site logo
ARRS InPractice
  • Latest Issue
  • Contact Us
Homepage > AJR OnTrend > Deep Learning Differentiates Small Renal Masses on Multiphase CT

Deep Learning Differentiates Small Renal Masses on Multiphase CT

Takashi Tanaka
Corresponding Author

A deep learning method with a convolutional neural network (CNN) can support the evaluation of small solid renal masses in dynamic CT images with acceptable diagnostic performance. Between 2012 and 2016, researchers at Japan’s Okayama University studied 1,807 image sets from 168 pathologically diagnosed small (≤ 4 cm) solid renal masses with four CT phases—unenhanced, corticomedullary, nephrogenic, and excretory—in 159 patients. Masses were classified as malignant (n = 136) or benign (n = 32) using a 5-point scale, and this dataset was then randomly divided into five subsets. As first AJR author, Takashi Tanaka explained, “four were used for augmentation and supervised training (48,832 images), and one was used for testing (281 images).” Utilizing the Inception-v3 architecture CNN model, the AUC for malignancy and accuracy at optimal cutoff values of output data were evaluated in six different CNN models. Finding no significant size difference between malignant and benign lesions, Tanaka’s team did find that the AUC value of the corticomedullary phase was higher than that of other phases (corticomedullary vs excretory, p = 0.022). Additionally, the highest accuracy (88%) was achieved in the corticomedullary phase images. Multivariate analysis revealed that the CNN model of corticomedullary phase was a significant predictor for malignancy, “compared with other CNN models, age, sex, and lesion size.”

Related

Previous StoryA Step Toward Automated Triage of Thyroid Cancer
Next StoryLow Back Pain Accounts for a Third of New Emergency Imaging in the U.S.

ARRS

Contact InPractice
Meetings
Articles with Credit
Books / Books with Credit
Online Courses
Web Lectures

AJR

AJR Journal
AJR Articles with Credit
Subscribe to AJR

ARRS Membership

Benefits
Join / Renew
Volunteer Opportunities
In-Training Radiologists
Senior Radiologists

Scholarships

Donate Now
Roentgen Fund®
Fellowships / Awards
Making a Difference

The American Roentgen Ray Society (ARRS) is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education activities for physicians. ARRS has been granted Deemed Status by the American Board of Radiology (ABR). Copyright ©, American Roentgen Ray Society, ARRS, All Rights Reserved.