Reducing false positives in deep learning-based brain metastasis detection by using both gradient-echo and spin-echo contrast-enhanced MRI: validation in a multi-center diagnostic cohort.

OBJECTIVES: To develop a deep learning (DL) for detection of brain metastasis (BM) that incorporates both gradient- and turbo spin-echo contrast-enhanced MRI (dual-enhanced DL) and evaluate it in a clinical cohort in comparison with human readers and DL using gradient-echo-based imaging only (GRE DL). MATERIALS AND METHODS: DL detection was developed using data from 200 patients with BM (training set) and tested in 62 (internal) and 48 (external) consecutive patients who underwent stereotactic radiosurgery and diagnostic dual-enhanced imaging (dual-enhanced DL) and later guide GRE imaging (GRE DL). The detection sensitivity and positive predictive value (PPV) were compared between two DLs. Two neuroradiologists independently analyzed BM and reference standards for BM were separately drawn by another neuroradiologist. The relative differences (RDs) from the reference standard BM numbers were compared between the DLs and neuroradiologists. RESULTS: Sensitivity was similar between GRE DL (93%, 95% confidence interval [CI]: 90-96%) and dual-enhanced DL (92% [89-94%]). The PPV of the dual-enhanced DL was higher (89% [86-92%], p < .001) than that of GRE DL (76%, [72-80%]). GRE DL significantly overestimated the number of metastases (false positives; RD: 0.05, 95% CI: 0.00-0.58) compared with neuroradiologists (RD: 0.00, 95% CI: - 0.28, 0.15, p < .001), whereas dual-enhanced DL (RD: 0.00, 95% CI: 0.00-0.15) did not show a statistically significant difference from neuroradiologists (RD: 0.00, 95% CI: - 0.20-0.10, p = .913). CONCLUSION: The dual-enhanced DL showed improved detection of BM and reduced overestimation compared with GRE DL, achieving similar performance to neuroradiologists. CLINICAL RELEVANCE STATEMENT: The use of deep learning-based brain metastasis detection with turbo spin-echo imaging reduces false positive detections, aiding in the guidance of stereotactic radiosurgery when gradient-echo imaging alone is employed. KEY POINTS: •Deep learning for brain metastasis detection improved by using both gradient- and turbo spin-echo contrast-enhanced MRI (dual-enhanced deep learning). •Dual-enhanced deep learning increased true positive detections and reduced overestimation. •Dual-enhanced deep learning achieved similar performance to neuroradiologists for brain metastasis counts.

Prolapsed Uterine Smooth Muscle Tumor of Uncertain Malignant Potential: A Case Report and Review of Radiologic Findings.

INTRODUCTION: Uterine smooth muscle tumor of uncertain malignant potential (STUMP) is a rare tumor that arises in the myometrium of the uterus. It is regarded as an intermediate malignant tumor according to the recent World Health Organization classification. Few studies have reported the radiologic findings of STUMP, and the differentiation of STUMP from leiomyoma remains controversial. CASE DESCRIPTION: A 42-year-old nulliparous female presented at our institution with massive vaginal bleeding. Radiological studies, including ultrasonography, computed tomography (CT), and magnetic resonance imaging, revealed an oval-shaped mass with well-defined margins in the uterus protruding into the vagina. The patient underwent a total abdominal hysterectomy, and the final pathology was confirmed as STUMP. CONCLUSION: Distinguishing STUMP from leiomyomas based solely on radiological findings can be challenging. However, if the uterine mass appears as a single mass lacking acoustic shadowing on ultrasound and demonstrates diffusion restriction with high T2 signal intensity on magnetic resonance imaging, consideration of STUMP may be necessary for proper patient management, given the poor prognosis associated with this tumor.

Huge Primary Clear Cell Hepatocellular Carcinoma: a Case Report and Review of Radiologic Findings.

INTRODUCTION: Clear cell hepatocellular carcinoma (HCC) is a rare subtype of HCC. Histologically, clear cell HCC is characterized by the cytoplasmic accumulation of glycogen with a clear cell appearance, constituting > 80% of tumor cells. Radiologically, clear cell HCC demonstrates early enhancement and washout similar to conventional HCC. Occasionally, enhancing capsule and intratumoral fat are accompanied by clear cell HCC. CASE DESCRIPTION: A 57-year-old male presented to our hospital with right upper quadrant abdominal pain. Ultrasonography, computed tomography, and magnetic resonance imaging revealed a large mass with a well-defined margin in the right hemiliver. The patient underwent a right hemihepatectomy, and the final histopathology revealed clear cell-type HCC. CONCLUSION: Distinguishing clear cell types from other types of HCC solely based on radiological findings is challenging. If hepatic tumors exhibit encapsulated margins, enhancing rims, intratumoral fat, and arterial phase hyperenhancement/washout pattern despite their large size, consideration of clear cell subtypes in the differential diagnosis list will aid patient management, implying better prognosis than not-otherwise-specified HCC.

Rosmarinic acid inhibits Ca2+-dependent pathways of T-cell antigen receptor-mediated signaling by inhibiting the PLC-gamma 1 and Itk activity.

Rosmarinic acid (RosA) is a hydroxylated compound frequently found in herbal plants and is mostly responsible for anti-inflammatory and antioxidative activity. Previously, we observed that RosA inhibited T-cell antigen receptor (TCR)- induced interleukin 2 (IL-2) expression and subsequent T-cell proliferation in vitro. In this study, we investigated in detail inhibitory mechanism of RosA on TCR signaling, which ultimately activates IL-2 promoter by activating transcription factors, such as nuclear factor of activated T cells (NF-AT) and activating protein-1 (AP-1). Interestingly, RosA inhibited NF-AT activation but not AP-1, suggesting that RosA inhibits Ca(2+)-dependent signaling pathways only. Signaling events upstream of NF-AT activation, such as the generation of inositol 1,4,5-triphosphate and Ca(2+) mobilization, and tyrosine phosphorylation of phospholipase C-gamma 1 (PLC-gamma 1) were strongly inhibited by RosA. Tyrosine phosphorylation of PLC-gamma 1 is largely dependent on 3 kinds of protein tyrosine kinases (PTKs), ie, Lck, ZAP-70, and Itk. We found that RosA efficiently inhibited TCR-induced tyrosine phosphorylation and subsequent activation of Itk but did not inhibit Lck or ZAP-70. ZAP-70-dependent signaling pathways such as the tyrosine phosphorylation of LAT and SLP-76 and serine/threonine phosphorylation of mitogen-activated protein kinases (MAPKs) were intact in the presence of RosA, confirming that RosA suppresses TCR signaling in a ZAP-70-independent manner. Therefore, we conclude that RosA inhibits TCR signaling leading to Ca(2+) mobilization and NF-AT activation by blocking membrane-proximal events, specifically, the tyrosine phosphorylation of inducible T cells kinase (Itk) and PLC-gamma 1.