{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T10:30:09Z","timestamp":1786357809371,"version":"build-2736575974"},"reference-count":31,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of Medicine and Pharmacy of Craiova"},{"id":[{"id":"https:\/\/ror.org\/031d5vw30","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Life"],"abstract":"<jats:p>Automated colorectal tumor segmentation on routine computed tomography (CT) remains technically challenging because of limited soft-tissue contrast, heterogeneous tumor morphology, complex bowel anatomy, and marked imbalance between tumor and background pixels. This retrospective technical feasibility study aimed to develop and evaluate an attention-enhanced ResNet50\u2013U-Net architecture for automated segmentation of primary colorectal tumors on contrast-enhanced abdominopelvic CT images. The dataset comprised 493 axial CT image\u2013mask pairs containing visible colorectal tumors, including 70 institutional images obtained from 25 patients and 423 images from publicly available colorectal cancer imaging resources. Reference masks were generated by manual tumor delineation performed by an experienced radiologist and reviewed by a second abdominal radiologist, with uncertain contours resolved by consensus. The proposed model combined an ImageNet-pretrained ResNet50 encoder with an attention-guided U-Net decoder and was trained using a composite Binary Cross-Entropy and Focal Tversky loss function to address foreground\u2013background class imbalance. Performance was assessed using five-fold image-level cross-validation. Predicted probability maps were binarized using a threshold of 0.5, and segmentation metrics were calculated through global micro-averaging within each validation fold. The model achieved a mean Intersection over Union of 0.7406 \u00b1 0.0276, a Dice similarity coefficient of 0.8507 \u00b1 0.0182, a pixel-level sensitivity of 0.9559 \u00b1 0.0266, and a pixel-level background specificity of 0.9956 \u00b1 0.0003. Qualitative assessment demonstrated substantial spatial agreement between predicted masks and expert annotations, although minor boundary discrepancies and small false-positive components were observed. These findings support the technical feasibility of attention-enhanced encoder\u2013decoder architectures for colorectal tumor segmentation on routine CT images. However, because validation was performed at the image level, entirely tumor-negative images were not included (preventing the evaluation of clinical specificity and false-positive rates), and no independent external test cohort was available, further patient-level, multicenter, and DICOM-based validation is required before clinical implementation. While the model demonstrated robust internal performance, future studies must prioritize large-scale external validation and patient-level cross-validation to rigorously assess generalizability and specificity.<\/jats:p>","DOI":"10.3390\/life16081309","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T09:24:53Z","timestamp":1786353893000},"page":"1309","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Enhanced ResNet\u2013U\u2013Net for Automated Colorectal Tumor Segmentation in CT Scans"],"prefix":"10.3390","volume":"16","author":[{"given":"Lucian Mihai","family":"Florescu","sequence":"first","affiliation":[{"name":"Department of Radiology and Medical Imaging, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cosmin Vasile","family":"Obleag\u0103","sequence":"additional","affiliation":[{"name":"Department of Surgical Oncology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1524-2494","authenticated-orcid":false,"given":"M\u0103d\u0103lin","family":"M\u0103muleanu","sequence":"additional","affiliation":[{"name":"Department of Automatic Control and Electronics, University of Craiova, 200585 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3099-4637","authenticated-orcid":false,"given":"Ioana Andreea","family":"C\u00eerlig","sequence":"additional","affiliation":[{"name":"Doctoral School, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alesandra","family":"Florescu","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3650-5037","authenticated-orcid":false,"given":"Mihai Alexandru","family":"Ene","sequence":"additional","affiliation":[{"name":"Doctoral School, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelia \u0218tefania","family":"Domenco","sequence":"additional","affiliation":[{"name":"Doctoral School, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandru Marian","family":"Olaru","sequence":"additional","affiliation":[{"name":"Department of Radiology and Medical Imaging, Emergency Clinical County Hospital of Craiova, 200642 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandra Gabriela Cosmina","family":"\u021a\u00e2ru","sequence":"additional","affiliation":[{"name":"Department of Radiology and Medical Imaging, Emergency Clinical County Hospital of Craiova, 200642 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1642-3587","authenticated-orcid":false,"given":"Raluca Elena","family":"Nica","sequence":"additional","affiliation":[{"name":"Department of Radiology and Medical Imaging, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rossy Vl\u0103du\u021b","family":"Teic\u0103","sequence":"additional","affiliation":[{"name":"Department of Radiology and Medical Imaging, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0954-1266","authenticated-orcid":false,"given":"Ioana Andreea","family":"Gheonea","sequence":"additional","affiliation":[{"name":"Department of Radiology and Medical Imaging, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1038\/s41575-019-0189-8","article-title":"Global Burden of Colorectal Cancer: Emerging Trends, Risk Factors and Prevention Strategies","volume":"16","author":"Keum","year":"2019","journal-title":"Nat. Rev. Gastroenterol. Hepatol."},{"key":"ref_2","first-page":"209","article-title":"Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1111\/jgh.16910","article-title":"Incidence and Mortality of Colorectal Cancer in Asia in 2022 and Projections for 2050","volume":"40","author":"Fu","year":"2025","journal-title":"J. Gastroenterol. Hepatol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1016\/j.aogh.2016.10.004","article-title":"The Incidence and Mortality of Colorectal Cancer and Its Relationship with the Human Development Index in Asia","volume":"82","author":"Ghoncheh","year":"2017","journal-title":"Ann. Glob. Health"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pardamean, C.I., Sudigyo, D., Budiarto, A., Mahesworo, B., Hidayat, A.A., Baurley, J.W., and Pardamean, B. (2023). Changing Colorectal Cancer Trends in Asians: Epidemiology and Risk Factors. Oncol. Rev., 17.","DOI":"10.3389\/or.2023.10576"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1007\/s11894-019-0703-8","article-title":"The Rise of Colorectal Cancer in Asia: Epidemiology, Screening, and Management","volume":"21","author":"Onyoh","year":"2019","journal-title":"Curr. Gastroenterol. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"\u0218erban, R.-E., Boldeanu, M.V., Florescu, D.N., Ionescu, M., \u0218erb\u0103nescu, M.-S., Boldeanu, L., Florescu, M.-M., Stepan, M.-D., Obleag\u0103, V.-C., and Constantin, C. (2024). Comparison between Substance P and Calcitonin Gene-Related Peptide and Their Receptors in Colorectal Adenocarcinoma. J. Clin. Med., 13.","DOI":"10.3390\/jcm13185616"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"\u0218erban, R.-E., Stepan, M.-D., Florescu, D.N., Boldeanu, M.-V., Florescu, M.-M., \u0218erb\u0103nescu, M.-S., Ionescu, M., Streba, L., Dr\u0103goescu, N.-A.-M., and Christopher, P. (2024). Expression of Calcitonin Gene-Related Peptide and Calcitonin Receptor-like Receptor in Colorectal Adenocarcinoma. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25084461"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Sahoo, P.K., Gupta, P., Lai, Y.-C., Chiang, S.-F., You, J.-F., Onthoni, D.D., and Chern, Y.-J. (2023). Localization of Colorectal Cancer Lesions in Contrast-Computed Tomography Images via a Deep Learning Approach. Bioengineering, 10.","DOI":"10.3390\/bioengineering10080972"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"102717","DOI":"10.1016\/j.compmedimag.2026.102717","article-title":"A Deep Learning-Based Automated Pipeline for Colorectal Cancer Detection in Contrast-Enhanced CT Images","volume":"128","author":"Qiu","year":"2026","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_11","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"9351","author":"Ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e70019","DOI":"10.1049\/ipr2.70019","article-title":"A Comprehensive Review of U-Net and Its Variants: Advances and Applications in Medical Image Segmentation","volume":"19","author":"Jiangtao","year":"2025","journal-title":"IET Image Process."},{"key":"ref_13","unstructured":"Neha, F., Bhati, D., Shukla, D.K., Dalvi, S.M., Mantzou, N., and Shubbar, S. (2024). U-Net in Medical Image Segmentation: A Review of Its Applications Across Modalities. arXiv."},{"key":"ref_14","first-page":"2495","article-title":"Colorectal Cancer Segmentation Algorithm Based on Deep Features from Enhanced CT Images","volume":"80","author":"Qiu","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref_15","unstructured":"Tong, T., and Li, M. (2022). Abdominal or Pelvic Enhanced CT Images within 10 Days before Surgery of 230 Patients with Stage II Colorectal Cancer (StageII-Colorectal-CT) [Dataset]. Cancer Imaging Arch., 10."},{"key":"ref_16","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention U-Net: Learning Where to Look for the Pancreas. arXiv."},{"key":"ref_17","unstructured":"Abraham, N., and Khan, N.M. (2018). A Novel Focal Tversky Loss Function with Improved Attention U-Net for Lesion Segmentation. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yao, L., Xia, Y., Zhang, H., Yao, J., Jin, D., Qiu, B., Zhang, Y., Li, S., Liang, Y., and Hua, X.-S. (2022). DeepCRC: Colorectum and Colorectal Cancer Segmentation in CT Scans via Deep Colorectal Coordinate Transform. Proceedings of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention, Singapore, 18\u201322 September 2022, Springer.","DOI":"10.1007\/978-3-031-16437-8_54"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1007\/s11547-024-01909-5","article-title":"A CT-Based Deep Learning for Segmenting Tumors and Predicting Microsatellite Instability in Patients with Colorectal Cancers: A Multicenter Cohort Study","volume":"130","author":"Chen","year":"2025","journal-title":"Radiol. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"7395","DOI":"10.1109\/TNNLS.2024.3386610","article-title":"A Colorectal Coordinate-Driven Method for Colorectum and Colorectal Cancer Segmentation in Conventional CT Scans","volume":"36","author":"Yao","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"64131","DOI":"10.1109\/ACCESS.2020.2982543","article-title":"Colorectal Tumor Segmentation of CT Scans Based on a Convolutional Neural Network with an Attention Mechanism","volume":"8","author":"Pei","year":"2020","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"104183","DOI":"10.1016\/j.compbiomed.2020.104183","article-title":"MDCC-Net: Multiscale Double-Channel Convolution U-Net Framework for Colorectal Tumor Segmentation","volume":"130","author":"Zheng","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3415603","DOI":"10.1155\/2022\/3415603","article-title":"Automatic Detection and Segmentation of Colorectal Cancer with Deep Residual Convolutional Neural Network","volume":"2022","author":"Akilandeswari","year":"2022","journal-title":"Evid. Based Complement. Altern. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e2432396","DOI":"10.2214\/AJR.24.32396","article-title":"Artificial Intelligence Model for Detection of Colorectal Cancer on Routine Abdominopelvic CT Examinations: A Training and External-Testing Study","volume":"224","author":"Kim","year":"2025","journal-title":"Am. J. Roentgenol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"105183","DOI":"10.1016\/j.ebiom.2024.105183","article-title":"Deep Learning for Colorectal Cancer Detection in Contrast-Enhanced CT without Bowel Preparation: A Retrospective, Multicentre Study","volume":"104","author":"Yao","year":"2024","journal-title":"EBioMedicine"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Endo, S., Nagata, K., Utano, K., Nozu, S., Yasuda, T., Takabayashi, K., Hirayama, M., Togashi, K., and Ohira, H. (2025). Development and Validation of Computer-Aided Detection for Colorectal Neoplasms Using Deep Learning Incorporated with Computed Tomography Colonography. BMC Gastroenterol., 25.","DOI":"10.1186\/s12876-025-03742-0"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, L., Xu, F., and Chen, L. (2025). Diagnostic Accuracy of Artificial Intelligence Based on Imaging Data for Predicting Distant Metastasis of Colorectal Cancer: A Systematic Review and Meta-Analysis. Front. Oncol., 15.","DOI":"10.3389\/fonc.2025.1558915"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"111301","DOI":"10.1016\/j.ejrad.2024.111301","article-title":"Diagnostic CT of Colorectal Cancer with Artificial Intelligence Iterative Reconstruction: A Clinical Evaluation","volume":"171","author":"Li","year":"2024","journal-title":"Eur. J. Radiol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1002\/jmrs.798","article-title":"Using a New Artificial Intelligence-Aided Method to Assess Body Composition CT Segmentation in Colorectal Cancer Patients","volume":"71","author":"Cao","year":"2024","journal-title":"J. Med. Radiat. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"9214337","DOI":"10.1155\/bmri\/9214337","article-title":"Advancements in Image-Based Analyses for Morphology and Staging of Colon Cancer: A Comprehensive Review","volume":"2025","author":"Ameyaw","year":"2025","journal-title":"Biomed. Res. Int."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1186\/s13244-025-02009-2","article-title":"An Interpretable CT-Based Machine Learning Model for Predicting Recurrence Risk in Stage II Colorectal Cancer","volume":"16","author":"Wu","year":"2025","journal-title":"Insights Imaging"}],"container-title":["Life"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/8\/1309\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T09:44:41Z","timestamp":1786355081000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/8\/1309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":31,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["life16081309"],"URL":"https:\/\/doi.org\/10.3390\/life16081309","relation":{},"ISSN":["2075-1729"],"issn-type":[{"value":"2075-1729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,10]]}}}