nnU-Net-Based Pancreas Segmentation and Volume Measurement on CT Imaging in Patients with Pancreatic Cancer.

RATIONALE AND OBJECTIVES: To develop and validate a deep learning (DL)-based method for pancreas segmentation on CT and automatic measurement of pancreatic volume in pancreatic cancer. MATERIALS AND METHODS: This retrospective study used 3D nnU-net architecture for fully automated pancreatic segmentation in patients with pancreatic cancer. The study used 851 portal venous phase CT images (499 pancreatic cancer and 352 normal pancreas). This dataset was divided into training (n = 506), internal validation (n = 126), and external test set (n = 219). For the external test set, the pancreas was manually segmented by two abdominal radiologists (R1 and R2) to obtain the ground truth. In addition, the consensus segmentation was obtained using Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm. Segmentation performance was assessed using the Dice similarity coefficient (DSC). Next, the pancreatic volumes determined by automatic segmentation were compared to those determined by manual segmentation by two radiologists. RESULTS: The DL-based model for pancreatic segmentation showed a mean DSC of 0.764 in the internal validation dataset and DSC of 0.807, 0.805, and 0.803 using R1, R2, and STAPLE as references in the external test dataset. The pancreas parenchymal volume measured by automatic and manual segmentations were similar (DL-based model: 65.5 ± 19.3 cm3 and STAPLE: 65.1 ± 21.4 cm3; p = 0.486). The pancreatic parenchymal volume difference between the DL-based model predictions and the manual segmentation by STAPLE was 0.5 cm3, with correlation coefficients of 0.88. CONCLUSION: The DL-based model efficiently generates automatic segmentation of the pancreas and measures the pancreatic volume in patients with pancreatic cancer.

A Cell-Penetrant Peptide Disrupting the Transcription Factor CP2c Complexes Induces Cancer-Specific Synthetic Lethality.

Despite advances in precision oncology, cancer remains a global public health issue. In this report, proof-of-principle evidence is presented that a cell-penetrable peptide (ACP52C) dissociates transcription factor CP2c complexes and induces apoptosis in most CP2c oncogene-addicted cancer cells through transcription activity-independent mechanisms. CP2cs dissociated from complexes directly interact with and degrade YY1, leading to apoptosis via the MDM2-p53 pathway. The liberated CP2cs also inhibit TDP2, causing intrinsic genome-wide DNA strand breaks and subsequent catastrophic DNA damage responses. These two mechanisms are independent of cancer driver mutations but are hindered by high MDM2 p60 expression. However, resistance to ACP52C mediated by MDM2 p60 can be sensitized by CASP2 inhibition. Additionally, derivatives of ACP52C conjugated with fatty acid alone or with a CASP2 inhibiting peptide show improved pharmacokinetics and reduced cancer burden, even in ACP52C-resistant cancers. This study enhances the understanding of ACP52C-induced cancer-specific apoptosis induction and supports the use of ACP52C in anticancer drug development.

Rational discovery of antimetastatic agents targeting the intrinsically disordered region of MBD2.

Although intrinsically disordered protein regions (IDPRs) are commonly engaged in promiscuous protein-protein interactions (PPIs), using them as drug targets is challenging due to their extreme structural flexibility. We report a rational discovery of inhibitors targeting an IDPR of MBD2 that undergoes disorder-to-order transition upon PPI and is critical for the regulation of the Mi-2/NuRD chromatin remodeling complex (CRC). Computational biology was essential for identifying target site, searching for promising leads, and assessing their binding feasibility and off-target probability. Molecular action of selected leads inhibiting the targeted PPI of MBD2 was validated in vitro and in cell, followed by confirming their inhibitory effects on the epithelial-mesenchymal transition of various cancer cells. Identified lead compounds appeared to potently inhibit cancer metastasis in a murine xenograft tumor model. These results constitute a pioneering example of rationally discovered IDPR-targeting agents and suggest Mi-2/NuRD CRC and/or MBD2 as a promising target for treating cancer metastasis.

Development of a MEL Cell-Derived Allograft Mouse Model for Cancer Research.

Murine erythroleukemia (MEL) cells are often employed as a model to dissect mechanisms of erythropoiesis and erythroleukemia in vitro. Here, an allograft model using MEL cells resulting in splenomegaly was established to develop a diagnostic model for isolation/quantification of metastatic cells, anti-cancer drug screening, and evaluation of the tumorigenic or metastatic potentials of molecules in vivo. In this animal model, circulating MEL cells from the blood stream were successfully isolated and quantified with an additional in vitro cultivation step. In terms of the molecular-pathological analysis, we were able to successfully evaluate the functional discrimination between methyl-CpG-binding domain 2 (Mbd2) and p66α in erythroid differentiation, and tumorigenic potential in spleen and blood stream of allograft model mice. In addition, we found that the number of circulating MEL cells in anti-cancer drug-treated mice was dose-dependently decreased. Our data demonstrate that the newly established allograft model is useful to dissect erythroleukemia pathologies and non-invasively provides valuable means for isolation of metastatic cells, screening of anti-cancer drugs, and evaluation of the tumorigenic potentials.