Dataset Information

Feasibility of anomaly score detected with deep learning in irradiated breast cancer patients with reconstruction.

ABSTRACT: The aim of this study is to evaluate cosmetic outcomes of the reconstructed breast in breast cancer patients, using anomaly score (AS) detected by generative adversarial network (GAN) deep learning algorithm. A total of 251 normal breast images from patients who underwent breast-conserving surgery were used for training anomaly GAN network. GAN-based anomaly detection was used to calculate abnormalities as an AS, followed by standardization by using z-score. Then, we reviewed 61 breast cancer patients who underwent mastectomy followed by reconstruction with autologous tissue or tissue expander. All patients were treated with adjuvant radiation therapy (RT) after reconstruction and computed tomography (CT) was performed at three-time points with a regular follow-up; before RT (Pre-RT), one year after RT (Post-1Y), and two years after RT (Post-2Y). Compared to Pre-RT, Post-1Y and Post-2Y demonstrated higher AS, indicating more abnormal cosmetic outcomes (Pre-RT vs. Post-1Y, P = 0.015 and Pre-RT vs. Post-2Y, P = 0.011). Pre-RT AS was higher in patients having major breast complications (P = 0.016). Patients with autologous reconstruction showed lower AS than those with tissue expander both at Pre-RT (2.00 vs. 4.19, P = 0.008) and Post-2Y (2.89 vs. 5.00, P = 0.010). Linear mixed effect model revealed that days after baseline were associated with increased AS (P = 0.007). Also, tissue expander was associated with steeper rise of AS, compared to autologous tissue (P = 0.015). Fractionation regimen was not associated with the change of AS (P = 0.389). AS detected by deep learning might be feasible in predicting cosmetic outcomes of RT-treated patients with breast reconstruction. AS should be validated in prospective studies.

SUBMITTER: Kim DY

PROVIDER: S-EPMC9399246 | biostudies-literature | 2022 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Feasibility of anomaly score detected with deep learning in irradiated breast cancer patients with reconstruction.

Kim Dong-Yun DY Lee Soo Jin SJ Kim Eun-Kyu EK Kang Eunyoung E Heo Chan Yeong CY Jeong Jae Hoon JH Myung Yujin Y Kim In Ah IA Jang Bum-Sup BS

NPJ digital medicine 20220823 1

The aim of this study is to evaluate cosmetic outcomes of the reconstructed breast in breast cancer patients, using anomaly score (AS) detected by generative adversarial network (GAN) deep learning algorithm. A total of 251 normal breast images from patients who underwent breast-conserving surgery were used for training anomaly GAN network. GAN-based anomaly detection was used to calculate abnormalities as an AS, followed by standardization by using z-score. Then, we reviewed 61 breast cancer pa ...[more]

PMID: 35999451

Similar Datasets

Project description:Considering the rising prevalence of breast reconstruction followed by radiotherapy (RT), evaluating the cosmetic impact of RT is crucial. Currently, there are limited tools for objectively assessing cosmetic outcomes in patients who have undergone reconstruction. Therefore, we validated the cosmetic outcome using a previously developed anomaly Generative Adversarial Network (GAN)-based model and evaluated its utility. Between January 2016 and December 2020, we collected computed tomography (CT) images from 82 breast cancer patients who underwent immediate reconstruction surgery followed by radiotherapy. Among these patients, 38 received immediate implant insertion, while 44 underwent autologous breast reconstruction. Anomaly scores (AS) were estimated using an anomaly GAN model at pre-RT, 1st follow-up, 1-year (Post-1Y) and 2-year (Post-2Y) after RT. Subsequently, the scores were analyzed in a time-series manner, considering reconstruction types (implant versus autologous), RT techniques, and the incidence of major complications. The median age of the patients was 46 years (range 29-62). The AS between Post-1Y and Post-2Y demonstrated a positive relationship (coefficient 0.515, P < 0.001). The AS was significantly associated with objective cosmetic indices, namely Breast Contour Difference (P = 0.009) and Breast Area Difference (P = 0.004), at both Post-1Y and Post-2Y. Subgroup analysis stratified by type of breast reconstruction revealed significantly higher AS values in patients who underwent prosthetic implant insertion compared to those with autologous reconstruction at all follow-up time points (1st follow-up, P = 0.001; Post-1Y, P < 0.001; and Post-2Y, P < 0.001). A threshold AS of ≥ 1.9 was associated with a 10% predicted risk of developing major complications. The feasibility of an AS generated by a GAN model for predicting both cosmetic outcomes and the likelihood of complications following RT has been successfully validated. Further investigation involving a larger patient cohort is warranted.

Project description:BackgroundWe retrospectively evaluated the quality of deep learning (DL) reconstructions of on-scanner accelerated intraoperative MRI (iMRI) during respective brain tumor surgery.MethodsAccelerated iMRI was performed using dual surface coils positioned around the area of resection. A DL model was trained on the fastMRI neuro dataset to mimic the data from the iMRI protocol. The evaluation was performed on imaging material from 40 patients imaged from Nov 1, 2021, to June 1, 2023, who underwent iMRI during tumor resection surgery. A comparative analysis was conducted between the conventional compressed sense (CS) method and the trained DL reconstruction method. Blinded evaluation of multiple image quality metrics was performed by two neuroradiologists and one neurosurgeon using a 1-to-5 Likert scale (1, nondiagnostic; 2, poor; 3, acceptable; 4, good; and 5, excellent), and the favored reconstruction variant.ResultsThe DL reconstruction was strongly favored or favored over the CS reconstruction for 33/40, 39/40, and 8/40 of cases for readers 1, 2, and 3, respectively. For the evaluation metrics, the DL reconstructions had a higher score than their respective CS counterparts for 72%, 72%, and 14% of the cases for readers 1, 2, and 3, respectively. Still, the DL reconstructions exhibited shortcomings such as a striping artifact and reduced signal.ConclusionDL shows promise in allowing for high-quality reconstructions of iMRI. The neuroradiologists noted an improvement in the perceived spatial resolution, signal-to-noise ratio, diagnostic confidence, diagnostic conspicuity, and spatial resolution compared to CS, while the neurosurgeon preferred the CS reconstructions across all metrics.Relevance statementDL shows promise to allow for high-quality reconstructions of iMRI, however, due to the challenging setting of iMRI, further optimization is needed.Key pointsiMRI is a surgical tool with a challenging image setting. DL allowed for high-quality reconstructions of iMRI. Additional optimization is needed due to the challenging intraoperative setting.

Project description:BackgroundRadiotherapy before mastectomy and autologous free-flap breast reconstruction can avoid adverse radiation effects on healthy donor tissues and delays to adjuvant radiotherapy. However, evidence for this treatment sequence is sparse. We aimed to explore the feasibility of preoperative radiotherapy followed by skin-sparing mastectomy and deep inferior epigastric perforator (DIEP) flap reconstruction in patients with breast cancer requiring mastectomy.MethodsWe conducted a prospective, non-randomised, feasibility study at two National Health Service trusts in the UK. Eligible patients were women aged older than 18 years with a laboratory diagnosis of primary breast cancer requiring mastectomy and post-mastectomy radiotherapy, who were suitable for DIEP flap reconstruction. Preoperative radiotherapy started 3-4 weeks after neoadjuvant chemotherapy and was delivered to the breast, plus regional nodes as required, at 40 Gy in 15 fractions (over 3 weeks) or 42·72 Gy in 16 fractions (over 3·2 weeks). Adverse skin radiation toxicity was assessed preoperatively using the Radiation Therapy Oncology Group toxicity grading system. Skin-sparing mastectomy and DIEP flap reconstruction were planned for 2-6 weeks after completion of preoperative radiotherapy. The primary endpoint was the proportion of open breast wounds greater than 1 cm width requiring a dressing at 4 weeks after surgery, assessed in all participants. This study is registered with ClinicalTrials.gov, NCT02771938, and is closed to recruitment.FindingsBetween Jan 25, 2016, and Dec 11, 2017, 33 patients were enrolled. At 4 weeks after surgery, four (12·1%, 95% CI 3·4-28·2) of 33 patients had an open breast wound greater than 1 cm. One (3%) patient had confluent moist desquamation (grade 3). There were no serious treatment-related adverse events and no treatment-related deaths.InterpretationPreoperative radiotherapy followed by skin-sparing mastectomy and immediate DIEP flap reconstruction is feasible and technically safe, with rates of breast open wounds similar to those reported with post-mastectomy radiotherapy. A randomised trial comparing preoperative radiotherapy with post-mastectomy radiotherapy is required to precisely determine and compare surgical, oncological, and breast reconstruction outcomes, including quality of life.FundingCancer Research UK, National Institute for Health Research.

Project description:BackgroundIn 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.MethodsCTVs 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.ResultsThe 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.ConclusionsThe 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.

Project description:BackgroundRadiotherapy plays an essential role in the oncologic management of breast cancer. However, patients who undergo radiotherapy experience significantly more wound complications during the reconstructive process. Deferoxamine has immense potential to up-regulate angiogenesis and improve reconstructive outcomes. The purpose of this study was to determine the impact of deferoxamine on breast cancer cell proliferation in vitro, to delineate oncologic safety concerns regarding the use of deferoxamine as a regenerative therapeutic.MethodsThe dose-dependent effect of radiation and deferoxamine on two triple-negative breast cancer cell lines (MDA-MB-231 and MDA-MB-468) was determined by means of MTS (percentage cell viability) and tumorsphere (sphere number) analysis. Radiation therapy and deferoxamine were delivered both individually and in combination, and all experiments were completed in triplicate. Intracellular iron, nuclear factor-κB localization, and apoptosis/necrosis assays were performed to delineate mechanism. Analysis of variance statistical analysis was performed using SPSS (p < 0.05).ResultsFor both cell lines, percentage viability and sphere number significantly decreased following exposure to 10 Gy of radiation. Surprisingly, the administration of 25 µM deferoxamine also significantly decreased each metric. The administration of deferoxamine (100 µM) in combination with radiation (10 Gy) resulted in significantly reduced percentage viability and sphere number compared with the administration of radiation alone. Deferoxamine treatment decreased intracellular iron, suppressed nuclear factor-κB activation, and induced apoptosis.ConclusionRadiation and deferoxamine significantly decrease breast cancer proliferation when delivered independently and in combination, suggesting deferoxamine may be safely used to facilitate improved reconstructive outcomes among triple-negative breast cancer survivors.Clinical question/level of evidenceTherapeutic, V.

Dataset Information

Feasibility of anomaly score detected with deep learning in irradiated breast cancer patients with reconstruction.

Publications

Feasibility of anomaly score detected with deep learning in irradiated breast cancer patients with reconstruction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets