{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:12:19Z","timestamp":1789999939633,"version":"4.0.1"},"reference-count":25,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T00:00:00Z","timestamp":1789776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Lightweight detectors are attractive for high-throughput low-dose CT lung-cancer screening, yet the training-time choices governing their accuracy are usually fixed without justification, as is the protocol used to evaluate them. We benchmarked the inter-slice input representation and the extent of bounding-box supervision for 2.5D pulmonary nodule detection under the official LUNA16 protocol. Methods: Using one YOLO11n backbone we compared a 2D central-slice baseline, thin-slab maximum-intensity projection, and adjacent-slice 2.5D input under loose and core-focused (60% of diameter) supervision. Evaluation followed the official subset0\u2013subset9 ten-fold protocol over all 888 scans and 1186 nodules, with whole-volume inference across 227,225 axial slices, annotations_excluded.csv applied, and paired scan-level bootstrap intervals. Supervision ratio, minimum box size, negative mining, three seeds and a YOLO26n backbone were ablated. Results: The representation dominated. Adjacent-slice input reached a competition performance metric (CPM) of 0.7795 (95% CI 0.7517\u20130.8005) against 0.6498 for the 2D baseline (+0.1297; 10 of 10 folds; d_z = 2.96), while thin-slab projection (0.5965) was worse than a plain 2D slice. Core-focused supervision gave no benefit (\u22120.0209) and no ratio improved on full-diameter supervision. Re-scoring the same checkpoints over only the slices holding an annotated nodule centre reversed the supervision result (+0.0027) and shrank the representation effect fourfold (+0.0348). Conclusions: Inter-slice representation, not supervision extent, is the dominant design factor, and the slice set searched at inference decides whether either factor is measurable.<\/jats:p>","DOI":"10.3390\/diagnostics16183038","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:50:03Z","timestamp":1789995003000},"page":"3038","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Inter-Slice Representation Outweighs Bounding-Box Supervision Extent in Lightweight 2.5D Pulmonary Nodule Detection: A Whole-Volume Benchmark on LUNA16"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8979-9821","authenticated-orcid":false,"given":"Lien-Feng","family":"Chou","sequence":"first","affiliation":[{"name":"Department of Medical Imaging and Radiological Sciences, Central Taiwan University of Science and Technology, Taichung 406, Taiwan"},{"name":"Department of Radiology, Nantou Hospital, Ministry of Health and Welfare, Nantou City 540, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4371-2114","authenticated-orcid":false,"given":"Bing-Ru","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Radiological Sciences, Central Taiwan University of Science and Technology, Taichung 406, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7748-7990","authenticated-orcid":false,"given":"Shou-Wei","family":"Chien","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Nantou Hospital, Ministry of Health and Welfare, Nantou City 540, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1482-3257","authenticated-orcid":false,"given":"Yu-Ming","family":"Huang","sequence":"additional","affiliation":[{"name":"Information Management Department, National Yunlin University of Science and Technology, Yunlin 64002, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"ref_1","first-page":"229","article-title":"Global Cancer Statistics 2022: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"National Lung Screening Trial Research Team (2011). Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening. N. Engl. J. Med., 365, 395\u2013409.","DOI":"10.1056\/NEJMoa1102873"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.media.2017.06.015","article-title":"Validation, Comparison, and Combination of Algorithms for Automatic Detection of Pulmonary Nodules in Computed Tomography Images: The LUNA16 Challenge","volume":"42","author":"Setio","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1093\/jamia\/ocy098","article-title":"3D Deep Learning for Detecting Pulmonary Nodules in CT Scans","volume":"25","author":"Gruetzemacher","year":"2018","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_5","first-page":"559","article-title":"Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks","volume":"Volume 10435","author":"Ding","year":"2017","journal-title":"Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2017, Quebec City, QC, Canada, 11\u201313 September 2017"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhu, W., Liu, C., Fan, W., and Xie, X. (2018, January 12\u201315). DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00079"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"10922","DOI":"10.1038\/s41598-026-42029-6","article-title":"WTAM-YOLO: A YOLOv11-Based Method for Pulmonary Nodule Detection","volume":"16","author":"Lan","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"12313","DOI":"10.1038\/s41598-025-97187-w","article-title":"Lung Nodule Detection Using a Multi-Scale Convolutional Neural Network and Global Channel Spatial Attention Mechanisms","volume":"15","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/TMI.2015.2482920","article-title":"Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation","volume":"35","author":"Roth","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1109\/TMI.2016.2536809","article-title":"Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks","volume":"35","author":"Setio","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s13244-025-02000-x","article-title":"A Multi-View CNN Model to Predict Resolving of New Lung Nodules on Follow-up Low-Dose Chest CT","volume":"16","author":"Wang","year":"2025","journal-title":"Insights Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, T., Luo, B., Sharda, A., and Wang, G. (2022). Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs. J. Imaging, 8.","DOI":"10.3390\/jimaging8070193"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1148\/radiol.2018180910","article-title":"Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas","volume":"290","author":"Beig","year":"2019","journal-title":"Radiology"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1016\/j.acra.2022.07.001","article-title":"Perinodular Parenchymal Features Improve Indeterminate Lung Nodule Classification","volume":"30","author":"Masquelin","year":"2023","journal-title":"Acad. Radiol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Song, X., Xie, H., Gao, T., Cheng, N., and Gou, J. (2025). Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty. Sensors, 25.","DOI":"10.3390\/s25144245"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1007\/s40747-025-02032-2","article-title":"Enhanced Pulmonary Nodule Detection Using a Transformer Framework with Dual Fusion and Gated Mechanism","volume":"11","author":"Sun","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans","volume":"38","author":"Armato","year":"2011","journal-title":"Med. Phys."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","article-title":"The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository","volume":"26","author":"Clark","year":"2013","journal-title":"J. Digit. Imaging"},{"key":"ref_19","unstructured":"Van Ginneken, B., and Jacobs, C. (2020). LUNA16 Part 1\/2 [Dataset]. Zenodo."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1111\/j.1541-0420.2008.01049.x","article-title":"Area under the Free-Response ROC Curve (FROC) and a Related Summary Index","volume":"65","author":"Bandos","year":"2009","journal-title":"Biometrics"},{"key":"ref_21","unstructured":"Khanam, R., and Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. arXiv."},{"key":"ref_22","unstructured":"Loshchilov, I., and Hutter, F. (2019, January 6\u20139). Decoupled Weight Decay Regularization. Proceedings of the 7th International Conference on Learning Representations (ICLR), New Orleans, LA, USA."},{"key":"ref_23","unstructured":"Jocher, G., and Qiu, J. (2026, August 01). Ultralytics YOLO26 (Version 8.4.117). Available online: https:\/\/docs.ultralytics.com\/models\/yolo26\/."},{"key":"ref_24","first-page":"65","article-title":"A Simple Sequentially Rejective Multiple Test Procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J. Stat."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/3038\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:20:57Z","timestamp":1789996857000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/3038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,19]]},"references-count":25,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["diagnostics16183038"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16183038","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,19]]}}}