In honor of Breast Cancer Awareness\nMonth, let\u2019s dive into three AI-powered solutions set to change the way we\ndetect, diagnose, and predict the disease. One deep-learning model is expected\nto someday identify risk of breast cancer up to five years into the future. <\/p>\n\n\n\n
Kinda makes Siri and Alexa\u2019s weather\nreports, Netflix updates, or reminders to pick up tacos a little\u2026well\u2026let\u2019s call\nit anticlimactic. <\/p>\n\n\n\n
1. Improved Early Breast Cancer<\/strong> Detection<\/strong><\/p>\n\n\n\n \u201cWomen with dense breasts are subject to the masking effect of mammographic density and its association with breast cancer risk. The objective of the DIMASOS 2 trial is to test whether combined mammography and ultrasound exams can improve early cancer detection and if this can feasibly and cost effectively be done in routine screening workflow,\u201d says Sylvia H. Heywang-K\u00f6brunner, MD, Head of Referenzzentrum Mammographie M\u00fcnchen (Reference Center Mammography Munich) and internationally recognized for her pioneering work in contrast-enhanced breast MRI and modern biopsy procedures.1<\/sup><\/p>\n\n\n\n The DIMASOS 2 trial is distinguished by its unique densitas densityai\u2122 software, developed by Densitas Inc, a leading provider of AI solutions for digital mammography.2<\/sup> The software, currently destined for about 24 clinics throughout Germany, will provide breast density measurements at point of care in order to identify women who would benefit from supplemental breast cancer screening. With standardized and reproducible patient-specific risk estimates\u00a0 \u2013 which would then flag a need for supplemental breast cancer screening \u2013 we may be able to significantly improve earlier breast cancer detection.\u00a0\u00a0 <\/p>\n\n\n\n The densitas densityai software delivers fully automated, standardized, and\nreproducible breast density assessments from standard DICOM clinical use\nmammograms. Results are generated by two distinct algorithms that decouple the\nbreast density assessment into quantitative and qualitative scales in alignment\nwith the ACR BI-RADS 4th<\/sup> and 5th<\/sup> edition density\nclassification system.1<\/sup><\/p>\n\n\n\n 2. Improved Breast Cancer<\/strong> Risk Prediction<\/strong><\/p>\n\n\n\n Researchers from the Massachusetts Institute of Technology (MIT) and Massachusetts General Hospital (MGH) believe they\u2019ve developed an advanced AI-powered tool to predict a woman\u2019s future risk of breast cancer, according to a new study published in Radiology<\/em>, May 2019.3<\/sup> <\/p>\n\n\n\n The ultimate hope, according to study lead author Adam Yala, a PhD candidate at MIT, is to tailor breast cancer screenings to individual women.4<\/sup> \u201cThere\u2019s much more information in a mammogram than just the four categories of breast density,\u201d Yala says. \u201cBy using the deep learning model, we learn subtle cues that are indicative of future cancer.\u201d<\/p>\n\n\n\n To find these \u201csubtle cues,\u201d the\nresearch team developed a deep learning (DL) model that uses full-field\nmammograms and traditional risk factors. Results thus far strongly suggest that\nthis DL model is more accurate than the\nTyrer-Cusick model (version 8), a current clinical standard.3<\/sup><\/p>\n\n\n\n Here are three key takeaway points reported in the Radiology <\/em>article:3<\/sup><\/p>\n\n\n\n 3. More Accurate Breast Cancer Diagnoses<\/strong> \u00a0<\/p>\n\n\n\n UCLA researchers are developing an AI system that may help pathologists read biopsies with greater accuracy \u2013 and thus result in better breast cancer detection and diagnoses. To test the system, described in a study published in JAMA Network Open, August, 2019, researchers compared system readings to independent diagnoses made by 87 practicing US pathologists. While the AI program nearly performed as well as human doctors in differentiating cancer from non-cancer cases, the AI program outperformed doctors when differentiating DCIS from atypia \u2013 considered the greatest challenge in breast cancer diagnosis.5<\/sup><\/p>\n\n\n\n The study\u2019s researchers feel positive\nthat AI can provide more accurate readings consistently \u2013 because by drawing\nfrom a large data set, the system will recognize patterns in the samples that\nare associated with cancer but are difficult for humans to see.<\/p>\n\n\n\n Quicker, consistent accuracy makes an\nenormous difference, explains Joann Elmore, MD, the study\u2019s senior author and a\nprofessor of medicine at the David Geffen School of Medicine at UCLA. \u201cIt is\ncritical to get a correct diagnosis from the beginning so that we can guide\npatients to the most effective treatments.\u201d<\/p>\n\n\n\n Despite all the OMG-ing and WOW-ing over how artificial intelligence will soon \u201cpersonalize\u201d a woman\u2019s breast screening, the issue of breast health and breast cancer rests between two humans \u2013 a doctor and a patient. In fact, AI\u2019s goal to \u201cpersonalize\u201d breast screening is about being able to apply huge amounts of data to one specific woman and then make sense of it all on an individual level. When it comes to taking that personalized data and pairing it with a personalized breast cancer treatment, that is still very much \u2013 and hopefully forever \u2013 the physician and patient\u2019s choice. <\/p>\n\n\n\n Resources <\/p>\n\n\n\n 1) Abdolell, M. (2019, September 18). Densitas Software Wins Procurement For DIMASOS Breast Screening Trial In Germany. <\/a><\/p>\n\n\n\n 2) Densitas. (n.d.).<\/a> <\/p>\n\n\n\n 3) Yala, A., MH, G., RK, R., J, T., Reiner, Collins, \u2026 Selvaraju RR. (2019, May 7). A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction. <\/a><\/p>\n\n\n\n