Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study
The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Purpose To investigate diagnostic performance by using a deep learning method with a convolutional neural network (CNN) for the differentiation of liver masses at dynamic contrast agent–enhanced computed tomography (CT). Materials and Methods This clinical retrospective study used CT image sets of liver masses over three phases (noncontrast-agent enhanced, arterial, and delayed). Masses were diagnosed according to five categories (category A, classic hepatocellular carcinomas [HCCs]; category B, malignant liver tumors other than classic and early HCCs; category C, indeterminate masses or mass-like lesions [including early HCCs and dysplastic nodules] and rare benign liver masses other than hemangiomas and cysts; category D, hemangiomas; and category E, cysts). Supervised training was performed by using 55 536 image sets obtained in 2013 (from 460 patients, 1068 sets were obtained and they were augmented by a factor of 52 [rotated, parallel-shifted, strongly enlarged, and noise-added images were generated from the original images]). The CNN was composed of six convolutional, three maximum pooling, and three fully connected layers. The CNN was tested with 100 liver mass image sets obtained in 2016 (74 men and 26 women; mean age, 66.4 years ± 10.6 [standard deviation]; mean mass size, 26.9 mm ± 25.9; 21, nine, 35, 20, and 15 liver masses for categories A, B, C, D, and E, respectively). Training and testing were performed five times. Accuracy for categorizing liver masses with CNN model and the area under receiver operating characteristic curve for differentiating categories A–B versus categories C–E were calculated. Results Median accuracy of differential diagnosis of liver masses for test data were 0.84. Median area under the receiver operating characteristic curve for differentiating categories A–B from C–E was 0.92. Conclusion Deep learning with CNN showed high diagnostic performance in differentiation of liver masses at dynamic CT. © RSNA, 2017 Online supplemental material is available for this article.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“several studies have already been published in areas such as lesion detection [7], classification [8], segmentation [9], image reconstruction [10, 11], and natural language processing [12].”
From Convolutional neural networks: an overview and application in radiology (2018) · cites this paper as [8]
In the citing paper
“The study showed that 2D-CNN using triphasic CT images was superior to that using biphasic or monophasic CT images.”
From Convolutional neural networks: an overview and application in radiology (2018) · cites this paper as [8]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Cancer incidence and mortality worldwide: Sources, methods and major patterns in GLOBOCAN 2012
Ferlay, J., Soerjomataram, I., Dikshit, R., Eser, S., Mathers, C., Rebelo, M., Parkin, D. M., Forman, D., & Bray, F. (2015) · International Journal of Cancer · doi:10.1002/ijc.29210 · Cited by 28,766
Investigation of the freely available easy-to-use software ‘EZR’ for medical statistics
Kanda, Y. (2013) · Bone Marrow Transplantation · doi:10.1038/bmt.2012.244 · Cited by 18,767
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891
Learning Hierarchical Features for Scene Labeling
Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.231 · Cited by 2,620
Going Deeper with Convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2014) · arXiv · doi:10.48550/arxiv.1409.4842 · Cited by 1,461
Fukushima, K., & Miyake, S. (1982) · Pattern Recognition · doi:10.1016/0031-3203(82)90024-3 · Cited by 742
Vieira, S., Pinaya, W. H. L., & Mechelli, A. (2017) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2017.01.002 · Cited by 656
Research works printed but not linked: 1
- Ye J, Biomedical Engineering and Informatics, 2009
Cited by
Items 401–500 of 663
Yasaka, K., Nomura, T., Kamohara, J., Hirakawa, H., Kubo, T., Kiryu, S., & Abe, O. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-024-01370-w · Cited by 8
Self-citationLucas, A., Wang, K., Santillan, C., Hsiao, A., Sirlin, C. B., & Murphy, P. M. (2019) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-018-0169-5 · Cited by 8
Afonso, J. P. L., Mascarenhas, M., Ferreira, J. P. S., Cardoso, H., Ribeiro, T., Andrade, P., Parente, M., Jorge, R. N., Mascarenhas, M., & Macedo, G. (2021) · Techniques and Innovations in Gastrointestinal Endoscopy · doi:10.1016/j.tige.2021.06.003 · Cited by 7
SpiCoNET: A Hybrid Deep Learning Model to Diagnose COVID-19 and Pneumonia Using Chest X-Ray Images
Tümen, V. (2022) · Traitement du signal · doi:10.18280/ts.390409 · Cited by 7
The value of multimodality MR in T staging evaluation after neoadjuvant therapy for rectal cancer
Liu, B., Sun, C., Zhao, X., Liu, L., Liu, S., & Ma, H. (2023) · Technology and Health Care · doi:10.3233/thc-220798 · Cited by 7
“ultrasound screening of breast cancer [30], enhanced CT differential diagnosis of liver lesions [31], 280”
Xue, M., Jiang, H., Zheng, J., Wu, Y., Xu, Y., Pan, J., & Zhu, W. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340787 · Cited by 7
“It has been demonstrated that approaches based on CNN exhibit excellent diagnostic performance in tasks based on multi-phase CT images [9-15].”
BackgroundInfluentialDuc, V. T., Phan, C. C., Le, H. M. D., Chau, T. L. M., Chanh, N. D. T., Duong, S. T. M., Huyen, H. C., Thanh, H. M., Hy, L. N. G., Nam, N. H., et al. (2022) · Cureus · doi:10.7759/cureus.21347 · Cited by 7
“There are a variety of strategies for segmenting the liver and liver tumors; the convolutional neural network (CNN) approach has progressively proven itself in offering more benefits as it can utilize spatial information, providing more accurate segmentation results [7-11].”
BackgroundZhen, S., Zhang, P., Huang, H., Jiang, Z., Jiang, Y., Sun, J., Zhang, L., Ruan, M., Chen, Q., Wang, Y., et al. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2025.1582322 · Cited by 7
“In addition, several types of benign masses also arise in the liver, including cyst, hemangioma, focal nodular hyperplasia, abscess and some benign nodules, such as cirrhotic nodules, regenerative nodules, dysplastic nodules and adenoma (4, 5).”
Nithiyaraj, E., & Selvaraj, A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07701-8 · Cited by 6
“Shigeru Kiryu et al. [13] developed a CNN to differentiate five liver tumours, where their CNN has five convolution, three max pooling and three fully connected layers.”
BackgroundModern Radiation Diagnostics and Intelligent Personalized Technologies in Hepatopancreatology
Karmazanovsky, G. G., Kondratyev, E. V., Gruzdev, I. S., Tikhonova, V. S., Shantarevich, M. Y., Zamyatina, K. A., Stashkiv, V. I., & Revishvili, A. S. (2022) · Annals of the Russian academy of medical sciences · doi:10.15690/vramn2053 · Cited by 6
Technological Advancements in Interventional Oncology
Posa, A., Barbieri, P., Mazza, G., Tanzilli, A., Natale, L., Sala, E., & Iezzi, R. (2023) · Diagnostics · doi:10.3390/diagnostics13020228 · Cited by 7
A Novel Autism Spectrum Disorder Children Dataset Based on Thermal Imaging
Melinda, M., Ahmadiar, A., Oktiana, M., ShadiqAdiNugraha, M., Qadrillah, M. A. L., & Yunidar, Y. (2023) · International Conference on Computer and Communication Engineering · doi:10.1109/iccce58854.2023.10246072 · Cited by 7
Ouattassi, N., Maâroufi, M., Slaoui, H., Andaloussi, T. B., Zarghili, A., & Alami, M. N. E. A. E. (2024) · Beni-Suef University Journal of Basic and Applied Sciences · doi:10.1186/s43088-024-00534-5 · Cited by 10
“…performance in medical fields including COVID-19 diagnosis [23], intracranial hemorrhage [24], critical findings in head CT scans [25], pulmonary tuberculosis [26], liver tumors [27], pathology, genetic mutation classification [28], and otolaryngology malignancies [29, 30], among others.”
BackgroundMa, J., Yang, H., Chou, Y., Yoon, J. H., Allison, T., Komandur, R., McDunn, J., Tasneem, A., Do, R. K., Schwartz, L. H., et al. (2024) · Medical Physics · doi:10.1002/mp.17504 · Cited by 7
Fujita, N., Yasaka, K., Kiryu, S., & Abe, O. (2025) · Emergency Radiology · doi:10.1007/s10140-025-02354-1 · Cited by 5
“Class imbalance causes sensitivity discrepancies between different groups [20].”
Self-citationWang, X., Nie, L., Yin, X., Xing, L., & Zheng, Y. (2023) · Medical Physics · doi:10.1002/mp.16340 · Cited by 6
Moroney, J., Trivella, J. P., George, B., & White, S. B. (2023) · Cancers · doi:10.3390/cancers15102791 · Cited by 8
“These models provided similar high accuracy in tumor detection to current DL and ML models, yet they relied on supervised rather than automated data acquisition and longer processing times [82,84,86].”
MethodSong, J., Dong, H., Chen, Y., Lin, L., Hu, H., & Chen, Y. (2023) · Smart innovation, systems and technologies · doi:10.1007/978-981-99-3311-2_20 · Cited by 6
Kim, D. H. (2025) · Journal of Personalized Medicine · doi:10.3390/jpm15050175 · Cited by 7
“In terms of lesion differentiation, Yasaka et al. [22] demonstrated that a CNN could distinguish benign from malignant liver lesions on contrast-enhanced CT scans, achieving an area under the curve (AUC) of 0.91, outperforming conventional radiological assessments.”
InfluentialLeveraging Large Language Models for Accurate AO Fracture Classification from CT Text Reports
Mergen, M., Spitzl, D., Ketzer, C., Strenzke, M., Marka, A. W., Makowski, M. R., Bressem, K. K., Adams, L. C., & Gassert, F. T. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01603-6 · Cited by 9
“Although convolutional neural networks (CNNs) have been widely utilized for lesion classification based on pixel-level image data [11], the capability of large language models (LLMs) to interpret and integrate textual information remains relatively underexplored [12, 13].”
Alam, Z., Maddali, A., Patel, S., Weber, N., Rikabi, S. A., Thiemann, D., Desai, K., & Monoky, D. (2025) · Journal of Neurology · doi:10.1007/s00415-025-13253-3 · Cited by 5
“In some cases, deep learning models have performed comparably to radiologists and even achieved higher consistency, especially in differentiating between similar-appearing lesions on MRI [78, 139, 140].”
Emerging role of artificial intelligence in gastroenterology and hepatology
Shrestha, U. K. (2025) · World Journal of Gastroenterology · doi:10.3748/wjg.v31.i39.111495 · Cited by 11
“One study has shown that DL with CNN can differentiate liver masses at dynamic contrast enhanced CT with high accuracy (AUC = 0.920)[108].”
InfluentialLee, J. M., & Bae, J. S. (2024) · Nature Reviews Clinical Oncology · doi:10.1038/s41571-024-00887-x · Cited by 7
“Indeed, other studies have demonstrated considerable progress in AI-based CT image analysis for liver cancer diagnosis with high accuracy 6,7 .”
Yang, Y., Liu, J., Chen, Q., Li, Y., Han, X., Hu, H., Lin, L., & Chen, Y.-W. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10781923 · Cited by 6
Afonso, J. P. L., Mascarenhas, M., Ribeiro, T., Cardoso, H., Andrade, P., Ferreira, J. P. S., Saraiva, M. M., & Macedo, G. (2022) · Gastro Hep Advances · doi:10.1016/j.gastha.2022.04.008 · Cited by 7
Huang, H., Xie, Y., Wang, G., Zhang, L., & Zhou, W. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107201 · Cited by 6
Augmenting care in hepatocellular carcinoma with artificial intelligence
Xu, F. W. X., Tang, S. S. K., Soh, H. N., Pang, N. Q., & Bonney, G. K. (2023) · Artificial Intelligence Surgery · doi:10.20517/ais.2022.33 · Cited by 8
Li, Y., Li, S., Ju, H., Harada, T., Zhang, H., Duan, T., Wang, G., Zhang, L., Gu, L., & Zhou, W. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109638 · Cited by 7
Tang, Y., Lin, Z., Zhou, L., Wang, W., Wen, L., Zhou, Y., Ge, Z., Chen, Z., Dai, W., Yang, Z., et al. (2024) · Journal Of Big Data · doi:10.1186/s40537-024-00989-4 · Cited by 6
“DL has also been widely applied in clinical medicine and achieved encouraging performance in medical image analysis of computed tomography [5], magnetic resonance imaging [6, 7], ultrasound [8], and ophthalmology images [9–12].”
MethodAbdelhamed, W., & El‐Kassas, M. (2025) · Hepatoma Research · doi:10.20517/2394-5079.2024.138 · Cited by 8
Lei, J., Xu, Y., Zhu, Y., Jiang, S., Tian, S., & Zhu, Y. (2025) · Abdominal Radiology · doi:10.1007/s00261-025-04853-8 · Cited by 5
Zheng, C., Chen, L., Jian, J., Li, J., & Gao, Z. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-020-03539-w · Cited by 5
“(2018) evaluated the ability of CNN in differential diagnosis of liver space occupying diseases on enhanced CT images [7].”
BackgroundOhtake, Y., Yasaka, K., Hamada, A., Fujita, N., & Abe, O. (2023) · Journal of Computer Assisted Tomography · doi:10.1097/rct.0000000000001490 · Cited by 5
Self-citationAnanda, S., Jain, R. K., Li, Y., Iwamoto, Y., Han, X., Kanasaki, S., Hu, H., & Chen, Y. (2023) · Bioengineering · doi:10.3390/bioengineering10080899 · Cited by 5
“However, the NC phase image exhibits poor/low contrast [2]), making it extremely challenging to distinguish between different organs.”
BackgroundInfluentialA Novel Approaches for Detect Liver Tumor Diagnosis using Convolution Neural Network
Nallasivan, G., Manthiramoorthy, C., Vargheese, M., Jasperline, T., Viswanathan, S., & Devaraj, S. (2023) · World Conference on Communication & Computing (WCONF) · doi:10.1109/wconf58270.2023.10235001 · Cited by 5
“To enhance data for better liver lesion categorization, we may use a Gan-based approach [4].”
MethodA Multi-phase CT Dataset for Automated Differential Diagnosis of Liver Tumors
Wu, X., Su, H., Hua, Y., Xu, Y., Wang, L., Wang, X., Wang, S., Jin, B., Liu, X., Wan, X., et al. (2025) · Scientific Data · doi:10.1038/s41597-025-06343-4 · Cited by 8
“Deep learning, particularly convolutional neural networks (CNNs), further improves accuracy by learning discriminative features directly from images 15–17 .”
Artificial intelligence (AI) and CT in abdominal imaging: image reconstruction and beyond
Pisuchpen, N., Rao, S. S., Noda, Y., Kongboonvijit, S., Rezaei, A., & Kambadakone, A. R. (2025) · Abdominal Radiology · doi:10.1007/s00261-025-05031-6 · Cited by 7
“This CNN model on triphasic CT images could differentiate malignant lesions from indeterminate and benign masses with an area under the receiver operating curve of 0.92, achieving an overall accuracy of 0.84 in classifying all liver lesions [56].”
InfluentialArtificial intelligence enabled tumor diagnosis and treatment: Status, breakthroughs and challenges
Hu, Y., Liang, S., Zhou, X., Zeng, Z., Ding, J., & Hua, D. (2025) · Critical Reviews in Oncology/Hematology · doi:10.1016/j.critrevonc.2025.104963 · Cited by 6
Haupt, M., & Maurer, M. H. (2026) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2026.100098 · Cited by 8
Bône, A., & Rohé, M.-M. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230692 · Cited by 4
“Using similar deep learning classification methods, other works proposed to directly diagnose hepatic masses from CT [9, 10, 11] or MRI [12, 13, 14].”
BackgroundMethodInfluentialGupta, P., Hsu, Y., Li, L., Chu, Y.-C., Chu, C., Wu, J., Chen, J., Tseng, W., Yang, Y., Lee, T., et al. (2024) · Journal of Gastroenterology and Hepatology · doi:10.1111/jgh.16803 · Cited by 5
Self-supervision Adversarial Learning Network for Liver Lesion Classification
Ma, C., Liu, Z., Song, Y., Qiu, C., Yu, A., & Zhang, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78609-0_46 · Cited by 4
Liver disease prediction using machine learning and deep learning: A comparative study
Singla, B., Taneja, S., Garg, R., & Nagrath, P. (2022) · Intelligent Decision Technologies · doi:10.3233/idt-210065 · Cited by 4
“Deep learning systems can perform radiological (on the basis of CT or MRI scan) classification of liver diseases [5,6].”
Bandari, E., Beuzen, T., Habashy, L., Raza, J., Yang, X., Kapeluto, J., Meneilly, G. S., & Madden, K. M. (2022) · JMIR Formative Research · doi:10.2196/34830 · Cited by 4
“Another recent study showed considerable success in classifying liver masses into 1 of 5 categories with 84% accuracy, using a CNN mode [14].”
BackgroundMa, L., Li, C., Li, H., Zhang, C., Deng, K., Zhang, W., & Xie, C. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e31451 · Cited by 5
“…of HCC and can be used for liver focal lesion segmentation [20], differentiation between benign and malignant liver tumors, fibrosis staging [21,22], MVI prediction [23], and prognostic predictions of patients after surgical resection [24], among others, with good predictive performance.”
BackgroundKanzawa, J., Yasaka, K., Ohizumi, Y., Morita, Y., Kurokawa, M., & Abe, O. (2024) · Radiological Physics and Technology · doi:10.1007/s12194-024-00834-6 · Cited by 4
“Recent studies have revealed that deep learning allows not only imaging diagnosis [7] but also image processing [6].”
Self-citationYousefzamani, M., & Mofrad, F. B. (2025) · Expert Review of Medical Devices · doi:10.1080/17434440.2025.2514764 · Cited by 6
“Papers [60,63,66] were performed to explore the efficiency of deep learning models in liver tumor and fibrosis detection and classification using CT images.”
InfluentialRole of Artificial Intelligence in Object Detection: A Review
Bisht, A. S., Jha, A. K., Sachdeva, A., & Sharma, N. (2022) · International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) · doi:10.1109/icac3n56670.2022.10074231 · Cited by 5
“Radiology researchers have also used CNN and several papers have been published in the areas of natural language processing [16], segmentation [17], lesion detection [18], image reconstruction [19-20] and classification [21].”
MethodYang, Y., Li, Y., Chen, Q., Han, X., Liu, J., Lin, L., Hu, H., & Chen, Y. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340586 · Cited by 5
Nikzad, N., Fuentes, D., Roach, M. A., Chowdhury, T., Cagley, M., Badawy, M., Elkheshen, A., Hassan, M. M., Elsayes, K. M., Beretta, L., et al. (2024) · Journal of Hepatocellular Carcinoma · doi:10.2147/jhc.s449996 · Cited by 5
“21,22 While HCC was identified with high accuracy (84–92%), a limitation of those studies was the focus on distinguishing HCC from other large liver masses such as cyst, hemangioma, nodular hyperplasia, intrahepatic cholangiocarcinoma, and colorectal metastasis.”
BackgroundNithiyaraj, E., & Arivazhagan, S. (2020) · International Journal of Innovative Science and Research Technology (IJISRT) · doi:10.38124/ijisrt20jul058 · Cited by 5
Dyna-PTM: OD-enhanced GCN for Metro Passenger Flow Prediction
He, C., Wang, H., Jiang, X., Ma, M., & Wang, P. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534153 · Cited by 7
“It also has achieved expert-level performance in various fields [21] such as classification, segmentation [22] and natural language processing [23].”
BackgroundDeep Learning-Based Pulmonary Nodule Screening: A Narrative Review
Mahajan, A., Agarwal, U., Agrawal, R., Venkatesh, A., Shukla, S., Bharadwaj, K. S. S., Apparao, M. L. V., Pawar, V., & Poonia, V. (2024) · Indian Journal of Medical and Paediatric Oncology · doi:10.1055/s-0044-1791954 · Cited by 3
Yan, J., Wang, J., Jian, F., Cui, X., Zhang, Y., Yang, X., Gao, Q., Ding, Z., 汤钊猷, Fan, J., et al. (2026) · Portal hypertension & cirrhosis · doi:10.1002/poh2.70033 · Cited by 7
Artificial Intellect, Radiomics and Radiogenomics
Dykan, I. M., & Kolotilov, N. (2021) · Radiation Diagnostics Radiation Therapy · doi:10.37336/2707-0700-2021-3-4 · Cited by 3
Okimoto, N., Yasaka, K., Cho, S., Koshino, S., Kanzawa, J., Asari, Y., Fujita, N., Kubo, T., Suzuki, Y., & Abe, O. (2024) · Radiological Physics and Technology · doi:10.1007/s12194-024-00817-7 · Cited by 3
“Previous studies have reported that deep learning assists not only imaging diagnosis [16] but also image processing [17, 18].”
BackgroundSelf-citationAutomatic Diagnosis of Hepatocellular Carcinoma and Metastases Based on Computed Tomography Images
Zossou, V.-B. S., Gnangnon, F. H. R., Biaou, O., de Vathaire, F., Allodji, R. S., & Ezin, E. C. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-024-01192-w · Cited by 3
“…remarkable performance in the image classification segment of the Ima-geNet Large Scale Visual Recognition Challenge (ILSVRC), there has been a surge of interest among computer vision researchers, exploring the application of CNNs on each CT or MRI to detect or classify FLLs [10, 23, 24].”
Qiao, S., Xue, M., Zuo, Y. L., Zheng, J., Jiang, H., Zeng, X., & Peng, D. (2024) · BioMedical Engineering OnLine · doi:10.1186/s12938-024-01297-x · Cited by 4
“However, the existing studies [8, 15] pay less attention to the connection between CT images of different phases, which may cause the loss of key information and increase the one-sided understanding of the lesion development trend of the model.”
BackgroundMethodInfluentialYasaka, K., Kawamura, M., Sonoda, Y., Kubo, T., Kiryu, S., & Abe, O. (2024) · Japanese Journal of Radiology · doi:10.1007/s11604-024-01718-w · Cited by 3
“Deep learning can be applied to detecting [9–12], staging [13–17], and classifying [18–20] lesions.”
Self-citationSarfati, E., Bône, A., Rohé, M.-M., Aubé, C., Ronot, M., Gori, P., & Isabelle Bloch, A. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10981163 · Cited by 3
“A larger lesion has indeed more chance of being an HCC, hence the huge differences of lesion sizes between HCCs and non-HCCs amongst datasets used for deep learning methods in the literature [10, 12, 13].”
InfluentialAsari, Y., Yasaka, K., Kurashima, J., Katayama, A., Kurokawa, M., & Abe, O. (2025) · Emergency Radiology · doi:10.1007/s10140-025-02366-x · Cited by 3
“Its applications span various tasks, including anomaly detection [8 ], differential diagnosis support [9], and disease staging [ 10 ].”
Self-citationDas, J. P., Ma, H. Y., de Jong, D., Prendergast, C. M., Dahooiyeh, A. B., Braumuller, B., Giarratana, A. O., Khonji, M. S., Paily, J., Shobeiri, P., et al. (2025) · Clinical Imaging · doi:10.1016/j.clinimag.2025.110571 · Cited by 4
Lee, G., Kim, J.-E., Lee, J., Ahn, G., Park, S. H., Kim, S. Y., Kim, K. W., Lee, S. S., & Kim, N. (2019) · International Forum on Medical Imaging in Asia (IFMIA) · doi:10.1117/12.2521021 · Cited by 3
Azer, S. A. (2020) · Intelligent systems reference library · doi:10.1007/978-3-030-42750-4_7 · Cited by 3
Screening of Hub Genes in Hepatocellular Carcinoma Based on Network Analysis and Machine Learning
Zhang, Y., Xie, Y., Huang, X., Zhang, L., & Shu, K. (2022) · Computational and Mathematical Methods in Medicine · doi:10.1155/2022/7300788 · Cited by 3
“Several studies have shown good results in classifying liver cancer images by using a machine learning approach [6, 7].”
BackgroundColon capsule endoscopy and artificial intelligence: a perfect match for panendoscopy
Ribeiro, T., Fernández-Urién, I., & Cardoso, H. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-99647-1.00007-1 · Cited by 3
Mizuki, M., Yasaka, K., Miyo, R., Ohtake, Y., Hamada, A., Hosoi, R., & Abe, O. (2023) · Canadian Association of Radiologists Journal · doi:10.1177/08465371231182904 · Cited by 3
“10 Recent studies have shown that deep learning can be applied not only in imaging diagnosis, 11 but also in image processing.”
BackgroundSelf-citationArtificial intelligence in gastroenterology and hepatology
Ahn, J. C., & Shah, V. H. (2023) · Elsevier eBooks · doi:10.1016/b978-0-443-15688-5.00016-4 · Cited by 4
Deep Learning for the Investigation of Lung and Pancreatic Tumors
Mahadevi, M., Marimuthu, M., Poornima, I. G. A., Vijayalakshmi, K., Vidyabharathi, D., & Priya, G. S. (2023) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac58438.2023.10290585 · Cited by 4
“Imaging with CNN has been proven to be effective in the diagnosis of cancer of the skin [15], diabetic retinal degeneration [16], and tumors of the liver [17].”
BackgroundAnalysis of Wire Rolling Processes Using Convolutional Neural Networks
CAPELIN, M., Martínez, G. A. S., Xing, Y. T., Siqueira, A. F., & Qian, W. (2024) · Advances in Science and Technology – Research Journal · doi:10.12913/22998624/183699 · Cited by 5
Long, X., Zeng, H., Zhang, Y., Lu, Q., Cao, Z., & Shu, H. (2024) · Journal of Hepatocellular Carcinoma · doi:10.2147/jhc.s452628 · Cited by 3
Song, J., Dong, H., Chen, Y., Zhang, X., Zhan, G., Jain, R. K., & Chen, Y. (2024) · Information · doi:10.3390/info15080493 · Cited by 5
Luo, Y., Yang, M., Liu, X., Qin, L., Yu, Z., Gao, Y., Xu, X., Zha, G., Zhu, X., Chen, G., et al. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2024.1440881 · Cited by 4
Machine Learning–Aided Diagnosis Enhances Human Detection of Perilunate Dislocations
Luan, A., von Rabenau, L., Serebrakian, A. T., Crowe, C. S., Do, B. H., Eberlin, K. R., Chang, J., & Pridgen, B. C. (2025) · Hand · doi:10.1177/15589447241308603 · Cited by 2
Yasaka, K., Asari, Y., Morita, Y., Kurokawa, M., Tajima, T., Akai, H., Yoshioka, N., Akahane, M., Ohtomo, K., Abe, O., et al. (2025) · Japanese Journal of Radiology · doi:10.1007/s11604-025-01787-5 · Cited by 6
“Deep learning not only supports diagnoses afforded by imaging [13–21] but also that of image-processing including deep learning reconstruction (DLR), which has been shown to reduce noise included in images [22–28].”
Self-citationSnekhalatha, U., Thanaraj, K. P., & Sangamithrai, K. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-2123-9_45 · Cited by 3
Object Detection using Deep Learning Algorithm CNN
Sumahasan, S. (2020) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2020.30594 · Cited by 4
Noguchi, T., Matsushita, Y., Kawata, Y., Shida, Y., & Machitori, A. (2021) · Polish Journal of Radiology · doi:10.5114/pjr.2021.110309 · Cited by 3
Esquinas, P. L., Luo, Y.-F., Farzam, P., Baldwin, T., Raboh, M., Binder, T. M., Sitek, A., Sakhi, O., Wang, Y., Suman, S., et al. (2022) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi52829.2022.9761517 · Cited by 3
“Direct comparison is difficult as these methods focus on different set of lesion types [16, 21], different modalities (multi-phase CT [20,21], MRI [16-19]), or assume lesion localization is known [16, 18, 19, 20].”
BackgroundNew technological advancements for interventional oncology
Muglia, R., & Solbiati, L. (2019) · Chinese Clinical Oncology · doi:10.21037/cco.2019.10.06 · Cited by 3
“Indeed, CNN has been recently used to classify autonomously hepatic nodules on CT with promising results (20), and in the future we may integrate MRI as the data input, with a higher level of soft-tissue contrast resolution and three-dimensional volumetric evaluation (18).”
MethodArtificial Intelligence in Diagnostic Imaging
Sollini, M., Loiacono, D., Volpe, D., Levra, A. G., Lomeo, E., Giacomello, E., Kirienko, M., Chiti, A., & Lanzi, P. L. (2023) · Wiley eBooks · doi:10.1002/9781119603627.ch31 · Cited by 4
An, C., Li, L., Yang, L., Zuo, M., Liu, W., Li, C., & Wu, P. (2025) · Journal of Hepatocellular Carcinoma · doi:10.2147/jhc.s532116 · Cited by 3
Advanced Detection of Liver Cirrhosis Utilizing LSTM and Neural Networks
Julian, B., & Annie, T. A. (2025) · doi:10.1109/iccsp64183.2025.11088752 · Cited by 2
“Yasaka et al. [5] applied CNNs to dynamic contrast-enhanced CT with high accuracy, though lacking temporal awareness.”
Hahnfeldt, R., Laukamp, K. R., Schönfeld, M. H., Galldiks, N., Werner, J.-M., Fervers, P., Görtz, L., Gertz, R. J., Nelles, C., Nasirov, N., et al. (2025) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2025.100054 · Cited by 2
Akbulut, S., & Çolak, C. (2026) · World Journal of Gastrointestinal Oncology · doi:10.4251/wjgo.v18.i2.113870 · Cited by 4
“…accurately classify liver lesions on multi-phasic MRI and dynamic contrast-enhanced CT, often outperforming or matching experienced radiologists, with reported accuracies and sensitivities for HCC detection and classification as high as 92% and 90%, respectively, and AUC values up to 0.992[71,72].”
InfluentialBoppana, S. H., Chandrashekar, A., Maddineni, G., Chakinala, R. C., Raj, R., Shivaprakash, R. B., Yarra, P., Sunkesula, V. C. K., & Mintz, C. D. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15072484 · Cited by 3
“…CNN on augmented dynamic contrast-enhanced CT image sets derived from 460 patients and tested it on 100 liver mass image sets obtained later at the same institution, reporting a median accuracy of 0.84 and a median AUC of 0.92 for differentiating malignant from nonmalignant lesion categories [37].”
InfluentialEnsemble of CNN and DenseNet121 Models for Pneumonia Prediction Using X-Ray Images
Saxena, S., Maji, S., Agarwal, A., & Goel, A. (2023) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i59117.2023.10397964 · Cited by 2
Mojtahedi, R., Hamghalam, M., Jarnagin, W. R., Gian, R. K., & Simpson, A. L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47425-5_28 · Cited by 2
Bhagya, A., & Perumal, S. A. (2024) · International Conference on Emerging Systems and Intelligent Computing (ESIC) · doi:10.1109/esic60604.2024.10481596 · Cited by 2
Giraldo‐Roldán, D., dos Santos, G. C., Araújo, A. L. D., Nakamura, T. C. R., Díaz, K. P., Lopes, M. A., Santos‐Silva, A. R., Kowalski, L. P., Moraes, M. C., & Vargas, P. A. (2024) · Head and Neck Pathology · doi:10.1007/s12105-024-01723-5 · Cited by 2
Medical Image Recognition for Diagnosis
Esukapalli, V. R., Velmurugan, S. N., Preethi, S., Kammara, C., Mungamuru, D., & Settipalli, H. V. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10726025 · Cited by 2
Yang, Y., Liu, J., Chen, Q., Han, X., Li, Y., Lin, L., Hu, H., & Chen, Y. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-7498-2_4 · Cited by 2
Inmutto, N., Pojchamarnwiputh, S., & Chiangmai, W. N. (2025) · Diagnostics · doi:10.3390/diagnostics15070821 · Cited by 2
“In-formed consent was not required due to the retrospective nature of this study.”
A Review of Deep Learning Methods for Early Prediction of Pancreatic Cancer in High-Risk Populations
Naresh, K., & Ganesh, D. (2024) · Intelligent Systems and Machine Learning Conference (ISML) · doi:10.1109/isml60050.2024.11007370 · Cited by 3
“Several recent studies [35–40] have specifically examined the suitability of deep learning models for detecting cancer in input photos.”
Sato, M., Yasaka, K., Abe, S., Kurashima, J., Asari, Y., Kiryu, S., & Abe, O. (2025) · Abdominal Radiology · doi:10.1007/s00261-025-05062-z · Cited by 2
“This technique can be applied not only to image-based tasks, including image processing [ 8 –10] and imaging diagnosis [11–13], but also to natural language processing [14– 18 ].”
Self-citationBai, X., & Xia, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04927-8_52 · Cited by 2
Raj, S. S., Malu, G., Sherly, E., & S, V. C. S. (2019) · International Conference on Advances in Computing, Communication and Control (ICAC3) · doi:10.1109/icac347590.2019.9036825 · Cited by 2
“Needless to say, there has been a surge of interest in the potential of CNN among radiology researchers, and several studies have already been published in areas such as lesion detection [5], classification [6], segmentation [7], and image reconstruction [8, 9].”
BackgroundGeduk, G., BİLTEKİN, H., & Şeker, Ç. (2022) · Selcuk Dental Journal · doi:10.15311/selcukdentj.835913 · Cited by 3
The Rise of Deep Learning in Radiology: An Overview of Recent Research
Chatterjee, D. (2019) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2019.6397 · Cited by 3
“Yasaka et al. [30] [31] performed classification of liver fibrosis stages from CT scans of the liver using CNNs.”
Künstliche Intelligenz in der Radiologie – was kann sie, was kann sie nicht?
Baeßler, B. (2021) · Praxis · doi:10.1024/1661-8157/a003597 · Cited by 3
Metadata
- Authors
- Yasaka, K., Akai, H., Abe, O., & Kiryu, S.
- Affiliations
- University of Tokyo Hospital (JP)
- Venue
- Radiology
- Published
- 2018-03
- Volume
- 286
- Issue
- 3
- Pages
- 887-896
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- OpenAlex
- W2765571304
- Cited by
- 663
- References
- 21
- Citations by year
- 2026: 36 · 2025: 84 · 2024: 75 · 2023: 101 · 2022: 105 · 2021: 114 · 2020: 69 · 2019: 51 · 2018: 28
- FWCI
- 24.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Radiology (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- liver mass, hepatocellular carcinoma, dynamic contrast-enhanced CT, convolutional neural networks, deep learning, computer-aided diagnosis, hepatic hemangioma, liver cysts, dysplastic nodules, image augmentation
- MeSH terms
- Machine Learning, Aged, Aged, 80 and over, Bile Duct Neoplasms, Contrast Media, Diagnosis, Differential, Female, Carcinoma, Hepatocellular, Humans, Liver Neoplasms, Middle Aged, Retrospective Studies, ROC Curve, Sensitivity and Specificity, Tomography, X-Ray Computed, Neural Networks, Computer, Cholangiocarcinoma
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.