matched control group without IC. RESULTS: The incidence of IC was 0.23% among 8320 patients receiving glycerin enema; however, there was no occurrence of IC among those who used other enema agents. The mean age ± standard deviation (SD) of patients with glycerin enema-related IC was 70.2 ± 11.7. The mean time interval ± SD from glycerin enema administration to IC occurrence was 5.5 h ± 3.9 h (range 1-15 h). Of the 19 glycerin enema-related IC cases, 15 (79.0%) were diagnosed within 8 h. The independent risk factors for glycerin-related IC were the constipation score [Odds ratio (OR), 2.0; 95% confidence interval (CI): 1.1-3.5, P = 0.017] and leukocytosis (OR, 4.5; 95%CI: 1.4-14.7, P = 0.012). CONCLUSION: The incidence of glycerin enema-related IC was 0.23% and occurred mostly in the elderly in the early period following enema administration. Glycerin enema-related IC was associated with the constipation score and leukocytosis.

Added Value of Bone Suppression Image in the Detection of Subtle Lung Lesions on Chest Radiographs with Regard to Reader's Expertise.

BACKGROUND: Chest radiographs (CXR) are the most commonly used imaging techniques by various clinicians and radiologists. However, detecting lung lesions on CXR depends largely on the reader's experience level, so there have been several trials to overcome this problem using post-processing of CXR. We investigated the added value of bone suppression image (BSI) in detecting various subtle lung lesions on CXR with regard to reader's expertise. METHODS: We applied a software program to generate BSI in 1,600 patients in the emergency department. Of them, 80 patients with subtle lung lesions and 80 patients with negative finding on CXR were retrospectively selected based on the subtlety scores on CXR and CT findings. Ten readers independently rated their confidence in deciding the presence or absence of a lung lesion at each of 960 lung regions on the two separated imaging sessions: CXR alone vs. CXR with BSI. RESULTS: The additional use of BSI for all readers significantly increased the mean area under the curve (AUC) in detecting subtle lung lesions (0.663 vs. 0.706; P < 0.001). The less experienced readers were, the more AUC differences increased: 0.067 (P < 0.001) for junior radiology residents; 0.064 (P < 0.001) for non-radiology clinicians; 0.044 (P < 0.001) for senior radiology residents; and 0.019 (P = 0.041) for chest radiologists. The additional use of BSI significantly increased the mean confidence regarding the presence or absence of lung lesions for 213 positive lung regions (2.083 vs. 2.357; P < 0.001) and for 747 negative regions (1.217 vs. 1.195; P = 0.008). CONCLUSION: The use of BSI increases diagnostic performance and confidence, regardless of reader's expertise, reduces the impact of reader's expertise and can be helpful for less experienced clinicians and residents in the detection of subtle lung lesions.

Joint approach of diffusion- and perfusion-weighted MRI in intra-axial mass like lesions in clinical practice simulation.

Although advanced magnetic resonance imaging (MRI) techniques provide useful information for the differential diagnosis of intra-axial mass-like lesions, the specific diagnostic role of multimodal MRI over conventional magnetic resonance imaging (CMRI) alone in the differential diagnosis of mass-like lesions from a large heterogeneous cohort has not been studied. In this study, we aimed to determine the added value of a joint approach of diffusion-weighted imaging (DWI) and dynamic-susceptibility-contrast perfusion imaging (DSC-PWI) for diagnosis of intra-axial mass-like lesions, comparing them with CMRI alone. Furthermore, we performed these evaluations in a manner simulating clinical practice. Our institutional review board approved this retrospective study and waived the requirement for informed consent. A total of 1038 patients with intra-axial mass-like lesions were retrospectively recruited according to their histological and clinico-radiological diagnoses made between January 2005 and December 2014. All patients underwent CMRI, DWI and DSC-PWI. The diagnostic accuracy and confidence in diagnosing each type of intra-axial mass-like lesions, and for differentiating the intra-axial brain tumors from non-neoplastic lesions, were compared according to the MRI protocols. The disease-specific sensitivity of joint approach differed according to specific disease entities in diagnosing each disease category. Joint approach provided the best diagnostic accuracy for discriminating intra-axial brain tumors from non-neoplastic lesions, with high diagnostic accuracy (95.3-96.7%), specificity (82-84.0%), positive-predictive-value (97.0-97.3%), and negative-predictive-value (84.8-92.7%), with the reader's confidence values being significantly improved over those on CMRI alone (all p-values < 0.001). In conclusion, joint approach of DWI, DSC-PWI to CMRI helps to differentiate non-neoplastic lesions from intra-axial brain tumors, and improves diagnostic confidence compared with CMRI alone. The benefit from the combined imaging differs for each disease category; thus joint approach needs to be customized according to clinical suspicion.

Intraductal Papillary Neoplasm of the Bile Duct: Clinical, Imaging, and Pathologic Features.

OBJECTIVE: We outline the concept of intraductal papillary neoplasm of the bile duct (IPNB), discuss the morphologic features of IPNB and the differential diagnoses, and describe the radiologic approaches used in multidisciplinary management. CONCLUSION: The concept of IPNB has been evolving. Because the imaging features of IPNB can be variable, different mimickers according to IPNB subtype can be considered. A multimodality approach is essential to obtain an optimal diagnosis and establish treatment plans.

Early fragment removal on in vitro fertilization day 2 significantly improves the subsequent development and clinical outcomes of fragmented human embryos / 대한생식의학회지

OBJECTIVE: To determine whether fragment removal on in vitro fertilization (IVF) day 2 improved the subsequent development and pregnancy outcomes of fragmented embryos compared to similar-grade embryos without fragment removal. METHODS: This study was a retrospective analysis involving 191 IVF cycles in which all embryos had over 10% fragmentation (grade 3 or 4) on day 2 of the IVF-embryo transfer cycle from March 2015 to December 2017. IVF cycles were divided into the fragment removal group (n=87) and the no fragment removal group (n=104) as a control cohort. Before fragment removal, embryos with fragmentation on day 2 were incubated in Ca2+- and Mg2+-free biopsy medium under paraffin oil for 30 minutes. Microsurgical fragment removal was performed with later-assisted hatching and a handmade suction micropipette that had an outer diameter of 30 µm. RESULTS: There were no significant differences in the characteristics of the patients between the control and the fragment removal groups. After fragment removal and subsequent in vitro culture for 24 hours, the number of blastomeres (7.1±1.7 vs. 6.9±1.6) was comparable between the transferred embryos in the two groups, but the morphological grade of the embryos in the fragment removal group (1.9±0.7) was significantly higher than that of the control group (3.1±0.5, p < 0.01). The clinical pregnancy (43.7%) and implantation rates (25.8%) in the fragment removal group were significantly higher than those in the control group (28.8% and 14.0%, respectively; p < 0.05). CONCLUSION: Early fragment removal on day 2 significantly improved the subsequent development and pregnancy outcomes of fragmented embryos.