{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T02:43:57Z","timestamp":1776912237397,"version":"3.51.2"},"reference-count":41,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:00:00Z","timestamp":1667865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin and the German Research Foundation (DFG)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Splenomegaly is a common cross-sectional imaging finding with a variety of differential diagnoses. This study aimed to evaluate whether a deep learning model could automatically segment the spleen and identify the cause of splenomegaly in patients with cirrhotic portal hypertension versus patients with lymphoma disease. This retrospective study included 149 patients with splenomegaly on computed tomography (CT) images (77 patients with cirrhotic portal hypertension, 72 patients with lymphoma) who underwent a CT scan between October 2020 and July 2021. The dataset was divided into a training (n = 99), a validation (n = 25) and a test cohort (n = 25). In the first stage, the spleen was automatically segmented using a modified U-Net architecture. In the second stage, the CT images were classified into two groups using a 3D DenseNet to discriminate between the causes of splenomegaly, first using the whole abdominal CT, and second using only the spleen segmentation mask. The classification performances were evaluated using the area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Occlusion sensitivity maps were applied to the whole abdominal CT images, to illustrate which regions were important for the prediction. When trained on the whole abdominal CT volume, the DenseNet was able to differentiate between the lymphoma and liver cirrhosis in the test cohort with an AUC of 0.88 and an ACC of 0.88. When the model was trained on the spleen segmentation mask, the performance decreased (AUC = 0.81, ACC = 0.76). Our model was able to accurately segment splenomegaly and recognize the underlying cause. Training on whole abdomen scans outperformed training using the segmentation mask. Nonetheless, considering the performance, a broader and more general application to differentiate other causes for splenomegaly is also conceivable.<\/jats:p>","DOI":"10.3390\/cancers14225476","type":"journal-article","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T11:46:43Z","timestamp":1667908003000},"page":"5476","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Two-Stage Deep Learning Model for Automated Segmentation and Classification of Splenomegaly"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6537-9419","authenticated-orcid":false,"given":"Aymen","family":"Meddeb","sequence":"first","affiliation":[{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin, Klinik f\u00fcr Radiologie, Hindenburgdamm 30, 12203 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2986-0907","authenticated-orcid":false,"given":"Tabea","family":"Kossen","sequence":"additional","affiliation":[{"name":"CLAIM\u2014Charit\u00e9 Lab for AI in Medicine, Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9249-8624","authenticated-orcid":false,"given":"Keno K.","family":"Bressem","sequence":"additional","affiliation":[{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin, Klinik f\u00fcr Radiologie, Hindenburgdamm 30, 12203 Berlin, Germany"},{"name":"Berlin Institute of Health, Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, Charit\u00e9platz 1, 10117 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noah","family":"Molinski","sequence":"additional","affiliation":[{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin, Institut f\u00fcr Neuroradiologie, Charit\u00e9platz 1, 10117 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernd","family":"Hamm","sequence":"additional","affiliation":[{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin, Klinik f\u00fcr Radiologie, Hindenburgdamm 30, 12203 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9489-2913","authenticated-orcid":false,"given":"Sebastian N.","family":"Nagel","sequence":"additional","affiliation":[{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, Corporate Member of Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin, Klinik f\u00fcr Radiologie, Hindenburgdamm 30, 12203 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1259\/bjr\/31542964","article-title":"Spleen in Haematological Malignancies: Spectrum of Imaging Findings","volume":"85","author":"Saboo","year":"2012","journal-title":"Br. J. Radiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1016\/j.immuni.2013.10.010","article-title":"The Spleen in Local and Systemic Regulation of Immunity","volume":"39","author":"Bronte","year":"2013","journal-title":"Immunity"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/0929-8266(95)00088-7","article-title":"Splenic Lesions in Hodgkin\u2019s and Non-Hodgkin\u2019s Lymphomas. An Ultrasonographic Study","volume":"2","author":"Stasi","year":"1995","journal-title":"Eur. J. Ultrasound"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.blre.2008.10.001","article-title":"Splenomegaly: Investigation, Diagnosis and Management","volume":"23","author":"Pozo","year":"2009","journal-title":"Blood Rev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1182\/asheducation.V2009.1.523.0010523","article-title":"The 2008 WHO Classification of Lymphomas: Implications for Clinical Practice and Translational Research","volume":"2009","author":"Jaffe","year":"2009","journal-title":"Hematology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.1148\/rg.276065170","article-title":"Cross-Sectional Imaging of Extranodal Involvement in Abdominopelvic Lymphoproliferative Malignancies1","volume":"27","author":"Leite","year":"2007","journal-title":"Radiographics"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1148\/radiographics.21.1.g01ja02161","article-title":"Extranodal Hodgkin Disease: Spectrum of Disease","volume":"21","author":"Guermazi","year":"2001","journal-title":"Radiographics"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1007\/s00432-015-2094-z","article-title":"The Significance of Pre-Therapeutic F-18-FDG PET\u2013CT in Lymphoma-Associated Hemophagocytic Lymphohistiocytosis When Pathological Evidence Is Unavailable","volume":"142","author":"Wang","year":"2016","journal-title":"J. Cancer Res. Clin."},{"key":"ref_9","first-page":"78","article-title":"Splenomegaly in 2,505 Patients in a Large University Medical Center from 1913 to 1995. 1913 to 1962: 2,056 Patients","volume":"169","year":"1998","journal-title":"West J. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1159\/000040975","article-title":"Splenomegaly at a University Hospital Compared to a Nearby County Hospital in 317 Patients","volume":"102","author":"Swaroop","year":"1999","journal-title":"Acta Haematol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/S0002-9629(15)41799-9","article-title":"Splenomegaly at a United States County Hospital: Diagnostic Evaluation of 170 Patients","volume":"312","year":"1996","journal-title":"Am. J. Med. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3059","DOI":"10.1200\/JCO.2013.54.8800","article-title":"Recommendations for Initial Evaluation, Staging, and Response Assessment of Hodgkin and Non-Hodgkin Lymphoma: The Lugano Classification","volume":"32","author":"Cheson","year":"2014","journal-title":"J. Clin. Oncol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"950","DOI":"10.3390\/tomography7040078","article-title":"Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen","volume":"7","author":"Meddeb","year":"2021","journal-title":"Tomography"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hssayeni, M.D., Croock, M.S., Salman, A.D., Al-khafaji, H.F., Yahya, Z.A., and Ghoraani, B. (2020). Intracranial Hemorrhage Segmentation Using a Deep Convolutional Model. Data, 5.","DOI":"10.3390\/data5010014"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"186","DOI":"10.18383\/j.tom.2019.00026","article-title":"A Fully Automated Deep Learning Network for Brain Tumor Segmentation","volume":"6","author":"Yogananda","year":"2020","journal-title":"Tomography"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.neucom.2021.08.157","article-title":"Liver, Kidney and Spleen Segmentation from CT Scans and MRI with Deep Learning: A Survey","volume":"490","author":"Altini","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"101672","DOI":"10.1016\/j.compmedimag.2019.101672","article-title":"Segmentation of Abdominal Organs in Computed Tomography Using a Generalized Statistical Shape Model","volume":"78","author":"Woloshuk","year":"2019","journal-title":"Comput. Med. Imag. Grap."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rickmann, A.-M., Senapati, J., Kovalenko, O., Peters, A., Bamberg, F., and Wachinger, C. (2022). AbdomenNet: Deep Neural Network for Abdominal Organ Segmentation in Epidemiologic Imaging Studies. BMC Med. Imaging, 22.","DOI":"10.1186\/s12880-022-00893-4"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e190102","DOI":"10.1148\/ryai.2020190102","article-title":"Fully Automatic Volume Measurement of the Spleen at CT Using Deep Learning","volume":"2","author":"Bukala","year":"2020","journal-title":"Radiol. Artif. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1109\/TMI.2018.2881110","article-title":"Splenomegaly Segmentation on Multi-Modal MRI Using Deep Convolutional Networks","volume":"38","author":"Huo","year":"2019","journal-title":"IEEE T. Med. Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.ejrad.2018.05.010","article-title":"Discriminatory CT-Textural Features in Splenic Infiltration of Lymphoma versus Splenomegaly in Liver Cirrhosis versus Normal Spleens in Controls and Evaluation of Their Role for Longitudinal Lymphoma Monitoring","volume":"104","author":"Reinert","year":"2018","journal-title":"Eur. J. Radiol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.ejrad.2017.04.007","article-title":"CT-Based Radiomics Signature for Differentiating Borrmann Type IV Gastric Cancer from Primary Gastric Lymphoma","volume":"91","author":"Ma","year":"2017","journal-title":"Eur. J. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lisson, C.S., Lisson, C.G., Mezger, M.F., Wolf, D., Schmidt, S.A., Thaiss, W.M., Tausch, E., Beer, A.J., Stilgenbauer, S., and Beer, M. (2022). Deep Neural Networks and Machine Learning Radiomics Modelling for Prediction of Relapse in Mantle Cell Lymphoma. Cancers, 14.","DOI":"10.3390\/cancers14082008"},{"key":"ref_24","unstructured":"The MONAI Consortium (2021, April 20). Project MONAI. Available online: https:\/\/zenodo.org\/record\/7245821#.Y2mzNORBxPY."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2016). Densely Connected Convolutional Networks. arXiv.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_26","unstructured":"Iqbal, H. (2022, October 22). PlotNeuralNet. Available online: https:\/\/github.com\/HarisIqbal88\/PlotNeuralNet."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1007\/s10278-017-9983-4","article-title":"Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions","volume":"30","author":"Akkus","year":"2017","journal-title":"J. Digit Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1097\/RLI.0000000000000647","article-title":"Fully Automated Segmentation of Connective Tissue Compartments for CT-Based Body Composition Analysis: A Deep Learning Approach","volume":"55","author":"Nowak","year":"2020","journal-title":"Invest. Radiol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"8214","DOI":"10.1038\/s41598-022-11990-3","article-title":"Deep Learning Model for the Automatic Classification of COVID-19 Pneumonia, Non-COVID-19 Pneumonia, and the Healthy: A Multi-Center Retrospective Study","volume":"12","author":"Nishio","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1186\/s12967-017-1214-8","article-title":"The Spleen in Liver Cirrhosis: Revisiting an Old Enemy with Novel Targets","volume":"15","author":"Li","year":"2017","journal-title":"J. Transl. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.forsciint.2018.08.012","article-title":"The Forensic Spleen: Morphological, Radiological, and Toxicological Investigations","volume":"291","author":"Palmiere","year":"2018","journal-title":"Forensic. Sci. Int."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s13244-020-00887-2","article-title":"Radiomics in Medical Imaging\u2014\u201cHow-to\u201d Guide and Critical Reflection","volume":"11","author":"Cester","year":"2020","journal-title":"Insights Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.1016\/j.ejso.2020.06.021","article-title":"Use of Radiomics to Extract Splenic Features to Predict Prognosis of Patients with Gastric Cancer","volume":"46","author":"Wang","year":"2020","journal-title":"Eur. J. Surg. Oncol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"716849","DOI":"10.3389\/fonc.2021.716849","article-title":"Spleen Radiomics Signature: A Potential Biomarker for Prediction of Early and Late Recurrences of Hepatocellular Carcinoma After Resection","volume":"11","author":"Li","year":"2021","journal-title":"Front. Oncol."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Enke, J.S., Moltz, J.H., D\u2019Anastasi, M., Kunz, W.G., Schmidt, C., Maurus, S., M\u00fchlberg, A., Katzmann, A., S\u00fchling, M., and Hahn, H. (2022). Radiomics Features of the Spleen as Surrogates for CT-Based Lymphoma Diagnosis and Subtype Differentiation. Cancers, 14.","DOI":"10.3390\/cancers14030713"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"226","DOI":"10.18383\/j.tom.2019.00005","article-title":"Reliability of Radiomic Features Across Multiple Abdominal CT Image Acquisition Settings: A Pilot Study Using ACR CT Phantom","volume":"5","author":"Lu","year":"2019","journal-title":"Tomography"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"238","DOI":"10.3390\/tomography7020022","article-title":"Stability of Radiomic Features across Different Region of Interest Sizes\u2014A CT and MR Phantom Study","volume":"7","author":"Jensen","year":"2021","journal-title":"Tomography"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Gulzar, Y., and Khan, S.A. (2022). Skin Lesion Segmentation Based on Vision Transformers and Convolutional Neural Networks\u2014A Comparative Study. Appl. Sci., 12.","DOI":"10.3390\/app12125990"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"8297","DOI":"10.1038\/s41598-022-12410-2","article-title":"Deep Learning Supports the Differentiation of Alcoholic and Other-than-Alcoholic Cirrhosis Based on MRI","volume":"12","author":"Luetkens","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"511","DOI":"10.3348\/kjr.2019.0821","article-title":"Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges","volume":"21","author":"Hwang","year":"2020","journal-title":"Korean J. Radiol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1016\/j.rcl.2007.05.009","article-title":"Fluorine-18 Fluorodeoxyglucose PET\/CT Patterns of Extranodal Involvement in Patients with Non-Hodgkin Lymphoma and Hodgkin\u2019s Disease","volume":"45","author":"Lievshitz","year":"2007","journal-title":"Radiol. Clin. N. A."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/14\/22\/5476\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:12:21Z","timestamp":1760145141000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/14\/22\/5476"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,8]]},"references-count":41,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["cancers14225476"],"URL":"https:\/\/doi.org\/10.3390\/cancers14225476","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,8]]}}}