Validation of Deep-Learning Image Reconstruction for Low-Dose Chest Computed Tomography Scan: Emphasis on Image Quality and Noise

Objective@#Iterative reconstruction degrades image quality. Thus, further advances in image reconstruction are necessary to overcome some limitations of this technique in low-dose computed tomography (LDCT) scan of the chest. Deep-learning image reconstruction (DLIR) is a new method used to reduce dose while maintaining image quality. The purposes of this study was to evaluate image quality and noise of LDCT scan images reconstructed with DLIR and compare with those of images reconstructed with the adaptive statistical iterative reconstruction-Veo at a level of 30% (ASiR-V 30%). @*Materials and Methods@#This retrospective study included 58 patients who underwent LDCT scan for lung cancer screening.Datasets were reconstructed with ASiR-V 30% and DLIR at medium and high levels (DLIR-M and DLIR-H, respectively). The objective image signal and noise, which represented mean attenuation value and standard deviation in Hounsfield units for the lungs, mediastinum, liver, and background air, and subjective image contrast, image noise, and conspicuity of structures were evaluated. The differences between CT scan images subjected to ASiR-V 30%, DLIR-M, and DLIR-H were evaluated. @*Results@#Based on the objective analysis, the image signals did not significantly differ among ASiR-V 30%, DLIR-M, and DLIR-H (p = 0.949, 0.737, 0.366, and 0.358 in the lungs, mediastinum, liver, and background air, respectively). However, the noise was significantly lower in DLIR-M and DLIR-H than in ASiR-V 30% (all p < 0.001). DLIR had higher signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) than ASiR-V 30% (p = 0.027, < 0.001, and < 0.001 in the SNR of the lungs, mediastinum, and liver, respectively; all p < 0.001 in the CNR). According to the subjective analysis, DLIR had higher image contrast and lower image noise than ASiR-V 30% (all p < 0.001). DLIR was superior to ASiR-V 30% in identifying the pulmonary arteries and veins, trachea and bronchi, lymph nodes, and pleura and pericardium (all p < 0.001). @*Conclusion@#DLIR significantly reduced the image noise in chest LDCT scan images compared with ASiR-V 30% while maintaining superior image quality.

Diagnostic Role of Conventional Ultrasonography and Shearwave Elastography in Asymptomatic Patients with Diffuse Thyroid Disease: Initial Experience with 57 Patients

PURPOSE: Thyroid ultrasonography (US) is a useful diagnostic tool in the evaluation of diffuse thyroid disease (DTD), whereas shearwave elastography is a dynamic technique that can provide information about tissue hardness by using acoustic shearwaves remotely induced by a focused ultrasonic beam. This study aims at investigating the role of conventional US and shearwave elastography in the diagnosis of asymptomatic patients with DTD. MATERIALS AND METHODS: Fifty-seven patients who underwent both conventional US and shearwave elastography were included in this study. Interobserver variability of the three radiologists in assessment of underlying thyroid echogenicity on conventional US was analyzed. Diagnostic performances for diagnosing DTD on conventional US and shearwave elastography were calculated and compared. RESULTS: Fair agreement was observed in the identification of DTD with conventional US (kappa value=0.27). The area under the receiver operating characteristic curve (Az) were 0.52-0.585 on conventional US by three radiologists. The Az values when using the mean and maximum elasticity values as a diagnostic criteria for DTD were 0.619 and 0.59 on shearwave elastography. Patients with DTD showed higher mean [24.1+/-10 kilo-Pascals (kPa)] and maximum (36.4+/-13.3 kPa) elasticity values on shearwave elastography when compared to the normal group (23.4+/-10.8 kPa and 33.7+/-12.4 kPa, respectively), although without statistical significance (p=0.802 and p=0.452, respectively). CONCLUSION: Conventional US did not show reliable interobserver agreement in the diagnosis of DTD. Although not statistically significant, shearwave elastography may provide additional information in the diagnosis of DTD. Therefore, larger prospective studies are needed to define the values of shearwave elastography for diagnosing DTD.

Clinical Applications of Neuroimaging with Susceptibility Weighted Imaging: Review Article

PURPOSE: Susceptibility-weighted magnetic resonance (MR) sequence is three-dimensional (3D), spoiled gradient-echo pulse sequences that provide a high sensitivity for the detection of blood degradation products, calcifications, and iron deposits. This pictorial review is aimed at illustrating and discussing its main clinical applications. MATERIALS AND METHODS: SWI is based on high-resolution, 3D, fully velocity-compensated gradient-echo sequences using both magnitude and phase images. To enhance the visibility of the venous structures, the magnitude images are multiplied with a phase mask generated from the filtered phase data, which are displayed at best after post-processing of the 3D dataset with the minimal intensity projection algorithm. A total of 200 patients underwent MR examinations that included SWI on a 3 tesla MR imager were enrolled. RESULTS: SWI is very useful in detecting multiple brain disorders. Among the 200 patients, 80 showed developmental venous anomaly, 22 showed cavernous malformation, 12 showed calcifications in various conditions, 21 showed cerebrovascular accident with susceptibility vessel sign or microbleeds, 52 showed brain tumors, 2 showed diffuse axonal injury, 3 showed arteriovenous malformation, 5 showed dural arteriovenous fistula, 1 showed moyamoya disease, and 2 showed Parkinson's disease. CONCLUSION: SWI is useful in detecting occult low flow vascular lesions, calcification and microbleed and characterising diverse brain disorders.

False Negative Fine Needle Aspiration Biopsy Results in Primary Thyroid Lymphoma

Ultrasonography-guided fine needle aspiration biopsy (US-FNA) is one of the methods used to diagnose thyroid lymphoma, but it has a relatively high false-negative rate. The authors report a case of a primary thyroid lymphoma associated with underlying lymphocytic thyroiditis that was initially misdiagnosed as lymphocytic thyroiditis based on US-FNA findings.

Complicated Thyroglossal Duct Cyst Mimicking Malignancy on Ultrasound: A Case Report

A Thyroglossal Duct Cyst (TGDC) is the most common cause of midline neck masses and is characterized in sonography as an anechoic or hypoechoic well-circumscribed cyst with posterior enhancement. TGDCs mostly occur in children and are easy to spot in them, but the sonographic appearance of TGDCs in adults is variable, ranging from a typical anechoic to a pseudosolid appearance. The presence of a solid component should alert the radiologist to the possibility of a cancer arising from the thyroglossal duct. We report here on our experience with a 58-year-old woman who had a complicated TGDC with a suspicious sonographic appearance of malignancy.

Histologic Characteristics of Hepatocellular Carcinomas Showing Atypical Enhancement Patterns on 4-Phase MDCT Examination

OBJECTIVE: To retrospectively define which histologic characteristics of small-sized hepatocellular carcinomas (HCCs) are related to atypical dynamic enhancement on multi-detector computed tomography (MDCT) imaging. MATERIALS AND METHODS: Seventy-three patients with 83 HCCs (3 cm or less in diameter) were included in this study. All patients underwent 4-phase MDCT imaging and subsequent surgery within eight weeks. Two independent radiologists blinded to the histologic findings retrospectively classified the HCCs as either typical (showing increased enhancement on arterial phase images followed by washout in late phase images) or atypical lesions demonstrating any other enhancement pattern. From the original pathologic reports, various histologic characteristics including gross morphology, nuclear histologic grades, presence of capsule formation, and capsule infiltration when a capsule was present, were compared among the two groups. RESULTS: An atypical enhancement pattern was seen in 30 (36.2%) of the 83 HCCs. The mean size of atypical HCCs (1.71 +/- 0.764) was significantly smaller than that of typical HCCs (2.31 +/- 0.598, p < 0.001). Atypical HCCs were frequently found to be vaguely nodular in gross morphology (n = 13, 43.3%) and to have grade I nuclear grades (n = 17, 56.7%). Capsule formation was significantly more common in typical HCCs (p < 0.001). Capsular infiltration was also more common in typical HCCs (p = 0.001). CONCLUSION: HCCs showing atypical dynamic enhancement on MDCT imaging are usually smaller than typical HCCs, vaguely nodular type in gross morphology in most cases, and well-differentiated in nuclear grades, and they lack of capsule formation or capsular infiltration.