Search

Detection of cancer in human organs at an early stage is a crucial task and is important for the survival of the patients, especially in terms of complex structure, dynamic size, and dynamic length in organs like the pancreas. To deal with this problem, pancreatic semantic segmentation was introduced, but it was hampered by challenges related to image modalities and the availability of limited datasets. This paper provides different deep learning models for pancreatic detection. The proposed model pipeline has two phases: pancreas localization and segmentation. In the first phase, rough regions of the pancreas are detected with YOLOv5, and the detected regions are cropped to avoid an imbalance between the pancreas region and the background. In the second phase, the detected regions are segmented with various models like UNet, VNet, SegResNet and HighResNet for effective detection of cancer regions. The experiments were conducted on a private dataset collected from the Champalimaud Foundation in Portugal. The model's performance is evaluated in terms of quantitative and qualitative analysis. From experiments, we found that, when compared to other Nets, YOLOv5 is superior in pancreatic area localization and 2.5D HighResNet is superior in segmentation. [ABSTRACT FROM AUTHOR]

Abstract Detection of cancer in human organs at an early stage is a crucial task and is important for the survival of the patients, especially in terms of complex structure, dynamic size, and dynamic length in organs like the pancreas. To deal with this problem, pancreatic semantic segmentation was introduced, but it was hampered by challenges related to image modalities and the availability of limited datasets. This paper provides different deep learning models for pancreatic detection. The proposed model pipeline has two phases: pancreas localization and segmentation. In the first phase, rough regions of the pancreas are detected with YOLOv5, and the detected regions are cropped to avoid an imbalance between the pancreas region and the background. In the second phase, the detected regions are segmented with various models like UNet, VNet, SegResNet and HighResNet for effective detection of cancer regions. The experiments were conducted on a private dataset collected from the Champalimaud Foundation in Portugal. The model’s performance is evaluated in terms of quantitative and qualitative analysis. From experiments, we found that, when compared to other Nets, YOLOv5 is superior in pancreatic area localization and 2.5D HighResNet is superior in segmentation.

Abstract Background Pancreatic cancer (PC) remains a significant healthcare challenge due to its aggressive nature and poor prognosis. The current gold standard that combines imaging modalities, endoscopy, and biopsies has limited diagnostic efficacy due to various shortcomings. Methods We propose a feasibility study for the use of a bioimpedance biomarker to detect PC. The biomarker was evaluated in a double blind study on ex vivo pancreata of mice: 15 LSL-KrasG12D; LSL-p53R172H; Pdx1-Cre, 2 LSL-KrasG12D, and 9 wild type controls (Study 1). To determine if the biomarker can distinguish between PC and acute pancreatitis (AP), we challenged it with 18 cerulein-induced AP and 6 saline-injected controls (Study 2). Results The results from Study 1 showed 100% specificity and 94% sensitivity against histopathology outcomes; for Study 2 all AP and saline-injected pancreases were diagnosed as non-cancerous. Regression analysis revealed a positive correlation between biomarker and pathologically analyzed cancer-induced fibrosis (r(24)= 0.73 (p

The objective of the study was the analysis of the main clinical characteristics identified in patients with malignant neoplasms of the pancreas, who received medical care in healthcare institutions of St. Petersburg in the period from 2015 to 2020.Methods and materials. A continuous study of clinical and statistical data of patients with pancreatic cancer receiving medical care in healthcare institutions of St. Petersburg (of federal and city subordination) for the period from 01.2015 to 02.2020 was carried out. In total, the study included depersonalized medical cards of 2141 patients diagnosed with pancreatic cancer.Results. During the studied period, more than half of the patients diagnosed with cancer of the pancreas received medical care in specialized oncological institutions of city subordination, a third – in federal institutions, 11.3 % – in multidisciplinary city hospitals. The maximum number of cases was in patients of older age groups: 41.7 % – 70 years and over, including 15.4 % – 80 years and over. The majority (39.7 %) of new patients with pancreatic cancer hospitalized in medical institutions of St. Petersburg were diagnosed with stage IV of the disease. The disease, according to examinations, was represented by stage III in 29.7 % of patients at the time of initial hospitalization. The pancreatic cancer was presented with stage III in 20 % of the patients. The disease was registered in 4.4 % of patients at stage I. Stage 0 or carcinoma in situ was diagnosed at initial presentation in 4.7 % of patients. The stage of the disease was not determined in 1.4 % of patients. The tumor was located in the head of the pancreas in 64.4 % of patients. The most common histological type of pancreatic cancer is ductal adenocarcinoma, which was verified in 72.0 % of patients. Type 2 diabetes mellitus was registered in 37 % of patients as concomitant disease.Conclusion. The results of the analysis of clinical and statistical data of patients with pancreatic cancer may become a background for conducting research on the early detection of this neoplasm.

Abstract Pancreatic cancer is characterized as the worst for diagnosis lacking symptoms at the early stage, which results in a low overall survival rate. The frequently used techniques for pancreatic cancer diagnosis rely on imaging and biopsy, which have limitations in requiring experienced personnel to operate the expensive instruments and analyze the results. Therefore, there is a high demand to develop alternative tools or methods to detect pancreatic cancer. Herein, we propose a new strategy to enhance the detection sensitivity of pancreatic cancer cells both in biofluids and on tissues by combining the unique property of dopamine coated Fe3O4 nanoparticles (Fe3O4@DOP NPs) to specifically quench and separate free 6-carboxyfluorescein (FAM) labeled DNA (H1-FAM/H2-FAM), and the key feature of hybridization chain reaction (HCR) amplification. We have determined the limit of detection (LOD) to be 21 ~ 41 cells/mL for three different pancreatic cancer cell lines. It was also discovered that the fluorescence intensity of pancreatic cancer cells was significantly higher than that of HPDE-C7 and HepG-2 cells (control cell lines), which express lower MUC1 protein. Moreover, the HCR amplification system was used to identify the cancer cells on pancreatic tissue, which indicated the versatility of our strategy in clinical application. Therefore, the presented detection strategy shows good sensitivity, specificity and has great potential for the diagnosis of pancreatic cancer. Graphical Abstract

Pancreatic cancer is characterized as the worst for diagnosis lacking symptoms at the early stage, which results in a low overall survival rate. The frequently used techniques for pancreatic cancer diagnosis rely on imaging and biopsy, which have limitations in requiring experienced personnel to operate the expensive instruments and analyze the results. Therefore, there is a high demand to develop alternative tools or methods to detect pancreatic cancer. Herein, we propose a new strategy to enhance the detection sensitivity of pancreatic cancer cells both in biofluids and on tissues by combining the unique property of dopamine coated Fe3O4 nanoparticles (Fe3O4@DOP NPs) to specifically quench and separate free 6-carboxyfluorescein (FAM) labeled DNA (H1-FAM/H2-FAM), and the key feature of hybridization chain reaction (HCR) amplification. We have determined the limit of detection (LOD) to be 21 ~ 41 cells/mL for three different pancreatic cancer cell lines. It was also discovered that the fluorescence intensity of pancreatic cancer cells was significantly higher than that of HPDE-C7 and HepG-2 cells (control cell lines), which express lower MUC1 protein. Moreover, the HCR amplification system was used to identify the cancer cells on pancreatic tissue, which indicated the versatility of our strategy in clinical application. Therefore, the presented detection strategy shows good sensitivity, specificity and has great potential for the diagnosis of pancreatic cancer. [ABSTRACT FROM AUTHOR]

Background: The DNA released into the bloodstream by malignant tumours· called circulating tumour DNA (ctDNA), is often a small fraction of total cell-free DNA shed predominantly by hematopoietic cells and is therefore challenging to detect. Understanding the biological properties of ctDNA is key to the investigation of its clinical relevance as a non-invasive marker for cancer detection and monitoring. Methods: We selected 40 plasma DNA samples of pancreatic cancer cases previously reported to carry a KRAS mutation at the ‘hotspot’ codon 12 and re-screened the cell-free DNA using a 4-size amplicons strategy (57 bp, 79 bp, 167 bp and 218 bp) combined with ultra-deep sequencing in order to investigate whether amplicon lengths could impact on the capacity of detection of ctDNA, which in turn could provide inference of ctDNA and non-malignant cell-free DNA size distribution. Findings: Higher KRAS amplicon size (167 bp and 218 bp) was associated with lower detectable cell-free DNA mutant allelic fractions (p

Artificial intelligence (AI) has come to play a pivotal role in revolutionizing medical practices, particularly in the field of pancreatic cancer detection and management. As a leading cause of cancer-related deaths, pancreatic cancer warrants innovative approaches due to its typically advanced stage at diagnosis and dismal survival rates. Present detection methods, constrained by limitations in accuracy and efficiency, underscore the necessity for novel solutions. AI-driven methodologies present promising avenues for enhancing early detection and prognosis forecasting. Through the analysis of imaging data, biomarker profiles, and clinical information, AI algorithms excel in discerning subtle abnormalities indicative of pancreatic cancer with remarkable precision. Moreover, machine learning (ML) algorithms facilitate the amalgamation of diverse data sources to optimize patient care. However, despite its huge potential, the implementation of AI in pancreatic cancer detection faces various challenges. Issues such as the scarcity of comprehensive datasets, biases in algorithm development, and concerns regarding data privacy and security necessitate thorough scrutiny. While AI offers immense promise in transforming pancreatic cancer detection and management, ongoing research and collaborative efforts are indispensable in overcoming technical hurdles and ethical dilemmas. This review delves into the evolution of AI, its application in pancreatic cancer detection, and the challenges and ethical considerations inherent in its integration., Competing Interests: The authors have declared that no competing interests exist., (Copyright © 2024, Daher et al.)

Background & Aims Little is known about whether the 2006 Sendai guidelines or 2012 Fukuoka guidelines are being used to determine the level of risk posed by suspected pancreatic mucinous cystic neoplasms (PCNs). We evaluated whether the guidelines accurately predicted which patients with suspected PCNs, which was based on cross-sectional imaging findings, would be found to have advanced neoplasia in surgery. Methods We performed a retrospective study of data collected from 194 patients with cystic lesions of the pancreas, which were assessed by cross-sectional imaging analyses, who underwent surgery for suspected PCNs at the Hospital at the University of Pennsylvania from 2000 through 2008. Imaging data were used to classify patients according to the Sendai guidelines as high risk or low risk and according to the Fukuoka guidelines as high risk, worrisome, or low risk. Pathology analyses of samples collected during surgery were used as the reference. A logistic regression model was created to identify factors associated with advanced neoplasia. The Sendai and Fukuoka guideline criteria were analyzed by univariate and multivariable logistic regression analyses. Results Advanced neoplasias were found in 36 patients (18.5%; 22 invasive cancers and 14 high-grade dysplasias). The median size of cysts was 33 mm. All patients found to have invasive cancers were accurately assigned to the Sendai guidelines high risk or Fukuoka guidelines high risk groups. However, 3 patients in the Sendai guidelines low risk and 2 patients in the Fukuoka guidelines low risk groups were found to have high-grade dysplasia. The Sendai guidelines identified patients with advanced neoplasia with 91.7% sensitivity, 21.5% specificity, 21% positive predictive value, and 91.9% negative predictive value. A designation of Fukuoka guidelines high risk identified patients with advanced neoplasia with 55.6% sensitivity, 73% specificity, 32% positive predictive value, and 87.9% negative predictive value. Overall, there was no statistically significant difference between the guidelines in predicting which patients had advanced neoplasia. On multivariate analysis, the presence of a mural nodule (odds ratio [OR], 2.88; 95% confidence interval [CI], 1.33–6.27; P = .008), dilated main pancreatic duct >10 mm (OR, 7.44; 95% CI, 2.36–23.52; P = .001), or enhancing solid component (OR, 2.92; 95% CI, 1.16–7.64; P = .02) were associated with detection of advanced neoplasia in pancreatic cysts. Conclusion On the basis of a retrospective analysis, the Sendai and Fukuoka guidelines accurately determine which patients with pancreatic cysts have advanced neoplasia. The guidelines accurately recommended surgical resection for all patients found to have invasive cancer, although some patients with high-grade dysplasia were missed. The updated Fukuoka guidelines are not superior to the Sendai guidelines in identifying neoplasias. Cyst size was not associated with advanced neoplasia. [ABSTRACT FROM AUTHOR]

Background: The DNA released into the bloodstream by malignant tumours· called circulating tumour DNA (ctDNA), is often a small fraction of total cell-free DNA shed predominantly by hematopoietic cells and is therefore challenging to detect. Understanding the biological properties of ctDNA is key to the investigation of its clinical relevance as a non-invasive marker for cancer detection and monitoring., Methods: We selected 40 plasma DNA samples of pancreatic cancer cases previously reported to carry a KRAS mutation at the 'hotspot' codon 12 and re-screened the cell-free DNA using a 4-size amplicons strategy (57 bp, 79 bp, 167 bp and 218 bp) combined with ultra-deep sequencing in order to investigate whether amplicon lengths could impact on the capacity of detection of ctDNA, which in turn could provide inference of ctDNA and non-malignant cell-free DNA size distribution., Findings: Higher KRAS amplicon size (167 bp and 218 bp) was associated with lower detectable cell-free DNA mutant allelic fractions (p < 0·0001), with up to 4·6-fold (95% CI: 2·6-8·1) difference on average when comparing the 218bp- and the 57bp-amplicons. The proportion of cases with detectable KRAS mutations was also hampered with increased amplicon lengths, with only half of the cases having detectable ctDNA using the 218 bp assay relative to those detected with amplicons less than 80 bp., Interpretation: Tumour-derived mutations are carried by shorter cell-free DNA fragments than fragments of wild-type allele. Targeting short amplicons increases the sensitivity of cell-free DNA assays for pancreatic cancer and should be taken into account for optimized assay design and for evaluating their clinical performance., Funding: IARC; MH CZ - DRO; MH SK; exchange program between IARC and Sao Paulo medical Sciences; French Cancer League., Competing Interests: Declaration of Competing Interest We declare no competing interests., (Copyright © 2019. Published by Elsevier B.V.)

The utility of KRAS mutations in plasma circulating cell-free DNA (cfDNA) samples as non-invasive biomarkers for the detection of pancreatic cancer has never been evaluated in a large case-control series. We applied a KRAS amplicon-based deep sequencing strategy combined with analytical pipeline specifically designed for the detection of low-abundance mutations to screen plasma samples of 437 pancreatic cancer cases, 141 chronic pancreatitis subjects, and 394 healthy controls. We detected mutations in 21.1% (N=92) of cases, of whom 82 (89.1%) carried at least one mutation at hotspot codons 12, 13 or 61, with mutant allelic fractions from 0.08% to 79%. Advanced stages were associated with an increased proportion of detection, with KRAS cfDNA mutations detected in 10.3%, 17,5% and 33.3% of cases with local, regional and systemic stages, respectively. We also detected KRAS cfDNA mutations in 3.7% (N=14) of healthy controls and in 4.3% (N=6) of subjects with chronic pancreatitis, but at significantly lower allelic fractions than in cases. Combining cfDNA KRAS mutations and CA19-9 plasma levels on a limited set of case-control samples did not improve the overall performance of the biomarkers as compared to CA19-9 alone. Whether the limited sensitivity and specificity observed in our series of KRAS mutations in plasma cfDNA as biomarkers for pancreatic cancer detection are attributable to methodological limitations or to the biology of cfDNA should be further assessed in large case-control series.