Machine learning to differentiate small round cell malignant tumors and non-small round cell malignant tumors of the nasal and paranasal sinuses using apparent diffusion coefficient values

Objective We used radiomics feature–based machine learning classifiers of apparent diffusion coefficient (ADC) maps to differentiate small round cell malignant tumors (SRCMTs) and non-SRCMTs of the nasal and paranasal sinuses. Materials A total of 267 features were extracted from each region of interest (ROI). Datasets were randomized into two sets, a training set (∼70%) and a test set (∼30%). We performed dimensional reductions using the Pearson correlation coefficient and feature selection analyses (analysis of variance [ANOVA], relief, recursive feature elimination [RFE]) and classifications using 10 machine learning classifiers. Results were evaluated with a leave-one-out cross-validation analysis. Results We compared the AUC for all the pipelines in the validation dataset using FeAture Explorer (FAE) software. The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUCs with ten features. When the “one-standard error” rule was used, FAE produced a simpler model with eight features, including Perc.01%, Perc.10%, Perc.90%, Perc.99%, S(1,0) SumAverg, S(5,5) AngScMom, S(5,5) Correlat, and WavEnLH_s-2. The AUCs of the training, validation, and test datasets achieved 0.995, 0.902, and 0.710, respectively. For ANOVA, the pipeline with the auto-encoder classifier yielded the highest AUC using only one feature, Perc.10% (training/validation/test datasets: 0.886/0.895/0.809, respectively). For the relief, the AUCs of the training, validation, and test datasets that used the LRLasso classifier using five features (Perc.01%, Perc.10%, S(4,4) Correlat, S(5,0) SumAverg, S(5,0) Contrast) were 0.892, 0.886, and 0.787, respectively. Compared with the RFE and relief, the results of all algorithms of ANOVA feature selection were more stable with the AUC values higher than 0.800. Conclusions We demonstrated the feasibility of combining artificial intelligence with the radiomics from ADC values in the differential diagnosis of SRCMTs and non-SRCMTs and the potential of this non-invasive approach for clinical applications. Key Points • The parameter with the best diagnostic performance in differentiating SRCMTs from non-SRCMTs was the Perc.10% ADC value. • Results of all the algorithms of ANOVA feature selection were more stable and the AUCs were higher than 0.800, as compared with RFE and relief. • The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUC.

Diagnostic performance of apparent diffusion coefficient values for the differentiation of intrahepatic cholangiocarcinoma from gastrointestinal adenocarcinoma liver metastases

Background We aimed to investigate whether there is a difference between intrahepatic cholangiocarcinoma (IHCC) and liver metastases of gastrointestinal system (GIS) adenocarcinoma in terms of apparent diffusion coefficient (ADC) values. Patients and methods From January 2018 to January 2020, we retrospectively examined 64 consecutive patients with liver metastases due to gastrointestinal system adenocarcinomas and 13 consecutive IHCC in our hospital’s medical records. After exclusions, fifty-three patients with 53 liver metastases and 10 IHCC were included in our study. We divided the patients into two groups as IHCC and liver metastases of GIS adenocarcinoma. For mean apparent diffusion coefficient (ADCmean) values, the region of interests (ROI) was placed in solid portions of the lesions. ADCmean values of groups were compared. Results The mean age of IHCC group was 62.50 ± 13.49 and mean age of metastases group was 61.15 ± 9.18. ADCmean values were significantly higher in the IHCC group compared to the metastatic group (p < 0.001). ROC curves method showed high diagnostic accuracy (AUC = 0.879) with cut-off value of < 1178 x 10-6 mm2/s for ADCmean (Sensitivity = 90.57, Specificity = 70.0, positive predictive value [PPV] = 94.1, negative predictive value [NPV] = 58.3) in differentiating adenocarcinoma metastases from IHCC. Conclusions The present study results suggest that ADC values have a potential role for differentiation between IHCC and GIS adenocarcinoma liver metastases which may be valuable for patient management.

A Comparative Assessment of MR BI-RADS 4 Breast Lesions With Kaiser Score and Apparent Diffusion Coefficient Value

ObjectivesTo investigate the diagnostic performance of the Kaiser score and apparent diffusion coefficient (ADC) to differentiate Breast Imaging Reporting and Data System (BI-RADS) Category 4 lesions at dynamic contrast-enhanced (DCE) MRI.MethodsThis was a single-institution retrospective study of patients who underwent breast MRI from March 2020 to June 2021. All image data were acquired with a 3-T MRI system. Kaiser score of each lesion was assigned by an experienced breast radiologist. Kaiser score+ was determined by combining ADC and Kaiser score. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of Kaiser score+, Kaiser score, and ADC. The area under the curve (AUC) values were calculated and compared by using the Delong test. The differences in sensitivity and specificity between different indicators were determined by the McNemar test.ResultsThe study involved 243 women (mean age, 43.1 years; age range, 18–67 years) with 268 MR BI-RADS 4 lesions. Overall diagnostic performance for Kaiser score (AUC, 0.902) was significantly higher than for ADC (AUC, 0.81; p = 0.004). There were no significant differences in AUCs between Kaiser score and Kaiser score+ (p = 0.134). The Kaiser score was superior to ADC in avoiding unnecessary biopsies (p &lt; 0.001). Compared with the Kaiser score alone, the specificity of Kaiser score+ increased by 7.82%, however, at the price of a lower sensitivity.ConclusionFor MR BI-RADS category 4 breast lesions, the Kaiser score was superior to ADC mapping regarding the potential to avoid unnecessary biopsies. However, the combination of both indicators did not significantly contribute to breast cancer diagnosis of this subgroup.

Percent change in apparent diffusion coefficient and plasma EBV DNA after induction chemotherapy identifies distinct prognostic response phenotypes in advanced nasopharyngeal carcinoma

Background To evaluate the prognostic value of the apparent diffusion coefficient (ADC) derived from diffusion-weighted magnetic resonance imaging (MRI) and monitor the early treatment response to induction chemotherapy (IC) with plasma EBV DNA in locoregionally advanced nasopharyngeal carcinoma (LA-NPC). Results A total of 307 stage III-IVb NPC patients were prospectively enrolled. All patients underwent MRI examinations to calculate ADC and plasma EBV DNA measurements pretreatment and post-IC. The participants’ ADC value of 92.5% (284/307) increased post-IC. A higher percent change in ADC value (ΔADC%high group) post-IC was associated with a higher 5-year OS rate (90.7% vs 74.9%, p < 0.001) than those in the ΔADC%low group. Interestingly, ΔADC% was closely related to the response measured by RECIST 1.1 (p < 0.001) and plasma EBV DNA level (p = 0.037). The AUC significantly increased when post-IC plasma EBV DNA was added to ΔADC% to predict treatment failure. Thus, based on ΔADC% and plasma EBV DNA, we further divided the participants into three new prognostic response phenotypes (early response, intermediate response, and no response) that correlated with disparate risks of death (p = 0.001), disease progression (p < 0.001), distant metastasis (p < 0.001), and locoregional relapse (p < 0.001). Conclusion The percentage change in ADC post-IC is indicative of treatment response and clinical outcome. ΔADC% and plasma EBV DNA-based response phenotypes may provide potential utility for early termination of treatment and allow guiding risk-adapted therapeutic strategies for LA-NPC.