ABSTRACT
Purpose@#Breast cancer brain metastases (BCBM) may involve subtypes that differ from the primary breast cancer lesion. This study aimed to develop a radiomics-based model that utilizes preoperative brain MRI for multiclass classification of BCBM subtypes and to investigate whether the model offers better prediction accuracy than the assumption that primary lesions and their BCBMs would be of the same subtype (non-conversion model) in an external validation set. @*Materials and Methods@#The training and external validation sets each comprised 51 cases (102 cases total). Four machine learning classifiers combined with three feature selection methods were trained on radiomic features and primary lesion subtypes for prediction of the following four subtypes: 1) hormone receptor (HR)+/human epidermal growth factor receptor 2 (HER2)-, 2) HR+/HER2+, 3) HR-/HER2+, and 4) triple-negative. After training, the performance of the radiomics-based model was compared to that of the non-conversion model in an external validation set using accuracy and F1-macro scores. @*Results@#The rate of discrepant subtypes between primary lesions and their respective BCBMs were 25.5% (n=13 of 51) in the training set and 23.5% (n=12 of 51) in the external validation set. In the external validation set, the accuracy and F1-macro score of the radiomics-based model were significantly higher than those of the non-conversion model (0.902 vs. 0.765, p=0.004; 0.861 vs. 0.699, p=0.002). @*Conclusion@#Our radiomics-based model represents an incremental advance in the classification of BCBM subtypes, thereby facilitating a more appropriate personalized therapy.
ABSTRACT
Cerebral amyloid angiopathy-related inflammation (CAA-RI) is a rare encephalopathy characterized by the coexistence of a perivascular inflammatory reaction in patients with cerebral amyloid angiopathy. CAA-RI diagnosis is challenging as its final diagnosis requires invasive procedures such as autopsy or brain biopsy. Therefore, multimodal imaging approaches with clinical considerations are essential for the probable diagnosis of CAA-RI. In particular, in the case of CAA-RI presented with uncommon clinical symptoms, the need for imaging in diagnosis is further highlighted by difficulties of clinical approaches. Herein, we report a case of CAA-RI with unusual clinical manifestation diagnosed using multimodal imaging including magnetic resonance imaging (MRI) and amyloid positron emission tomography-computed tomography (PET-CT). Multimodal imaging approaches using adequate MRI sequences and PET-CT scans could facilitate the diagnosis of CAA-RI without requiring invasive pathological confirmation.
ABSTRACT
Purpose@#Neuregulin 1 (NRG1) gene fusion is a potentially actionable oncogenic driver. The oncoprotein binds to ERBB3-ERBB2 heterodimers and activates downstream signaling, supporting a therapeutic approach for inhibiting ERBB3/ERBB2. However, the frequency and clinicopathological features of solid tumors harboring NRG1 fusions in Korean patients remain largely unknown. @*Materials and Methods@#We reviewed archival data from next-generation sequencing panel tests conducted at a single institution, specifically selecting patients with in-frame fusions that preserved the functional domain. The clinicopathological characteristics of patients harboring NRG1 fusions were retrospectively reviewed. @*Results@#Out of 8,148 patients, NRG1 fusions were identified in 22 patients (0.27%). The average age of the patients was 59 years (range, 32 to 78 years), and the male-to-female ratio was 1:1.2. The lung was the most frequently observed primary site (n=13), followed by the pancreaticobiliary tract (n=3), gastrointestinal tract (n=2, stomach and rectum each), ovary (n=2), breast (n=1), and soft tissue (n=1). Histologically, all tumors demonstrated adenocarcinoma histology, with the exception of one case of sarcoma. CD74 (n=8) and SLC3A2 (n=4) were the most frequently identified fusion partners. Dominant features included the presence of fewer than three co-occurring genetic alterations, a low tumor mutation burden, and low programmed death-ligand 1 expression. Various clinical responses were observed in patients with NRG1 fusions. @*Conclusion@#Despite the rarity of NRG1 fusions in Korean patients with solid tumors, identification through next-generation sequencing enables the possibility of new targeted therapies.
ABSTRACT
Dynamic contrast-enhanced MRI (DCE-MRI) is a noninvasive imaging technique used to evaluate tissue vascularity/permeability features through consecutive imaging acquisitions after gadolinium-based contrast agent administration. Over the past several decades, techniques and protocols for DCE-MRI have evolved, leading to growing applications of DCE-MRI for different neurological disorders. Although most established applications of DCE-MRI are for studying tumors, an increasing number of studies have been evaluating the use of this technique for neurodegenerative and other miscellaneous diseases. The purpose of this article was to provide an overview of DCE-MRI and its clinical applications in various neurological diseases.
ABSTRACT
Purpose@#This study aimed to investigate whether a deep learning model for automated detection of unruptured intracranial aneurysms on time-of-flight (TOF) magnetic resonance angiography (MRA) can achieve a target diagnostic performance comparable to that of human radiologists for approval from the Korean Ministry of Food and Drug Safety as an artificial intelligence-applied software. @*Materials and Methods@#In this single-center, retrospective, confirmatory clinical trial, the diagnostic performance of the model was evaluated in a predetermined test set. After sample size estimation, the test set consisted of 135 aneurysm-containing examinations with 168 intracranial aneurysms and 197 aneurysm-free examinations. The target sensitivity and specificity were set as 87% and 92%, respectively. The patient-wise sensitivity and specificity of the model were analyzed. Moreover, the lesion-wise sensitivity and false-positive detection rate per case were also investigated. @*Results@#The sensitivity and specificity of the model were 91.11% [95% confidence interval (CI): 84.99, 95.32] and 93.91% (95% CI:89.60, 96.81), respectively, which met the target performance values. The lesion-wise sensitivity was 92.26%. The overall falsepositive detection rate per case was 0.123. Of the 168 aneurysms, 13 aneurysms from 12 examinations were missed by the model. @*Conclusion@#The present deep learning model for automated detection of unruptured intracranial aneurysms on TOF MRA achieved the target diagnostic performance comparable to that of human radiologists. With high standalone performance, this model may be useful for accurate and efficient diagnosis of intracranial aneurysm.
ABSTRACT
Purpose@#This study aimed to investigate whether a deep learning model for automated detection of unruptured intracranial aneurysms on time-of-flight (TOF) magnetic resonance angiography (MRA) can achieve a target diagnostic performance comparable to that of human radiologists for approval from the Korean Ministry of Food and Drug Safety as an artificial intelligence-applied software. @*Materials and Methods@#In this single-center, retrospective, confirmatory clinical trial, the diagnostic performance of the model was evaluated in a predetermined test set. After sample size estimation, the test set consisted of 135 aneurysm-containing examinations with 168 intracranial aneurysms and 197 aneurysm-free examinations. The target sensitivity and specificity were set as 87% and 92%, respectively. The patient-wise sensitivity and specificity of the model were analyzed. Moreover, the lesion-wise sensitivity and false-positive detection rate per case were also investigated. @*Results@#The sensitivity and specificity of the model were 91.11% [95% confidence interval (CI): 84.99, 95.32] and 93.91% (95% CI:89.60, 96.81), respectively, which met the target performance values. The lesion-wise sensitivity was 92.26%. The overall falsepositive detection rate per case was 0.123. Of the 168 aneurysms, 13 aneurysms from 12 examinations were missed by the model. @*Conclusion@#The present deep learning model for automated detection of unruptured intracranial aneurysms on TOF MRA achieved the target diagnostic performance comparable to that of human radiologists. With high standalone performance, this model may be useful for accurate and efficient diagnosis of intracranial aneurysm.
ABSTRACT
PURPOSE: The purpose of this study is to investigate dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and plasma cytokines and angiogenic factors (CAFs) as pharmacodynamic and prognostic biomarkers of bevacizumab monotherapy in colorectal cancer with liver metastasis (CRCLM). MATERIALS AND METHODS: From July 2011 to March 2012, 28 patients with histologically confirmed CRCLM received bevacizumab monotherapy followed by combined FOLFOX therapy. The mean age of the patients was 57 years (range, 30 to 77 years). DCE-MRI (K(trans) and IAUC₆₀) was performed at baseline, first follow-up (3 days after bevacizumab monotherapy), and second follow-up (3 days after combined therapy). CAF levels (vascular endothelial growth factor [VEGF], placental growth factor [PlGF], and interleukin-8) were assessed on the same days. Progression-free survival (PFS) time distributions were summarized using the Kaplan-Meier method and compared using log-rank tests. RESULTS: The median PFS period was 11.2 months. K(trans), IAUC₆₀, VEGF, and PlGF values on the first follow-up day were significantly different compared with baseline values. No differences were observed on the second follow-up day. A > 40% decrease in K(trans) from baseline to first follow-up was associated with a longer PFS (hazard ratio, 0.349; 95% confidence interval, 0.133 to 0.912; p=0.032). Changes in CAFs did not show correlation with PFS time. CONCLUSION: DCE-MRI parameters and CAFs are pharmacodynamic biomarkers of bevacizumab for CRCLM. In our study, change in K(trans) at 3 days after bevacizumab monotherapy was a favorable prognostic factor; however, the value of CAFs as a prognostic biomarker was not found.
Subject(s)
Humans , Angiogenesis Inducing Agents , Bevacizumab , Biomarkers , Colorectal Neoplasms , Cytokines , Disease-Free Survival , Endothelial Growth Factors , Follow-Up Studies , Liver , Magnetic Resonance Imaging , Methods , Neoplasm Metastasis , Plasma , Vascular Endothelial Growth Factor AABSTRACT
PURPOSE: We evaluated the safety and effectiveness of the Magnetic Resonance-guided Focused Ultrasound (MRgFUS) with the ExAblate Conformal Bone System for the palliation of painful bone metastases. MATERIALS AND METHODS: Our Institutional Review Board approved this study, and all patients gave informed consent prior to enrollment. A total of six painful metastatic bone lesions in five patients were treated using MRgFUS with the ExAblate Conformal Bone System for pain palliation. The follow-up sessions were at 3 days, 2 weeks, 1, 2, and 3 months, and 1 year after treatment. Efficacy was evaluated by the changes in visual analog scale (VAS) scores. At 3-months and 1-year follow-ups, unenhanced computed tomography and contrast-enhanced MR imaging examinations were performed. All adverse events were assessed to evaluate treatment safety. RESULTS: All patients showed significant pain relief within 2 weeks. Two patients experienced complete pain reduction that lasted for 1 year. Two other patients showed pain relief measured as VAS scores of 2 and 4 on their last follow-up. Although the remaining patient had experienced significant pain relief in two lesions, the VAS score re-increased on his last follow-up. The size of the enhancing soft tissue mass in metastatic lesions decreased, and new bone formation was seen on follow-up images. Although adverse events were not serious, non-specific leg pain and second degree skin burn were noted. CONCLUSION: MRgFUS was demonstrated to be effective palliative treatment within 2 weeks in selected patients with painful bone metastases.
Subject(s)
Adult , Aged , Female , Humans , Male , Middle Aged , Young Adult , Bone Neoplasms/secondary , Contrast Media , High-Intensity Focused Ultrasound Ablation/adverse effects , Magnetic Resonance Imaging, Interventional/methods , Magnetic Resonance Spectroscopy , Pain , Pain Management , Palliative Care , Prospective Studies , Tomography, X-Ray Computed , Treatment OutcomeABSTRACT
PURPOSE: We evaluated the safety and effectiveness of the Magnetic Resonance-guided Focused Ultrasound (MRgFUS) with the ExAblate Conformal Bone System for the palliation of painful bone metastases. MATERIALS AND METHODS: Our Institutional Review Board approved this study, and all patients gave informed consent prior to enrollment. A total of six painful metastatic bone lesions in five patients were treated using MRgFUS with the ExAblate Conformal Bone System for pain palliation. The follow-up sessions were at 3 days, 2 weeks, 1, 2, and 3 months, and 1 year after treatment. Efficacy was evaluated by the changes in visual analog scale (VAS) scores. At 3-months and 1-year follow-ups, unenhanced computed tomography and contrast-enhanced MR imaging examinations were performed. All adverse events were assessed to evaluate treatment safety. RESULTS: All patients showed significant pain relief within 2 weeks. Two patients experienced complete pain reduction that lasted for 1 year. Two other patients showed pain relief measured as VAS scores of 2 and 4 on their last follow-up. Although the remaining patient had experienced significant pain relief in two lesions, the VAS score re-increased on his last follow-up. The size of the enhancing soft tissue mass in metastatic lesions decreased, and new bone formation was seen on follow-up images. Although adverse events were not serious, non-specific leg pain and second degree skin burn were noted. CONCLUSION: MRgFUS was demonstrated to be effective palliative treatment within 2 weeks in selected patients with painful bone metastases.