Winter is over: The use of Artificial Intelligence to individualise radiation therapy for breast cancer

Poortmans, Philip; Takanen, Silvia; Marta, Gustavo Nader; Meattini, Icro; Kaidar‐Person, Orit

doi:10.1016/j.breast.2019.11.011

Cited by 32 publications

(18 citation statements)

References 88 publications

(116 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…31,[103][104][105] The ultimate aim is to achieve individualised, risk-adapted radiotherapy, combining a variety of biomarkers with novel applications of artificial intelligence. [106][107][108] Early breast cancer: systemic therapy…”

Section: Early Breast Cancer: Locoregional Therapymentioning

confidence: 99%

Breast cancer

et al. 2021

View full text Add to dashboard Cite

Breast cancer is still the most common cancer worldwide. But the way breast cancer is viewed has changed drastically since its molecular hallmarks were extensively characterised, now including immunohistochemical markers (eg, ER, PR, HER2 [ERBB2], and proliferation marker protein Ki-67 [MKI67]), genomic markers (eg, BRCA1, BRCA2, and PIK3CA), and immunomarkers (eg, tumour-infiltrating lymphocytes and PD-L1). New biomarker combinations are the basis for increasingly complex diagnostic algorithms. Neoadjuvant combination therapy, often including targeted agents, is a standard of care (especially in HER2-positive and triple-negative breast cancer), and the basis for de-escalation of surgery in the breast and axilla and for risk-adapted post-neoadjuvant strategies. Radiotherapy remains an important cornerstone of breast cancer therapy, but de-escalation schemes have become the standard of care. ER-positive tumours are treated with 5-10 years of endocrine therapy and chemotherapy, based on an individual risk assessment. For metastatic breast cancer, standard therapy options include targeted approaches such as CDK4 and CDK6 inhibitors, PI3K inhibitors, PARP inhibitors, and anti-PD-L1 immunotherapy, depending on tumour type and molecular profile. This range of treatment options reflects the complexity of breast cancer therapy today.

show abstract

Section: Early Breast Cancer: Locoregional Therapymentioning

confidence: 99%

Breast cancer

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Deep learning-based auto-segmentation has been widely investigated in head & neck, lung, and prostate cancers and has demonstrated clinically relevant impact with regard to saving time and mitigating inter-observer variability [23,24,34]. Although several studies have reported the feasibility of the deep learning-based approach for the breast, training and testing has only been performed for ipsilateral breast CTVs [35,36].…”

Section: Discussionmentioning

confidence: 99%

Clinical feasibility of deep learning-based auto-segmentation of target volumes and organs-at-risk in breast cancer patients after breast-conserving surgery

et al. 2021

View full text Add to dashboard Cite

Background In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical target volume (CTV) and organs-at-risk (OARs) segmentation for treatment planning increases physicians’ workload and inter-physician variability considerably. In this study, we evaluated the potential benefits of deep learning-based auto-segmented contours by comparing them to manually delineated contours for breast cancer patients. Methods CTVs for bilateral breasts, regional lymph nodes, and OARs (including the heart, lungs, esophagus, spinal cord, and thyroid) were manually delineated on planning computed tomography scans of 111 breast cancer patients who received breast-conserving surgery. Subsequently, a two-stage convolutional neural network algorithm was used. Quantitative metrics, including the Dice similarity coefficient (DSC) and 95% Hausdorff distance, and qualitative scoring by two panels from 10 institutions were used for analysis. Inter-observer variability and delineation time were assessed; furthermore, dose-volume histograms and dosimetric parameters were also analyzed using another set of patient data. Results The correlation between the auto-segmented and manual contours was acceptable for OARs, with a mean DSC higher than 0.80 for all OARs. In addition, the CTVs showed favorable results, with mean DSCs higher than 0.70 for all breast and regional lymph node CTVs. Furthermore, qualitative subjective scoring showed that the results were acceptable for all CTVs and OARs, with a median score of at least 8 (possible range: 0–10) for (1) the differences between manual and auto-segmented contours and (2) the extent to which auto-segmentation would assist physicians in clinical practice. The differences in dosimetric parameters between the auto-segmented and manual contours were minimal. Conclusions The feasibility of deep learning-based auto-segmentation in breast RT planning was demonstrated. Although deep learning-based auto-segmentation cannot be a substitute for radiation oncologists, it is a useful tool with excellent potential in assisting radiation oncologists in the future. Trial registration Retrospectively registered.

show abstract

“…An early diagnosis of breast cancer and appropriate risk analysis are crucial for the treatment of this disease and there are new studies reporting the use of big data and AI to achieve an earlier diagnosis of breast cancer (9). In the multidisciplinary treatment of breast cancer, in addition to experience-based medicine, AI technologies are now being developed in the fi elds of surgery, oncology and radiation oncology, to offer the patients the opportunities for personalized treatment (4,10,11).…”

Section: Introductionmentioning

confidence: 99%

National study on use of artificial intelligence in breast disease and cancer

Emiroğlu¹,

Esin²,

Erdogan³

et al. 2022

BLL

View full text Add to dashboard Cite

BACKGROUND: The aim of this study was to examine the thoughts, reservations, approaches and perspectives on the future of artifi cial intelligence (AI) held by physicians specializing in breast healthcare in our country. METHODS: Our survey was sent to the members of the Federation of Turkish Breast Disease Associations (MHDF) by e-mail. The survey investigates the attitudes towards the use of AI in breast disease and cancer, including demographic characteristics of the participants, their daily practice and approaches, and their stance on the future. RESULTS: The questionnaire was sent to a total of 1,890 people via e-mail. 108 (40.1 %) participants believed that the use of AI in breast disease would improve their fi eld of expertise moderately, 103 (38.3 %) expected this improvement to be considerable. 169 (70.3 %) respondents identifi ed 'rapid diagnosis' as the most important advantage of AI. 123 (45.7 %) participants considered concerns about potential medical errors and liability issues to be the most worrying aspects of AI. CONCLUSION: According to our study, the use of AI technology in the diagnosis and treatment of breast disease and cancer seems to be benefi cial for both physicians and patients. However, physicians have some concerns about possible medical errors and liability issues that AI might cause (Tab. 1, Ref. 25).

show abstract

Winter is over: The use of Artificial Intelligence to individualise radiation therapy for breast cancer

Cited by 32 publications

References 88 publications

Breast cancer

Breast cancer

Clinical feasibility of deep learning-based auto-segmentation of target volumes and organs-at-risk in breast cancer patients after breast-conserving surgery

National study on use of artificial intelligence in breast disease and cancer

Contact Info

Product

Resources

About