RESUMO
OBJECTIVE: To develop an automatic COVID-19 Reporting and Data System (CO-RADS)-based classification in a multi-demographic setting. METHODS: This multi-institutional review boards-approved retrospective study included 2720 chest CT scans (mean age, 58 years [range 18-100 years]) from Italian and Russian patients. Three board-certified radiologists from three countries assessed randomly selected subcohorts from each population and provided CO-RADS-based annotations. CT radiomic features were extracted from the selected subcohorts after preprocessing steps like lung lobe segmentation and automatic noise reduction. We compared three machine learning models, logistic regression (LR), multilayer perceptron (MLP), and random forest (RF) for the automated CO-RADS classification. Model evaluation was carried out in two scenarios, first, training on a mixed multi-demographic subcohort and testing on an independent hold-out dataset. In the second scenario, training was done on a single demography and externally validated on the other demography. RESULTS: The overall inter-observer agreement for the CO-RADS scoring between the radiologists was substantial (k = 0.80). Irrespective of the type of validation test scenario, suspected COVID-19 CT scans were identified with an accuracy of 84%. SHapley Additive exPlanations (SHAP) interpretation showed that the "wavelet_(LH)_GLCM_Imc1" feature had a positive impact on COVID prediction both with and without noise reduction. The application of noise reduction improved the overall performance between the classifiers for all types. CONCLUSION: Using an automated model based on the COVID-19 Reporting and Data System (CO-RADS), we achieved clinically acceptable performance in a multi-demographic setting. This approach can serve as a standardized tool for automated COVID-19 assessment. KEYPOINTS: ⢠Automatic CO-RADS scoring of large-scale multi-demographic chest CTs with mean AUC of 0.93 ± 0.04. ⢠Validation procedure resembles TRIPOD 2b and 3 categories, enhancing the quality of experimental design to test the cross-dataset domain shift between institutions aiding clinical integration. ⢠Identification of COVID-19 pneumonia in the presence of community-acquired pneumonia and other comorbidities with an AUC of 0.92.
Assuntos
COVID-19 , Pneumonia , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Demografia , Humanos , Pessoa de Meia-Idade , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodos , Adulto JovemRESUMO
The objective of this study is to evaluate the feasibility of a disease-specific deep learning (DL) model based on minimum intensity projection (minIP) for automated emphysema detection in low-dose computed tomography (LDCT) scans. LDCT scans of 240 individuals from a population-based cohort in the Netherlands (ImaLife study, mean age ± SD = 57 ± 6 years) were retrospectively chosen for training and internal validation of the DL model. For independent testing, LDCT scans of 125 individuals from a lung cancer screening cohort in the USA (NLST study, mean age ± SD = 64 ± 5 years) were used. Dichotomous emphysema diagnosis based on radiologists' annotation was used to develop the model. The automated model included minIP processing (slab thickness range: 1 mm to 11 mm), classification, and detection maps generation. The data-split for the pipeline evaluation involved class-balanced and imbalanced settings. The proposed DL pipeline showed the highest performance (area under receiver operating characteristics curve) for 11 mm slab thickness in both the balanced (ImaLife = 0.90 ± 0.05) and the imbalanced dataset (NLST = 0.77 ± 0.06). For ImaLife subcohort, the variation in minIP slab thickness from 1 to 11 mm increased the DL model's sensitivity from 75 to 88% and decreased the number of false-negative predictions from 10 to 5. The minIP-based DL model can automatically detect emphysema in LDCTs. The performance of thicker minIP slabs was better than that of thinner slabs. LDCT can be leveraged for emphysema detection by applying disease specific augmentation.
Assuntos
Enfisema , Enfisema Pulmonar , Tomografia Computadorizada por Raios X , Inteligência Artificial , Enfisema/diagnóstico por imagem , Humanos , Enfisema Pulmonar/diagnóstico por imagem , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodosRESUMO
Artificial Intelligence (AI) algorithms for automatic lung nodule detection and classification can assist radiologists in their daily routine of chest CT evaluation. Even though many AI algorithms for these tasks have already been developed, their implementation in the clinical workflow is still largely lacking. Apart from the significant number of false-positive findings, one of the reasons for that is the bias that these algorithms may contain. In this review, different types of biases that may exist in chest CT AI nodule detection and classification algorithms are listed and discussed. Examples from the literature in which each type of bias occurs are presented, along with ways to mitigate these biases. Different types of biases can occur in chest CT AI algorithms for lung nodule detection and classification. Mitigation of them can be very difficult, if not impossible to achieve completely.
RESUMO
There is no real need to discuss the potential advantages - mainly the excellent soft tissue contrast, nonionizing radiation, flow, and molecular information - of magnetic resonance imaging (MRI) as an intraoperative diagnosis and therapy system particularly for neurological applications and oncological therapies. Difficult patient access in conventional horizontal-field superconductive magnets, very high investment and operational expenses, and the need for special nonferromagnetic therapy tools have however prevented the widespread use of MRI as imaging and guidance tool for therapy purposes. The interventional use of MRI systems follows for the last 20+ years the strategy to use standard diagnostic systems and add more or less complicated and expensive components (eg, MRI-compatible robotic systems, specially shielded in-room monitors, dedicated tools and devices made from low-susceptibility materials, etc) to overcome the difficulties in the therapy process. We are proposing to rethink that approach using an in-room portable ultrasound (US) system that can be safely operated till 1 m away from the opening of a 3T imaging system. The live US images can be tracked using an optical inside-out approach adding a camera to the US probe in combination with optical reference markers to allow direct fusion with the MRI images inside the MRI suite. This leads to a comfortable US-guided intervention and excellent patient access directly on the MRI patient bed. This was combined with an entirely mechanical MRI-compatible 7 degrees of freedom holding arm concept, which shows that this test environment is a different way to create a cost-efficient and effective setup that combines the advantages of MRI and US by largely avoiding the drawbacks of current interventional MRI concepts.
RESUMO
For the real-time fusion of different modalities, a variety of tracking methods are available including the optical, electromagnetic (EM) and image-based tracking. But as a drawback optical tracking suffers from line of sight issues and EM tracking requires the manual referencing for the fusion procedure and is not usable in Magnetic Resonance Imaging (MRI) environment. To avoid these issues, we propose a real-time setup containing a camera capable of inside-Out tracking using combined circular markers attached to Ultrasound (US) probe and a suitable platform for automatic overlay of MRI and US image using markers. This new approach could help clinicians carry out successful surgical procedures by requiring least system interaction and solving line of sight issues. As a proof-of-concept, we show our first result by mimicking common liver tumor intervention using framed marker fusion technique in a candle gel phantom. We evaluated the tracking error distances using the combination of special markers with Inside-Out approach and conventional optical tracking. The results achieved show comparable performance to the standard Outside-In tracking and manual reference approach, while easing the interventional procedure in terms of hardware and line of sight requirements.