Design of Optimal Deep Learning-Based Pancreatic Tumor and Nontumor Classification Model Using Computed Tomography Scans

Pancreatic tumor is a lethal kind of tumor and its prediction is really poor in the current scenario. Automated pancreatic tumor classification using computer-aided diagnosis (CAD) model is necessary to track, predict, and classify the existence of pancreatic tumors. Artificial intelligence (AI) can offer extensive diagnostic expertise and accurate interventional image interpretation. With this motivation, this study designs an optimal deep learning based pancreatic tumor and nontumor classification (ODL-PTNTC) model using CT images. The goal of the ODL-PTNTC technique is to detect and classify the existence of pancreatic tumors and nontumor. The proposed ODL-PTNTC technique includes adaptive window filtering (AWF) technique to remove noise existing in it. In addition, sailfish optimizer based Kapur’s Thresholding (SFO-KT) technique is employed for image segmentation process. Moreover, feature extraction using Capsule Network (CapsNet) is derived to generate a set of feature vectors. Furthermore, Political Optimizer (PO) with Cascade Forward Neural Network (CFNN) is employed for classification purposes. In order to validate the enhanced performance of the ODL-PTNTC technique, a series of simulations take place and the results are investigated under several aspects. A comprehensive comparative results analysis stated the promising performance of the ODL-PTNTC technique over the recent approaches.

Multidisciplinary treatment of advanced or recurrent solid pseudopapillary neoplasm of the pancreas: three case reports

Background Solid pseudopapillary neoplasm (SPN) is a rare pancreatic tumor that predominantly affects young females. Prognosis is excellent; however, 10–15% of patients show metastasis at the time of surgery or develop tumor recurrence after pancreatectomy. Case presentation We reviewed the clinical course of three patients with advanced or recurrent SPN and subsequently underwent multidisciplinary treatment at our institution between 2002 and 2019. The primary tumor was resected in all three patients, and metastases were also resected if indicated. Intensive combined therapy, including re-resection, chemotherapy, ablation, arterial chemoembolization, and radiation therapy, allowed all patients to survive for a long time. The literature review showed that resection seems to be more effective than other treatments for metastatic SPN. Conclusions Multidisciplinary treatment, including resection, may improve the prognosis of patients with SPN with recurrence or metastasis.

Novel Use of Hypoxia-Inducible Polymerizable Protein to Augment Chemotherapy for Pancreatic Cancer

Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive malignancies and is the fourth leading cause of cancer-related deaths in the United States. Unfortunately, 80–85% of patients are diagnosed with unresectable, advanced stage tumors. These tumors are incurable and result in a median survival less than approximately six months and an overall 5-year survival rate of less than 7%. Whilst chemotherapy is a critical treatment, cure is not possible without surgical resection. The poor clinical outcomes in PDAC can be partially attributed to its dense desmoplastic stroma, taking up roughly 80% of the tumor mass. The stroma surrounding the tumor disrupts the normal architecture of pancreatic tissue leading to poor vascularization, high intratumoral pressure along with hypoxia and an acidic tumor microenvironment. This complicated microenvironment presents a significant challenge for drug delivery. The current manuscript discusses a novel approach to overcome many of these various obstacles. A complex of gemcitabine (GEM) and hemoglobin S (HbS) was formulated, which self-polymerizes under hypoxic and acidic conditions. When polymerized, HbS has the potential to break the tumor stroma, decrease intratumoral pressure, and therefore improve the treatment efficacy of standard therapy. Intratumoral injection of HbS with a fluorescent small molecule surrogate for GEM into a pancreatic tumor xenograft resulted in improved dissemination of the small molecule throughout the pancreatic tumor. The self-polymerization of HbS + GEM was significantly more effective than either agent individually at decreasing tumor size in an in vivo PDAC mouse model. These findings would suggest a clinical benefit from delivering the complex of GEM and HbS via direct injection by endoscopic ultrasound (EUS). With such a treatment option, patients with locally advanced disease would have the potential to become surgical candidates, offering them a chance for cure.

An automated deep learning based pancreatic tumor diagnosis and classification model using computed tomography images

PurposeThe advancements of deep learning (DL) models demonstrate significant performance on accurate pancreatic tumor segmentation and classification.Design/methodology/approachThe presented model involves different stages of operations, namely preprocessing, image segmentation, feature extraction and image classification. Primarily, bilateral filtering (BF) technique is applied for image preprocessing to eradicate the noise present in the CT pancreatic image. Besides, noninteractive GrabCut (NIGC) algorithm is applied for the image segmentation process. Subsequently, residual network 152 (ResNet152) model is utilized as a feature extractor to originate a valuable set of feature vectors. At last, the red deer optimization algorithm (RDA) tuned backpropagation neural network (BPNN), called RDA-BPNN model, is employed as a classification model to determine the existence of pancreatic tumor.FindingsThe experimental results are validated in terms of different performance measures and a detailed comparative results analysis ensured the betterment of the RDA-BPNN model with the sensitivity of 98.54%, specificity of 98.46%, accuracy of 98.51% and F-score of 98.23%.Originality/valueThe study also identifies several novel automated deep learning based approaches used by researchers to assess the performance of the RDA-BPNN model on benchmark dataset and analyze the results in terms of several measures.

Differential Expression of Polyamine Pathways in Human Pancreatic Tumor Progression and Effects of Polyamine Blockade on Tumor Microenvironment

Pancreatic cancer is the fourth leading cause of cancer death. Existing therapies only moderately improve pancreatic ductal adenocarcinoma (PDAC) patient prognosis. The present study investigates the importance of the polyamine metabolism in the pancreatic tumor microenvironment. Relative mRNA expression analysis identified differential expression of polyamine biosynthesis, homeostasis, and transport mediators in both pancreatic epithelial and stromal cells from low-grade pancreatic intraepithelial neoplasia (PanIN-1) or primary PDAC patient samples. We found dysregulated mRNA levels that encode for proteins associated with the polyamine pathway of PDAC tumors compared to early lesions. Next, bioinformatic databases were used to assess expression of select genes involved in polyamine metabolism and their impact on patient survival. Higher expression of pro-polyamine genes was associated with poor patient prognosis, supporting the use of a polyamine blockade therapy (PBT) strategy for inhibiting pancreatic tumor progression. Moreover, PBT treatment of syngeneic mice injected intra-pancreatic with PAN 02 tumor cells resulted in increased survival and decreased tumor weights of PDAC-bearing mice. Histological assessment of PBT-treated tumors revealed macrophage presence and significantly increased expression of CD86, a T cell co-stimulatory marker. Collectively, therapies which target polyamine metabolism can be used to disrupt tumor progression, modulate tumor microenvironment, and extend overall survival.

Cancer-Associated Fibroblasts in Pancreatic Ductal Adenocarcinoma: An Update on Heterogeneity and Therapeutic Targeting

Pancreatic ductal adenocarcinoma (PDAC) is a leading cause of cancer-related morbidity and mortality in the western world, with limited therapeutic strategies and dismal long-term survival. Cancer-associated fibroblasts (CAFs) are key components of the pancreatic tumor microenvironment, maintaining the extracellular matrix, while also being involved in intricate crosstalk with cancer cells and infiltrating immunocytes. Therefore, they are potential targets for developing therapeutic strategies against PDAC. However, recent studies have demonstrated significant heterogeneity in CAFs with respect to their origins, spatial distribution, and functional phenotypes within the PDAC tumor microenvironment. Therefore, it is imperative to understand and delineate this heterogeneity prior to targeting CAFs for PDAC therapy.

The potential role of STAT3 In the APE1/NF-kB regulatory axis in K-rasLSL.G12D/+;Pdx-1-Cre (KC) pancreatic tumor model

APE1/Ref-1 (apurinic/apyrimidinic endonuclease-redox effector factor 1) is a multifunctional protein that has been shown to be overexpressed in multiple types of cancer. The overexpression of APE1/Ref-1 is linked to higher cancer cell survival and increased patient mortality. Furthermore, APE1/Ref-1 is a key regulator of transcription factors (TF) through redox signaling and protein-protein interaction. It is involved in proliferative and inflammatory signaling upregulated in cancer. Transcription factor NF-kB is involved in inflammatory cytokine expression and has been shown to be regulated by Ref-1. My project investigated how Ref-1 regulates NF-kB, specifically Rel-A, in a model using K-rasLSL.G12D/+; Pdx-1-Cre (KC) pancreatic tumor cells (KC3590) derived from genetically engineered mice. Additionally, I explored other TFs within the APE1/Ref-1 signaling pathway, such as STAT3, in this model. My work involved knocking down STAT3 levels within four variations of the KC3590 line. These were the KC3590/ΔNF-kB (parent) and KC3590/ΔNF-kB vector lines (vector) which contain exon deletions within the NF-kB gene rendering it nonfunctional. KC3590/13 and KC3590/15 are cell lines which are KC3590/ΔNF-B cells with functional full-length NF-kB added to the cells. Previous experiments demonstrated that the ΔNF-kB and ΔNF-kB vector lines are resistant to treatment by the specific Ref-1 inhibitors, including APX3330, which inhibit the redox signaling function of Ref-1. Initial data demonstrated that adding back functional NF-kB to the NF-kB deficient cells reestablished sensitivity to APX3330, presumably due to the reintroduction of the Ref-1 target, NF-kB. Knockdown of STAT3 expression in the ΔNF-kB and ΔNF-kB vector lines demonstrated some sensitivity to APX3330, however, in the C13/15 cell lines, no enhanced sensitivity was observed. These data support the hypothesis that NF-kB is the major TF driving the growth of KC pancreatic tumor cells. Subsequent studies will clarify further the role of APE1/Ref-1 regulation in the KC model and the relative importance of APE1/Ref-1’s target TFs.