Dynamic Changes of Convolutional Neural Network-based Mammographic Breast Cancer Risk Score Among Women Undergoing Chemoprevention Treatment.
Dynamic Changes of Convolutional Neural Network-based Mammographic Breast Cancer Risk Score Among Women Undergoing Chemoprevention Treatment.
复制标题
DOI：
10.1016/j.clbc.2020.11.007
复制
发表时间：
2021-08
影响因子：
3.1
通讯作者：
Ha R
中科院分区：
文献类型：
--
作者：
Manley H;Mutasa S;Chang P;Desperito E;Crew K;Ha R
我们调查了我们的基于卷积神经网络的乳腺癌风险模型是否可以修改，方法是在接受了已知化学预防药物降低风险治疗的女性身上进行测试。与基线相比，治疗组中有更多的女性乳腺癌风险评分降低(P<；.01)，这表明我们的卷积神经网络风险模型在评估化学预防策略的有效性方面具有潜在的实用价值。我们调查了我们的基于卷积神经网络(CNN)的乳腺癌风险模型是否可以修改，方法是在接受了降低风险的化学预防治疗的女性身上进行测试。我们对2007-2015年间在我们机构被诊断为不典型增生、小叶原位癌或导管原位癌的患者进行了一项回顾性队列研究。从电子健康档案中提取临床特征、化学预防使用和乳房X光摄影图像。我们根据化学预防的使用情况将其分为两组。在基线和随后的后续评估中进行乳房X光检查，以输入我们的CNN风险模型。比较两组化疗预防组从基线到随访的风险评分变化。变化类别包括保持高风险、保持低风险、从低风险增加到高风险、从高风险减少到低风险。无序多分类回归模型用于统计分析，P<；0.05被认为具有统计学意义。在541例患者中，184例(34%)接受过化学预防治疗(第1组)，357例(66%)未接受化学预防治疗(第2组)。使用我们的CNN乳腺癌风险评分，与组2相比，组1的乳腺癌风险显著降低(33.7%比22.9%；P<；.01)。与第二组相比，第一组中患乳腺癌风险增加的女性明显更少(11.4%比20.2%；P<；.01)。在多变量分析中，我们的模型预测的乳腺癌风险增加与化学预防治疗的使用呈负相关(P=0.02)。我们基于CNN的乳腺癌风险评分是可以修改的，在评估已知化学预防药物的有效性和测试新的化学预防策略方面具有潜在的实用价值。
We investigated whether our convolutional neural network-based breast cancer risk model is modifiable by testing it on women who had undergone risk-reducing treatment with known chemoprevention agents. Compared with baseline, significantly more women in the treatment group had a decrease in the breast cancer risk score (P < .01), indicating that our convolutional neural network risk model is modifiable with potential utility in assessing the efficacy of chemoprevention strategies. We investigated whether our convolutional neural network (CNN)-based breast cancer risk model is modifiable by testing it on women who had undergone risk-reducing chemoprevention treatment. We conducted a retrospective cohort study of patients diagnosed with atypical hyperplasia, lobular carcinoma in situ, or ductal carcinoma in situ at our institution from 2007 to 2015. The clinical characteristics, chemoprevention use, and mammography images were extracted from the electronic health records. We classified two groups according to chemoprevention use. Mammograms were performed at baseline and subsequent follow-up evaluations for input to our CNN risk model. The 2 chemoprevention groups were compared for the risk score change from baseline to follow-up. The change categories included stayed high risk, stayed low risk, increased from low to high risk, and decreased from high to low risk. Unordered polytomous regression models were used for statistical analysis, with P < .05 considered statistically significant. Of 541 patients, 184 (34%) had undergone chemoprevention treatment (group 1) and 357 (66%) had not (group 2). Using our CNN breast cancer risk score, significantly more women in group 1 had shown a decrease in breast cancer risk compared with group 2 (33.7% vs. 22.9%; P < .01). Significantly fewer women in group 1 had an increase in breast cancer risk compared with group 2 (11.4% vs. 20.2%; P < .01). On multivariate analysis, an increase in breast cancer risk predicted by our model correlated negatively with the use of chemoprevention treatment (P = .02). Our CNN-based breast cancer risk score is modifiable with potential utility in assessing the efficacy of known chemoprevention agents and testing new chemoprevention strategies.
登录
查看更多内容
使用乳房X线图像数据区分卷积神经网络的机器学习方法，将非典型导管增生与导管癌区分开的精度。
DOI：
10.2214/ajr.18.20250
发表时间：
2019-05
期刊：
AJR. American journal of roentgenology
影响因子：
--
作者：
Ha R;Mutasa S;Sant EPV;Karcich J;Chin C;Liu MZ;Jambawalikar S
通讯作者：
Jambawalikar S
影响因子：
3.9
作者：
Roetzheim, Richard G.;Lee, Ji-Hyun;Kiluk, John V.
通讯作者：
Kiluk, John V.
影响因子：
3.3
作者：
Trivedi, Meghna S.;Coe, Austin M.;Crew, Katherine D.
通讯作者：
Crew, Katherine D.
影响因子：
0.9
作者：
Reimers, Laura;Crew, Katherine D
通讯作者：
Crew, Katherine D
影响因子：
5.9
作者：
Mullooly, Maeve;Bejnordi, Babak Ehteshami;Gierach, Gretchen L.
通讯作者：
Gierach, Gretchen L.