A Guideline for Open-Source Tools to Make Medical Imaging Data Ready for Artificial Intelligence Applications: A Society of Imaging Informatics in Medicine (SIIM) Survey.

In recent years, the role of Artificial Intelligence (AI) in medical imaging has become increasingly prominent, with the majority of AI applications approved by the FDA being in imaging and radiology in 2023. The surge in AI model development to tackle clinical challenges underscores the necessity for preparing high-quality medical imaging data. Proper data preparation is crucial as it fosters the creation of standardized and reproducible AI models while minimizing biases. Data curation transforms raw data into a valuable, organized, and dependable resource and is a fundamental process to the success of machine learning and analytical projects. Considering the plethora of available tools for data curation in different stages, it is crucial to stay informed about the most relevant tools within specific research areas. In the current work, we propose a descriptive outline for different steps of data curation while we furnish compilations of tools collected from a survey applied among members of the Society of Imaging Informatics (SIIM) for each of these stages. This collection has the potential to enhance the decision-making process for researchers as they select the most appropriate tool for their specific tasks.

Reproducibility of Deep Learning Algorithms Developed for Medical Imaging Analysis: A Systematic Review.

Since 2000, there have been more than 8000 publications on radiology artificial intelligence (AI). AI breakthroughs allow complex tasks to be automated and even performed beyond human capabilities. However, the lack of details on the methods and algorithm code undercuts its scientific value. Many science subfields have recently faced a reproducibility crisis, eroding trust in processes and results, and influencing the rise in retractions of scientific papers. For the same reasons, conducting research in deep learning (DL) also requires reproducibility. Although several valuable manuscript checklists for AI in medical imaging exist, they are not focused specifically on reproducibility. In this study, we conducted a systematic review of recently published papers in the field of DL to evaluate if the description of their methodology could allow the reproducibility of their findings. We focused on the Journal of Digital Imaging (JDI), a specialized journal that publishes papers on AI and medical imaging. We used the keyword "Deep Learning" and collected the articles published between January 2020 and January 2022. We screened all the articles and included the ones which reported the development of a DL tool in medical imaging. We extracted the reported details about the dataset, data handling steps, data splitting, model details, and performance metrics of each included article. We found 148 articles. Eighty were included after screening for articles that reported developing a DL model for medical image analysis. Five studies have made their code publicly available, and 35 studies have utilized publicly available datasets. We provided figures to show the ratio and absolute count of reported items from included studies. According to our cross-sectional study, in JDI publications on DL in medical imaging, authors infrequently report the key elements of their study to make it reproducible.

Comparison of Magnetic Resonance-Based Elastography and Ultrasound Shear Wave Elastography in Patients With Suspicion of Nonalcoholic Fatty Liver Disease.

ABSTRACT: This study investigated the correlation between magnetic resonance elastography (MRE) and shear wave ultrasound elastography (SWE) in patients with clinically diagnosed or suspected nonalcoholic fatty liver disease (NAFLD). Subjects with or at risk of NAFLD identified by magnetic resonance imaging (MRI) proton density fat fraction (PDFF) were prospectively enrolled. For each patient, 6 valid 2-dimensional SWE measurements were acquired using a Logiq E10 scanner (GE HealthCare, Waukesha, WI). A reliability criterion of an interquartile range to median ratio of ≤15% was used for SWE to indicate quality dataset. Magnetic resonance elastography, and MR-fat quantification data were collected the same day as part of the patient's clinical standard of care. Magnetic resonance imaging PDFF was used as a reference to quantify fat with >6.4% indicating NAFLD. Pearson correlation and t-test were performed for statistical analyses. A total of 140 patients were enrolled, 112 of which met SWE reliability measurement criteria. Magnetic resonance elastography and 2-dimensional SWE showed a positive correlation across all study subjects ( r = 0.27; P = 0.004). When patients were grouped according to steatosis and fibrosis state, a positive correlation was observed between MRE and SWE in patients with fibrosis ( r = 0.30; P = 0.03), without fibrosis ( r = 0.27; P = 0.03), and with NAFLD ( r = 0.28; P = 0.02). No elastography technique correlated with liver fat quantification ( P > 0.52). Magnetic resonance elastography was significantly different between patients with and without fibrosis ( P < 0.0001). However, this difference was not apparent with SWE ( P = 0.09). In patients with suspected or known NAFLD, MRE, and SWE demonstrated a positive correlation. In addition, these noninvasive imaging modalities may be useful adjunct techniques for monitoring NAFLD.

Ultrasound-Based Machine Learning Approach for Detection of Nonalcoholic Fatty Liver Disease.

OBJECTIVES: Current diagnosis of nonalcoholic fatty liver disease (NAFLD) relies on biopsy or MR-based fat quantification. This prospective study explored the use of ultrasound with artificial intelligence for the detection of NAFLD. METHODS: One hundred and twenty subjects with clinical suspicion of NAFLD and 10 healthy volunteers consented to participate in this institutional review board-approved study. Subjects were categorized as NAFLD and non-NAFLD according to MR proton density fat fraction (PDFF) findings. Ultrasound images from 10 different locations in the right and left hepatic lobes were collected following a standard protocol. MRI-based liver fat quantification was used as the reference standard with >6.4% indicative of NAFLD. A supervised machine learning model was developed for assessment of NAFLD. To validate model performance, a balanced testing dataset of 24 subjects was used. Sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy with 95% confidence interval were calculated. RESULTS: A total of 1119 images from 106 participants was used for model development. The internal evaluation achieved an average precision of 0.941, recall of 88.2%, and precision of 89.0%. In the testing set AutoML achieved a sensitivity of 72.2% (63.1%-80.1%), specificity of 94.6% (88.7%-98.0%), positive predictive value (PPV) of 93.1% (86.0%-96.7%), negative predictive value of 77.3% (71.6%-82.1%), and accuracy of 83.4% (77.9%-88.0%). The average agreement for an individual subject was 92%. CONCLUSIONS: An ultrasound-based machine learning model for identification of NAFLD showed high specificity and PPV in this prospective trial. This approach may in the future be used as an inexpensive and noninvasive screening tool for identifying NAFLD in high-risk patients.

Comparison of Gray-scale Inversion to Improve Detection of Pulmonary Nodules on Chest X-rays Between Radiologists and a Deep Convolutional Neural Network.

Detection of pulmonary nodules on chest x-rays is an important task for radiologists. Previous studies have shown improved detection rates using gray-scale inversion. The purpose of our study was to compare the efficacy of gray-scale inversion in improving the detection of pulmonary nodules on chest x-rays for radiologists and machine learning models (ML). We created a mixed dataset consisting of 60, 2-view (posteroanterior view - PA and lateral view) chest x-rays with computed tomography confirmed nodule(s) and 62 normal chest x-rays. Twenty percent of the cases were separated for a testing dataset (24 total images). Data augmentation through mirroring and transfer learning was used for the remaining cases (784 total images) for supervised training of 4 ML models (grayscale PA, grayscale lateral, gray-scale inversion PA, and gray-scale inversion lateral) on Google's cloud-based AutoML platform. Three cardiothoracic radiologists analyzed the complete 2-view dataset (n=120) and, for comparison to the ML, the single-view testing subsets (12 images each). Gray-scale inversion (area under the curve (AUC) 0.80, 95% confidence interval (CI) 0.75-0.85) did not improve diagnostic performance for radiologists compared to grayscale (AUC 0.84, 95% CI 0.79-0.88). Gray-scale inversion also did not improve diagnostic performance for the ML. The ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5% respectively). In the limited testing dataset, the ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5%, respectively). Further investigation of other post-processing algorithms to improve diagnostic performance of ML is warranted.

Tumoral oxygenation and biodistribution of Lonidamine oxygen microbubbles following localized ultrasound-triggered delivery.

Prior work has shown that microbubble-assisted delivery of oxygen improves tumor oxygenation and radiosensitivity, albeit over a limited duration. Lonidamine (LND) has been investigated because of its ability to stimulate glycolysis, lactate production, inhibit mitochondrial respiration, and inhibit oxygen consumption rates in tumors but suffers from poor bioavailability. The goal of this work was to characterize LND-loaded oxygen microbubbles and assess their ability to oxygenate a human head and neck squamous cell carcinoma (HNSCC) tumor model, while also assessing LND biodistribution. In tumors treated with surfactant-shelled microbubbles with oxygen core (SE61O2) and ultrasound, pO2 levels increased to a peak 19.5 ± 9.7 mmHg, 50 s after injection and returning to baseline after 120 s. In comparison, in tumors treated with SE61O2/LND and ultrasound, pO2 levels showed a peak increase of 29.0 ± 8.3 mmHg, which was achieved 70 s after injection returning to baseline after 300 s (p < 0.001). The co-delivery of O2andLNDvia SE61 also showed an improvement of LND biodistribution in both plasma and tumor tissues (p < 0.001). In summary, ultrasound-sensitive microbubbles loaded with O2 and LND provided prolonged oxygenation relative to oxygenated microbubbles alone, as well as provided an ability to locally deliver LND, making them more appropriate for clinical translation.

Assessment of Axillary Lymph Nodes for Metastasis on Ultrasound Using Artificial Intelligence.

The purpose of this study was to evaluate an artificial intelligence (AI) system for the classification of axillary lymph nodes on ultrasound compared to radiologists. Ultrasound images of 317 axillary lymph nodes from patients referred for ultrasound guided fine needle aspiration or core needle biopsy and corresponding pathology findings were collected. Lymph nodes were classified into benign and malignant groups with histopathological result serving as the reference. Google Cloud AutoML Vision (Mountain View, CA) was used for AI image classification. Three experienced radiologists also classified the images and gave a level of suspicion score (1-5). To test the accuracy of AI, an external testing dataset of 64 images from 64 independent patients was evaluated by three AI models and the three readers. The diagnostic performance of AI and the humans were then quantified using receiver operating characteristics curves. In the complete set of 317 images, AutoML achieved a sensitivity of 77.1%, positive predictive value (PPV) of 77.1%, and an area under the precision recall curve of 0.78, while the three radiologists showed a sensitivity of 87.8% ± 8.5%, specificity of 50.3% ± 16.4%, PPV of 61.1% ± 5.4%, negative predictive value (NPV) of 84.1% ± 6.6%, and accuracy of 67.7% ± 5.7%. In the three external independent test sets, AI and human readers achieved sensitivity of 74.0% ± 0.14% versus 89.9% ± 0.06% (p = .25), specificity of 64.4% ± 0.11% versus 50.1 ± 0.20% (p = .22), PPV of 68.3% ± 0.04% versus 65.4 ± 0.07% (p = .50), NPV of 72.6% ± 0.11% versus 82.1% ± 0.08% (p = .33), and accuracy of 69.5% ± 0.06% versus 70.1% ± 0.07% (p = .90), respectively. These preliminary results indicate AI has comparable performance to trained radiologists and could be used to predict the presence of metastasis in ultrasound images of axillary lymph nodes.

Incorporation of a Machine Learning Algorithm With Object Detection Within the Thyroid Imaging Reporting and Data System Improves the Diagnosis of Genetic Risk.

BACKGROUND: The role of next generation sequencing (NGS) for identifying high risk mutations in thyroid nodules following fine needle aspiration (FNA) biopsy continues to grow. However, ultrasound diagnosis even using the American College of Radiology's Thyroid Imaging Reporting and Data System (TI-RADS) has limited ability to stratify genetic risk. The purpose of this study was to incorporate an artificial intelligence (AI) algorithm of thyroid ultrasound with object detection within the TI-RADS scoring system to improve prediction of genetic risk in these nodules. METHODS: Two hundred fifty-two nodules from 249 patients that underwent ultrasound imaging and ultrasound-guided FNA with NGS with or without resection were retrospectively selected for this study. A machine learning program (Google AutoML) was employed for both automated nodule identification and risk stratification. Two hundred one nodules were used for model training and 51 reserved for testing. Three blinded radiologists scored the images of the test set nodules using TI-RADS and assigned each nodule as high or low risk based on the presence of highly suspicious imaging features on TI-RADS (very hypoechoic, taller-than-wide, extra-thyroidal extension, punctate echogenic foci). Subsequently, the TI-RADS classification was modified to incorporate AI for T4 nodules while treating T1-3 as low risk and T5 as high risk. All diagnostic predictions were compared to the presence of a high-risk mutation and pathology when available. RESULTS: The AI algorithm correctly located all nodules in the test dataset (100% object detection). The model predicted the malignancy risk with a sensitivity of 73.9%, specificity of 70.8%, positive predictive value (PPV) of 70.8%, negative predictive value (NPV) of 73.9% and accuracy of 72.4% during the testing. The radiologists performed with a sensitivity of 52.1 ± 4.4%, specificity of 65.2 ± 6.4%, PPV of 59.1 ± 3.5%, NPV of 58.7 ± 1.8%, and accuracy of 58.8 ± 2.5% when using TI-RADS and sensitivity of 53.6 ± 17.6% (p=0.87), specificity of 83.3 ± 7.2% (p=0.06), PPV of 75.7 ± 8.5% (p=0.13), NPV of 66.0 ± 8.8% (p=0.31), and accuracy of 68.7 ± 7.4% (p=0.21) when using AI-modified TI-RADS. CONCLUSIONS: Incorporation of AI into TI-RADS improved radiologist performance and showed better malignancy risk prediction than AI alone when classifying thyroid nodules. Employing AI in existing thyroid nodule classification systems may help more accurately identifying high-risk nodules.

Aloe Vera-Derived Gel-Blended PHBV Nanofibrous Scaffold for Bone Tissue Engineering.

Today, composite scaffolds fabricated by natural and synthetic polymers have attracted a lot of attention among researchers in the field of tissue engineering, and given their combined properties that can play a very useful role in repairing damaged tissues. In the current study, aloe vera-derived gel-blended poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (PHBV) nanofibrous scaffold was fabricated by electrospinning, and then, PHBV and PHBV gel fabricated scaffolds characterized by scanning electron microscope, protein adsorption, cell attachment, tensile and cell's viability tests. After that, osteogenic supportive property of the scaffolds was studied by culturing of human-induced pluripotent stem cells on the scaffolds under osteogenic medium and evaluating of the common bone-related markers. The results showed that biocompatibility of the PHBV nanofibrous scaffold significantly improved when combined with the aloe vera gel. In addition, higher amounts of alkaline phosphatase activity, mineralization, and bone-related gene and protein expression were detected in stem cells when grown on PHBV-gel scaffold in comparison with those stem cells grown on the PHBV and culture plate. Taken together, it can be concluded that aloe vera gel-blended PHBV scaffold has a great promising osteoinductive potential that can be used as a suitable bioimplant for bone tissue engineering applications to accelerate bone regeneration and also degraded completely along with tissue regeneration.

Transgluteal ultrasonography in spica cast in postreduction assessment of developmental dysplasia of the hip.

PURPOSE: The position of the femoral head in spica cast after the reduction of developmental dysplasia of the hip (DDH) should be examined and followed up closely and regularly. The study aimed to use the transgluteal ultrasonography approach for this purpose and compare its accuracy with the results of CT scan, which is the most commonly used modality. METHODS: Twenty-three patients with an average age of 20-21 months were examined for 1 year after the reduction of DDH, both closed and open. Ultrasonography and CT scan were performed on the patients on the same day, and the results were interpreted by different radiologists. Transgluteal ultrasonography in spica cast was performed while the legs were abducted, internally rotated, and flexed. A blanket was placed under the patient to elevate the cast. RESULTS: Thirty cases of proper reduction (81%) and 7 cases of dislocated hip (19%) were reported in transgluteal ultrasonography, and 29 cases of proper reduction (78%) and 8 cases of dislocated hip (22%) were reported in the CT scan. The rate of agreement between the results of ultrasonography and CT scan was 91%. CONCLUSION: Transgluteal ultrasonography can be used as an excellent modality to examine the position of the femoral head in relation to the posterior rim of the acetabulum in spica cast. The position of the femoral head can be viewed properly needless of perineal opening in the cast. Thus, transgluteal ultrasonography can replace the CT scan to assess the position of the femoral head. Sonography does not expose patients to radiation and does not require sedation.

Micro-RNA-incorporated electrospun nanofibers improve osteogenic differentiation of human-induced pluripotent stem cells.

Smart scaffolds have a great role in the damaged tissue reconstruction. The aim of this study was developing a scaffold that in addition to its fiber's topography has also content of micro-RNAs (miRNAs), which play a regulatory role during osteogenesis. In this study, we inserted two important miRNAs, including miR-22 and miR-126 in the electrospun polycaprolactone (PCL) nanofibers and after scaffold characterization, osteoinductivity of the fabricated nanofibers was investigated by evaluating of the osteogenic differentiation potential of induced pluripotent stem cells (iPSCs) when grown on miRNAs-incorporated PCL nanofibers (PCL-miR) and empty PCL. MiRNAs incorporation had no effect on the fibers size and morphology, cell attachment, and protein adsorption, although viability and proliferation rate of the human iPSCs were increased after a week in PCL-miR compared to the empty PCL. The results obtained from alkaline phosphatase activity, calcium content, bone-related genes, and proteins expression assays demonstrated that the highest osteogenic markers were observed in iPSCs grown on the PCL-miR compared to the cells cultured on PCL and culture plate. According to the results, miR-incorporated PCL nanofibers could be considered as a promising potential tissue-engineered construct for the treatment of patients with bone lesions and defects.

CAD system based on B-mode and color Doppler sonographic features may predict if a thyroid nodule is hot or cold.

OBJECTIVES: The aim of this study was to evaluate if the analysis of sonographic parameters could predict if a thyroid nodule was hot or cold. METHODS: Overall, 102 thyroid nodules, including 51 hyperfunctioning (hot) and 51 hypofunctioning (cold) nodules, were evaluated in this study. Twelve sonographic features (i.e., seven B-mode and five Doppler features) were extracted for each nodule type. The isthmus thickness, nodule volume, echogenicity, margin, internal component, microcalcification, and halo sign features were obtained in the B-mode, while the vascularity pattern, resistive index (RI), peak systolic velocity, end diastolic velocity, and peak systolic/end diastolic velocity ratio (SDR) were determined, based on Doppler ultrasounds. All significant features were incorporated in the computer-aided diagnosis (CAD) system to classify hot and cold nodules. RESULTS: Among all sonographic features, only isthmus thickness, nodule volume, echogenicity, RI, and SDR were significantly different between hot and cold nodules. Based on these features in the training dataset, the CAD system could classify hot and cold nodules with an area under the curve (AUC) of 0.898. Also, in the test dataset, hot and cold nodules were classified with an AUC of 0.833. CONCLUSIONS: 2D sonographic features could differentiate hot and cold thyroid nodules. The CAD system showed a great potential to achieve it automatically. KEY POINTS: • Cold nodules represent higher volume (p = 0.005), isthmus thickness (p = 0.035), RI (p = 0.020), and SDR (p = 0.044) and appear hypoechogenic (p = 0.010) in US. • Nodule volume with an AUC of 0.685 and resistive index with an AUC of 0.628 showed the highest classification potential among all B-mode and Doppler features respectively. • The proposed CAD system could distinguish hot nodules from cold ones with an AUC of 0.833 (sensitivity 90.00%, specificity 70.00%, accuracy 80.00%, PPV 87.50%, and NPV 75.00%).