Objective The study aimed to develop a machine learning(ML)-coupled interpretable radiomics signature to predict the pathological status of non-palpable suspicious breast microcalcifications(MCs).Methods We enrolled 4...Objective The study aimed to develop a machine learning(ML)-coupled interpretable radiomics signature to predict the pathological status of non-palpable suspicious breast microcalcifications(MCs).Methods We enrolled 463 digital mammographical view images from 260 consecutive patients detected with non-palpable MCs and BI-RADS scored at 4(training cohort,n=428;independent testing cohort,n=35)in the First Affiliated Hospital of Nanjing Medical University between September 2010 and January 2019.Subsequently,837 textures and 9 shape features were subsequently extracted from each view and finally selected by an XGBoostembedded recursive feature elimination technique(RFE),followed by four machine learning-based classifiers to build the radiomics signature.Results Ten radiomic features constituted a malignancy-related signature for breast MCs as logistic regression(LR)and support vector machine(SVM)yielded better positive predictive value(PPV)/sensitivity(SE),0.904(95%CI,0.865–0.949)/0.946(95%CI,0.929–0.977)and 0.891(95%CI,0.822–0.939)/0.939(95%CI,0.907–0.973)respectively,outperforming their negative predictive value(NPV)/specificity(SP)from 10-fold crossvalidation(10FCV)of the training cohort.The optimal prognostic model was obtained by SVM with an area under the curve(AUC)of 0.906(95%CI,0.834–0.969)and accuracy(ACC)0.787(95%CI,0.680–0.855)from 10FCV against AUC 0.810(95%CI,0.760–0.960)and ACC 0.800 from the testing cohort.Conclusion The proposed radiomics signature dependens on a set of ML-based advanced computational algorithms and is expected to identify pathologically cancerous cases from mammographically undecipherable MCs and thus offer prospective clinical diagnostic guidance.展开更多
In this work,we propose the possible assignment of the newly observed X(2239),as well asη(2225),as a molecular state from the interaction of a baryonΛand an antibaryonΛ¯.With the help of effective Lagrangians,...In this work,we propose the possible assignment of the newly observed X(2239),as well asη(2225),as a molecular state from the interaction of a baryonΛand an antibaryonΛ¯.With the help of effective Lagrangians,theΛΛ¯interaction is described within the one-boson-exchange model withη,η′,ω,ϕ,andσexchanges considered.After inserting the potential kernel into the quasipotential Bethe-Salpeter equation,the bound states from theΛΛ¯interaction can be studied by searching for the pole of the scattering amplitude.Two loosely bound states with spin parities IG(JPC)=0+(0−+)and 0−(1−−)appear near the threshold with almost the same parameter.The 0−(1−−)state can be assigned to X(2239)observed at BESⅢ,which is very close to theΛΛ¯threshold.The scalar mesonη(2225)can be interpreted as a 0+(0−+)state from theΛΛ¯interaction.The annihilation effect is also discussed through a coupled-channel calculation plus a phenomenological optical potential.It provides large widths to two bound states produced from theΛΛ¯interaction.The mass of the 1−state is slightly larger than the mass of the 0−state after including the annihilation effect,which is consistent with our assignment of these two states as X(2239)andη(2225),respectively.The results suggest that further investigation is required to understand the structures near theΛΛ¯threshold,such as X(2239),η(2225),and X(2175).展开更多
基金supported in part by the State’s Key Project of Research and Development Plan(Grant Nos.2017YFC0109202 and 2017YFA0104302)in part by the National Natural Science Foundation(Grant No.61871117)in part by Science and Technology Program of Guangdong(Grant No.2018B030333001).
文摘Objective The study aimed to develop a machine learning(ML)-coupled interpretable radiomics signature to predict the pathological status of non-palpable suspicious breast microcalcifications(MCs).Methods We enrolled 463 digital mammographical view images from 260 consecutive patients detected with non-palpable MCs and BI-RADS scored at 4(training cohort,n=428;independent testing cohort,n=35)in the First Affiliated Hospital of Nanjing Medical University between September 2010 and January 2019.Subsequently,837 textures and 9 shape features were subsequently extracted from each view and finally selected by an XGBoostembedded recursive feature elimination technique(RFE),followed by four machine learning-based classifiers to build the radiomics signature.Results Ten radiomic features constituted a malignancy-related signature for breast MCs as logistic regression(LR)and support vector machine(SVM)yielded better positive predictive value(PPV)/sensitivity(SE),0.904(95%CI,0.865–0.949)/0.946(95%CI,0.929–0.977)and 0.891(95%CI,0.822–0.939)/0.939(95%CI,0.907–0.973)respectively,outperforming their negative predictive value(NPV)/specificity(SP)from 10-fold crossvalidation(10FCV)of the training cohort.The optimal prognostic model was obtained by SVM with an area under the curve(AUC)of 0.906(95%CI,0.834–0.969)and accuracy(ACC)0.787(95%CI,0.680–0.855)from 10FCV against AUC 0.810(95%CI,0.760–0.960)and ACC 0.800 from the testing cohort.Conclusion The proposed radiomics signature dependens on a set of ML-based advanced computational algorithms and is expected to identify pathologically cancerous cases from mammographically undecipherable MCs and thus offer prospective clinical diagnostic guidance.
基金*Supported by the National Natural Science Foundation of China(11675228,11775050,61871124),the Fundamental Research Funds for the Central Universities,the national defense Pre-Research foundation of China,by State Key Laboratory of Acoustics,Chinese Academy of Sciences(SKLA201604),Science and Technology on Sonar Laboratory,the Stable Supporting Fund of Acoustic Science and Technology Laboratory。
文摘In this work,we propose the possible assignment of the newly observed X(2239),as well asη(2225),as a molecular state from the interaction of a baryonΛand an antibaryonΛ¯.With the help of effective Lagrangians,theΛΛ¯interaction is described within the one-boson-exchange model withη,η′,ω,ϕ,andσexchanges considered.After inserting the potential kernel into the quasipotential Bethe-Salpeter equation,the bound states from theΛΛ¯interaction can be studied by searching for the pole of the scattering amplitude.Two loosely bound states with spin parities IG(JPC)=0+(0−+)and 0−(1−−)appear near the threshold with almost the same parameter.The 0−(1−−)state can be assigned to X(2239)observed at BESⅢ,which is very close to theΛΛ¯threshold.The scalar mesonη(2225)can be interpreted as a 0+(0−+)state from theΛΛ¯interaction.The annihilation effect is also discussed through a coupled-channel calculation plus a phenomenological optical potential.It provides large widths to two bound states produced from theΛΛ¯interaction.The mass of the 1−state is slightly larger than the mass of the 0−state after including the annihilation effect,which is consistent with our assignment of these two states as X(2239)andη(2225),respectively.The results suggest that further investigation is required to understand the structures near theΛΛ¯threshold,such as X(2239),η(2225),and X(2175).