Improving Ultrasonic Testing by Using Machine Learning Framework Based on Model Interpretation Strategy

Ultrasonic testing(UT)is increasingly combined with machine learning(ML)techniques for intelligently identifying damage.Extracting signifcant features from UT data is essential for efcient defect characterization.Moreover,the hidden physics behind ML is unexplained,reducing the generalization capability and versatility of ML methods in UT.In this paper,a generally applicable ML framework based on the model interpretation strategy is proposed to improve the detection accuracy and computational efciency of UT.Firstly,multi-domain features are extracted from the UT signals with signal processing techniques to construct an initial feature space.Subsequently,a feature selection method based on model interpretable strategy(FS-MIS)is innovatively developed by integrating Shapley additive explanation(SHAP),flter method,embedded method and wrapper method.The most efective ML model and the optimal feature subset with better correlation to the target defects are determined self-adaptively.The proposed framework is validated by identifying and locating side-drilled holes(SDHs)with 0.5λcentral distance and different depths.An ultrasonic array probe is adopted to acquire FMC datasets from several aluminum alloy specimens containing two SDHs by experiments.The optimal feature subset selected by FS-MIS is set as the input of the chosen ML model to train and predict the times of arrival(ToAs)of the scattered waves emitted by adjacent SDHs.The experimental results demonstrate that the relative errors of the predicted ToAs are all below 3.67%with an average error of 0.25%,signifcantly improving the time resolution of UT signals.On this basis,the predicted ToAs are assigned to the corresponding original signals for decoupling overlapped pulse-echoes and reconstructing high-resolution FMC datasets.The imaging resolution is enhanced to 0.5λby implementing the total focusing method(TFM).The relative errors of hole depths and central distance are no more than 0.51%and 3.57%,respectively.Finally,the superior performance of the proposed FS-MIS is validated by comparing it with initial feature space and conventional dimensionality reduction techniques.

Resolution Enhancement in Ultrasonic TOFD Imaging by Combining Sparse Deconvolution and Synthetic Aperture Focusing Technique(Sparse-SAFT)

The shallow subsurface defects are difficult to be identified and quantified by ultrasonic time-of-flight diffraction(TOFD)due to the low resolution induced by pulse width and beam spreading.In this paper,Sparse-SAFT is proposed to improve the time resolution and lateral resolution in TOFD imaging by combining sparse deconvolution and synthetic aperture focusing technique(SAFT).The mathematical model in the frequency domain is established based on the l1 and l2 norm constraints,and the optimization problem is solved for enhancing time resolution.On this basis,SAFT is employed to improve lateral resolution by delay-and-sum beamforming.The simulated and experimental results indicate that the lateral wave and tip-diffracted waves can be decoupled with Sparse-SAFT.The shallow subsurface defects with a height of 3.0 mm at the depth of 3.0 mm were detected quantitatively,and the relative measurement errors of flaw heights and depths were no more than 10.3%.Compared to conventional SAFT,the time resolution and lateral resolution are enhanced by 72.5 and 56%with Sparse-SAFT,respectively.Finally,the proposed method is also suitable for improving resolution to detect the defects beyond dead zone.

TCR-mimic antibody-drug conjugates targeting intracellular tumor-specific mutant antigen KRAS G12V mutation

Limited clinical application of antibody-drug conjugates(ADCs)targeting tumor associated antigens(TAAs)is usually caused by on-target off-tumor side effect.Tumor-specific mutant antigens(TSMAs)only expressed in tumor cells which are ideal targets for ADCs.In addition,intracellular somatic mutant proteins can be presented on the cell surface by human leukocyte antigen class I(HLA I)molecules forming tumor-specific peptide/HLA I complexes.KRAS G12 V mutation frequently occurred in varied cancer and was verified as a promising target for cancer therapy.In this study,we generated two TCR-mimic antibodydrug conjugates(TCRm-ADCs),2E8-MMAE and 2 A5-MMAE,targeting KRAS G12 V/HLAA*0201 complex,which mediated specific antitumor activity in vitro and in vivo without obvious toxicity.Our findings are the first time validate the strategy of TCRm-ADCs targeting intracellular TSMAs,which improves the safety of antibody-based drugs and provides novel strategy for precision medicine in cancer therapy.

Updated prevalence of latent prostate cancer in Chinese population and comparison of biopsy results: An autopsy-based study

Prostate cancer detected by autopsy is named latent prostate cancer.As the repertoire of clinical prostate cancer,latent cancer may better reflect the disease burden.Unlike clinical prostate specimens,which are obtained exclusively from biopsy-positive cases,prostate specimens obtained through autopsy provide information on biopsy-negative cases,helping calculate the true sensitivity of prostate biopsy.From 2014 to 2021,we collected autopsy specimens of the prostate from body donors in China and performed transperineal and transrectal biopsies on specimens before step-sectioning and pathological measurements.We found that the crude prevalence of latent prostate cancer in middle-aged and elderly men was 35.1%(81/231),which was higher than previous estimates for Chinese populations.The overall per-patient sensitivities of transperineal and transrectal biopsies were not significantly different(33.3%vs.32.1%,p=0.82),but the two approaches differed in preferential sampling area along the proximal-distal axis of the prostate.Transperineal biopsy had a higher sensitivity for detecting clinically significant lesions in the distal third(34.7%vs.16.3%,p=0.02)and distal half(30.6%vs.18.1%,p=0.04),while transrectal biopsy had a higher sensitivity for lesions in the proximal half(25.0%vs.13.9%,p=0.046).Both transperineal and transrectal methods of biopsy missed most small lesions(<0.1 mL)and 35.3%(6/17)of large lesions(>0.5 mL).In conclusion,the prevalence of latent prostate cancer in China has increased over the past 2 decades.Systematic transperineal and transrectal methods of biopsy had comparable sensitivities but had different preferential sampling areas.Both approaches miss one-third of large lesions.

Emerging new therapeutic antibody derivatives for cancer treatment

Monoclonal antibodies constitute a promising class of targeted anticancer agents that enhance natural immune system functions to suppress cancer cell activity and eliminate cancer cells.The successful application of IgG monoclonal antibodies has inspired the development of various types of therapeutic antibodies,such as antibody fragments,bispecific antibodies,and antibody derivatives(e.g.,antibody-drug conjugates and immunocytokines).