Monday, April 1, 2019

Artificial Intelligence Can Detect Wrist Fractures

A study published in Radiology: Artificial Intelligence found that convolutional neural networks could detect and show fractures on wrist radiographs with a high level of sensitivity and specificity.

A dataset of 7356 wrist radiographs was split into training (90%) and validation (10%) sets.  The models were tested on an unseen test set of 524 consecutive emergency wrist radiographic studies with two radiologists in consensus as the reference standard.

The model detected and correctly localized 310 (91.2%) of 340 and 236 (96.3%) of 245 of all radius and ulna fractures on the frontal and lateral views, respectively. The per-study sensitivity, specificity were 98.1%, and 72.9%, respectively.

The authors concluded that convolutional neural networks were able to detect and localize radius and ulna fractures on wrist radiographs with high sensitivity and specificity.

Friday, March 1, 2019

Low Radiation Dose CT Leads to Inferior Diagnoses

Jensen et al reported in Radiology that CT evaluation of colorectal liver metastases was not as accurate after reducing the radiation exposure by more than 50 percent. 

Their study included 52 patients with biopsy-proven colorectal cancer liver metastases and few benign lesions as well.  Each patient underwent two CT scans-a standard radiation dose (SD) contrast CT and a reduced radiation dose (RD) CT scan- during the same breast hold.

Reduced dose CT resulted in a mean dose reduction of 54% compared with standard dose. Of the 260 lesions, 233 were metastatic and 27 benign, 212 were detected with RD CT, whereas 252 were detected with SD CT.   Mean qualitative scores ranked SD images as higher quality versus RD series images.

The authors concluded that CT evaluation of colorectal liver metastases is compromised with reduced radiation dose, and the use of iterative reconstructions could not maintain observer performance.

Friday, February 1, 2019

Double Reading Improves Breast Cancer Screening

A study by Taylor-Phillips et al published in Radiology reports that double reading of mammography screening studies increases the number of cancers detected and reduces recalls. 

The authors conducted a retrospective analysis, 805 206 women who were evaluated through screening and diagnostic studies at 33 English breast centers.

The first reader recalled (4.76%; 38 295 of 805 206 women). Two readers recalled 6.19% of women in total (49 857 of 805 206 women) but arbitration of discordant readings reduced the recall rate to 4.08%. A total of 7055 cancers were detected, of which 627 or 8.89% were detected by the second reader only. These additional cancers were more likely to be ductal carcinoma in situ 30.5%; (183 of 600 vs. 22.0%; 1344 of 6114, and additional invasive cancers were smaller (mean size, 14.2 vs. 16.7 mm), had fewer involved nodes, and were likely to be lower grade.

The authors concluded that double reading with arbitration reduces recall rates and increases cancer detection compared with single reading. 

Tuesday, January 1, 2019

Contrast Enhanced Ultrasound in Breast Cancer

Vraka et al published in vivo their research regarding the correlation of findings between contrast enhanced ultrasound (CEUS) and pathological and prognostic factors in breast cancer. 

They retrospectively analyzed 34 breast cancers on which CEUS studies were performed and they looked at qualitative findings and quantitative characteristics.

They found that indistinct tumor margins were characteristic of high-grade malignancy and also in estrogen negative tumors.  They also found that perilesional enhancement was seen in tumors positive for Ki-67 expression.  Finally, heterogeneous sentinel lymph node enhancement was associated with metastatic infiltration.

Although the authors suggested their study cohort was rather small, their findings correlated well with histopathological and prognostic factors used in the initial diagnosis and therapy of patients with breast cancer, the most common cancer in women. 

Saturday, December 1, 2018

Thermal Ablation is Effective in the Treatment of NSCLC

According to a study published in Radiology researchers found that thermal ablation (TA) and stereotactic radiotherapy (STR) delivered comparable two and five-year outcomes in the treatment of early-stage non-small cell lung cancer (NSCLC)

This retrospective study included 28 834 patients (TA, 1102 patients; SRT, 27 732 patients) were identified in the 2004–2013 National Cancer Database.
There was no statistically significant difference in overall survival between TA and SRT at a mean follow-up of 52 months. Overall survival rates of TA and SRT were 85.4% vs. 86.3% in 1 year, 65.2% vs. 64.5% in 2 years,47.8% vs. 45.9% in 3 yearsand 24.6% vs. 26.1% in 5 years.  Unplanned hospital readmission rates were higher (3.7 vs. 0.2%) for patients who underwent TA versus those who underwent SRT.
Thermal ablation has an advantage of enabling physicians to collect biopsy samples during the procedure, while the one-time treatment offers lower direct costs for patients and insurance providers alike.
The authors concluded that TA has equally good results to STR in the treatment of stage 1 non–small cell lung cancer in patients who are deemed inoperable.

Thursday, November 1, 2018

Carotid artery wall thickness measured by MRI better in predicting CVC than Ultrasound

A study by Zhang et al published in Radiology found magnetic resonance imaging (MRI) wall thickness measurements of carotid arteries enhances the quality of cardiovascular disease (CVC) risk assessment. 

The researchers enrolled 698 patients from the Multi-Ethnic Study of Atherosclerosis (MESA) from July 2000 to December 2013. Their average age was 63 years old and had no known history of cardiovascular disease. Patients underwent ultrasound and MRI between 2000 and 2004 to compare carotid artery wall thickness. 

The researchers found the association between wall thickness and cardiovascular events was stronger with contrast and non-contrast-enhanced MRI than it was for the ultrasound-based carotid intima-media thickness test. When included in the same model, MRI wall thickness, but not intima-media thickness, remained associated with the outcomes.

Monday, October 1, 2018

Breast MRI Improves depiction of DCIS Components

A study by Kuhl et al published in Radiology found magnetic resonance imaging (MRI) of the breast improves depiction of ductal carcinoma in situ (DCIS) components of invasive breast cancers prior to surgery.

The authors performed a prospective two-center study of 593 patients with biopsy proven invasive breast cancer that underwent breast MRI in addition to conventional imaging. 

The outcomes showed surgical-pathologic evaluation demonstrated DCIS components in 139 (23%) women. MRI had significantly higher sensitivity in the diagnosis of DCIS components pre-operatively in (84%; 118 women out of 139) than that of conventional imaging, which detected (36%; 51 of the 139 women). More than 50 percent of DCIS components were detected with MRI alone. 

The researchers also found the sensitivity benefits of MR imaging over conventional imaging improved with increasing relative size, and with increasing nuclear grade of DCIS components. Positive margin rates were generally low and did not diverge significantly between the 139 women with DCIS components versus the 454 women who lacked them.

The authors concluded that breast MRI improves depiction of DCIS components of invasive breast cancers before surgery.