-
Cureus Nov 2021In neuro-oncology, magnetic resonance imaging (MRI) is a critically important, non-invasive radiologic assessment technique for brain tumor diagnosis, especially glioma.... (Review)
Review
In neuro-oncology, magnetic resonance imaging (MRI) is a critically important, non-invasive radiologic assessment technique for brain tumor diagnosis, especially glioma. Deep learning improves MRI image characterization and interpretation through the utilization of raw imaging data and provides unprecedented enhancement of images and representation for detection and classification through deep neural networks. This systematic review and quality appraisal method aim to summarize deep learning approaches used in neuro-oncology imaging to aid healthcare professionals. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, a total of 20 low-risk studies on the established use of deep learning models to identify glioma genetic mutations and grading were selected, based on a Quality Assessment of Diagnostic Accuracy Studies 2 score of ≥9. The included studies provided the deep learning models used alongside their outcome measures, the number of patients, and the molecular markers for brain glioma classification. In 19 studies, the researchers determined that the deep learning model improved the clinical outcome and treatment protocol in patients with a brain tumor. In five studies, the authors determined the sensitivity of the deep learning model used, and in four studies, the authors determined the specificity of the models. Convolutional neural network models were used in 16 studies. In eight studies, the researchers examined glioma grading by using different deep learning models compared with other models. In this review, we found that deep learning models significantly improve the diagnostic and classification accuracy of brain tumors, particularly gliomas without the need for invasive methods. Most studies have presented validated results and can be used in clinical practice to improve patient care and prognosis.
PubMed: 34926051
DOI: 10.7759/cureus.19580 -
Neuro-oncology Jun 2023Quantitative imaging analysis through radiomics is a powerful technology to non-invasively assess molecular correlates and guide clinical decision-making. There has been...
BACKGROUND
Quantitative imaging analysis through radiomics is a powerful technology to non-invasively assess molecular correlates and guide clinical decision-making. There has been growing interest in image-based phenotyping for meningiomas given the complexities in management.
METHODS
We systematically reviewed meningioma radiomics analyses published in PubMed, Embase, and Web of Science until December 20, 2021. We compiled performance data and assessed publication quality using the radiomics quality score (RQS).
RESULTS
A total of 170 publications were grouped into 5 categories of radiomics applications to meningiomas: Tumor detection and segmentation (21%), classification across neurologic diseases (54%), grading (14%), feature correlation (3%), and prognostication (8%). A majority focused on technical model development (73%) versus clinical applications (27%), with increasing adoption of deep learning. Studies utilized either private institutional (50%) or public (49%) datasets, with only 68% using a validation dataset. For detection and segmentation, radiomic models had a mean accuracy of 93.1 ± 8.1% and a dice coefficient of 88.8 ± 7.9%. Meningioma classification had a mean accuracy of 95.2 ± 4.0%. Tumor grading had a mean area-under-the-curve (AUC) of 0.85 ± 0.08. Correlation with meningioma biological features had a mean AUC of 0.89 ± 0.07. Prognostication of the clinical course had a mean AUC of 0.83 ± 0.08. While clinical studies had a higher mean RQS compared to technical studies, quality was low overall with a mean RQS of 6.7 ± 5.9 (possible range -8 to 36).
CONCLUSIONS
There has been global growth in meningioma radiomics, driven by data accessibility and novel computational methodology. Translatability toward complex tasks such as prognostication requires studies that improve quality, develop comprehensive patient datasets, and engage in prospective trials.
Topics: Humans; Meningioma; Prospective Studies; Neoplasm Grading; Meningeal Neoplasms
PubMed: 36723606
DOI: 10.1093/neuonc/noad028 -
Insights Into Imaging Dec 2023Calcifications on mammography can be indicative of breast cancer, but the prognostic value of their appearance remains unclear. This systematic review and meta-analysis... (Review)
Review
BACKGROUND
Calcifications on mammography can be indicative of breast cancer, but the prognostic value of their appearance remains unclear. This systematic review and meta-analysis aimed to evaluate the association between mammographic calcification morphology descriptors (CMDs) and clinicopathological factors.
METHODS
A comprehensive literature search in Medline via Ovid, Embase.com, and Web of Science was conducted for articles published between 2000 and January 2022 that assessed the relationship between CMDs and clinicopathological factors, excluding case reports and review articles. The risk of bias and overall quality of evidence were evaluated using the QUIPS tool and GRADE. A random-effects model was used to synthesize the extracted data. This systematic review is reported according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA).
RESULTS
Among the 4715 articles reviewed, 29 met the inclusion criteria, reporting on 17 different clinicopathological factors in relation to CMDs. Heterogeneity between studies was present and the overall risk of bias was high, primarily due to small, inadequately described study populations. Meta-analysis demonstrated significant associations between fine linear calcifications and high-grade DCIS [pooled odds ratio (pOR), 4.92; 95% confidence interval (CI), 2.64-9.17], (comedo)necrosis (pOR, 3.46; 95% CI, 1.29-9.30), (micro)invasion (pOR, 1.53; 95% CI, 1.03-2.27), and a negative association with estrogen receptor positivity (pOR, 0.33; 95% CI, 0.12-0.89).
CONCLUSIONS
CMDs detected on mammography have prognostic value, but there is a high level of bias and variability between current studies. In order for CMDs to achieve clinical utility, standardization in reporting of CMDs is necessary.
CRITICAL RELEVANCE STATEMENT
Mammographic calcification morphology descriptors (CMDs) have prognostic value, but in order for CMDs to achieve clinical utility, standardization in reporting of CMDs is necessary.
SYSTEMATIC REVIEW REGISTRATION
CRD42022341599 KEY POINTS: • Mammographic calcifications can be indicative of breast cancer. • The prognostic value of mammographic calcifications is still unclear. • Specific mammographic calcification morphologies are related to lesion aggressiveness. • Variability between studies necessitates standardization in calcification evaluation to achieve clinical utility.
PubMed: 38051355
DOI: 10.1186/s13244-023-01529-z -
Frontiers in Oncology 2023Extra-axial brain tumors are extra-cerebral tumors and are usually benign. The choice of treatment for extra-axial tumors is often dependent on the growth of the tumor,...
Extra-axial brain tumors are extra-cerebral tumors and are usually benign. The choice of treatment for extra-axial tumors is often dependent on the growth of the tumor, and imaging plays a significant role in monitoring growth and clinical decision-making. This motivates the investigation of imaging biomarkers for these tumors that may be incorporated into clinical workflows to inform treatment decisions. The databases from Pubmed, Web of Science, Embase, and Medline were searched from 1 January 2000 to 7 March 2022, to systematically identify relevant publications in this area. All studies that used an imaging tool and found an association with a growth-related factor, including molecular markers, grade, survival, growth/progression, recurrence, and treatment outcomes, were included in this review. We included 42 studies, comprising 22 studies (50%) of patients with meningioma; 17 studies (38.6%) of patients with pituitary tumors; three studies (6.8%) of patients with vestibular schwannomas; and two studies (4.5%) of patients with solitary fibrous tumors. The included studies were explicitly and narratively analyzed according to tumor type and imaging tool. The risk of bias and concerns regarding applicability were assessed using QUADAS-2. Most studies (41/44) used statistics-based analysis methods, and a small number of studies (3/44) used machine learning. Our review highlights an opportunity for future work to focus on machine learning-based deep feature identification as biomarkers, combining various feature classes such as size, shape, and intensity. PROSPERO, CRD42022306922.
PubMed: 37182138
DOI: 10.3389/fonc.2023.1131013 -
Nuclear Medicine and Molecular Imaging Mar 2017The recent advance in hybrid imaging techniques enables offering simultaneous positron emission tomography (PET)/magnetic resonance imaging (MRI) in various clinical... (Review)
Review
The recent advance in hybrid imaging techniques enables offering simultaneous positron emission tomography (PET)/magnetic resonance imaging (MRI) in various clinical fields. F-fluorodeoxyglucose (FDG) PET has been widely used for diagnosis and evaluation of oncologic patients. The growing evidence from research and clinical experiences demonstrated that PET/MRI with FDG can provide comparable or superior diagnostic performance more than conventional radiological imaging such as computed tomography (CT), MRI or PET/CT in various cancers. Combined analysis using structural information and functional/molecular information of tumors can draw additional diagnostic information based on PET/MRI. Further studies including determination of the diagnostic efficacy, optimizing the examination protocol, and analysis of the hybrid imaging results is necessary for extending the FDG PET/MRI application in clinical oncology.
PubMed: 28250855
DOI: 10.1007/s13139-016-0411-3 -
Molecular Imaging and Biology Aug 2020Due to its metabolism via the serotonin and kynurenine pathways, tryptophan plays a key role in multiple disease processes including cancer. Imaging tryptophan uptake...
Due to its metabolism via the serotonin and kynurenine pathways, tryptophan plays a key role in multiple disease processes including cancer. Imaging tryptophan uptake and metabolism in vivo can be achieved with tryptophan derivative positron emission tomography (PET) radiotracers. While human studies with such tracers have been confined to C-11-labeled compounds, preclinical development of F-18-labeled tryptophan-based radiotracers has surged in recent years. We performed a systematic review of studies reporting on such F-18-labeled tryptophan tracers to summarize and compare their biological characteristics and their potential for tumor imaging, with a particular focus on key enzymes of the kynurenine pathway (indoleamine 2,3-dioxygenase [IDO] and tryptophan 2,3-dioxygenase [TDO]), which play an important role in tumoral immune resistance. From a PubMed search, English language articles including data on the preparation and radiochemical and/or biological characteristics of F-18-labeled tryptophan derivative radiotracers were reviewed. A total of 19 original papers included data on 15 unique radiotracers, the majority of which were synthesized with an adequate radiochemical yield. Automated synthesis was reported for 1-(2-[F]fluoroethyl)-L-tryptophan, the most extensively evaluated tracer thus far. Biodistribution studies showed high uptake in the pancreas, while the L-type amino acid transporter was the dominant transport mechanism for most of the reviewed tracers. Tracers tested for tumor uptake showed accumulation in tumor cell lines in vitro and in xenografts in vivo, often with favorable tumor-to-background uptake ratios in comparison with clinically used F-18-labeled radiotracers. Five tracers showed promise for imaging IDO activity, including 1-(2-[F]fluoroethyl)-L-tryptophan and a F-18-labeled analog of alpha-[C]methyl-L-tryptophan tested clinically in previous studies. Two radiotracers were metabolized by TDO but showed defluorination in vivo. In summary, most F-18-labeled tryptophan derivative PET tracers share common transport mechanisms and biodistribution characteristics. Several reported tracers could be candidates for further testing and validation toward PET imaging applications in a variety of human diseases.
Topics: Animals; Biological Transport; Fluorine Radioisotopes; Halogenation; Heterografts; Humans; Indoleamine-Pyrrole 2,3,-Dioxygenase; Mice; Positron-Emission Tomography; Radiopharmaceuticals; Serotonin; Tissue Distribution; Tryptophan; Tryptophan Oxygenase
PubMed: 31512038
DOI: 10.1007/s11307-019-01430-6 -
Contrast Media & Molecular Imaging 2020Magnetic resonance imaging (MRI) has taken an important role in the diagnosis of inflammatory bowel diseases (IBD). In the wake of current advances in nanotechnology,...
BACKGROUND AND AIMS
Magnetic resonance imaging (MRI) has taken an important role in the diagnosis of inflammatory bowel diseases (IBD). In the wake of current advances in nanotechnology, the drug delivery industry has seen a surge of nanoparticles advertising high specificity in target imaging. Given the rapid development of the field, this review has assembled related articles to explore whether molecular contrast agents can improve the diagnostic capability on gastrointestinal imaging, especially for IBD.
METHODS
Relevant articles published between 1998 and 2018 from a literature search of PubMed and EMBASE were reviewed. Data extraction was performed on the studies' characteristics, experimental animals, modelling methods, nanoparticles type, magnetic resonance methods, and means of quantitative analysis.
RESULTS
A total of 8 studies were identified wherein the subjects were animals, and all studies employed MR equipment. One group utilized a perfluorocarbon solution and the other 7 groups used either magnetic nanoparticles or gadolinium- (Gd-) related nanoparticles for molecular contrast. With ultrasmall superparamagnetic iron oxide (USPIO) particles and Gd-related nanoparticles, signal enhancements were found in the mucosa or with focal lesion of IBD-related model in T1-weighted images (T1WI), whereas superparamagnetic iron oxide (SPIO) particles showed a signal decrease in the intestinal wall of the model in T1WI or T2-weighted images. The signal-to-noise ratio (SNR) was employed to analyze bowel intensity in 3 studies. And the percentage of normalized enhancement was used in 1 study for assessing the severity of inflammation.
CONCLUSION
Molecular MRI with contrast agents can improve the early diagnosis of IBD and quantitate the severity of inflammation in experimental studies.
Topics: Animals; Contrast Media; Gadolinium; Humans; Inflammatory Bowel Diseases; Magnetic Resonance Imaging; Mice, Inbred C57BL; Molecular Imaging; Nanoparticles; Rats, Sprague-Dawley
PubMed: 32454803
DOI: 10.1155/2020/4764985 -
World Journal of Nuclear Medicine 2017Ovarian cancer (OC) often presents at an advanced stage with frequent relapses despite optimal treatment; thus, accurate staging and restaging are required for improving... (Review)
Review
Systematic Review on the Accuracy of Positron Emission Tomography/Computed Tomography and Positron Emission Tomography/Magnetic Resonance Imaging in the Management of Ovarian Cancer: Is Functional Information Really Needed?
Ovarian cancer (OC) often presents at an advanced stage with frequent relapses despite optimal treatment; thus, accurate staging and restaging are required for improving treatment outcomes and prognostication. Conventionally, staging of OC is performed using contrast-enhanced computed tomography (CT). Nevertheless, recent advances in the field of hybrid imaging have made positron emission tomography/CT (PET/CT) and PET/magnetic resonance imaging (PET/MRI) as emerging potential noninvasive imaging tools for improved management of OC. Several studies have championed the role of PET/CT for the detection of recurrence and prognostication of OC. We provide a systematic review and meta-analysis of the latest publications regarding the role of molecular imaging in the management of OC. We retrieved 57 original research articles with one article having overlap in both diagnosis and staging; 10 articles (734 patients) regarding the role of PET/CT in diagnosis of OC; 12 articles (604 patients) regarding staging of OC; 22 studies (1429 patients) for detection of recurrence; and 13 articles for prognostication and assessment of treatment response. We calculated pooled sensitivity and specificity of PET/CT performance in various aspects of imaging of OC. We also discussed the emerging role of PET/MRI in the management of OC. We aim to give the readers and objective overview on the role of molecular imaging in the management of OC.
PubMed: 28670174
DOI: 10.4103/wjnm.WJNM_31_17 -
RoFo : Fortschritte Auf Dem Gebiete Der... May 2014To evaluate the detection rate of prostate cancer (PCa) after magnetic resonance-guided biopsy (MRGB); to monitor the patient cohort with negative MRGB results and to... (Review)
Review
OBJECTIVES
To evaluate the detection rate of prostate cancer (PCa) after magnetic resonance-guided biopsy (MRGB); to monitor the patient cohort with negative MRGB results and to compare our own results with other reports in the current literature.
MATERIALS AND METHODS
A group of 41 patients was included in this IRB-approved study and subjected to combined MRI and MRGB. MRGB was performed in a closed 1.5 T MR unit and the needle was inserted rectally. The follow-up period ranged between 12 and 62 months (mean 3.1 years). To compare the results with the literature, a systematic literature search was performed. Eighteen publications were evaluated.
RESULTS
The cancer-suspicious regions were punctured successfully in all cases. PCa was detected in eleven patients (26.9 %) who were all clinically significant. MRGB showed a benign histology in the remaining 30 patients. In the follow-up (mean 3.1 years) of patients with benign histology, no new PCa was diagnosed. The missed cancer rate during follow-up was 0.0 % in our study.
CONCLUSION
MRGB is effective for the detection of clinically significant cancer, and this is in accordance with the recent literature. In the follow-up of patients with benign histology, no new PCa was discovered. Although the probability of developing PCa after negative MRGB is very low, active surveillance is reasonable.
Topics: Adult; Aged; Austria; Diagnosis, Differential; Humans; Image-Guided Biopsy; Magnetic Resonance Imaging, Interventional; Male; Middle Aged; Prostate; Prostatic Hyperplasia; Prostatic Neoplasms; Retrospective Studies; Sensitivity and Specificity
PubMed: 24497092
DOI: 10.1055/s-0033-1355546 -
Journal of Imaging Apr 2021(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of... (Review)
Review
(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.
PubMed: 34460516
DOI: 10.3390/jimaging7040066