<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2025-25-4-684-693</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-493</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Выявление аномалий в условиях ограниченности и неопределенности данных с использованием zero-shot и few-shot подходов</article-title><trans-title-group xml:lang="en"><trans-title>Anomaly detection under data scarcity and uncertainty using zero-shot and few-shot approaches</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1970-5217</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Милантьев</surname><given-names>С. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Milantev</surname><given-names>S. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сергей Андреевич Милантьев, аспирант</p><p>197101; Санкт-Петербург</p><p>sc 57225127274</p></bio><bio xml:lang="en"><p>Sergey A. Milantev, PhD Student</p><p>197101; Saint Petersburg</p><p>sc 57225127274</p></bio><email xlink:type="simple">geerkus@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-9731-0105</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Михайлова</surname><given-names>П. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Mikhailova</surname><given-names>P. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Полина Дмитриевна Михайлова, магистр</p><p>197022; Санкт-Петербург</p></bio><bio xml:lang="en"><p>Polina D. Mikhailova, Magister</p><p>197022; Saint Petersburg</p></bio><email xlink:type="simple">polina.delitzsch@gmail.com</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-6711-6399</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Бессмертный</surname><given-names>И. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Bessmertny</surname><given-names>I. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Игорь Александрович Бессмертный, доктор технических наук, профессор, профессор</p><p>197101; Санкт-Петербург</p><p>sc 36661767800</p></bio><bio xml:lang="en"><p>Igor A. Bessmertny, D.Sc., Full Professor</p><p>197101; Saint Petersburg</p><p>sc 36661767800</p></bio><email xlink:type="simple">bessmertny@itmo.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Университет ИТМО</institution><country>Россия</country></aff><aff xml:lang="en"><institution>ITMO University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный электротехнический университет «ЛЭТИ» им. В.И. Ульянова (Ленина)</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg Electrotechnical University “LETI”</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>29</day><month>08</month><year>2025</year></pub-date><volume>25</volume><issue>4</issue><fpage>684</fpage><lpage>693</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Милантьев С.А., Михайлова П.Д., Бессмертный И.А., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Милантьев С.А., Михайлова П.Д., Бессмертный И.А.</copyright-holder><copyright-holder xml:lang="en">Milantev S.A., Mikhailova P.D., Bessmertny I.A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://ntv.elpub.ru/jour/article/view/493">https://ntv.elpub.ru/jour/article/view/493</self-uri><abstract><sec><title>   Введение</title><p>   Введение. Выявление аномалий в условиях ограниченного объема данных представляет собой актуальную задачу в различных прикладных областях, включая медицинскую диагностику. Методы машинного обучения обычно требуют наличия образцов аномалий для их выявления, что не всегда возможно. Существующие методы выявления аномалий при малом количестве (few-shot) или полном отсутствии (zero-shot) обучающих данных об аномалиях имеют ряд ограничений. Существующее требование нормального распределения данных снижает точность распознавания аномалий.</p></sec><sec><title>   Метод</title><p>   Метод. В представленной работе задача повышения точности и полноты выявления ранее не встречавшихся на изображениях аномалий решается путем комбинирования моделей Contrastive Language-Image Pretraining (CLIP) и доменно-ориентированного трансформера BERT Pre-Training of Image Transformers (BeiT). Модели CLIP и BeiT позволяют одновременно решать задачи бинарной сегментации и классификации аномалий. Более точное выявление аномалий достигается использованием взвешенных эмбеддингов от каждого модуля. Одновременно автоматизируется генерация текстовых представлений на основе Large Language Model, что существенно улучшает обобщающую способность модели.</p></sec><sec><title>   Основные результаты</title><p>   Основные результаты. Оценка эффективности разработанных моделей выполнена на тестовой выборке Benchmarks for Medical Anomaly Detection). Для домена кожных новообразований тестовая выборка сформирована из датасетов ISIC-18, ISIC-19, SD-198 и 7-point criteria database. Разработанный метод продемонстрировал в среднем увеличение метрики ROC AUC (при классификации, на уровне image-level) на 10,95 %, а метрики ROC AUC (при сегментации, на уровне pixel-level) — на 0,66 % по сравнению с известными решениями.</p></sec><sec><title>   Обсуждение</title><p>   Обсуждение. Проведенные эксперименты показали высокую эффективность предложенного подхода на задачах классификации и сегментации аномалий, метод продемонстрировал превосходящие результаты по средним значениям метрик. Анализ инференса показал, что использование вариационного автоэнкодера в составе CLIP+BeiT для генерации центроидов способствует более стабильной работе модели в few-shot подходе.</p><p>   Практическая значимость предложенного метода заключается в его адаптивности и устойчивости к изменяющимся распределениям данных, что делает его перспективным решением для автоматизированного анализа аномалий в медицинской диагностике, промышленном контроле и других областях, где может наблюдаться высокая неопределенность данных.</p></sec></abstract><trans-abstract xml:lang="en"><p>   Anomaly detection under conditions of limited data volume represents a pressing challenge across numerous applied domains, including medical diagnostics. Machine learning methods typically rely on the availability of annotated anomalous samples for training, which is often impractical. Existing anomaly detection techniques designed for few-shot or zero-shot scenarios suffer from various limitations. In particular, the common assumption of normally distributed data reduces the accuracy of anomaly classification. In this study, the task of improving the accuracy and completeness of anomaly detection in previously unseen images by leveraging a combination of the Contrastive Language-Image Pretraining (CLIP) and the domain-specific transformer BERT Pre-Training of Image Transformers (BeiT) models. The integration of CLIP and BeiT models enables simultaneous binary segmentation and anomaly classification. Enhanced anomaly detection is achieved through the use of weighted embeddings from each module. Additionally, the automated generation of textual representations based on a Large Language Model significantly enhances the generalization capacity of the system. The performance of the proposed models was evaluated on the Benchmarks for Medical Anomaly Detection test set. For the dermatological domain, a test set was constructed from ISIC-18, ISIC-19, SD-198, and 7-point criteria database. The proposed method demonstrated an average improvement in the ROC-AUC metric by 10.95 % at the image-level and by 0.66 % at the pixel-level compared to existing state-of-the-art solutions. Experimental results confirm the high effectiveness of the proposed approach in anomaly classification and segmentation tasks, showing superior average metric values. Inference analysis revealed that the incorporation of a variational autoencoder within the CLIP+BeiT architecture for centroid generation enhances the model stability in few-shot scenarios. The practical significance of the proposed method lies in its adaptability and robustness to changing data distributions, making it a promising solution for automated anomaly analysis in medical diagnostics, industrial monitoring, and other domains characterized by high data uncertainty.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>детекция аномалий</kwd><kwd>zero-shot</kwd><kwd>few-shot</kwd><kwd>трансформер</kwd><kwd>мультизадачное обучение</kwd></kwd-group><kwd-group xml:lang="en"><kwd>anomaly detection</kwd><kwd>zero-shot</kwd><kwd>few-shot</kwd><kwd>transformer</kwd><kwd>multi-task learning</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Работа поддержана Минобрнауки Российской Федерации, тема № FFZM-2025-0005</funding-statement><funding-statement xml:lang="en">The work was supported by the Ministry of Education and Science of the Russian Federation, topic No. FZZM-2025- 0005</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Bao J., Sun H., Deng H., He Y., Zhang Z., Li X. BMAD: Benchmarks for Medical Anomaly Detection // arXiv. 2023. arXiv:2306.11876. doi: 10.48550/arXiv.2306.11876</mixed-citation><mixed-citation xml:lang="en">Bao J., Sun H., Deng H., He Y., Zhang Z., Li X. BMAD: Benchmarks for Medical Anomaly Detection. arXiv, 2023, arXiv:2306.11876. doi: 10.48550/arXiv.2306.11876</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Chen L., You Z., Zhang N., Xi J., Le X. UTRAD: Anomaly detection and localization with U-Transformer // Neural Networks. 2022. V. 147. P. 53–62. doi: 10.1016/j.neunet.2021.12.008</mixed-citation><mixed-citation xml:lang="en">Chen L., You Z., Zhang N., Xi J., Le X. UTRAD: Anomaly detection and localization with U-Transformer. Neural Networks, 2022, vol. 147, pp. 53–62. doi: 10.1016/j.neunet.2021.12.008</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Salehi M., Sadjadi N., Baselizadeh S., Rohban M.H., Rabiee H.R. Multiresolution knowledge distillation for anomaly detection // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021. P. 14897–14907. doi: 10.1109/CVPR46437.2021.01466</mixed-citation><mixed-citation xml:lang="en">Salehi M., Sadjadi N., Baselizadeh S., Rohban M.H., Rabiee H.R. Multiresolution knowledge distillation for anomaly detection. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 14897–14907. doi: 10.1109/CVPR46437.2021.01466</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Deng H., Li X. Anomaly detection via reverse distillation from one-class embedding // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. P. 9727–9736. doi: 10.1109/CVPR52688.2022.00951</mixed-citation><mixed-citation xml:lang="en">Deng H., Li X. Anomaly detection via reverse distillation from one-class embedding. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 9727–9736. doi: 10.1109/CVPR52688.2022.00951</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Roth K., Pemula L., Zepeda J., Schölkopf B., Brox T., Gehler P. Towards total recall in industrial anomaly detection // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. P. 14298–14308. doi: 10.1109/CVPR52688.2022.01392</mixed-citation><mixed-citation xml:lang="en">Roth K., Pemula L., Zepeda J., Schölkopf B., Brox T., Gehler P. Towards total recall in industrial anomaly detection. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 14298–14308. doi: 10.1109/CVPR52688.2022.01392</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Lee S., Lee S., Song B. CFA: coupled-hypersphere-based feature adaptation for target-oriented anomaly localization // IEEE Access. 2022. V. 10. P. 78446–78454. doi: 10.1109/ACCESS.2022.3193699</mixed-citation><mixed-citation xml:lang="en">Lee S., Lee S., Song B. CFA: coupled-hypersphere-based feature adaptation for target-oriented anomaly localization. IEEE Access, 2022, vol. 10, pp. 78446–78454. doi: 10.1109/ACCESS.2022.3193699</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Gudovskiy D., Ishizaka S., Kozuka K. CFLOW-AD: real-time unsupervised anomaly detection with localization via conditional normalizing flows // Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2022. P. 1819–1828. doi: 10.1109/WACV51458.2022.00188</mixed-citation><mixed-citation xml:lang="en">Gudovskiy D., Ishizaka S., Kozuka K. CFLOW-AD: real-time unsupervised anomaly detection with localization via conditional normalizing flows. Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 1819–1828. doi: 10.1109/WACV51458.2022.00188</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Chen X., Han Y., Zhang J. APRIL-GAN: a Zero-/Few-shot anomaly classification and segmentation method // arXiv. 2023. arXiv:2305.17382v3. doi: 10.48550/arXiv.2305.17382</mixed-citation><mixed-citation xml:lang="en">Chen X., Han Y., Zhang J. APRIL-GAN: a Zero-/Few-shot anomaly classification and segmentation method. arXiv, 2023, arXiv:2305.17382v3. doi: 10.48550/arXiv.2305.17382</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Hu J., Chen Y., Yi Z. Automated segmentation of macular edema in OCT using deep neural networks // Medical Image Analysis. 2019. V. 55. P. 216–227. doi: 10.1016/j.media.2019.05.002</mixed-citation><mixed-citation xml:lang="en">Hu J., Chen Y., Yi Z. Automated segmentation of macular edema in OCT using deep neural networks. Medical Image Analysis, 2019, vol. 55, pp. 216–227. doi: 10.1016/j.media.2019.05.002</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Wang X., Peng Y., Lu L., Lu Z., Bagheri M., Summers R. ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases // Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 3462–3471. doi: 10.1109/CVPR.2017.369</mixed-citation><mixed-citation xml:lang="en">Wang X., Peng Y., Lu L., Lu Z., Bagheri M., Summers R. ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 3462–3471. doi: 10.1109/CVPR.2017.369</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Bejnordi B., Veta M., van Diest P.J., van Ginneken B., Karssemeijer N., Litjens G., van der Laak J.A.W.M. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer // JAMA Journal of the American Medical Association. 2017. V. 318. N 22. P. 2199–2210. doi: 10.1001/jama.2017.14585</mixed-citation><mixed-citation xml:lang="en">Bejnordi B., Veta M., van Diest P.J., van Ginneken B., Karssemeijer N., Litjens G., van der Laak J.A.W.M. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA Journal of the American Medical Association, 2017, vol. 318, no. 22, pp. 2199–2210. doi: 10.1001/jama.2017.14585</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Tschandl P., Rosendahl C., Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions // Scientific Data. 2018. V. 5. P. 180161. doi: 10.1038/sdata.2018.161</mixed-citation><mixed-citation xml:lang="en">Tschandl P., Rosendahl C., Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data, 2018, vol. 5, pp. 180161. doi: 10.1038/sdata.2018.161</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Codella N.C.F., Gutman D., Celebi M.E., Helba B., Marchetti M.A., Dusza S.W., Kalloo A., Liopyris K., Mishra N., Kittler H., Halpern A. Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) // Proc. of the IEEE 15&lt;sup&gt;th&lt;/sup&gt; International Symposium on Biomedical Imaging (ISBI 2018). 2018. Р. 168–172. doi: 10.1109/ISBI.2018.8363547</mixed-citation><mixed-citation xml:lang="en">Codella N.C.F., Gutman D., Celebi M.E., Helba B., Marchetti M.A., Dusza S.W., Kalloo A., Liopyris K., Mishra N., Kittler H., Halpern A. Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). Proc. of the IEEE 15&lt;sup&gt;th&lt;/sup&gt; International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 168–172. doi: 10.1109/ISBI.2018.8363547</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Combalia M., Codella N.C.F., Rotemberg V., Helba B., Vilaplana V., Reiter O., Carrera C., Barreiro A., Halpern A.C., Puig S., Malvehy J. BCN20000: Dermoscopic lesions in the wild // arXiv. 2019. arXiv:1908.02288. doi: 10.48550/arXiv.1908.02288</mixed-citation><mixed-citation xml:lang="en">Combalia M., Codella N.C.F., Rotemberg V., Helba B., Vilaplana V., Reiter O., Carrera C., Barreiro A., Halpern A.C., Puig S., Malvehy J. BCN20000: Dermoscopic lesions in the wild. arXiv, 2019, arXiv:1908.02288. doi: 10.48550/arXiv.1908.02288</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Sun X., Yang J., Sun M., Wang K. A benchmark for automatic visual classification of clinical skin disease images // Lecture Notes in Computer Science. 2016. V. 9910. P. 206–222. doi: 10.1007/978-3-319-46466-4_13</mixed-citation><mixed-citation xml:lang="en">Sun X., Yang J., Sun M., Wang K. A benchmark for automatic visual classification of clinical skin disease images. Lecture Notes in Computer Science, 2016, vol. 9910, pp. 206–222. doi: 10.1007/978-3-319-46466-4_13</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Kawahara J., Daneshvar S., Argenziano G., Hamarneh G. Seven-point checklist and skin lesion classification using multitask multimodal neural nets // IEEE Journal of Biomedical and Health Informatics. 2019. V. 23. N 2. P.538–546. doi: 10.1109/JBHI.2018.2824327</mixed-citation><mixed-citation xml:lang="en">Kawahara J., Daneshvar S., Argenziano G., Hamarneh G. Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE Journal of Biomedical and Health Informatics, 2019, vol. 23, no. 2, pp. 538–546. doi: 10.1109/JBHI.2018.2824327</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Baid U., Ghodasara S., Mohan S., Bilello M., Calabrese E., Colak E., et al. The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification // arXiv. 2021. arXiv:2107.02314. doi: 10.48550/arXiv.2107.02314</mixed-citation><mixed-citation xml:lang="en">Baid U., Ghodasara S., Mohan S., Bilello M., Calabrese E., Colak E., et al. The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv, 2021, arXiv:2107.02314. doi: 10.48550/arXiv.2107.02314</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Bilic P, Christ P., Li H.B., Vorontsov E., Ben-Cohen A., Kaissis G., et al. The Liver Tumor Segmentation benchmark (LiTS) // arXiv. 2019. arXiv:190.04056. doi: 10.48550/arXiv.1901.04056</mixed-citation><mixed-citation xml:lang="en">Bilic P, Christ P., Li H.B., Vorontsov E., Ben-Cohen A., Kaissis G., et al. The Liver Tumor Segmentation benchmark (LiTS). arXiv, 2019, arXiv:190.04056. doi: 10.48550/arXiv.1901.04056</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
