Deep Learning for Automated Segmentation of Liver Lesions at CT in Patients with Colorectal Cancer Liver Metastases.

Purpose To evaluate the performance, agreement, and efficiency of a fully convolutional network (FCN) for liver lesion detection and segmentation at CT examinations in patients with colorectal liver metastases (CLMs). Materials and Methods This retrospective study evaluated an automated method using an FCN that was trained, validated, and tested with 115, 15, and 26 contrast material-enhanced CT examinations containing 261, 22, and 105 lesions, respectively. Manual detection and segmentation by a radiologist was the reference standard. Performance of fully automated and user-corrected segmentations was compared with that of manual segmentations. The interuser agreement and interaction time of manual and user-corrected segmentations were assessed. Analyses included sensitivity and positive predictive value of detection, segmentation accuracy, Cohen κ, Bland-Altman analyses, and analysis of variance. Results In the test cohort, for lesion size smaller than 10 mm (n = 30), 10-20 mm (n = 35), and larger than 20 mm (n = 40), the detection sensitivity of the automated method was 10%, 71%, and 85%; positive predictive value was 25%, 83%, and 94%; Dice similarity coefficient was 0.14, 0.53, and 0.68; maximum symmetric surface distance was 5.2, 6.0, and 10.4 mm; and average symmetric surface distance was 2.7, 1.7, and 2.8 mm, respectively. For manual and user-corrected segmentation, κ values were 0.42 (95% confidence interval: 0.24, 0.63) and 0.52 (95% confidence interval: 0.36, 0.72); normalized interreader agreement for lesion volume was -0.10 ± 0.07 (95% confidence interval) and -0.10 ± 0.08; and mean interaction time was 7.7 minutes ± 2.4 (standard deviation) and 4.8 minutes ± 2.1 (P < .001), respectively. Conclusion Automated detection and segmentation of CLM by using deep learning with convolutional neural networks, when manually corrected, improved efficiency but did not substantially change agreement on volumetric measurements.© RSNA, 2019Supplemental material is available for this article.

[1]  Syamsiah Mashohor,et al.  Review of liver segmentation and computer assisted detection/diagnosis methods in computed tomography , 2017, Artificial Intelligence Review.

[2]  J. Stoker,et al.  Diagnostic imaging of colorectal liver metastases with CT, MR imaging, FDG PET, and/or FDG PET/CT: a meta-analysis of prospective studies including patients who have not previously undergone treatment. , 2010, Radiology.

[3]  Hayit Greenspan,et al.  Fully Convolutional Network for Liver Segmentation and Lesions Detection , 2016, LABELS/DLMIA@MICCAI.

[4]  H. Bismuth,et al.  Early Recurrence After Hepatectomy for Colorectal Liver Metastases: What Optimal Definition and What Predictive Factors? , 2016, The oncologist.

[5]  J. Bloem,et al.  Hepatic metastases in patients with colorectal cancer: relationship between size of metastases, standard of reference, and detection rates. , 2002, Radiology.

[6]  A. Jemal,et al.  Cancer treatment and survivorship statistics, 2012 , 2012, CA: a cancer journal for clinicians.

[7]  Florence Morin-Roy,et al.  Validation of a semiautomated liver segmentation method using CT for accurate volumetry. , 2015, Academic radiology.

[8]  C. Mathers,et al.  Cancer incidence and mortality worldwide: Sources, methods and major patterns in GLOBOCAN 2012 , 2015, International journal of cancer.

[9]  Julian L Wichmann,et al.  Assessment of colorectal liver metastases using MRI and CT: impact of observer experience on diagnostic performance and inter-observer reproducibility with histopathological correlation. , 2014, European journal of radiology.

[10]  Fucang Jia,et al.  Automatic Segmentation of Liver Tumor in CT Images with Deep Convolutional Neural Networks , 2015 .

[11]  L. Påhlman,et al.  Managing synchronous liver metastases from colorectal cancer: a multidisciplinary international consensus. , 2015, Cancer treatment reviews.

[12]  A. Shinagare,et al.  Update on the role of imaging in management of metastatic colorectal cancer. , 2014, Radiographics : a review publication of the Radiological Society of North America, Inc.

[13]  Atle Bjørnerud,et al.  Volumetric glioma quantification: comparison of manual and semi-automatic tumor segmentation for the quantification of tumor growth , 2015, Acta radiologica.

[14]  Jayaram K. Udupa,et al.  A framework for evaluating image segmentation algorithms , 2006, Comput. Medical Imaging Graph..

[15]  Nikos Papanikolaou,et al.  Automated and Semiautomated Segmentation of Rectal Tumor Volumes on Diffusion-Weighted MRI: Can It Replace Manual Volumetry? , 2016, International journal of radiation oncology, biology, physics.

[16]  C. Pal,et al.  Deep Learning: A Primer for Radiologists. , 2017, Radiographics : a review publication of the Radiological Society of North America, Inc.

[17]  S. Majumdar,et al.  Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and Morphometry. , 2018, Radiology.

[18]  G Y Zou,et al.  Confidence interval estimation for the Bland–Altman limits of agreement with multiple observations per individual , 2013, Statistical methods in medical research.

[19]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[20]  P. Silverman.  Liver metastases: imaging considerations for protocol development with Multislice CT (MSCT) , 2006, Cancer imaging : the official publication of the International Cancer Imaging Society.

[21]  A. Jemal,et al.  Colorectal cancer statistics, 2017 , 2017, CA: a cancer journal for clinicians.

[22]  P. Prassopoulos,et al.  Treatment response classification of liver metastatic disease evaluated on imaging. Are RECIST unidimensional measurements accurate? , 2009, European Radiology.

[23]  Samuel Kadoury,et al.  Liver segmentation: indications, techniques and future directions , 2017, Insights into Imaging.

[24]  K. Lee,et al.  Limited detection of small (≤ 10 mm) colorectal liver metastasis at preoperative CT in patients undergoing liver resection , 2017, PloS one.

[25]  L. Schwartz,et al.  New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). , 2009, European journal of cancer.

[26]  N. Kemeny,et al.  Metastatic Colorectal Cancer: From Improved Survival to Potential Cure , 2010, Oncology.

[27]  E. Abdalla,et al.  AHPBA/SSO/SSAT sponsored consensus conference on the multidisciplinary treatment of colorectal cancer metastases. , 2013, HPB : the official journal of the International Hepato Pancreato Biliary Association.

[28]  I. Steffen,et al.  Size determination and response assessment of liver metastases with computed tomography--comparison of RECIST and volumetric algorithms. , 2013, European journal of radiology.

[29]  B. Erickson,et al.  Systematic review of outcomes of patients undergoing resection for colorectal liver metastases in the setting of extra hepatic disease. , 2014, European journal of cancer.

[30]  O. Abe,et al.  Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study. , 2017, Radiology.