These data suggest that detection of mRNA coding for CEA and/or CK20 using qPCR has potential clinical utility as a prognostic marker and should be evaluated in larger clinical studies. Identification of patients at high risk for metastatic disease after curative resection of colorectal cancer might be improved by analyzing peritoneal lavage specimens in addition to blood samples. This is based on the observation that in more than half of qPCR-positive patients, disseminated colorectal cancer cells were detected in peritoneal lavage specimens but not in blood samples, and that 71% of them had recurrence.
To bridge the translational gap between recent discoveries of distinct molecular phenotypes of pancreatic cancer and tangible improvements in patient outcome, there is an urgent need to develop strategies and tools informing and improving the clinical decision process. Radiomics and machine learning approaches can offer non-invasive whole tumor analytics for clinical imaging data-based classification. The retrospective study assessed baseline computed tomography (CT) from 207 patients with proven pancreatic ductal adenocarcinoma (PDAC). Following expert level manual annotation, Pyradiomics was used for the extraction of 1474 radiomic features. The molecular tumor subtype was defined by immunohistochemical staining for KRT81 and HNF1a as quasi-mesenchymal (QM) vs. non-quasi-mesenchymal (non-QM). A Random Forest machine learning algorithm was developed to predict the molecular subtype from the radiomic features. The algorithm was then applied to an independent cohort of histopathologically unclassifiable tumors with distinct clinical outcomes. The classification algorithm achieved a sensitivity, specificity and ROC-AUC (area under the receiver operating characteristic curve) of 0.84 ± 0.05, 0.92 ± 0.01 and 0.93 ± 0.01, respectively. The median overall survival for predicted QM and non-QM tumors was 16.1 and 20.9 months, respectively, log-rank-test p = 0.02, harzard ratio (HR) 1.59. The application of the algorithm to histopathologically unclassifiable tumors revealed two groups with significantly different survival (8.9 and 39.8 months, log-rank-test p < 0.001, HR 4.33). The machine learning-based analysis of preoperative (CT) imaging allows the prediction of molecular PDAC subtypes highly relevant for patient survival, allowing advanced pre-operative patient stratification for precision medicine applications.
Ninety-eight patients with documented mesenteric infarction during a 19-year period were reviewed. In 13 patients infarction was due to a mesenteric venous thrombosis (MVT). Patients with MVT distinguished themselves from those having another aetiology by: (1) longer history of pain before admission (median 8 days, P less than 0.0001); (2) typical appearance of the bowel at laparotomy (10/13); (3) a localized segment of ischaemic jejunum or ileum of less than 120 cm in length (12/13) allowing better operability at the first laparotomy (P = 0.006). In hospital the mortality was lower for venous mesenteric infarction (5/13, 38 per cent) than for mesenteric infarction of other aetiologies (70/85, 82 per cent) (P = 0.002). Patients with primary venous mesenteric infarction showed a better survival rate (one death in eight patients) than patients with associated diseases such as liver cirrhosis, sepsis or previous operation who had a poor prognosis with a mortality comparable to other aetiologies of acute bowel ischaemia (four deaths in five patients). Since the high recurrence rate of this disease in the early postoperative period was due to residual venous thrombosis and to a hypercoagulable state, a wide bowel resection is recommended followed by early and long-term anticoagulation. Thrombectomy is probably inefficient since it removes only centrally located thrombi and leaves peripheral occlusion, which is responsible for the recurrence.
The differentiation of autoimmune pancreatitis (AIP) and pancreatic ductal adenocarcinoma (PDAC) poses a relevant diagnostic challenge and can lead to misdiagnosis and consequently poor patient outcome. Recent studies have shown that radiomics-based models can achieve high sensitivity and specificity in predicting both entities. However, radiomic features can only capture low level representations of the input image. In contrast, convolutional neural networks (CNNs) can learn and extract more complex representations which have been used for image classification to great success. In our retrospective observational study, we performed a deep learning-based feature extraction using CT-scans of both entities and compared the predictive value against traditional radiomic features. In total, 86 patients, 44 with AIP and 42 with PDACs, were analyzed. Whole pancreas segmentation was automatically performed on CT-scans during the portal venous phase. The segmentation masks were manually checked and corrected if necessary. In total, 1411 radiomic features were extracted using PyRadiomics and 256 features (deep features) were extracted using an intermediate layer of a convolutional neural network (CNN). After feature selection and normalization, an extremely randomized trees algorithm was trained and tested using a two-fold shuffle-split cross-validation with a test sample of 20% (n = 18) to discriminate between AIP or PDAC. Feature maps were plotted and visual difference was noted. The machine learning (ML) model achieved a sensitivity, specificity, and ROC-AUC of 0.89 ± 0.11, 0.83 ± 0.06, and 0.90 ± 0.02 for the deep features and 0.72 ± 0.11, 0.78 ± 0.06, and 0.80 ± 0.01 for the radiomic features. Visualization of feature maps indicated different activation patterns for AIP and PDAC. We successfully trained a machine learning model using deep feature extraction from CT-images to differentiate between AIP and PDAC. In comparison to traditional radiomic features, deep features achieved a higher sensitivity, specificity, and ROC-AUC. Visualization of deep features could further improve the diagnostic accuracy of non-invasive differentiation of AIP and PDAC.
Eighty-one cases of mesenteric infarction documented by angiography, laparotomy or autopsy were reviewed to assess the cause of the persistently high mortality. Thirty-seven patients (46 per cent) were felt to have inoperable lesions and were treated by supportive care only, while forty-four (54 per cent) underwent bowel resection and/or revascularization. Of these 44 patients 20 (45 per cent) survived, 14 (32 per cent) died of an early recurrence of infarction and 10 (23 per cent) died of an unrelated cause. In view of the high recurrence rate in the early postoperative period, treatment must prevent the causes of persistent or recurrent ischaemia such as vasoconstriction and reperfusion tissue damage. On the basis of recent clinical and experimental research we suggest that treatment should include routine angiography with selective perfusion of vasodilators through the superior mesenteric artery, pharmacological prevention of ischaemic and reperfusion tissue damage before surgery, and postoperative anticoagulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.