Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT.

BACKGROUND: This study systematically compares the impact of innovative deep learning image reconstruction (DLIR, TrueFidelity) to conventionally used iterative reconstruction (IR) on nodule volumetry and subjective image quality (IQ) at highly reduced radiation doses. This is essential in the context of low-dose CT lung cancer screening where accurate volumetry and characterization of pulmonary nodules in repeated CT scanning are indispensable. MATERIALS AND METHODS: A standardized CT dataset was established using an anthropomorphic chest phantom (Lungman, Kyoto Kaguku Inc., Kyoto, Japan) containing a set of 3D-printed lung nodules including six diameters (4 to 9 mm) and three morphology classes (lobular, spiculated, smooth), with an established ground truth. Images were acquired at varying radiation doses (6.04, 3.03, 1.54, 0.77, 0.41 and 0.20 mGy) and reconstructed with combinations of reconstruction kernels (soft and hard kernel) and reconstruction algorithms (ASIR-V and DLIR at low, medium and high strength). Semi-automatic volumetry measurements and subjective image quality scores recorded by five radiologists were analyzed with multiple linear regression and mixed-effect ordinal logistic regression models. RESULTS: Volumetric errors of nodules imaged with DLIR are up to 50% lower compared to ASIR-V, especially at radiation doses below 1 mGy and when reconstructed with a hard kernel. Also, across all nodule diameters and morphologies, volumetric errors are commonly lower with DLIR. Furthermore, DLIR renders higher subjective IQ, especially at the sub-mGy doses. Radiologists were up to nine times more likely to score the highest IQ-score to these images compared to those reconstructed with ASIR-V. Lung nodules with irregular margins and small diameters also had an increased likelihood (up to five times more likely) to be ascribed the best IQ scores when reconstructed with DLIR. CONCLUSION: We observed that DLIR performs as good as or even outperforms conventionally used reconstruction algorithms in terms of volumetric accuracy and subjective IQ of nodules in an anthropomorphic chest phantom. As such, DLIR potentially allows to lower the radiation dose to participants of lung cancer screening without compromising accurate measurement and characterization of lung nodules.

PULMONARY NODULE DETECTION IN CHEST CT USING A DEEP LEARNING-BASED RECONSTRUCTION ALGORITHM.

This study's aim was to assess whether deep learning image reconstruction (DLIR) techniques are non-inferior to ASIR-V for the clinical task of pulmonary nodule detection in chest computed tomography. Up to 6 (range 3-6, mean 4.2) artificial lung nodules (diameter: 3, 5, 8 mm; density: -800, -630, +100 HU) were inserted at different locations in the Kyoto Kagaku Lungman phantom. In total, 16 configurations (10 abnormal, 6 normal) were scanned at 7.6, 3, 1.6 and 0.38 mGy CTDIvol (respectively 0, 60, 80 and 95% dose reduction). Images were reconstructed using 50% ASIR-V and a deep learning-based algorithm with low (DL-L), medium (DL-M) and high (DL-H) strength. Four chest radiologists evaluated 256 series by locating and scoring nodules on a five-point scale. No statistically significant difference was found among the reconstruction algorithms (p = 0.987, average across readers AUC: 0.555, 0.561, 0.557, 0.558 for ASIR-V, DL-L, DL-M, DL-H).

Lesion detection on a combined "All-in-One" window compared to conventional window settings in thoracic oncology chest CT examinations.

PURPOSE: The purpose of this study was to investigate if lesion detection using a single "All-in-One" (AIO) window was non-inferior to lesion detection on conventional window settings in thoracic oncology chest computed tomography (CT) examinations. MATERIALS AND METHODS: In a retrospective study, 50 consecutive chest CT examinations of 50 patients (31 men, 19 women; mean age 64±10 [SD] years, range: 35-82 years) containing 417 lesions, were reviewed by 6 radiologists, subdivided into 2 groups of 3 radiologists each, with similar levels of expertise in each group (senior staff member, junior staff member and radiology resident). All examinations were reviewed in conventional or AIO window settings by one of the groups. A 'lesion' was defined as any abnormality seen on the chest CT examination, including both benign and malignant lesions, findings in chest and upper abdomen, and measurable and non-measurable disease. Lesions were listed as 'missed' when they were not seen by at least two out of three observers. F-tests were used to evaluate the significance of the variables of interest within a mixed model framework and kappa statistics to report interobserver agreement. RESULTS: On a reader level, 54/417 lesions (12.9%) were not detected by the senior staff member reading the studies in conventional window settings and 45/417 (10.8%) by the senior staff member reading the AIO images. For the junior staff member and radiology resident this was respectively 55/417 (13.2%) and 67/417 (16.1%) for the conventional window settings and 43/417 (10.3%) and 61/417 (14.6%) for the AIO window. On a lesion level, 68/417 (16.3%) were defined as 'missed' lesions (lesions not detected by at least 2 readers): 21/68 (30.9%) on the AIO-window, 30/68 (44.1%) on conventional views and 17/68 (25.0%) on both views. The use of the AIO window did not result in an increase of missed lesions (P>0.99). Interobserver agreement in both groups was similar (P=0.46). Regarding lesions that were categorized as 'missed' on the AIO window or on conventional window settings, there was no effect of location (chest or upper abdomen) (P=0.35), window (P=0.97) and organ (P=0.98). CONCLUSIONS: A single AIO-window is non-inferior to multiple conventional window settings for lesion detection on chest CT examinations in thoracic oncology patients.

Bilateral adrenal haemorrhage after a high energetic trauma: a case report and review of current literature.

Most adrenal injuries are asymptomatic. In traumatic events, adrenal haemorrhage is very likely to be accompanied by injuries to other organs. Isolated adrenal injury after trauma is very rare and mostly unilateral. We report a case of a 44-year-old male who suffered a major traffic accident with multiple trauma, including a bilateral adrenal haemorrhage. This caused a primary adrenal insufficiency, as proven with a cortisol stimulation test with synthetic corticotrophin. Bilateral adrenal haemorrhage is a very rare but potentially fatal disorder and should not be missed. This case illustrates that early diagnosis and prompt treatment with hydrocortisone may contribute to a beneficial outcome.

Septic Thrombophlebitis of the Right Ovarian Vein.

BACKGROUND: A 26-year-old woman presented at the emergency department with a painful abdomen and fever up to 39°C, despite antibiotics. She had given prematurely birth by caesarian section to a twin 8 days earlier. On clinical examination she had a diffuse painful and tender abdomen, especially on the right side and suprapubic region. Laboratory findings showed an increased c-reactive protein of 24 mg/dL (normal < 0,3) and increased white blood cell count of 13 Å~ 10E9/L (normal 4,3-10 Å~ 10E9/L). There was also a decreased hemoglobin level of 8,4 g/dL (normal 12-15 g/dL). An ultrasonography was performed by the gynecologist and revealed a large heterogeneous fluid collection anteriorly of the uterus.

Update in non small-cell lung cancer staging.

Significant progress has been made with the introduction of the TNM-7 staging system for non-small cell lung cancer (NSCLC). Constituting the first major revision in 12 years, the seventh edition of NSCLC TNM (TNM-7) is based on the recommendations from the International Association for the Study of Lung Cancer (IASLC) Lung Cancer Staging Project of 2007. This new TNM iteration includes a subset analysis on SCLC and carcinoid tumors. A thorough understanding of its principles by the radiologist is helpful to increase efficiency and to improve communication with the referring clinicians.

Asymptomatic pneumatosis intestinalis in AIDS.

Pneumatosis intestinalis is an unusual entity in which subserosal or submucosal collections of gas occur in the bowel wall. We present a case of asymptomatic linear pneumatosis intestinalis and free abdominal air in a 67-year-old man with acquired immunodeficiency syndrome (AIDS) who improved spontaneously following conservative management. Pneumatosis intestinalis is a late-stage phenomenon in patients with AIDS that characteristically involves the cecum, ascending and transverse colon or the rectum with sparing of the descending colon and the sigmoid. For these patients, non-operative management is appropriate.

Diffusion restriction in a superficial breast lesion.

OBJECTIVE: To report the imaging findings of a 22-year-old Asian woman with a freely movable retro-areolar nodule in the right breast, first noticed after a holiday in The Philippines. MATERIAL AND METHODS: We preformed clinical examination, mammography and ultrasound with color Doppler imaging. A differential diagnosis of epidermal inclusion cyst, complex cyst, well demarcated carcinoma and echinococcus cyst was proposed. For further differential diagnosis, a MRI of the breasts was performed on a 1.5 superconducting system, with a bilateral breast coil. T2- and T1 weighted images, followed by axial echo-planar diffusion-weighted MRI (DW-MRI) were performed with b values of 0, 500, and 1000 mm2/s (trace images and ADC maps). RESULTS: The high signal intensity on T2 weighted images confirmed the cystic character of the lesion. The high signal intensity on T1 FS weighted images can be seen in complex cysts and inclusion cysts, but is less likely in an echinococcus cyst. On DW-MRI there is a marked diffusion restriction in the nodule, which can be seen in complex cysts and inclusion cysts. A well demarcated carcinoma is less likely, unless a tumour with a very high cellularity. Because neither carcinoma nor echinococcus cyst could be ruled out, a surgical excision was performed. Pathological examination revealed normal squamous epithelium with stratification and lamellated keratin, consistent with an epidermal inclusion cyst. CONCLUSION: We argue that in selected cases DW-MRI can be useful to narrow the differential diagnosis and notable differentiate epidermal inclusion cysts from echinococcus cysts.

Chest MSCT acquisition and injection protocols.

The past decade there has been an enormous advance in imaging technology, most obvious in the field of magnetic resonance imaging (MRI) and computed tomography (CT). Today nearly every radiology department has a multislice CT (MSCT) available for routine imaging, many of which are increasingly being replaced by last generation 16- and 64-slice CT scanners. However, the use of fast CT scanners requires a better insight in acquisition and contrast media injection protocols in order to achieve the best possible result. It is the aim of this article to give a review of the basic principles of CT protocol design for the chest and the kinetics of contrast media injection.

Management of cystic pancreatic masses.

This paper presents our experience on the characterization of cystic pancreatic lesions using CT and MRI. First of all, true cystic pancreatic neoplasms should be differentiated from pseudocysts. Noninvasive characterization of cystic pancreatic neoplasms continues to rely principally on CT and MRI. Despite the presence of classic radiological characteristics of various cystic pancreatic neoplasms, these lesions continue to be problematic for the radiologist. They are most frequently incidental findings that are not related to the reason for imaging the patients in whom they are discovered. The radiological and clinical challenges are to determine the benign or malignant nature of the lesion and its potential resectability. The heterogeneity among cystic lesions and overlap in imaging characteristics should cause radiologists to approach the specific characterization of cystic pancreatic masses with a substantial degree of humility. Recommending an appropriate management approach based on imaging findings, in conjunction with clinical information and clinical consultation, may therefore be more important than attempting to assign a specific diagnosis to a cystic pancreatic lesion.