-
Frontiers in Oncology 2022Here, we conducted a scoping review to (i) establish which machine learning (ML) methods have been applied to hematological malignancy imaging; (ii) establish how ML is...
BACKGROUND
Here, we conducted a scoping review to (i) establish which machine learning (ML) methods have been applied to hematological malignancy imaging; (ii) establish how ML is being applied to hematological cancer radiology; and (iii) identify addressable research gaps.
METHODS
The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews guidelines. The inclusion criteria were (i) pediatric and adult patients with suspected or confirmed hematological malignancy undergoing imaging (); (ii) any study using ML techniques to derive models using radiological images to apply to the clinical management of these patients (); and (iii) original research articles conducted in any setting globally (). Quality Assessment of Diagnostic Accuracy Studies 2 criteria were used to assess diagnostic and segmentation studies, while the Newcastle-Ottawa scale was used to assess the quality of observational studies.
RESULTS
Of 53 eligible studies, 33 applied diverse ML techniques to diagnose hematological malignancies or to differentiate them from other diseases, especially discriminating gliomas from primary central nervous system lymphomas (n=18); 11 applied ML to segmentation tasks, while 9 applied ML to prognostication or predicting therapeutic responses, especially for diffuse large B-cell lymphoma. All studies reported discrimination statistics, but no study calculated calibration statistics. Every diagnostic/segmentation study had a high risk of bias due to their case-control design; many studies failed to provide adequate details of the reference standard; and only a few studies used independent validation.
CONCLUSION
To deliver validated ML-based models to radiologists managing hematological malignancies, future studies should (i) adhere to standardized, high-quality reporting guidelines such as the Checklist for Artificial Intelligence in Medical Imaging; (ii) validate models in independent cohorts; (ii) standardize volume segmentation methods for segmentation tasks; (iv) establish comprehensive prospective studies that include different tumor grades, comparisons with radiologists, optimal imaging modalities, sequences, and planes; (v) include side-by-side comparisons of different methods; and (vi) include low- and middle-income countries in multicentric studies to enhance generalizability and reduce inequity.
PubMed: 36605438
DOI: 10.3389/fonc.2022.1080988 -
Cureus Dec 2022We performed a systematic review and meta-analysis of patients with suspected recurrent cholesteatoma who underwent non-echo planar imaging (non-EPI) using... (Review)
Review
We performed a systematic review and meta-analysis of patients with suspected recurrent cholesteatoma who underwent non-echo planar imaging (non-EPI) using diffusion-weighted magnetic resonance imaging (MRI), with surgery as the reference standard. We searched Medline, Google Scholar, and the Cochrane database for diagnostic test accuracy studies. The following prespecified subgroup analyses were performed: patient age, number of radiologists interpreting MRI, study design, and risk of bias. We used a bivariate model using a generalized linear mixed model to pool accuracies. Of the 460 records identified, 32 studies were included, of which 50% (16/32) were low risk of bias. The overall pooled sensitivity was 92.2% (95% CI 87.3-95.3%), and specificity was 91.7% (85.2-95.5%). The positive likelihood ratio was 11.1 (4.5-17.8), and the negative likelihood ratio was 0.09 (0.04-0.13). The pooled diagnostic odds ratio was 130.3 (20.5-240). Heterogeneity was moderate on visual inspection of the hierarchical summary receiver operating characteristic curve. Subgroup analyses showed prospective studies reporting higher accuracies (p=0.027), which were driven by higher specificity (prospective 93.1% (88.4-96.0%) versus retrospective 81.2% (81.0-81.4%)). There was no difference in subgroups comparing patient age (p=0.693), number of radiologists interpreting MRI (p=0.503), or risk of bias (p=0.074). No publication bias was detected (p=0.98). In conclusion, non-EPI is a highly sensitive and specific diagnostic test able to identify recurrent cholesteatomas of moderate to large sizes. This test can be considered a non-invasive alternative to second-look surgery.
PubMed: 36601207
DOI: 10.7759/cureus.32127 -
Diagnostic and Interventional Imaging May 2023The purpose of this study was to perform a systematic review of the literature on the diagnostic performance, in independent test cohorts, of artificial intelligence... (Review)
Review
Artificial intelligence algorithms aimed at characterizing or detecting prostate cancer on MRI: How accurate are they when tested on independent cohorts? - A systematic review.
PURPOSE
The purpose of this study was to perform a systematic review of the literature on the diagnostic performance, in independent test cohorts, of artificial intelligence (AI)-based algorithms aimed at characterizing/detecting prostate cancer on magnetic resonance imaging (MRI).
MATERIALS AND METHODS
Medline, Embase and Web of Science were searched for studies published between January 2018 and September 2022, using a histological reference standard, and assessing prostate cancer characterization/detection by AI-based MRI algorithms in test cohorts composed of more than 40 patients and with at least one of the following independency criteria as compared to the training cohort: different institution, different population type, different MRI vendor, different magnetic field strength or strict temporal splitting.
RESULTS
Thirty-five studies were selected. The overall risk of bias was low. However, 23 studies did not use predefined diagnostic thresholds, which may have optimistically biased the results. Test cohorts fulfilled one to three of the five independency criteria. The diagnostic performance of the algorithms used as standalones was good, challenging that of human reading. In the 12 studies with predefined diagnostic thresholds, radiomics-based computer-aided diagnosis systems (assessing regions-of-interest drawn by the radiologist) tended to provide more robust results than deep learning-based computer-aided detection systems (providing probability maps). Two of the six studies comparing unassisted and assisted reading showed significant improvement due to the algorithm, mostly by reducing false positive findings.
CONCLUSION
Prostate MRI AI-based algorithms showed promising results, especially for the relatively simple task of characterizing predefined lesions. The best management of discrepancies between human reading and algorithm findings still needs to be defined.
Topics: Male; Humans; Artificial Intelligence; Magnetic Resonance Imaging; Algorithms; Prostatic Neoplasms; Diagnosis, Computer-Assisted
PubMed: 36517398
DOI: 10.1016/j.diii.2022.11.005 -
Journal of Clinical Medicine Nov 2022Pulmonary endarterectomy (PEA) is the treatment of choice in case of chronic thromboembolic pulmonary hypertension (CTEPH). PEA is performed by an increasing number of... (Review)
Review
Pulmonary endarterectomy (PEA) is the treatment of choice in case of chronic thromboembolic pulmonary hypertension (CTEPH). PEA is performed by an increasing number of surgeons; however, the reported outcomes are limited to a few registries or to individual centers' experiences. This systematic review focuses on pre-operative evaluation, intra-operative procedure and post-operative results in patients submitted to PEA for CTEPH. The literature included was searched using a formal strategy, combining the terms "pulmonary endarterectomy" AND "chronic pulmonary hypertension" and focusing on studies published in the last 5 years (2017-2022) to give a comprehensive overview on the most updated literature. The selection of the adequate surgical candidate is a crucial point, and the decision should always be performed by expert multidisciplinary teams composed of surgeons, pulmonologists and radiologists. In all the included studies, the surgical procedure was performed through a median sternotomy with intermittent deep hypothermic circulatory arrest under cardiopulmonary bypass. In case of residual pulmonary hypertension, alternative combined treatments should be considered (balloon angioplasty and/or medical therapy until lung transplantation in highly selected cases). Short- and long-term outcomes, although not homogenous across the different studies, are acceptable in highly experienced CTEPH centers.
PubMed: 36498551
DOI: 10.3390/jcm11236976 -
Medicine Nov 2022The purpose of this study was to conduct a systematic review for understanding the availability and limitations of artificial intelligence (AI) approaches that could...
BACKGROUND
The purpose of this study was to conduct a systematic review for understanding the availability and limitations of artificial intelligence (AI) approaches that could automatically identify and quantify computed tomography (CT) findings in traumatic brain injury (TBI).
METHODS
Systematic review, in accordance with PRISMA 2020 and SPIRIT-AI extension guidelines, with a search of 4 databases (Medline, Embase, IEEE Xplore, and Web of Science) was performed to find AI studies that automated the clinical tasks for identifying and quantifying CT findings of TBI-related abnormalities.
RESULTS
A total of 531 unique publications were reviewed, which resulted in 66 articles that met our inclusion criteria. The following components for identification and quantification regarding TBI were covered and automated by existing AI studies: identification of TBI-related abnormalities; classification of intracranial hemorrhage types; slice-, pixel-, and voxel-level localization of hemorrhage; measurement of midline shift; and measurement of hematoma volume. Automated identification of obliterated basal cisterns was not investigated in the existing AI studies. Most of the AI algorithms were based on deep neural networks that were trained on 2- or 3-dimensional CT imaging datasets.
CONCLUSION
We identified several important TBI-related CT findings that can be automatically identified and quantified with AI. A combination of these techniques may provide useful tools to enhance reproducibility of TBI identification and quantification by supporting radiologists and clinicians in their TBI assessments and reducing subjective human factors.
Topics: Humans; Artificial Intelligence; Reproducibility of Results; Radionuclide Imaging; Brain Injuries, Traumatic; Tomography, X-Ray Computed
PubMed: 36451512
DOI: 10.1097/MD.0000000000031848 -
Surgical Innovation Feb 2023Immersive virtual reality (iVR) facilitates surgical decision-making by enabling surgeons to interact with complex anatomic structures in realistic 3-dimensional...
Immersive virtual reality (iVR) facilitates surgical decision-making by enabling surgeons to interact with complex anatomic structures in realistic 3-dimensional environments. With emerging interest in its applications, its effects on patients and providers should be clarified. This systematic review examines the current literature on iVR for patient-specific preoperative planning. A literature search was performed on five databases for publications from January 1, 2000 through March 21, 2021. Primary studies on the use of iVR simulators by surgeons at any level of training for patient-specific preoperative planning were eligible. Two reviewers independently screened titles, abstracts, and full texts, extracted data, and assessed quality using the Quality Assessment Tool for Studies with Diverse Designs (QATSDD). Results were qualitatively synthesized, and descriptive statistics were calculated. The systematic search yielded 2,555 studies in total, with 24 full-texts subsequently included for qualitative synthesis, representing 264 medical personnel and 460 patients. Neurosurgery was the most frequently represented discipline (10/24; 42%). Preoperative iVR did not significantly improve patient-specific outcomes of operative time, blood loss, complications, and length of stay, but may decrease fluoroscopy time. In contrast, iVR improved surgeon-specific outcomes of surgical strategy, anatomy visualization, and confidence. Validity, reliability, and feasibility of patient-specific iVR models were assessed The mean QATSDD score of included studies was 32.9%. Immersive VR improves surgeon experiences of preoperative planning, with minimal evidence for impact on short-term patient outcomes. Future work should focus on high-quality studies investigating long-term patient outcomes, and utility of preoperative iVR for trainees.
Topics: Humans; Reproducibility of Results; Virtual Reality; Neurosurgical Procedures; Neurosurgery; Surgeons
PubMed: 36448920
DOI: 10.1177/15533506221143235 -
Tomography (Ann Arbor, Mich.) Nov 2022Breast cancer patients who have pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) are more likely to have better clinical outcomes. The ability to... (Review)
Review
Breast cancer patients who have pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) are more likely to have better clinical outcomes. The ability to predict which patient will respond to NAC early in the treatment course is important because it could help to minimize unnecessary toxic NAC and to modify regimens mid-treatment to achieve better efficacy. Machine learning (ML) is increasingly being used in radiology and medicine because it can identify relationships amongst complex data elements to inform outcomes without the need to specify such relationships a priori. One of the most popular deep learning methods that applies to medical images is the Convolutional Neural Networks (CNN). In contrast to supervised ML, deep learning CNN can operate on the whole images without requiring radiologists to manually contour the tumor on images. Although there have been many review papers on supervised ML prediction of pCR, review papers on deep learning prediction of pCR are sparse. Deep learning CNN could also incorporate multiple image types, clinical data such as demographics and molecular subtypes, as well as data from multiple treatment time points to predict pCR. The goal of this study is to perform a systematic review of deep learning methods that use whole-breast MRI images without annotation or tumor segmentation to predict pCR in breast cancer.
Topics: Humans; Female; Breast Neoplasms; Deep Learning; Magnetic Resonance Imaging; Breast; Neoadjuvant Therapy
PubMed: 36412691
DOI: 10.3390/tomography8060232 -
Frontiers in Public Health 2022The COVID-19 pandemic and restrictions on travel and quarantine measures made people turn to self-medication (SM) to control the symptoms of their diseases. Different... (Meta-Analysis)
Meta-Analysis
BACKGROUND
The COVID-19 pandemic and restrictions on travel and quarantine measures made people turn to self-medication (SM) to control the symptoms of their diseases. Different studies were conducted worldwide on different populations, and their results were different. Therefore, this global systematic review and meta-analysis was conducted to estimate the pooled prevalence of self-medication.
METHODS
In this systematic review and meta-analysis, databases of Scopus, PubMed, Embase, and Web of Science were searched without a time limit. All eligible observational articles that reported self-medication during the COVID-19 pandemic were analyzed. Heterogeneity among the studies was assessed using Cochran's Q test and I statistics. A random-effects model was used to estimate the pooled prevalence of self-medication. The methodological quality of the articles was evaluated with the Newcastle-Ottawa Scale.
RESULTS
Fifty-six eligible studies were reviewed. The pooled prevalence of self-medication was 48.6% (95% CI: 42.8-54.3). The highest and lowest prevalence of self-medication was in Asia (53%; 95% CI: 45-61) and Europe (40.8%; 95% CI: 35-46.8). Also, the highest and lowest prevalence of self-medication was related to students (54.5; 95% CI: 40.8-68.3) and healthcare workers (32.5%; 16-49). The prevalence of self-medication in the general population (48.8%; 40.6-57) and in patients with COVID-19 (41.7%; 25.5-58). The prevalence of self-medication was higher in studies that collected data in 2021 than in 2020 (51.2 vs. 48%). Publication bias was not significant ( = 0.320).
CONCLUSION
During the COVID-19 pandemic, self-medication was highly prevalent, so nearly half of the people self-medicated. Therefore, it seems necessary to provide public education to control the consequences of self-medication.
Topics: Humans; Prevalence; COVID-19; Pandemics; Quarantine; Students
PubMed: 36408026
DOI: 10.3389/fpubh.2022.1041695 -
Cancers Oct 2022Breast cancer is among the most common and fatal diseases for women, and no permanent treatment has been discovered. Thus, early detection is a crucial step to control... (Review)
Review
Breast cancer is among the most common and fatal diseases for women, and no permanent treatment has been discovered. Thus, early detection is a crucial step to control and cure breast cancer that can save the lives of millions of women. For example, in 2020, more than 65% of breast cancer patients were diagnosed in an early stage of cancer, from which all survived. Although early detection is the most effective approach for cancer treatment, breast cancer screening conducted by radiologists is very expensive and time-consuming. More importantly, conventional methods of analyzing breast cancer images suffer from high false-detection rates. Different breast cancer imaging modalities are used to extract and analyze the key features affecting the diagnosis and treatment of breast cancer. These imaging modalities can be divided into subgroups such as mammograms, ultrasound, magnetic resonance imaging, histopathological images, or any combination of them. Radiologists or pathologists analyze images produced by these methods manually, which leads to an increase in the risk of wrong decisions for cancer detection. Thus, the utilization of new automatic methods to analyze all kinds of breast screening images to assist radiologists to interpret images is required. Recently, artificial intelligence (AI) has been widely utilized to automatically improve the early detection and treatment of different types of cancer, specifically breast cancer, thereby enhancing the survival chance of patients. Advances in AI algorithms, such as deep learning, and the availability of datasets obtained from various imaging modalities have opened an opportunity to surpass the limitations of current breast cancer analysis methods. In this article, we first review breast cancer imaging modalities, and their strengths and limitations. Then, we explore and summarize the most recent studies that employed AI in breast cancer detection using various breast imaging modalities. In addition, we report available datasets on the breast-cancer imaging modalities which are important in developing AI-based algorithms and training deep learning models. In conclusion, this review paper tries to provide a comprehensive resource to help researchers working in breast cancer imaging analysis.
PubMed: 36358753
DOI: 10.3390/cancers14215334 -
Frontiers in Public Health 2022Chest computerized tomography (CT) plays an important role in detecting patients with suspected coronavirus disease 2019 (COVID-19), however, there are no systematic... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Chest computerized tomography (CT) plays an important role in detecting patients with suspected coronavirus disease 2019 (COVID-19), however, there are no systematic summaries on whether the chest CT findings of patients within mainland China are applicable to those found in patients outside.
METHODS
Relevant studies were retrieved comprehensively by searching PubMed, Embase, and Cochrane Library databases before 15 April 2022. Quality assessment of diagnostic accuracy studies (QUADAS) was used to evaluate the quality of the included studies, which were divided into two groups according to whether they were in mainland China or outside. Data on diagnostic performance, unilateral or bilateral lung involvement, and typical chest CT imaging appearances were extracted, and then, meta-analyses were performed with R software to compare the CT features of COVID-19 pneumonia between patients from within and outside mainland China.
RESULTS
Of the 8,258 studies screened, 19 studies with 3,400 patients in mainland China and 14 studies with 554 outside mainland China were included. Overall, the risk of quality assessment and publication bias was low. The diagnostic value of chest CT is similar between patients from within and outside mainland China (93, 91%). The pooled incidence of unilateral lung involvement (15, 7%), the crazy-paving sign (31, 21%), mixed ground-glass opacities (GGO) and consolidations (51, 35%), air bronchogram (44, 25%), vascular engorgement (59, 33%), bronchial wall thickening (19, 12%), and septal thickening (39, 26%) in patients from mainland China were significantly higher than those from outside; however, the incidence rates of bilateral lung involvement (75, 84%), GGO (78, 87%), consolidations (45, 58%), nodules (12, 17%), and pleural effusion (9, 15%) were significantly lower.
CONCLUSION
Considering that the chest CT features of patients in mainland China may not reflect those of the patients abroad, radiologists and clinicians should be familiar with various CT presentations suggestive of COVID-19 in different regions.
Topics: Humans; COVID-19; SARS-CoV-2; Tomography, X-Ray Computed; Databases, Factual; China
PubMed: 36311632
DOI: 10.3389/fpubh.2022.939095