Roi Anteby1, Eyal Klang2,3,4, Nir Horesh5, Ido Nachmany5, Orit Shimon6, Yiftach Barash3,4, Uri Kopylov7, Shelly Soffer3,8. 1. School of Public Health, Harvard University, Boston, MA, USA. 2. Institute for Healthcare Delivery Science, Department of Population Health Science and Policy, Mount Sinai, New York, NY, USA. 3. Deep Vision Lab, The Chaim Sheba Medical Center, Ramat Gan, Israel. 4. Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Sackler Medical School, Tel Aviv University, Tel Aviv, Israel. 5. Department of Surgery and Transplantation B, Sheba Medical Center, Tel Hashomer, Sackler Medical School, Tel Aviv University, Tel Aviv, Israel. 6. Department of Anesthesia, Rabin Medical Center, Beilinson Hospital, Petach Tikvah, Sackler Medical School, Tel Aviv University, Tel Aviv, Israel. 7. Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, Sackler Medical School, Tel Aviv University, Tel Aviv, Israel. 8. Internal Medicine B, Assuta Medical Center, Ashdod, Ben-Gurion University of the Negev, Be'er Sheva, Israel.
Abstract
BACKGROUND & AIMS: While biopsy is the gold standard for liver fibrosis staging, it poses significant risks. Noninvasive assessment of liver fibrosis is a growing field. Recently, deep learning technology has revolutionized medical image analysis. This technology has the potential to enhance noninvasive fibrosis assessment. We systematically examined the application of deep learning in noninvasive liver fibrosis imaging. METHODS: Embase, MEDLINE, Web of Science, and IEEE Xplore databases were used to identify studies that reported on the accuracy of deep learning for classification of liver fibrosis on noninvasive imaging. The search keywords were "liver or hepatic," "fibrosis or cirrhosis," and "neural or deep learning networks." Risk of bias and applicability were evaluated using the QUADAS-2 tool. RESULTS: Sixteen studies were retrieved. Imaging modalities included ultrasound (n=10), computed tomography (n=3), and magnetic resonance imaging (n=3). The studies analyzed a total of 40,405 radiological images from 15,853 patients. All but two of the studies were retrospective. In most studies the "ground truth" reference was the METAVIR score for pathological staging (n=9,56%). The majority of the studies reported an accuracy >85% when compared to histopathology. Fourteen studies (87.5%) had a high risk of bias and concerns regarding applicability. CONCLUSIONS: Deep learning has the potential to play an emerging role in liver fibrosis classification. Yet, it is still limited by a relatively small number of retrospective studies. Clinicians should facilitate the use of this technology by sharing databases and standardized reports. This may optimize the noninvasive evaluation of liver fibrosis on a large scale. This article is protected by copyright. All rights reserved.
BACKGROUND & AIMS: While biopsy is the gold standard for liver fibrosis staging, it poses significant risks. Noninvasive assessment of liver fibrosis is a growing field. Recently, deep learning technology has revolutionized medical image analysis. This technology has the potential to enhance noninvasive fibrosis assessment. We systematically examined the application of deep learning in noninvasive liver fibrosis imaging. METHODS: Embase, MEDLINE, Web of Science, and IEEE Xplore databases were used to identify studies that reported on the accuracy of deep learning for classification of liver fibrosis on noninvasive imaging. The search keywords were "liver or hepatic," "fibrosis or cirrhosis," and "neural or deep learning networks." Risk of bias and applicability were evaluated using the QUADAS-2 tool. RESULTS: Sixteen studies were retrieved. Imaging modalities included ultrasound (n=10), computed tomography (n=3), and magnetic resonance imaging (n=3). The studies analyzed a total of 40,405 radiological images from 15,853 patients. All but two of the studies were retrospective. In most studies the "ground truth" reference was the METAVIR score for pathological staging (n=9,56%). The majority of the studies reported an accuracy >85% when compared to histopathology. Fourteen studies (87.5%) had a high risk of bias and concerns regarding applicability. CONCLUSIONS: Deep learning has the potential to play an emerging role in liver fibrosis classification. Yet, it is still limited by a relatively small number of retrospective studies. Clinicians should facilitate the use of this technology by sharing databases and standardized reports. This may optimize the noninvasive evaluation of liver fibrosis on a large scale. This article is protected by copyright. All rights reserved.
Entities:
Keywords:
Deep Learning; Diagnostic Imaging; Liver Fibrosis; Neural Networks (Computer)