AI and HealthCare, Author Interviews, Brain Cancer - Brain Tumors, Lancet, Mammograms / 30.01.2026
AI-Supported Mammography Screening Showed Consistently More Favourable outcomes Compared with Standard Screening
MedicalResearch.com Interview with:
[caption id="attachment_72182" align="alignleft" width="200"]
Dr. Lång[/caption]
Kristina Lång MD PhD
Associate professor, Diagnostic Radiology
Translational Medicine, Lund University
Senior consultant, Unilabs Mammography Unit
Skåne University Hospital, Malmö, Sweden
MedicalResearch.com: What is the background for this study?
Response: Prior to the start of the trial, several retrospective studies had shown that AI could discriminate between screening mammograms at low and high risk of cancer, with performance comparable to that of average breast radiologists. These findings suggested a potential to improve both the efficiency and sensitivity of mammography screening. This motivated us to design and evaluate an AI-supported screening procedure in a randomised controlled trial. The MASAI trial was among the first prospective studies in this field and, to date, remains the only randomised trial with reported results on the use of AI in breast cancer screening.
In European breast cancer screening programmes, every mammogram is usually read by two radiologists, so called double reading, to ensure a high sensitivity. In the MASAI trial we compared AI-supported mammography screening to standard double reading without AI. I
n the AI-supported approach, mammograms identified as low-risk by the AI were read by a single radiologist, while high-risk mammograms underwent double reading, with AI providing additional detection support.
Dr. Lång[/caption]
Kristina Lång MD PhD
Associate professor, Diagnostic Radiology
Translational Medicine, Lund University
Senior consultant, Unilabs Mammography Unit
Skåne University Hospital, Malmö, Sweden
MedicalResearch.com: What is the background for this study?
Response: Prior to the start of the trial, several retrospective studies had shown that AI could discriminate between screening mammograms at low and high risk of cancer, with performance comparable to that of average breast radiologists. These findings suggested a potential to improve both the efficiency and sensitivity of mammography screening. This motivated us to design and evaluate an AI-supported screening procedure in a randomised controlled trial. The MASAI trial was among the first prospective studies in this field and, to date, remains the only randomised trial with reported results on the use of AI in breast cancer screening.
In European breast cancer screening programmes, every mammogram is usually read by two radiologists, so called double reading, to ensure a high sensitivity. In the MASAI trial we compared AI-supported mammography screening to standard double reading without AI. I
n the AI-supported approach, mammograms identified as low-risk by the AI were read by a single radiologist, while high-risk mammograms underwent double reading, with AI providing additional detection support.
Dr. Wayne Furman[/caption]
Wayne L. Furman, MD
Department of Oncology
Jude Children's Research Hospital
Memphis, TN 38105-3678
MedicalResearch.com: What is the background for this study? What are the main findings?
Dr. Furman: Despite improvement in 2-yr EFS from 46% to 66% with the inclusion of dinutuximab, a monoclonal antibody that recognizes a glycoprotein on neuroblasts called ‘GD2’ (disialoganglioside), more than one-third of children with high-risk neuroblastoma still are not cured. Therefore novel therapeutic approaches are needed for this subset of patients. The clinical evaluation of various anti-GD 2 monoclonal antibodies in children with neuroblastoma has been exclusively focused on treatment of patients after recovery from consolidation, in a state of ‘minimal residual disease’. This is because traditionally chemotherapy has been thought to be too immunosuppressive to combine with monoclonal antibodies. However recent studies suggest, even in the setting of “bulky” solid tumors, the combination of chemotherapy with monoclonal antibodies can enhance the effectiveness of the antibodies. First, chemotherapy can increase the efficacy of antibodies by depleting cells of the immune system that suppress immune function. Also chemotherapy-induced tumor cell death can trigger tumor antigen release, uptake by antigen processing cells and an enhanced antitumor immune response. There is also data that anti-GD2 monoclonal antibodies can suppress tumor cell growth independent of immune system involvement. Furthermore anti-GD2 monoclonal antibodies and chemotherapy have non-overlapping toxicities. All of these reasons were good reasons to evaluate the addition of a novel anti-GD2 monoclonal antibody, called hu14.18K322A, to chemotherapy, outside the setting of minimal residual disease, in children with newly diagnosed children with high-risk neuroblastoma.
Dr. Katarina Truvé[/caption]
Katarina Truvé PhD
Swedish University of Agricultural Sciences and
Kerstin Lindblad-Toh
Uppsala University
MedicalResearch.com: What is the background for this study? What are the main findings?
Dr. Truvé: Gliomas are malignant brain tumors that are rarely curable. These tumors occur with similar frequencies in both dogs and humans. Gliomas in dogs are strikingly similar at the biological and imaging level to human tumor counterparts. Some dog breeds such as Boxer and Bulldog are at considerably higher risk of developing glioma. Since these breeds at high risk are recently related, they are most likely carrying shared genetic risk factors. Our goal was therefore to use the dog genome to locate genes that may be involved in the development of glioma in both dogs and humans. We found a strongly associated locus and identified three candidate genes, DENR, P2RX7 and CAMKK2 in the genomic region. We have shown that CAMKK2 is lower expressed in glioma tumors than normal tissue in both dogs and human, and it has been reported that the associated canine mutation in P2RX7 results in a decrease in receptor function.
Dr. Roger Stupp[/caption]
MedicalResearch.com Interview with:
Roger Stupp, MD
Professor & Chairman
Department of Oncology & Cancer Center
University of Zurich & University Hospital Zurich (USZ)
Zürich / Switzerland
Medical Research: What is the background for this study?
Dr. Stupp: Tumor Treating Fields are an entirely novel modality in cancer treatment. Over 10 years ago researchers demonstrated that alternating electrical fields will block cell growth, interfere with organelle assembly, in particular perturb the spindle apparatus and cell division, all leading to mitotic arrest and ultimately apoptosis. This was shown in vitro, but importantly also in vivo animal models including not only mice and rats, but also hamsters and rabbits with deep seated solid tumours. So the question was whether we can demonstrate such an effect also in the clinic.
Glioblastoma are locally invasive and aggressive tumours in the brain. They usually do not metastasise however they grow diffusely within the CNS and despite the best possible surgery, radiation and chemotherapy virtually always recur. We thus applied alternating electrical fields therapy, so called Tumor Treating Fields to the scalp of patients with newly diagnosed glioblastoma. After the end of standard chemoradiotherapy (TMZ/RT), patients were randomized to receive either standard maintenance TMZ-chemotherapy alone or in combination with TTFields. Almost 700 patients were randomized, here we report on a preplanned interim analysis looking at the first 315 patients included once they were followed for at least 18 months. The data on the first 315 patients are mature and allowed the IDMC to conclude that the trial should be stopped and the results made available.
Medical Research: What are the main findings?
Dr. Stupp: The study demonstrated a consistent prolongation of both progression-free and also of overall survival for patients who have been treated with TTFields in addition to standard therapy. The median progression-free survival and overall survival were prolonged by 3 months, translating to an absolute increase in overall survival at 2 years of 14%, from 29% to 43%. Or a hazard ratio of 0.74 for overall survival and of 0.62 for progression-free survival.
