Value of contrast-enhanced CT based radiomic machine learning algorithm in differentiating gastrointestinal stromal tumors with KIT exon 11 mutation: a two-center study.

PURPOSE Knowing the genetic phenotype of gastrointestinal stromal tumors (GISTs) is essential for patients who receive therapy with tyrosine kinase inhibitors. The aim of this study was to develop a radiomic algorithm for predicting GISTs with KIT exon 11 mutation. METHODS We enrolled 106 patients (80 in the training set, 26 in the validation set) with clinicopathologically confirmed GISTs from two centers. Preoperative and postoperative clinical characteristics were selected and analyzed to construct the clinical model. Arterial phase, venous phase, delayed phase, and tri-phase combined radiomics algorithms were generated from the training set based on contrast-enhanced computed tomography (CE-CT) images. Various radiomics feature selection methods were used, namely least absolute shrinkage and selection operator (LASSO); minimum redundancy maximum relevance (mRMR); and generalized linear model (GLM) as a machine-learning classifier. Independent predictive factors were determined to construct preoperative and postoperative radiomics nomograms by multivariate logistic regression analysis. The performances of the clinical model, radiomics algorithm, and radiomics nomogram in distinguishing GISTs with the KIT exon 11 mutation were evaluated by area under the curve (AUC) of the receiver operating characteristics. RESULTS Of 106 patients who underwent genetic analysis, 61 had the KIT exon 11 mutation. The combined radiomics algorithm was found to be the best prediction model for differentiating the expression status of the KIT exon 11 mutation (AUC = 0.836; 95% confidence interval [CI], 0.640-0.951) in the validation set. The clinical model, and preoperative and postoperative radiomics nomograms had AUCs of 0.606 (95% CI, 0.397-0.790), 0.715 (95% CI, 0.506-0.873), and 0.679 (95% CI, 0.468-0.847), respectively, with the validation set. CONCLUSION The radiomics algorithm could distinguish GISTs with the KIT exon 11 mutation based on CE-CT images and could potentially be used for selective genetic analysis to support the precision medicine of GISTs.

A high-frequency linear ultrasonic array utilizing an interdigitally bonded 2-2 piezo-composite.

This paper describes the development of a high-frequency 256-element linear ultrasonic array utilizing an interdigitally bonded (IB) piezo-composite. Several IB composites were fabricated with different commercial and experimental piezoelectric ceramics and evaluated to determine a suitable formulation for use in high-frequency linear arrays. It was found that the fabricated fine-scale 2-2 IB composites outperformed 1-3 IB composites with identical pillar- and kerf-widths. This result was not expected and lead to the conclusion that dicing damage was likely the cause of the discrepancy. Ultimately, a 2-2 composite fabricated using a fine-grain piezoelectric ceramic was chosen for the array. The composite was manufactured using one IB operation in the azimuth direction to produce approximately 19-µm-wide pillars separated by 6-µm-wide kerfs. The array had a 50 µm (one wavelength in water) azimuth pitch, two matching layers, and 2 mm elevation length focused to 7.3 mm using a polymethylpentene (TPX) lens. The measured pulse-echo center frequency for a representative array element was 28 MHz and -6-dB bandwidth was 61%. The measured single-element transmit -6-dB directivity was estimated to be 50°. The measured insertion loss was 19 dB after compensating for the effects of attenuation and diffraction in the water bath. A fine-wire phantom was used to assess the lateral and axial resolution of the array when paired with a prototype system utilizing a 64-channel analog beamformer. The -6-dB lateral and axial resolutions were estimated to be 125 and 68 µm, respectively. An anechoic cyst phantom was also imaged to determine the minimum detectable spherical inclusion, and thus the 3-D resolution of the array and beamformer. The minimum anechoic cyst detected was approximately 300 µm in diameter.