Siegel, R. L. et al. Most cancers statistics, 2023. CA Most cancers J. Clin. 73, 17–48 (2023).
Google Scholar
Chhikara, B. S. & Parang, Okay. International most cancers statistics 2022: the tendencies projection evaluation. Chem. Biol. Lett. 10, 451–451 (2023).
Xia, C. et al. Most cancers statistics in China and United States, 2022: profiles, tendencies, and determinants. Chin. Med. J. 135, 584–590 (2022).
Google Scholar
Sickles, E. A. ACR BI-RADS atlas, breast imaging reporting and knowledge system. J. Am. Coll. Radiol. 39 (2013).
Ohuchi, N. et al. Sensitivity and specificity of mammography and adjunctive ultrasonography to display screen for breast most cancers within the Japan Strategic Anti-cancer Randomized Trial (J-START): a randomised managed trial. Lancet 387, 341–348 (2016).
Google Scholar
Berg, W. A. et al. Detection of breast most cancers with addition of annual screening ultrasound or a single screening MRI to mammography in ladies with elevated breast most cancers danger. JAMA 307, 1394–1404 (2012).
Google Scholar
Shen, S. et al. A multi-centre randomised trial evaluating ultrasound vs mammography for screening breast most cancers in high-risk Chinese language ladies. Br. J. Most cancers 112, 998–1004 (2015).
Google Scholar
Brem, R. F., Lenihan, M. J., Lieberman, J. & Torrente, J. Screening breast ultrasound: previous, current, and future. Am. J. Roentgenol. 204, 234–240 (2015).
Google Scholar
Sood, R. et al. Ultrasound for breast most cancers detection globally: a scientific assessment and meta-analysis. J. Glob. Oncol. 5, 1–17 (2019).
Park, Y. et al. Pan-Asian tailored ESMO medical follow tips for the administration of sufferers with early breast most cancers: a KSMO-ESMO initiative endorsed by CSCO, ISMPO, JSMO, MOS, SSO and TOS. Ann. Oncol. 31, 451–469 (2020).
Google Scholar
Weese, J. & Lorenz, C. 4 Challenges in Medical Picture Evaluation from an Industrial Perspective (Elsevier, 2016).
González-Villà, S. et al. A assessment on mind constructions segmentation in magnetic resonance imaging. Artif. Intell. Med. 73, 45–69 (2016).
Google Scholar
Geirhos, R. et al. Shortcut studying in deep neural networks. Nat. Mach. Intell. 2, 665–673 (2020).
Google Scholar
Cao, Okay. et al. Giant-scale pancreatic most cancers detection by way of non-contrast CT and deep studying. Nat. Med. 29, 3033–3043 (2023).
Google Scholar
Goetz, L., Seedat, N., Vandersluis, R. & Schaar, M. Generalization—a key problem for accountable AI in patient-facing medical functions. npj Digit. Med. 7, 126 (2024).
Google Scholar
Tiu, E. et al. Professional-level detection of pathologies from unannotated chest X-ray pictures by way of self-supervised studying. Nat. Biomed. Eng. 6, 1399–1406 (2022).
Google Scholar
Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T. J. & Zou, J. A visible–language basis mannequin for pathology picture evaluation utilizing medical Twitter. Nat. Med. 29, 2307–2316 (2023).
Google Scholar
Xu, H. et al. An entire-slide basis mannequin for digital pathology from real-world knowledge. Nature 630, 181–188 (2024).
De Fauw, J. et al. Clinically relevant deep studying for analysis and referral in retinal illness. Nat. Med. 24, 1342–1350 (2018).
Google Scholar
Zhou, Y. et al. A basis mannequin for generalizable illness detection from retinal pictures. Nature 622, 156–163 (2023).
Google Scholar
Yap, M. H. et al. Automated breast ultrasound lesions detection utilizing convolutional neural networks. IEEE J. Biomed. Well being Inform. 22, 1218–1226 (2017).
Google Scholar
Al-Dhabyani, W., Gomaa, M., Khaled, H. & Fahmy, A. Dataset of breast ultrasound pictures. Knowledge Transient 28, 104863 (2020).
Google Scholar
Lin, Z. et al. A brand new dataset and a baseline mannequin for breast lesion detection in ultrasound movies. In Worldwide Convention on Medical Picture Computing and Laptop-Assisted Intervention (eds Wang, L. et al.) 614–623 (Springer, 2022).
Malin, B. A., Emam, Okay. E. & O’Keefe, C. M. Biomedical knowledge privateness: issues, views, and up to date advances. J. Am. Med. Inform. Assoc. 20, 2–6 (2013).
Google Scholar
Shen, Y. et al. Synthetic intelligence system reduces false-positive findings within the interpretation of breast ultrasound exams. Nat. Commun. 12, 5645 (2021).
Google Scholar
Wu, T., Sultan, L. R., Tian, J., Cary, T. W. & Sehgal, C. M. Machine studying for diagnostic ultrasound of triple-negative breast most cancers. Breast Most cancers Res. Deal with. 173, 365–373 (2019).
Google Scholar
Ozaki, J. et al. Deep studying methodology with a convolutional neural community for picture classification of regular and metastatic axillary lymph nodes on breast ultrasonography. Jpn J. Radiol. 40, 814–822 (2022).
Google Scholar
Zuluaga-Gomez, J., Al Masry, Z., Benaggoune, Okay., Meraghni, S. & Zerhouni, N. A CNN-based methodology for breast most cancers analysis utilizing thermal pictures. Comput. Strategies Biomech. Biomed. Eng. Imaging Vis. 9, 131–145 (2021).
Google Scholar
Ong Ly, C. et al. Shortcut studying in medical AI hinders generalization: methodology for estimating AI mannequin generalization with out exterior knowledge. npj Digit. Med. 7, 124 (2024).
Google Scholar
Namli, T. et al. A scalable and clear knowledge pipeline for AI-enabled well being knowledge ecosystems. Entrance. Med. 11, 1393123 (2024).
Google Scholar
Brown, T. et al. Language fashions are few-shot learners. Adv. Neural Inf. Course of. Syst. 33, 1877–1901 (2020).
Ouyang, L. et al. Coaching language fashions to observe directions with human suggestions. Adv. Neural Inf. Course of. Syst. 35, 27730–27744 (2022).
Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. Excessive-resolution picture synthesis with latent diffusion fashions. In Proc. IEEE/CVF Convention on Laptop Imaginative and prescient and Sample Recognition 10684–10695 (IEEE, 2022).
Gemini Staff Google. Gemini: a household of extremely succesful multimodal fashions. Preprint at (2023).
Bommasani, R. et al. On the alternatives and dangers of basis fashions. Preprint at (2021).
Bluethgen, C. et al. A vision-language basis mannequin for the era of real looking chest X-ray pictures. Nat. Biomed. Eng. 9, 494–506 (2025).
Google Scholar
Wang, J. et al. Self-improving generative basis mannequin for artificial medical picture era and medical functions. Nat. Med. 31, 609–617 (2025).
McKinney, S. M. et al. Worldwide analysis of an AI system for breast most cancers screening. Nature 577, 89–94 (2020).
Google Scholar
Lee, C. H. et al. Breast most cancers screening with imaging: suggestions from the society of breast imaging and the ACR on using mammography, breast MRI, breast ultrasound, and different applied sciences for the detection of clinically occult breast most cancers. J. Am. Coll. Radiol. 7, 18–27 (2010).
Google Scholar
Marmot, M. G. et al. The advantages and harms of breast most cancers screening: an unbiased assessment. Br. J. Most cancers 108, 2205–2240 (2013).
Google Scholar
Qian, X. et al. Potential evaluation of breast most cancers danger from multimodal multiview ultrasound pictures by way of clinically relevant deep studying. Nat. Biomed. Eng. 5, 522–532 (2021).
Google Scholar
Pacilè, S. et al. Bettering breast most cancers detection accuracy of mammography with the concurrent use of a synthetic intelligence device. Radiol. Artif. Intell. 2, 190208 (2020).
Google Scholar
Dembrower, Okay. et al. Impact of synthetic intelligence-based triaging of breast most cancers screening mammograms on most cancers detection and radiologist workload: a retrospective simulation research. Lancet Digit. Well being 2, 468–474 (2020).
Google Scholar
Zhou, L.-Q. et al. Lymph node metastasis prediction from main breast most cancers US pictures utilizing deep studying. Radiology 294, 19–28 (2020).
Google Scholar
Tafreshi, N. Okay., Kumar, V., Morse, D. L. & Gatenby, R. A. Molecular and useful imaging of breast most cancers. Most cancers Management 17, 143–155 (2010).
Google Scholar
Zhao, S., Zuo, W.-J., Shao, Z.-M. & Jiang, Y.-Z. Molecular subtypes and precision therapy of triple-negative breast most cancers. Ann. Transl. Med. 8, 499 (2020).
Tsang, J. Y. & Tse, G. M. Molecular classification of breast most cancers. Adv. Anat. Pathol. 27, 27–35 (2020).
Google Scholar
Ho, J., Jain, A. & Abbeel, P. Denoising diffusion probabilistic fashions. Adv. Neural Inf. Course of. Syst. 33, 6840–6851 (2020).
Radford, A. et al. Studying transferable visible fashions from pure language supervision. In Worldwide Convention on Machine Studying 8748–8763 (PMLR, 2021).
Fan, L. et al. Scaling legal guidelines of artificial pictures for mannequin coaching… for now. In Proc. IEEE/CVF Convention on Laptop Imaginative and prescient and Sample Recognition 7382–7392 (IEEE, 2024).
Ktena, I. et al. Generative fashions enhance equity of medical classifiers below distribution shifts. Nat. Med. 30, 1166–1173 (2024).
Dhariwal, P. & Nichol, A. Diffusion fashions beat GANS on picture synthesis. Adv. Neural Inf. Course of. Syst. 34, 8780–8794 (2021).
Ho, J. & Salimans, T. Classifier-free diffusion steering. In NeurIPS Workshop on Deep Generative Fashions and Downstream Functions Poster (NeurIPS, 2021).
Zhang, L., Rao, A. & Agrawala, M. Including conditional management to text-to-image diffusion fashions. In Proc. IEEE/CVF Worldwide Convention on Laptop Imaginative and prescient 3836–3847 (IEEE,2023).
Hu, E. J. et al. LoRA: Low-rank adaptation of enormous language fashions. In Worldwide Convention on Studying Representations Poster (ICLR, 2022).
Lu, C. et al. DPM-Solver: a quick ODE solver for diffusion probabilistic mannequin sampling in round 10 steps. Adv. Neural Inf. Course of. Syst. 35, 5775–5787 (2022).
Lu, C. et al. DPM-Solver++: quick solver for guided sampling of diffusion probabilistic fashions. Mach. Intell. Res. 22, 730–751 (2025).
Google Scholar
Kazdan, J. et al. CPsample: classifier protected sampling for guarding coaching knowledge throughout diffusion. In Proc. thirteenth Worldwide Convention on Studying Representations (ICLR, 2025).
Lin, W. et al. PMC-CLIP: contrastive language-image pre-training utilizing biomedical paperwork. In Proc. Worldwide Convention on Medical Picture Computing and Laptop-Assisted Intervention 525–536 (Springer, 2023).
Wang, Z., Wu, Z., Agarwal, D. & Solar, J. MedCLIP: contrastive studying from unpaired medical pictures and textual content. In Proc. Convention on Empirical Strategies in Pure Language Processing 3876 (ACL, 2022).
Eslami, S., Meinel, C. & de Melo, G. in Findings of the Affiliation for Computational Linguistics: EACL 2023 (eds Vlachos, A. & Augenstein, I.) 1181–1193 (ACL, 2023).
Zhang, S. et al. A multimodal biomedical basis mannequin skilled from fifteen million picture–textual content pairs. NEJM AI 2, 2400640 (2025).
Google Scholar
Chen, X., Xie, S. & He, Okay. An empirical research of coaching self-supervised imaginative and prescient transformers. In Proc. IEEE/CVF Worldwide Convention on Laptop Imaginative and prescient 9640–9649 (IEEE, 2021).
He, Okay. et al. Masked autoencoders are scalable imaginative and prescient learners. In Proc. IEEE/CVF Convention on Laptop Imaginative and prescient and Sample Recognition 16000–16009 (IEEE, 2022).
Geman, D., Geman, S., Hallonquist, N. & Younes, L. Visible Turing check for pc imaginative and prescient programs. Proc. Natl Acad. Sci. USA 112, 3618–3623 (2015).
Google Scholar
Carlini, N. et al. Extracting coaching knowledge from massive language fashions. In thirtieth USENIX Safety Symposium (USENIX Safety 21) 2633–2650 (USENIX, 2021).
Elmore, J. G., Armstrong, Okay., Lehman, C. D. & Fletcher, S. W. Screening for breast most cancers. JAMA 293, 1245–1256 (2005).
Google Scholar
Myers, E. R. et al. Advantages and harms of breast most cancers screening: a scientific assessment. JAMA 314, 1615–1634 (2015).
Google Scholar
Yuan, W.-H., Hsu, H.-C., Chen, Y.-Y. & Wu, C.-H. Supplemental breast cancer-screening ultrasonography in ladies with dense breasts: a scientific assessment and meta-analysis. Br. J. Most cancers 123, 673–688 (2020).
Google Scholar
Yap, M. H. et al. Breast ultrasound area of curiosity detection and lesion localisation. Artif. Intell. Med. 107, 101880 (2020).
Google Scholar
Pinder, S. E. Ductal carcinoma in situ (DCIS): pathological options, differential analysis, prognostic components and specimen analysis. Fashionable Pathol. 23, 8–13 (2010).
Google Scholar
Ernster, V. L. & Barclay, J. Will increase in ductal carcinoma in situ (DCIS) of the breast in relation to mammography: a dilemma. J. Natl Most cancers Inst. Monogr. 1997, 151–156 (1997).
Google Scholar
Winchester, D. P., Jeske, J. M. & Goldschmidt, R. A. The analysis and administration of ductal carcinoma in-situ of the breast. CA Most cancers J. Clin. 50, 184–200 (2000).
Google Scholar
Watanabe, T. et al. Ultrasound picture classification of ductal carcinoma in situ (DCIS) of the breast: evaluation of 705 DCIS lesions. Ultrasound Med. Biol. 43, 918–925 (2017).
Google Scholar
Kim, S. H. et al. Correlation of ultrasound findings with histology, tumor grade, and organic markers in breast most cancers. Acta Oncol. 47, 1531–1538 (2008).
Google Scholar
Ahsan, M. M., Mahmud, M. P., Saha, P. Okay., Gupta, Okay. D. & Siddique, Z. Impact of information scaling strategies on machine studying algorithms and mannequin efficiency. Applied sciences 9, 52 (2021).
Google Scholar
Frid-Adar, M. et al. GAN-based artificial medical picture augmentation for elevated CNN efficiency in liver lesion classification. Neurocomputing 321, 321–331 (2018).
Google Scholar
Sagers, L. W. et al. Augmenting medical picture classifiers with artificial knowledge from latent diffusion fashions. Preprint at (2023).
Kerlikowske, Okay., Smith-Bindman, R., Ljung, B.-M. & Grady, D. Analysis of irregular mammography outcomes and palpable breast abnormalities. Ann. Intern. Med. 139, 274–284 (2003).
Google Scholar
Weigel, M. T. & Dowsett, M. Present and rising biomarkers in breast most cancers: prognosis and prediction. Endocr. Relat. Most cancers 17, 245–262 (2010).
Google Scholar
Baxevanis, C. N., Fortis, S. P. & Perez, S. A. in Seminars in Most cancers Biology Vol. 72 76–89 (Elsevier, 2021).
Liedtke, C. et al. Response to neoadjuvant remedy and long-term survival in sufferers with triple-negative breast most cancers. J. Clin. Oncol. 26, 1275–1281 (2008).
Google Scholar
Kennecke, H. et al. Metastatic conduct of breast most cancers subtypes. J. Clin. Oncol. 28, 3271–3277 (2010).
Google Scholar
Rao, R., Euhus, D., Mayo, H. G. & Balch, C. Axillary node interventions in breast most cancers: a scientific assessment. JAMA 310, 1385–1394 (2013).
Google Scholar
Cianfrocca, M. & Goldstein, L. J. Prognostic and predictive components in early-stage breast most cancers. Oncologist 9, 606–616 (2004).
Google Scholar
Selvaraju, R. R. et al. Grad-CAM: visible explanations from deep networks by way of gradient-based localization. In Proc. IEEE Worldwide Convention on Laptop Imaginative and prescient 618–626 (IEEE, 2017).
Gatys, L. A., Ecker, A. S. & Bethge, M. Picture type switch utilizing convolutional neural networks. In Proc. IEEE Convention on Laptop Imaginative and prescient and Sample Recognition 2414–2423 (IEEE, 2016).
Zhu, J.-Y., Park, T., Isola, P. & Efros, A. A. Unpaired image-to-image translation utilizing cycle-consistent adversarial networks. In Proc. IEEE Worldwide Convention on Laptop Imaginative and prescient 2223–2232 (IEEE, 2017).
He, Okay., Gkioxari, G., Dollár, P. & Girshick, R. Masks R-CNN. In Proc. IEEE Worldwide Convention on Laptop Imaginative and prescient 2961–2969 (IEEE, 2017).
DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Evaluating the areas below two or extra correlated receiver working attribute curves: a nonparametric strategy. Biometrics 44, 837–845 (1988).
Solar, X. & Xu, W. Quick implementation of DeLong’s algorithm for evaluating the areas below correlated receiver working attribute curves. IEEE Sign Course of. Lett. 21, 1389–1393 (2014).
Google Scholar
Benjamini, Y., Drai, D., Elmer, G., Kafkafi, N. & Golani, I. Controlling the false discovery price in conduct genetics analysis. Behav.Mind Res. 125, 279–284 (2001).
Google Scholar
Glickman, M. E., Rao, S. R. & Schultz, M. R. False discovery price management is a advisable different to Bonferroni-type changes in well being research. J. Clin. Epidemiol. 67, 850–857 (2014).
Google Scholar
Hsu, W. et al. Exterior validation of an ensemble mannequin for automated mammography interpretation by synthetic intelligence. JAMA Netw. Open 5, 2242343 (2022).
Google Scholar
Park, S. H. et al. Strategies for medical analysis of synthetic intelligence algorithms for medical analysis. Radiology 306, 20–31 (2023).
Google Scholar
Ahn, J. S. et al. Affiliation of synthetic intelligence-aided chest radiograph interpretation with reader efficiency and effectivity. JAMA Netw. Open 5, 2229289 (2022).
Google Scholar
Twilt, J. J. et al. AI-assisted vs unassisted identification of prostate most cancers in magnetic resonance pictures. JAMA Netw. Open 8, 2515672 (2025).
Google Scholar
Gommers, J. J. et al. Affect of AI determination help on radiologists’ efficiency and visible search in screening mammography. Radiology 316, 243688 (2025).
Google Scholar
Hunter, D. J. & Holmes, C. The place medical statistics meets synthetic intelligence. N. Engl. J. Med. 389, 1211–1219 (2023).
Google Scholar
Hwang, Y.-T. & Su, N.-C. Pattern measurement willpower for evaluating accuracies between two diagnostic checks below a paired design. Biom. J. 64, 771–804 (2022).
Google Scholar
Riesthuis, P., Otgaar, H. & Bücken, C. Able to ROC? A tutorial on simulation-based energy analyses for null speculation significance, minimum-effect, and equivalence testing for ROC curve analyses. Behav. Res. Strategies 57, 1–20 (2025).
Google Scholar
Jung, S.-H. A Dunnett-type check and its pattern measurement calculation for evaluating Okay ROC curves with a management. Diagnostics 14, 1813 (2024).
Google Scholar
Gómez-Flores, W., Gregorio-Calas, M. J. & de Albuquerque Pereira, W. C. BUS-BRA: a breast ultrasound dataset for assessing computer-aided analysis programs. Med. Phys. 51, 3110–3123 (2024).
Google Scholar
Li, Y. BUSI dataset with scanner machine augmentation. figshare (2025).
