Sang Joon Park

Alpha-fetoprotein (AFP), Lens culinaris-agglutinin-reactive fraction of AFP (AFP-L3), and protein induced by vitamin K absence or antagonist-II (PIVKA-II) are widely used as tumor markers for the diagnosis of hepatocellular carcinoma (HCC). This study compared the diagnostic values of AFP, AFP-L3, and PIVKA-II individually and in combination to find the best biomarker or biomarker panel.Seventy-nine patients with newly diagnosed HCC and 77 non-HCC control patients with liver cirrhosis were enrol

Computed tomography texture features have the potential to be used as prognostic biomarkers in unresectable NSCLC patients undergoing definitive CCRT.

Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust model requires large, high-quality data with annotations that are expensive to obtain. This situation poses a conundrum that annually-collected chest x-rays cannot be utilized due to the absence of labels, especially in deprived areas. In this study, we present a framework named distillation for self-supervision and self-train learning (DISTL) inspired by the learnin

PURPOSE: Cell-free DNA (cfDNA) is gaining attention as a novel biomarker for oncologic outcomes. We investigated the clinical significance of cfDNA in hepatocellular carcinoma (HCC) patients treated with radiotherapy (RT). MATERIALS AND METHODS: Fifty-five patients with HCC who received RT were recruited from two prospective study cohorts: one cohort of 34 patients who underwent conventionally fractionated RT and a second of 21 patients treated with stereotactic body radiation therapy. cfDNA was

Under the global COVID-19 crisis, developing robust diagnosis algorithm for COVID-19 using CXR is hampered by the lack of the well-curated COVID-19 data set, although CXR data with other disease are abundant. This situation is suitable for vision transformer architecture that can exploit the abundant unlabeled data using pre-training. However, the direct use of existing vision transformer that uses the corpus generated by the ResNet is not optimal for correct feature embedding. To mitigate this

<b><i>Background/Aim:</i></b> In the era of immunotherapy, treatment-related lymphopenia (TRL) is gaining attention. In this study, TRL was investigated in patients with bone metastasis from hepatocellular carcinoma (HCC) treated with radiotherapy (RT). <b><i>Methods:</i></b> Clinical data of 302 patients receiving RT for 511 bone metastases from HCC between 2005 and 2018 were reviewed. Data on absolute lymphocyte count (ALC) from pre-RT to 12 mont

Federated learning, which shares the weights of the neural network across clients, is gaining attention in the healthcare sector as it enables training on a large corpus of decentralized data while maintaining data privacy. For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals. Unfortunately, the exchange of the weights quickly consumes the network bandwidth if highly expressive network a

PURPOSE: The aim of this study was to investigate the usefulness of a personalized, 3-dimensional (3D)-printed, transparent liver model with focal liver lesions (FLLs) for lesion-by-lesion imaging-pathologic matching. MATERIALS AND METHODS: This preliminary, prospective study was approved by our institutional review board, and written informed consent was obtained. Twenty patients (male-to-female ratio, 13:7; mean age, 56 years) with multiple FLLs, including at least one presumed malignant, or a