Molecular imaging and deep learning analysis of uMUC1 expression in response to chemotherapy in an orthotopic model of ovarian cancer.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhao H
PROVIDER: S-EPMC7484755 | biostudies-literature | 2020 Sep
REPOSITORIES: biostudies-literature
Publications
Molecular imaging and deep learning analysis of uMUC1 expression in response to chemotherapy in an orthotopic model of ovarian cancer.
Zhao Hongwei H Hayat Hasaan H Ma Xiaohong X Fan Daguang D Wang Ping P Moore Anna A
Scientific reports 20200910 1
Artificial Intelligence (AI) algorithms including deep learning have recently demonstrated remarkable progress in image-recognition tasks. Here, we utilized AI for monitoring the expression of underglycosylated mucin 1 (uMUC1) tumor antigen, a biomarker for ovarian cancer progression and response to therapy, using contrast-enhanced in vivo imaging. This was done using a dual-modal (magnetic resonance and near infrared optical imaging) uMUC1-specific probe (termed MN-EPPT) consisted of iron-oxide ...[more]
Similar Datasets
Project description:BackgroundOvarian cancer (OC) is the most lethal gynecological cancer in the United States. Among the different types of OC, serous ovarian cancer (SOC) stands out as the most prevalent. Transcriptomics techniques generate extensive gene expression data, yet only a few of these genes are relevant to clinical diagnosis.MethodsMethods for feature selection (FS) address the challenges of high dimensionality in extensive datasets. This study proposes a computational framework that applies FS techniques to identify genes highly associated with platinum-based chemotherapy response on SOC patients. Using SOC datasets from the Gene Expression Omnibus (GEO) database, LASSO and varSelRF FS methods were employed. Machine learning classification algorithms such as random forest (RF) and support vector machine (SVM) were also used to evaluate the performance of the models.ResultsThe proposed framework has identified biomarkers panels with 9 and 10 genes that are highly correlated with platinum-paclitaxel and platinum-only response in SOC patients, respectively. The predictive models have been trained using the identified gene signatures and accuracy of above 90% was achieved.ConclusionsIn this study, we propose that applying multiple feature selection methods not only effectively reduces the number of identified biomarkers, enhancing their biological relevance, but also corroborates the efficacy of drug response prediction models in cancer treatment.
| S-EPMC11326537 | biostudies-literature
Project description:Pancreatic cancer decreases survival time and quality of life because of drug resistance and peripheral neuropathy during conventional treatment. This study was undertaken to investigate whether ?v?3 integrin receptor antagonist compounds NDAT and XT199 can suppress the development of cisplatin resistance and cisplatin-induced peripheral neuropathy in an orthotopic pancreatic SUIT2-luc cancer cell mouse model. Anticancer effects of these compounds and their combination with cisplatin were assessed in this tumor mouse model with bioluminescent signaling and histopathology, and a cytokine assay was used to examine expression of inflammatory cytokines IL-1?, IL-6, IL-10, and TNF-? from plasma samples. To determine the neuroprotective effects of the compounds on cisplatin-induced peripheral neuropathy, behavioral hind-limb posture of the mice was evaluated. The combination therapy of NDAT or XT199 with cisplatin elicited greater inhibition of tumor growth and increased tumor necrosis compared to cisplatin alone. NDAT and XT199 in combination with cisplatin significantly decreased expression of pro-inflammatory cytokines IL-1?, IL-6, and TNF-? and significantly increased expression of anti-inflammatory cytokine IL-10 in comparison to cisplatin alone. Cisplatin-treated groups showed stocking-glove hind-limb posture, whereas NDAT and XT199 with cisplatin-treated groups displayed normal hind-limb posture. Results clearly suggest that NDAT and XT199 treatment with cisplatin that inactivates NF-?B may contribute to increased antitumor and anti-inflammatory efficacy as well as alleviate cisplatin-mediated loss of motor function in this pancreatic tumor mouse model.
| S-EPMC7056702 | biostudies-literature
Project description:PURPOSE:To develop a mouse ovarian cancer model that allows modulating the expression levels of human vascular targets in mouse xenograft tumors and to test whether expression of CD276 during tumor angiogenesis can be visualized by molecularly targeted ultrasound in vivo. EXPERIMENTAL DESIGN:CD276-expressing MILE SVEN 1 (MS1) mouse endothelial cells were engineered and used for coinjection with 2008 human ovarian cancer cells for subcutaneous xenograft tumor induction in 15 nude mice. Fourteen control mice were injected with 2008 cells only. After confirming their binding specificity in flow chamber cell attachment studies, anti-CD276 antibody-functionalized contrast microbubbles were used for in vivo CD276-targeted contrast-enhanced ultrasound imaging. RESULTS:CD276-targeted ultrasound imaging signal was significantly higher (P = 0.006) in mixed MS1/2008 tumors than in control tumors. Compared with control microbubbles, the ultrasound signal using CD276-targeted microbubbles was significantly higher (P = 0.002), and blocking with purified anti-CD276 antibody significantly decreased (P = 0.0096) the signal in mixed MS1/2008 tumors. Immunofluorescence analysis of the tumor tissue confirmed higher quantitative immunofluorescence signal in mixed MS1/2008 tumors than in control 2008 only tumors, but showed not significantly different (P = 0.54) microvessel density. CONCLUSIONS:Our novel small animal model allows for modulating the expression of human tumor-associated vascular endothelial imaging targets in a mouse host and these expression differences can be visualized noninvasively by ultrasound molecular imaging. The animal model can be applied to other human vascular targets and may facilitate the preclinical development of new imaging probes such as microbubbles targeted at human vascular markers not expressed in mice.
| S-EPMC3965293 | biostudies-literature
Project description:Raman spectroscopy enables nondestructive, label-free imaging with unprecedented molecular contrast, but is limited by slow data acquisition, largely preventing high-throughput imaging applications. Here, we present a comprehensive framework for higher-throughput molecular imaging via deep-learning-enabled Raman spectroscopy, termed DeepeR, trained on a large data set of hyperspectral Raman images, with over 1.5 million spectra (400 h of acquisition) in total. We first perform denoising and reconstruction of low signal-to-noise ratio Raman molecular signatures via deep learning, with a 10× improvement in the mean-squared error over common Raman filtering methods. Next, we develop a neural network for robust 2-4× spatial super-resolution of hyperspectral Raman images that preserve molecular cellular information. Combining these approaches, we achieve Raman imaging speed-ups of up to 40-90×, enabling good-quality cellular imaging with a high-resolution, high signal-to-noise ratio in under 1 min. We further demonstrate Raman imaging speed-up of 160×, useful for lower resolution imaging applications such as the rapid screening of large areas or for spectral pathology. Finally, transfer learning is applied to extend DeepeR from cell to tissue-scale imaging. DeepeR provides a foundation that will enable a host of higher-throughput Raman spectroscopy and molecular imaging applications across biomedicine.
| S-EPMC9286315 | biostudies-literature
Project description:Ovarian cancer poses a major worldwide health issue, marked by high death rates and a deficiency in reliable diagnostic methods. The precise and prompt detection of ovarian cancer holds great importance in advancing patient outcomes and determining suitable treatment plans. Medical imaging techniques are vital in diagnosing ovarian cancer, but achieving accurate diagnoses remains challenging. Deep learning (DL), particularly convolutional neural networks (CNNs), has emerged as a promising solution to improve the accuracy of ovarian cancer detection. This systematic review explores the role of DL in improving the diagnostic accuracy for ovarian cancer. The methodology involved the establishment of research questions, inclusion and exclusion criteria, and a comprehensive search strategy across relevant databases. The selected studies focused on DL techniques applied to ovarian cancer diagnosis using medical imaging modalities, as well as tumour differentiation and radiomics. Data extraction, analysis, and synthesis were performed to summarize the characteristics and findings of the selected studies. The review emphasizes the potential of DL in enhancing the diagnosis of ovarian cancer by accelerating the diagnostic process and offering more precise and efficient solutions. DL models have demonstrated their effectiveness in categorizing ovarian tissues and achieving comparable diagnostic performance to that of experienced radiologists. The integration of DL into ovarian cancer diagnosis holds the promise of improving patient outcomes, refining treatment approaches, and supporting well-informed decision-making. Nevertheless, additional research and validation are necessary to ensure the dependability and applicability of DL models in everyday clinical settings.
| S-EPMC10867948 | biostudies-literature
Project description:While high-grade serous ovarian carcinoma (HGSOC) is the most common histologic subtype of ovarian cancer, significant tumor heterogeneity exists. In addition, chemotherapy induces changes in gene expression and alters the mutational profile. To evaluate the notion that patients with HGSOC could be better classified for optimal treatment based on gene expression, we compared genetic variants [by DNA next-generation sequencing (NGS) using a 50 gene Ion Torrent panel] and gene expression (using the NanoString PanCancer 770 gene Panel) in the tumor from 20 patients with HGSOC before and after neoadjuvant chemotherapy (NACT). NGS was performed on plasma cell free DNA (cfDNA) on a select group of patients (n = 14) to assess the utility of using cfDNA to monitor these changes. A total of 86 genes had significant changes in RNA expression after NACT. Thirty-eight genetic variants (including SNPs) from 6 genes were identified in tumors pre-NACT, while 59 variants from 19 genes were detected in the cfDNA. The number of DNA variants were similar after NACT. Of the 59 variants in the plasma pre-NACT, only 6 persisted, whereas 33 of 38 specific variants in the tumor DNA remained unchanged. Pathway analysis showed the most significant alterations in the cell cycle and DNA damage pathways.Implications: Gene expression profiles at the time of interval debulking provide additional genetic information that could help impact treatment decisions after NACT; although, continued collection and analysis of matched tumor and cfDNA from multiple time points are needed to determine the role of cfDNA in the management of HGSOC. Mol Cancer Res; 16(5); 813-24. ©2018 AACR.
| S-EPMC6497146 | biostudies-literature
Project description:PurposeTumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non-small cell lung cancer (NSCLC).Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans).ResultsDeep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17-17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016).ConclusionsWe demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.
| S-EPMC6548658 | biostudies-literature
Project description:Glioblastoma (GBM) is an aggressive and malignant primary brain tumor. The blood-brain barrier (BBB) limits the therapeutic options available to tackle this incurable tumor. Transient disruption of the BBB by focused ultrasound (FUS) is a promising and safe approach to increase the brain and tumor concentration of drugs administered systemically. Non-invasive, sensitive, and reliable imaging approaches are required to better understand the impact of FUS on the BBB and brain microenvironment. In this study, nuclear imaging (SPECT/CT and PET/CT) was used to quantify neuroinflammation 48 h post-FUS and estimate the influence of FUS on BBB opening and tumor growth in vivo. BBB disruptions were performed on healthy and GBM-bearing mice (U-87 MG xenograft orthotopic model). The BBB recovery kinetics were followed and quantified by [99mTc]Tc-DTPA SPECT/CT imaging at 0.5 h, 3 h and 24 h post-FUS. The absence of neuroinflammation was confirmed by [18F]FDG PET/CT imaging 48 h post-FUS. The presence of the tumor and its growth were evaluated by [68Ga]Ga-RGD2 PET/CT imaging and post-mortem histological analysis, showing that tumor growth was not influenced by FUS. In conclusion, molecular imaging can be used to evaluate the time frame for systemic treatment combined with transient BBB opening and to test its efficacy over time.
| S-EPMC9610067 | biostudies-literature
Project description:ObjectiveThe aim of the study is to develop and validate a deep learning model to predict the platinum sensitivity of patients with epithelial ovarian cancer (EOC) based on contrast-enhanced magnetic resonance imaging (MRI).MethodsIn this retrospective study, 93 patients with EOC who received platinum-based chemotherapy (≥4 cycles) and debulking surgery at the Sun Yat-sen Memorial Hospital from January 2011 to January 2020 were enrolled and randomly assigned to the training and validation cohorts (2:1). Two different models were built based on either the primary tumor or whole volume of the abdomen as the volume of interest (VOI) within the same cohorts, and then a pre-trained convolutional neural network Med3D (Resnet 10 version) was transferred to automatically extract 1,024 features from two MRI sequences (CE-T1WI and T2WI) of each patient to predict platinum sensitivity. The performance of the two models was compared.ResultsA total of 93 women (mean age, 50.5 years ± 10.5 [standard deviation]) were evaluated (62 in the training cohort and 31 in the validation cohort). The AUCs of the whole abdomen model were 0.97 and 0.98 for the training and validation cohorts, respectively, which was better than the primary tumor model (AUCs of 0.88 and 0.81 in the training and validation cohorts, respectively). In k-fold cross-validation and stratified analysis, the whole abdomen model maintained a stable performance, and the decision function value generated by the model was a prognostic indicator that successfully discriminates high- and low-risk recurrence patients.ConclusionThe non-manually segmented whole-abdomen deep learning model based on MRI exhibited satisfactory predictive performance for platinum sensitivity and may assist gynecologists in making optimal treatment decisions.
| S-EPMC9727155 | biostudies-literature
Project description:Using an orthotopic model of ovarian cancer, we studied the delivery of siRNA in nanoparticles of tri-block copolymers consisting of hyperbranched polyethylenimine-graft-polycaprolactone-block-poly(ethylene glycol) (hyPEI-g-PCL-b-PEG) with and without a folic acid targeting ligand. A SKOV-3/LUC FRα overexpressing cell line was employed to mimic the clinical manifestations of ovarian cancer. Both targeted and non-targeted micelleplexes were able to effectively deliver siRNA to the primary tumor and its metastases, as measured by gamma scintillation counting and confocal microscopy. Stability of the micelleplexes was demonstrated with a serum albumin binding study. Regarding biodistribution, intravenous (I.V.) administration showed a slight advantage of FRα targeted over non-targeted micelleplex accumulation within the tumor. However, both formulations displayed significant liver uptake. On the other hand, intraperitoneally (I.P.) injected mice showed a modest 6% of the injected dose per gram (ID/g) uptake within the primary and most interestingly also in the metastatic lesions which subsequently resulted in a 62% knockdown of firefly luciferase expression in the tumor after a single injection. While this is, to the best of our knowledge, the first paper that correlates quantitative tumor accumulation in an orthotopic tumor model with in vivo gene silencing, these data demonstrate that PEI-g-PCL-b-PEG-Fol conjugates are a promising option for gene knockdown in ovarian cancer.
| S-EPMC6056733 | biostudies-literature