Automatic Ventriculomegaly Detection in Fetal Brain MRI: A Step-by-Step Deep Learning Model for Novel 2D-3D Linear Measurements.

In this study, we developed an automated workflow using a deep learning model (DL) to measure the lateral ventricle linearly in fetal brain MRI, which are subsequently classified into normal or ventriculomegaly, defined as a diameter wider than 10 mm at the level of the thalamus and choroid plexus. To accomplish this, we first trained a UNet-based deep learning model to segment the brain of a fetus into seven different tissue categories using a public dataset (FeTA 2022) consisting of fetal T2-weighted images. Then, an automatic workflow was developed to perform lateral ventricle measurement at the level of the thalamus and choroid plexus. The test dataset included 22 cases of normal and abnormal T2-weighted fetal brain MRIs. Measurements performed by our AI model were compared with manual measurements performed by a general radiologist and a neuroradiologist. The AI model correctly classified 95% of fetal brain MRI cases into normal or ventriculomegaly. It could measure the lateral ventricle diameter in 95% of cases with less than a 1.7 mm error. The average difference between measurements was 0.90 mm in AI vs. general radiologists and 0.82 mm in AI vs. neuroradiologists, which are comparable to the difference between the two radiologists, 0.51 mm. In addition, the AI model also enabled the researchers to create 3D-reconstructed images, which better represent real anatomy than 2D images. When a manual measurement is performed, it could also provide both the right and left ventricles in just one cut, instead of two. The measurement difference between the general radiologist and the algorithm (p = 0.9827), and between the neuroradiologist and the algorithm (p = 0.2378), was not statistically significant. In contrast, the difference between general radiologists vs. neuroradiologists was statistically significant (p = 0.0043). To the best of our knowledge, this is the first study that performs 2D linear measurement of ventriculomegaly with a 3D model based on an artificial intelligence approach. The paper presents a step-by-step approach for designing an AI model based on several radiological criteria. Overall, this study showed that AI can automatically calculate the lateral ventricle in fetal brain MRIs and accurately classify them as abnormal or normal.

Deep learning LI-RADS grading system based on contrast enhanced multiphase MRI for differentiation between LR-3 and LR-4/LR-5 liver tumors.

BACKGROUND: To develop a deep learning (DL) method based on multiphase, contrast-enhanced (CE) magnetic resonance imaging (MRI) to distinguish Liver Imaging Reporting and Data System (LI-RADS) grade 3 (LR-3) liver tumors from combined higher-grades 4 and 5 (LR-4/LR-5) tumors for hepatocellular carcinoma (HCC) diagnosis. METHODS: A total of 89 untreated LI-RADS-graded liver tumors (35 LR-3, 14 LR-4, and 40 LR-5) were identified based on the radiology MRI interpretation reports. Multiphase 3D T1-weighted gradient echo imaging was acquired at six time points: pre-contrast, four phases immediately post-contrast, and one hepatobiliary phase after intravenous injection of gadoxetate disodium. Image co-registration was performed across all phases on the center tumor slice to correct motion. A rectangular tumor box centered on the tumor area was drawn to extract subset tumor images for each imaging phase, which were used as the inputs to a convolutional neural network (CNN). The pre-trained AlexNet CNN model underwent transfer learning using liver MRI data for LI-RADS tumor grade classification. The output probability number closer to 1 or 0 indicated a higher possibility of being combined LR-4/LR-5 tumor or LR-3 tumor, respectively. Five-fold cross validation was used for training (60% dataset), validation (20%) and testing processes (20%). RESULTS: The DL CNN model for LI-RADS grading using inputs of multiphase liver MRI data acquired at three time points (pre-contrast, arterial, and washout phase) achieved a high accuracy of 0.90, sensitivity of 1.0, precision of 0.835, and AUC of 0.95 with reference to the expert human radiologist report. The CNN output of probability provided radiologists a confidence level of the model's grading for each liver lesion. CONCLUSIONS: An AlexNet CNN model for LI-RADS grading of liver lesions provided diagnostic performance comparable to radiologists and offered valuable clinical guidance for differentiating intermediate LR-3 liver lesions from more-likely malignant LR-4/LR-5 lesions in HCC diagnosis.

AAPM medical physics practice guideline 6.a.: Performance characteristics of radiation dose index monitoring systems.

The American Association of Physicists in Medicine (AAPM) is a nonprofit professional society whose primary purposes are to advance the science, education and professional practice of medical physics. The AAPM has more than 8,000 members and is the principal organization of medical physicists in the United States. The AAPM will periodically define new practice guidelines for medical physics practice to help advance the science of medical physics and to improve the quality of service to patients throughout the United States. Existing medical physics practice guidelines will be reviewed for the purpose of revision or renewal, as appropriate, on their fifth anniversary or sooner. Each medical physics practice guideline represents a policy statement by the AAPM, has undergone a thorough consensus process in which it has been subjected to extensive review, and requires the approval of the Professional Council. The medical physics practice guidelines recognize that the safe and effective use of diagnostic and therapeutic radiology requires specific training, skills, and techniques, as described in each document. Reproduction or modification of the published practice guidelines and technical standards by those entities not providing these services is not authorized. The following terms are used in the AAPM practice guidelines: •Must and Must Not: Used to indicate that adherence to the recommendation is considered necessary to conform to this practice guideline. •Should and Should Not: Used to indicate a prudent practice to which exceptions may occasionally be made in appropriate circumstances.

Pulmonary nodules with ground-glass opacity can be reliably measured with low-dose techniques regardless of iterative reconstruction: results of a phantom study.

OBJECTIVE: Pulmonary nodules of ground-glass opacity represent one imaging manifestation of a slow-growing variant of lung cancer. The objective of this phantom study was to quantify the effect of the radiation dose used for the examination (volume CT dose index [CTDI(vol)]), type of reconstruction algorithm, and choice of postreconstruction enhancement algorithms on the measurement error when assessing the volume of simulated lung nodules with CT, focusing on two radiodensity levels. MATERIALS AND METHODS: Twelve synthetic nodules of two radiodensities (-630 and -10 HU), three shapes (spherical, lobulated, and spiculated), and two sizes (nominal diameters of 5 and 10 mm) were inserted into an anthropomorphic chest phantom and scanned with techniques varying in CTDI(vol) (from subscreening dose [0.8 mGy] to diagnostic levels [6.5 mGy]), reconstruction algorithms (iterative reconstruction and filtered back projection), and different postreconstruction enhancement algorithms. Nodule volume was measured from the resulting reconstructed CT images with a matched filter estimator. RESULTS: No significant over- or underestimation of nodule volume was observed across individual variables, with low percentage error overall (-1.4%) and for individual variables (range, -3.4% to 0.4%). The magnitude of percentage error was also low (overall average percentage error < 6% and SD values < 4.5%) and for individual variables (absolute percentage error range 3.3-5.6%). No clinically significant differences were observed between different levels of CTDI(vol), use of iterative reconstruction algorithms, or use of different postreconstruction enhancement algorithms. CONCLUSION: These results indicate that, if validated for other measurement tools and scanners, lung nodule volume measurements from scans acquired and reconstructed with significantly different acquisition and reconstruction techniques can be reliably compared.

Detection of pulmonary embolism during pregnancy: comparing radiation doses of CTPA and pulmonary scintigraphy.

OBJECTIVE: In pregnant patients pulmonary embolism is a common occurrence with potentially devastating outcomes, necessitating timely imaging diagnosis. In every patient, especially in pregnant patients, radiation exposure is an important consideration while selecting the best imaging modality. MATERIALS AND METHODS: We performed a retrospective analysis comparing radiation doses of computed tomography pulmonary angiography (CTPA), perfusion scintigraphy, and perfusion/ventilation scintigraphy for suspected pulmonary embolism in 53 pregnant patients at our hospital between 2006 and 2012. Effective dose and breast-absorbed and uterus-absorbed doses for CTPA as well as effective dose and breast and fetus-absorbed doses for pulmonary scintigraphy were estimated using International Commission on Radiological Protection 103 weighting factors. RESULTS: For CTPA and perfusion scintigraphy, average doses were estimated as effective doses of 21 and 1.04 mSv, breast-absorbed doses of 44 and 0.28 mGy, and uterus-absorbed dose of 0.46 mGy and fetal-absorbed dose of 0.25 mGy, respectively. With inclusion of the ventilation component of pulmonary scintigraphy, doses increased to an effective dose of 1.29 mSv, a breast-absorbed dose of 0.37 mGy, and a fetal-absorbed dose of 0.40 mGy. CONCLUSION: Perfusion nuclear medicine study has a statistically significantly lower effective and breast-absorbed dose (P<0.0001) when compared with CTPA. Similarly, the fetal-absorbed dose for pulmonary scintigraphy has a statistically lower dose (P=0.0010) when compared with CTPA, even if the ventilation component of pulmonary scintigraphy is performed, although these values are so small that they are unlikely to be clinically significant.