The prognosis of patients with lung adenocarcinoma (LUAD), especially early-stage LUAD, is dependent on clinicopathological features. However, its predictive utility is limited. In this study, we developed and trained a DeepRePath model based on a deep convolutional neural network (CNN) using multi-scale pathology images to predict the prognosis of patients with early-stage LUAD. DeepRePath was pre-trained with 1067 hematoxylin and eosin-stained whole-slide images of LUAD from the Cancer Genome Atlas. DeepRePath was further trained and validated using two separate CNNs and multi-scale pathology images of 393 resected lung cancer specimens from patients with stage I and II LUAD. Of the 393 patients, 95 patients developed recurrence after surgical resection. The DeepRePath model showed average area under the curve (AUC) scores of 0.77 and 0.76 in cohort I and cohort II (external validation set), respectively. Owing to low performance, DeepRePath cannot be used as an automated tool in a clinical setting. When gradient-weighted class activation mapping was used, DeepRePath indicated the association between atypical nuclei, discohesive tumor cells, and tumor necrosis in pathology images showing recurrence. Despite the limitations associated with a relatively small number of patients, the DeepRePath model based on CNNs with transfer learning could predict recurrence after the curative resection of early-stage LUAD using multi-scale pathology images.

Purpose: Cardiac 2-deoxy-2-[F-18]fluoro-D-glucose positron emission tomography (FDG PET) is widely used to assess myocardial viability in patients with ischemic heart disease. While sufficient glucose uptake is a prerequisite for accurate interpretation of cardiac viability, there are a lack of data on which clinical variables have the most significant impact on myocardial glucose metabolism. Therefore, this study was designed to evaluate several clinical variables that could affect myocardial glucose metabolism. Methods: A total of 214 consecutive cases were retrospectively enrolled in this study. All subjects received 250 mg of acipimox and underwent glucose loading as preparation for cardiac FDG PET/CT. Three-dimensional regions of interest (ROIs) were drawn on PET/CT fusion images. Myocardial glucose uptake ratio (MGUR = SUVmax of LV myocardium/SUVmean of liver) was then calculated. Multiple clinical variables including body mass index (BMI), blood glucose levels at different times, administered insulin dosage, lipid profiles, and ejection fraction were measured and analyzed for correlation with myocardial glucose uptake. After dichotomizing the subjects based on a BMI of 25, each group’s MGUR was compared. Results: Myocardial uptake showed significant correlations with BMI (r = −0.162, p = 0.018), HbA1c (r = −0.150, p = 0.030), and triglyceride levels (r = −0.137, p = 0.046). No other clinical variables showed a significant correlation with myocardial glucose uptake. After multiple linear regression analysis, BMI (p = 0.032) and HbA1c (p = 0.050) showed a correlation with MGUR. In group analysis, after dividing patients based on BMI, the obese group showed significantly lower myocardial uptake than the non-obese group (3.8 ± 1.9 vs. 4.4 ± 2.1, p = 0.031). Conclusions: Among several clinical variables, BMI and HbA1c levels were related to myocardial glucose uptake. A prospective study would be needed to examine whether a protocol that additionally considers BMI and HbA1c levels is necessary for the current cardiac FDG PET protocol.

A 60-year-old man diagnosed with gastric adenocarcinoma underwent FDG PET/CT. After completing 9 cycles of combination chemotherapy with nivolumab and FOLFOX, he had multiple new nodular uptakes in the bilateral cervical chains and mediastinum. The pathology of the right neck node confirmed reactive lymph node hyperplasia without evidence of malignancy, suggesting pseudoprogression after immunotherapy. It is worthwhile to report these PET image patterns, as they could significantly influence clinical decision-making.

Frontotemporal dementia is a clinical syndrome that is characterized by a progressive deterioration in behavior, personality, and/or language, with relative preservation of memory, and its phenotype and molecular basis are heterogeneous. We present a case of a 62-year-old female patient who underwent ¹⁸F-FDG PET/CT and ¹⁸F-FP-CIT PET/CT for differential diagnosis of psychiatric disease and types of dementia. ¹⁸F-FDG PET/CT image showed a compatible finding for frontotemporal dementia, and ¹⁸F-FP-CIT PET/CT image showed dominantly decreased dopamine transporter activity in the bilateral caudate nucleus.

Aortic angiosarcomas are rare. Due to its rarity and metastatic presentation, it is difficult to diagnose metastatic aortic angiosarcoma. We describe the clinicopathological and radiologic features of a metastatic aortic angiosarcoma presenting as musculoskeletal metastases. A 59-year-old male patient presented with left thigh pain. Plain radiographs revealed multifocal osteolytic lesions in the left femur shaft. Abdominopelvic computed tomography showed a lobulated osteolytic lesion in the left iliac bone. Magnetic resonance images revealed multifocal soft tissue lesions in the thigh musculature. A positron emission tomography/computed tomography (PET/CT) scan demonstrated multiple foci of increased uptake in the left femur bone, pelvis, left thigh, and calf musculature. Focal increased uptake in the lower abdominal aorta was newly detected. Pelvis biopsy showed tumor cell nests of epithelioid cells. The tumor cells showed vasoformative features. Immunohistochemically, the tumor cells showed positivity for vimentin, CD31, and ERG. The pathologic diagnosis of epithelioid angiosarcoma was established. The origin of the tumor was presumed to be the aorta. This case underscores the importance of PET scans in identifying primary lesions. In terms of the histopathologic diagnosis of biopsy samples with tumor cells exhibiting epithelioid neoplastic morphology, employing appropriate ancillary techniques such as immunocytochemistry with vascular markers may assist in accurately diagnosing metastatic angiosarcoma.

MicroRNA transcriptomes from fresh tumors and the adjacent normal tissues were profiled in 10 Korean patients diagnosed with lung adenocarcinoma using a next-generation sequencing (NGS) technique called miRNA-seq. The sequencing quality was assessed using FastQC, and low-quality or adapter-contaminated portions of the reads were removed using Trim Galore. Quality-assured reads were analyzed using miRDeep2 and Bowtie. The abundance of known miRNAs was estimated using the reads per million (RPM) normalization method. Subsequently, using DESeq2 and Wx, we identified differentially expressed miRNAs and potential miRNA biomarkers for lung adenocarcinoma tissues compared to adjacent normal tissues, respectively. We defined reliable miRNA biomarkers for lung adenocarcinoma as those detected by both methods. The miRNA-seq data are available in the Gene Expression Omnibus (GEO) database under accession number GSE196633, and all processed data can be accessed via the Mendeley data website.