ABSTRACT
Primary hepatic schwannoma is an extremely rare tumor with a good prognosis. Preoperative diagnosis is often challenging due to nonspecific clinical symptoms and its rarity. Here, we report a case of a 56-year-old male patient misdiagnosed with malignant liver tumor, later identified as primary hepatic schwannoma. Furthermore, clinical and histopathological features of 19 cases of primary hepatic schwannoma are also documented. The age of the patients ranged from 38 to 72 years, with a mean age of 56.4 years, and the disease was more common in females. Patients typically presented without clinical symptoms and were not associated with neurofibromatosis type 1. Histopathological features of the tumor were similar to soft tissue schwannoma, characterized by a thick capsule consisting of Antoni A and Antoni B areas. Immunohistochemically, the tumor showed strong positivity and diffusely stained with S-100, while being negative for CD34, CD117, and SMA. Complete resection of the tumor was achieved in all patients. The prognosis was favorable, with no signs of recurrence. Follow-up examinations revealed disease-free survival ranging from 6 to 27 months. Differential diagnosis of primary hepatic schwannoma from malignant liver tumors and metastatic liver tumors can be made based on histopathological features and immunohistochemical staining with S-100.
ABSTRACT
Primary liver cancer arises either from hepatocytic or biliary lineage cells, giving rise to hepatocellular carcinoma (HCC) or intrahepatic cholangiocarcinoma (ICCA). Combined hepatocellular- cholangiocarcinomas (cHCC-CCA) exhibit equivocal or mixed features of both, causing diagnostic uncertainty and difficulty in determining proper management. Here, we perform a comprehensive deep learning-based phenotyping of multiple cohorts of patients. We show that deep learning can reproduce the diagnosis of HCC vs. CCA with a high performance. We analyze a series of 405 cHCC-CCA patients and demonstrate that the model can reclassify the tumors as HCC or ICCA, and that the predictions are consistent with clinical outcomes, genetic alterations and in situ spatial gene expression profiling. This type of approach could improve treatment decisions and ultimately clinical outcome for patients with rare and biphenotypic cancers such as cHCC-CCA.
