Feasible CT features to distinguish incidental rib enhancement from sclerotic metastasis in patients with malignancies.

OBJECTIVE: To investigate the CT features of incidental rib enhancement (RE) and to summarize the CT characteristics for distinguishing the RE from sclerotic metastasis (SM) in patients with malignancies. MATERIAL AND METHODS: This retrospective observational study enrolled 79 patients with RE (involved 133 ribs) during October 2014 and December 2021. Another 53 patients with SM (160 SM) in the same period were selected randomly for comparison. The location, enhancement patterns of RE were reviewed. The CT values of RE regions and SM were measured and statistically analyzed. RESULTS: Most REs (70 patients, 88.6%) were in the 1st to 6th ribs. 50 patients had solitary RE and 29 with multiple REs in a regional distribution. All the REs were closely connected to the intercostal venous plexus (ICVP) ipsilateral to the injection site. No visible abnormalities on unenhanced scans were detected in all REs. One hundred and twenty REs (90.2%) had nodular/patchy enhancement. The CT value of RE regions in the venous phase was lower than that in the arterial phase (589.8 ± 344.2 HU versus 1188.5 ± 325.3 HU, p < 0.001). During the venous phase, most REs (125, 94.0%) shrank or disappeared. SM appeared similar on both contrast-enhanced and unenhanced scans in terms of shape and CT values. CONCLUSION: The RE demonstrated characteristic CT features. The manifestations of nodular/patchy enhancement in the arterial phase, decreased density and shrinkage or disappearance during the venous phase, and no abnormality on unenhanced scans, as well as a close connection with the ICVP, may help differentiate RE from SM.

Response evaluation of hepatocellular carcinoma treated with stereotactic body radiation therapy: magnetic resonance imaging findings.

PURPOSE: To summarize the magnetic resonance imaging manifestations of hepatocellular carcinoma (HCC) with and without progression after stereotactic body radiation therapy (SBRT) and evaluate the treatment effect using the modified Liver Reporting and Data System (LI-RADS). METHODS: Between January 2015 and December 2020, 102 patients with SBRT-treated HCC were included. Tumor size, signal intensity, and enhancement patterns at each follow-up period were analyzed. Three different patterns of enhancement: APHE and wash-out, non-enhancement, and delayed enhancement. For modified LI-RADS, delayed enhancement with no size increase were considered to be a "treatment-specific expected enhancement pattern" for LR-TR non-viable. RESULTS: Patients were divided into two groups: without (n = 96) and with local progression (n = 6). Among patients without local progression, APHE and wash-out pattern demonstrated conversion to the delayed enhancement (71.9%) and non-enhancement (20.8%) patterns, with decreased signal intensity on T1WI(92.9%) and DWI(99%), increased signal intensity on T1WI (99%), and decreased size. The signal intensity and enhancement patterns stabilized after 6-9 months. Six cases with progression exhibited tumor growth, APHE and wash-out, and increased signal intensity on T2WI/DWI. Based on the modified LI-RADS criteria, 74% and 95% showed LR-TR-nonviable in 3 and 12 months post-SBRT, respectively. CONCLUSIONS: After SBRT, the signal intensity and enhancement patterns of HCCs showed a temporal evolution. Tumor growth, APHE and wash-out, and increased signal intensity on T2WI/DWI indicates tumor progression. Modified LI-RADS criteria showed good performance in evaluating nonviable lesions after SBRT.

Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases.

Backgrounds: A significant proportion of breast cancer patients showed receptor discordance between primary cancers and breast cancer brain metastases (BCBM), which significantly affected therapeutic decision-making. But it was not always feasible to obtain BCBM tissues. The aim of the present study was to analyze the receptor status of primary breast cancer and matched brain metastases and establish radiomic signatures to predict the receptor status of BCBM. Methods: The receptor status of 80 matched primary breast cancers and resected brain metastases were retrospectively analyzed. Radiomic features were extracted using preoperative brain MRI (contrast-enhanced T1-weighted imaging, T2-weighted imaging, T2 fluid-attenuated inversion recovery, and combinations of these sequences) collected from 68 patients (45 and 23 for training and test sets, respectively) with BCBM excision. Using least absolute shrinkage selection operator and logistic regression model, the machine learning-based radiomic signatures were constructed to predict the estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status of BCBM. Results: Discordance between the primary cancer and BCBM was found in 51.3% of patients, with 27.5%, 27.5%, and 5.0% discordance for ER, PR, and HER2, respectively. Loss of receptor expression was more common (33.8%) than gain (18.8%). The radiomic signatures built using combination sequences had the best performance in the training and test sets. The combination model yielded AUCs of 0.89, 0.88, and 0.87, classification sensitivities of 71.4%, 90%, and 87.5%, specificities of 81.2%, 76.9%, and 71.4%, and accuracies of 78.3%, 82.6%, and 82.6% for ER, PR, and HER2, respectively, in the test set. Conclusions: Receptor conversion in BCBM was common, and radiomic signatures show potential for noninvasively predicting BCBM receptor status.

Identifying Outcomes of Patients With Advanced Pancreatic Adenocarcinoma and RECIST Stable Disease Using Radiomics Analysis.

PURPOSE: Few studies have explored the biomarkers for predicting the heterogeneous outcomes of patients with advanced pancreatic adenocarcinoma showing stable disease (SD) on the initial postchemotherapy computed tomography. We aimed to devise a radiomics signature (RS) to predict these outcomes for further risk stratification. MATERIALS AND METHODS: Patients with advanced pancreatic adenocarcinoma and SD after chemotherapy were included. Pancreatic lesions on initial postchemotherapy computed tomography images were evaluated by radiomics analysis for predicting early death (≤ 1 year). RS was then internally and externally tested. The progression-free survival and objective response rate were compared between the low-risk and high-risk group of patients classified following RS. RESULTS: Approximately 62.7% of patients receiving chemotherapy showed SD at first response evaluation in the primary cohort, which were 59.6% and 57.9% in internal and external testing cohorts, respectively. The RS predicted 1-year overall survival well, with areas under the receiver operating characteristic curve of 0.91 in the training cohort, 0.90 in the validation cohort, 0.84 in the internal testing cohort, and 0.87 in the external testing cohort. The high-risk group had a shorter median progression-free survival (7.3 months v 9.0 months, P = .016, in the training cohort; 5.9 months v 9.2 months, P = .026, in the internal testing cohort) and a lower objective response rate (2.2% v 24.0% in the training cohort) than the low-risk group. In addition, RS was not related to the clinical characteristics and chemotherapy regimens. CONCLUSION: RS independently predicts the outcomes of patients with SD after chemotherapy well and can help to improve treatment decisions by identifying patients for whom current treatment may not be suitable.

Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study.

BACKGROUND: Accurate detection is essential for brain metastasis (BM) management, but manual identification is laborious. This study developed, validated, and evaluated a BM detection (BMD) system. METHODS: Five hundred seventy-three consecutive patients (10 448 lesions) with newly diagnosed BMs and 377 patients without BMs were retrospectively enrolled to develop a multi-scale cascaded convolutional network using 3D-enhanced T1-weighted MR images. BMD was validated using a prospective validation set comprising an internal set (46 patients with 349 lesions; 44 patients without BMs) and three external sets (102 patients with 717 lesions; 108 patients without BMs). The lesion-based detection sensitivity and the number of false positives (FPs) per patient were analyzed. The detection sensitivity and reading time of three trainees and three experienced radiologists from three hospitals were evaluated using the validation set. RESULTS: The detection sensitivity and FPs were 95.8% and 0.39 in the test set, 96.0% and 0.27 in the internal validation set, and ranged from 88.9% to 95.5% and 0.29 to 0.66 in the external sets. The BMD system achieved higher detection sensitivity (93.2% [95% CI, 91.6-94.7%]) than all radiologists without BMD (ranging from 68.5% [95% CI, 65.7-71.3%] to 80.4% [95% CI, 78.0-82.8%], all P < .001). Radiologist detection sensitivity improved with BMD, reaching 92.7% to 95.0%. The mean reading time was reduced by 47% for trainees and 32% for experienced radiologists assisted by BMD relative to that without BMD. CONCLUSIONS: BMD enables accurate BM detection. Reading with BMD improves radiologists' detection sensitivity and reduces their reading times.

MetaMixUp: Learning Adaptive Interpolation Policy of MixUp With Metalearning.

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semisupervised learning (SSL), and domain adaption. However, despite its empirical success, its deficiency of randomly mixing samples has poorly been studied. Since deep networks are capable of memorizing the entire data set, the corrupted samples generated by vanilla MixUp with a badly chosen interpolation policy will degrade the performance of networks. To overcome overfitting to corrupted samples, inspired by metalearning (learning to learn), we propose a novel technique of learning to a mixup in this work, namely, MetaMixUp. Unlike the vanilla MixUp that samples interpolation policy from a predefined distribution, this article introduces a metalearning-based online optimization approach to dynamically learn the interpolation policy in a data-adaptive way (learning to learn better). The validation set performance via metalearning captures the noisy degree, which provides optimal directions for interpolation policy learning. Furthermore, we adapt our method for pseudolabel-based SSL along with a refined pseudolabeling strategy. In our experiments, our method achieves better performance than vanilla MixUp and its variants under SL configuration. In particular, extensive experiments show that our MetaMixUp adapted SSL greatly outperforms MixUp and many state-of-the-art methods on CIFAR-10 and SVHN benchmarks under the SSL configuration.