The Feasibility of Using a Deep Learning-Based Model to Determine Cardiac Computed Tomographic Contrast Dose.

PURPOSE: This study aimed to predict contrast effects in cardiac computed tomography (CT) from CT localizer radiographs using a deep learning (DL) model and to compare the prediction performance of the DL model with that of conventional models based on patients' physical size. METHODS: This retrospective study included 473 (256 men and 217 women) cardiac CT scans between May 2014 and August 2017. We developed and evaluated DL models that predict milligrams of iodine per enhancement of the aorta from CT localizer radiographs. To assess the model performance, we calculated and compared Pearson correlation coefficient ( r ) between the actual iodine dose that was necessary to obtain a contrast effect of 1 HU (iodine dose per contrast effect [IDCE]) and IDCE predicted by DL, body weight, lean body weight, and body surface area of patients. RESULTS: The model was tested on 52 cases for the male group (mean [SD] age, 63.7 ± 11.4) and 44 cases for the female group (mean [SD] age, 69.8 ± 11.6). Correlation coefficients between the actual and predicted IDCE were 0.607 for the male group and 0.412 for the female group, which were higher than the correlation coefficients between the actual IDCE and body weight (0.539 for male, 0.290 for female), lean body weight (0.563 for male, 0.352 for female), and body surface area (0.587 for male, 0.349 for female). CONCLUSIONS: The performance for predicting contrast effects by analyzing CT localizer radiographs with the DL model was at least comparable with conventional methods using the patient's body size, notwithstanding that no additional measurements other than CT localizer radiographs were required.

Preliminary assessment of automated radiology report generation with generative pre-trained transformers: comparing results to radiologist-generated reports.

PURPOSE: In this preliminary study, we aimed to evaluate the potential of the generative pre-trained transformer (GPT) series for generating radiology reports from concise imaging findings and compare its performance with radiologist-generated reports. METHODS: This retrospective study involved 28 patients who underwent computed tomography (CT) scans and had a diagnosed disease with typical imaging findings. Radiology reports were generated using GPT-2, GPT-3.5, and GPT-4 based on the patient's age, gender, disease site, and imaging findings. We calculated the top-1, top-5 accuracy, and mean average precision (MAP) of differential diagnoses for GPT-2, GPT-3.5, GPT-4, and radiologists. Two board-certified radiologists evaluated the grammar and readability, image findings, impression, differential diagnosis, and overall quality of all reports using a 4-point scale. RESULTS: Top-1 and Top-5 accuracies for the different diagnoses were highest for radiologists, followed by GPT-4, GPT-3.5, and GPT-2, in that order (Top-1: 1.00, 0.54, 0.54, and 0.21, respectively; Top-5: 1.00, 0.96, 0.89, and 0.54, respectively). There were no significant differences in qualitative scores about grammar and readability, image findings, and overall quality between radiologists and GPT-3.5 or GPT-4 (p > 0.05). However, qualitative scores of the GPT series in impression and differential diagnosis scores were significantly lower than those of radiologists (p < 0.05). CONCLUSIONS: Our preliminary study suggests that GPT-3.5 and GPT-4 have the possibility to generate radiology reports with high readability and reasonable image findings from very short keywords; however, concerns persist regarding the accuracy of impressions and differential diagnoses, thereby requiring verification by radiologists.

Deep learning-based reconstruction and 3D hybrid profile order technique for MRCP at 3T: evaluation of image quality and acquisition time.

OBJECTIVES: To evaluate the image quality of the 3D hybrid profile order technique and deep-learning-based reconstruction (DLR) for 3D magnetic resonance cholangiopancreatography (MRCP) within a single breath-hold (BH) at 3 T magnetic resonance imaging (MRI). METHODS: This retrospective study included 32 patients with biliary and pancreatic disorders. BH images were reconstructed with and without DLR. The signal-to-noise ratio (SNR), contrast, contrast-to-noise ratio (CNR) between the common bile duct (CBD) and periductal tissues, and full width at half maximum (FWHM) of CBD on 3D-MRCP were evaluated quantitatively. Two radiologists scored image noise, contrast, artifacts, blur, and overall image quality of the three image types using a 4-point scale. Quantitative and qualitative scores were compared using the Friedman test and post hoc Nemenyi test. RESULTS: The SNR and CNR were not significantly different when under respiratory gating- and BH-MRCP without DLR. However, they were significantly higher under BH with DLR than under respiratory gating (SNR, p = 0.013; CNR, p = 0.027). The contrast and FWHM of MRCP under BH with and without DLR were lower than those under respiratory gating (contrast, p < 0.001; FWHM, p = 0.015). Qualitative scores for noise, blur, and overall image quality were higher under BH with DLR than those under respiratory gating (blur, p = 0.003; overall, p = 0.008). CONCLUSIONS: The combination of the 3D hybrid profile order technique and DLR is useful for MRCP within a single BH and does not lead to the deterioration of image quality and space resolution at 3 T MRI. CLINICAL RELEVANCE STATEMENT: Considering its advantages, this sequence might become the standard protocol for MRCP in clinical practice, at least at 3.0 T. KEY POINTS: • The 3D hybrid profile order can achieve MRCP within a single breath-hold without a decrease in spatial resolution. • The DLR significantly improved the CNR and SNR of BH-MRCP. • The 3D hybrid profile order technique with DLR reduces the deterioration of image quality in MRCP within a single breath-hold.

Combination Use of Compressed Sensing and Deep Learning for Shoulder Magnetic Resonance Imaging With Various Sequences.

OBJECTIVE: For compressed sensing (CS) to become widely used in routine magnetic resonance imaging (MRI), it is essential to improve image quality. This study aimed to evaluate the usefulness of combining CS and deep learning-based reconstruction (DLR) for various sequences in shoulder MRI. METHODS: This retrospective study included 37 consecutive patients who underwent undersampled shoulder MRIs, including T1-weighted (T1WI), T2-weighted (T2WI), and fat-saturation T2-weighted (FS-T2WI) images. Images were reconstructed using the conventional wavelet-based denoising method (wavelet method) and a combination of wavelet and DLR-based denoising methods (hybrid-DLR method) for each sequence. The signal-to-noise ratio and contrast-to-noise ratio of the bone, muscle, and fat and the full width at half maximum of the shoulder joint were compared between the 2 image types. In addition, 2 board-certified radiologists scored the image noise, contrast, sharpness, artifacts, and overall image quality of the 2 image types on a 4-point scale. RESULTS: The signal-to-noise ratios and contrast-to-noise ratios of the bone, muscle, and fat in T1WI, T2WI, and FS-T2WI obtained from the hybrid-DLR method were significantly higher than those of the conventional wavelet method ( P < 0.001). However, there were no significant differences in the full width at half maximum of the shoulder joint in any of the sequences ( P > 0.05). Furthermore, in all sequences, the mean scores of the image noise, sharpness, artifacts, and overall image quality were significantly higher in the hybrid-DLR method than in the wavelet method ( P < 0.001), but there were no significant differences in contrast among the sequences ( P > 0.05). CONCLUSIONS: The DLR denoising method can improve the image quality of CS in T1-weighted images, T2-weighted images, and fat-saturation T2-weighted images of the shoulder compared with the wavelet denoising method alone.

Update on the Use of Artificial Intelligence in Hepatobiliary MR Imaging.

The application of machine learning (ML) and deep learning (DL) in radiology has expanded exponentially. In recent years, an extremely large number of studies have reported about the hepatobiliary domain. Its applications range from differential diagnosis to the diagnosis of tumor invasion and prediction of treatment response and prognosis. Moreover, it has been utilized to improve the image quality of DL reconstruction. However, most clinicians are not familiar with ML and DL, and previous studies about these concepts are relatively challenging to understand. In this review article, we aimed to explain the concepts behind ML and DL and to summarize recent achievements in their use in the hepatobiliary region.

[A case of hemophagocytic syndrome associated with miliary tuberculosis].

We reported a case of a 76-year-female with hemophagocytic syndrome caused by military tuberculosis. The patients had complained high fever over 38.0 degrees C and anorexia. Her chest X-ray and computed tomography revealed disseminated miliary shadows in both lung fields. Laboratory examinations revealed anemia, thrombocytopenia and liver dysfunction. Bonemarrow aspirate revealed tuberculous granulomas and tubercle bacilli by acid-fast stains, and hemophagocytosis by macrophages. We diagnosed as miliary tuberculosis and tuberculosis-associated hemophagocytic syndrome, and started antituberculous and steroid therapy. After these therapy, fever, laboratory examinations dramatically improved. In this case, serum IL-18, sICAM-1, sVCAM-1 were elevated. These cytokines and adhesion molecules were reported to elevate in both hemophagocytic syndrome and tuberculosis correlating with disease activity. We conclude that IL-18, sICAM-1, sVCAM-1 may play important roles in pathogenesis of tuberculosis associated hemophagocytic syndrome.