Artificial intelligence (AI) powered by deep learning (DL) has shown remarkable progress in image recognition tasks. Over the past decade, AI has proven its feasibility for applications in medical imaging. Various aspects of clinical practice in neuroimaging can be improved with the help of AI. For example, AI can aid in detecting brain metastases, predicting treatment response of brain tumors, generating a parametric map of dynamic contrast-enhanced MRI, and enhancing radiomics research by extracting salient features from input images. In addition, image quality can be improved via AI-based image reconstruction or motion artifact reduction. In this review, we summarize recent clinical applications of DL in various aspects of neuroimaging.

Purpose: To evaluate whether the added value of contrast leakage information from dynamic susceptibility contrast magnetic resonance imaging (DSC MRI) is a better prognostic imaging biomarker than the cerebral blood volume (CBV) value in distinguishing true progression from pseudoprogression in glioblastoma patients. Materials and Methods: Forty-nine glioblastoma patients who had undergone MRI after concurrent chemoradiotherapy with temozolomide were enrolled in this retrospective study. Twenty features were extracted from the normalized relative CBV (nCBV) and extraction fraction (EF) map of the contrast-enhancing region in each patient. After univariable analysis, we used multivariable stepwise logistic regression analysis to identify significant predictors for differentiating between pseudoprogression and true progression. Receiver operating characteristic (ROC) analysis was employed to determine the best cutoff values for the nCBV and EF features. Finally, leave-one-out cross-validation was used to validate the best predictor in differentiating between true progression and pseudoprogression. Results: Multivariable stepwise logistic regression analysis showed that MGMT (O⁶-methylguanine-DNA methyltransferase) and EF max were independent differentiating variables (P = 0.004 and P = 0.02, respectively). ROC analysis yielded the best cutoff value of 95.75 for the EF max value for differentiating the two groups (sensitivity, 61%; specificity, 84.6%; AUC, 0.681 ± 0.08; 95% CI, 0.524-0.837; P = 0.03). In the leave-one-out cross-validation of the EF max value, the cross-validated values for predicting true progression and pseudoprogression accuracies were 69.4% and 71.4%, respectively. Conclusion: We demonstrated that contrast leakage information parameter from DSC MRI showed significance in differentiating true progression from pseudoprogression in glioblastoma patients.

Purpose: To assess conventional MRI features associated with residual soft-tissue sarcomas following unplanned excision (UPE), and to compare the diagnostic performance of conventional MRI only with that of MRI including diffusion-weighted imaging (DWI) for residual tumors after UPE. Materials and Methods: We included 103 consecutive patients who had received UPE of a soft-tissue sarcoma with wide excision of the tumor bed between December 2013 and December 2019 and who also underwent conventional MRI and DWI in this retrospective study. The presence of focal enhancement, soft-tissue edema, fascial enhancement, fluid collections, and hematoma on MRI including DWI was reviewed by two musculoskeletal radiologists. We used classification and regression tree (CART) analysis to identify the most significant MRI features. We compared the diagnostic performances of conventional MRI and added DWI using the McNemar test. Results: Residual tumors were present in 69 (66.9%) of 103 patients, whereas no tumors were found in 34 (33.1%) patients. CART showed focal enhancement to be the most significant predictor of residual tumors and correctly predicted residual tumors in 81.6% (84/103) and 78.6% (81/103) of patients for Reader 1 and Reader 2, respectively. Compared with conventional MRI only, the addition of DWI for Reader 1 improved specificity (32.8% vs. 56%, 33.3% vs. 63.0%, P < 0.05), decreased sensitivity (96.8% vs. 84.1%, 98.7% vs. 76.7%, P < 0.05), without a difference in diagnostic accuracy (76.7% vs. 74.8%, 72.9% vs. 71.4%) in total and in subgroups. For Reader 2, diagnostic performance was not significantly different between the sets of MRI (P > 0.05). Conclusion: After UPE of a soft-tissue sarcoma, the presence or absence of a focal enhancement was the most significant MRI finding predicting residual tumors. MRI provided good diagnostic accuracy for detecting residual tumors, and the addition of DWI to conventional MRI may increase specificity.

Purpose: To evaluate the clinical benefit of 2D contrast-enhanced T2 fluid-attenuated inversion recovery (CE-T2 FLAIR) image for detecting leptomeningeal metastasis (LM) in the brain metastasis work-up for lung cancer. Materials and Methods: From June 2017 to July 2019, we collected all consecutive patients with lung cancer who underwent brain magnetic resonance image (MRI), including contrast-enhanced 3D fast spin echo T1 black-blood image (CE-T1WI) and CE-T2 FLAIR; we recruited clinico-radiologically suspected LM cases. Two independent readers analyzed the images for LM in three sessions: CE-T1WI, CE-T2 FLAIR, and their combination. Results: We recruited 526 patients with suspected lung cancer who underwent brain MRI; of these, we excluded 77 (insufficient image protocol, unclear pathology, different contrast media, poor image quality). Of the 449 patients, 34 were clinico-radiologically suspected to have LM; among them, 23 were diagnosed with true LM. The calculated detection performance of CE-T1WI, CE-T2 FLAIR, and combined analysis obtained from the 34 suspected LM were highest in the combined analysis (AUC: 0.80, 0.82, and 0.89, respectively). The inter-observer agreement was also the highest in the combined analysis (0.68, 0.72, and 0.86, respectively). In quantitative analyses, CNR of CE-T2 FLAIR was significantly higher than that of CE-T1WI (Wilcoxon signed rank test, P < 0.05). Conclusion: Adding CE-T2 FLAIR might provide better detection for LM in the brain-metastasis screening for lung cancer.

Encapsulated papillary carcinoma (EPC) is an uncommon breast malignancy that is known to be indolent and associated with an excellent prognosis. However, there is a rare possibility of locoregional relapse or metastasis. Here, we present a case of recurrent EPC in the ipsilateral internal mammary lymph node (IMLN) that was detected in the postoperative magnetic resonance imaging with abbreviated protocol (AB-MRI). AB-MRI could facilitate the early detection of recurrent disease in the IMLN and may provide prognostic gain for such patients.

In this report we present a case of disseminated diffuse large B-cell lymphoma (DLBCL) in a 79-year-old man affecting the bone, soft tissue, testis, and both kidneys, which are rarely affected sites. The formation of a large mass in the bone, soft tissue, and testis due to DLBCL is rarely seen nowadays. In this article, we describe the imaging findings and clinical significance of multifocal extranodal involvement in DLBCL, focusing on involvement of bone, soft tissue, and testis.

Sarcoidosis is a systemic disease of unknown etiology that can involve almost any organ systems, characterized by the presence of non-caseating granulomas in affected organs. Typically, the lungs and mediastinal lymph nodes are the most-affected sites, with cutaneous manifestations being the second. Subcutaneous nodules are a rare manifestation of cutaneous sarcoidosis, and it is even rarer for subcutaneous sarcoidosis to be associated with pulmonary sarcoidosis. Here, we present a case of subcutaneous sarcoidosis of the distal lower leg associated with pulmonary sarcoidosis.

Gadoxetic acid-enhanced magnetic resonance imaging (MRI) has been widely used to detect and characterize focal hepatic lesions. Because gadoxetic acid is a hepatocyte-specific contrast agent, its patterns during hepatobiliary phase enhancement provide useful information for differential diagnoses of focal hepatic lesions. Hepatic angiomyolipoma (AML) is a rare mesenchymal hepatic neoplasm composed of blood vessels, epithelioid cells, and varying amounts of adipose tissue components. Hepatic AMLs usually show marked hypointensity during the hepatobiliary phase of gadoxetic acid-enhanced MRI as hepatic AMLs are devoid of hepatocytes and fibrotic components. The present study describes a patient with hepatic AML and an atypical imaging feature. This tumor showed hyperintensity during the hepatobiliary phase of gadoxetic acid-enhanced MRI, mimicking hepatocellular tumors such as hepatocellular adenoma. The hepatobiliary hyperintensity of this lesion was likely due to multifocal entrapped hepatocytes resulting from an intrasinusoidal growth pattern of tumor cells and insufficient hepatic parenchymal enhancement during the hepatobiliary phase of gadoxetic acid-enhanced MRI.

Paratesticular liposarcoma is a very rare tumor that is typically reported as isolated cases of or as components of larger studies of liposarcomas. Image findings are similar to those of other anatomic sites, but in less-common sites, their appearance may be less familiar, and they may be mistaken for other pathologies. In addition, atypical image findings of liposarcoma make diagnosis more difficult. Herein, we report on the case of a 45-year-old male patient who presented with a painless, palpable mass in the right scrotum. The patient was diagnosed with paratesticular liposarcoma by excisional biopsy.

Tuberculous epididymo-orchitis, a rare form of extrapulmonary tuberculosis, results from hematogenous dissemination or retrograde extension from the lower urinary tract. Herein, we studied the case of a 22-year-old male patient who presented with refractory left scrotal pain and inflammation. The patient also complained of multifocal pain involving the right buttock, posterior thigh, and right wrist, without trauma history. The patient was diagnosed with multifocal tuberculosis by sputum AFB study and right sacroiliac joint biopsy.

The number of women undergoing breast augmentation surgery with a prosthesis for cosmetic purposes or reconstruction after a mastectomy is steadily increasing. Hematoma is one of complications associated with breast augmentation surgery. It usually occurs early in the postoperative period. It rarely occurs late (after six months). However, chronic hematomas after prosthesis removal have not yet been reported in the radiological literature. We present a case of unilateral chronic organizing hematoma that developed late and grew persistently over long period after breast explantation, mimicking a soft tissue tumor of the chest wall clinically. Meanwhile, characteristic magnetic resonance imaging features of heterogeneous signal intensities on T1-weighted and T2-weighted images and dark signal intensity with a persistent enhancement of the peripheral wall of the lesion were found. These can be used for a differential diagnosis.