Machine Learning-Based Prediction of Pathological Responses and Prognosis After Neoadjuvant Chemotherapy for Non-Small-Cell Lung Cancer: A Retrospective Study.

BACKGROUND: Neoadjuvant chemotherapy has variable efficacy in patients with non-small-cell lung cancer (NSCLC), yet reliable noninvasive predictive markers are lacking. This study aimed to develop a radiomics model predicting pathological complete response and postneoadjuvant chemotherapy survival in NSCLC. MATERIALS AND METHODS: Retrospective data collection involved 130 patients with NSCLC who underwent neoadjuvant chemotherapy and surgery. Patients were randomly divided into training and independent testing sets. Nine radiomics features from prechemotherapy computed tomography (CT) images were extracted from intratumoral and peritumoral regions. An auto-encoder model was constructed, and its performance was evaluated. X-tile software classified patients into high and low-risk groups based on their predicted probabilities. survival of patients in different risk groups and the role of postoperative adjuvant chemotherapy were examined. RESULTS: The model demonstrated area under the receiver operating characteristic (ROC) curve of 0.874 (training set) and 0.876 (testing set). The larger the area under curve (AUC), the better the model performance. Calibration curve and decision curve analysis indicated excellent model calibration (Hosmer-Lemeshow test, P = .763, the higher the P-value, the better the model fit) and potential clinical applicability. Survival analysis revealed significant differences in overall survival (P = .011) and disease-free survival (P = .017) between different risk groups. Adjuvant chemotherapy significantly improved survival in the low-risk group (P = .041) but not high-risk group (P = 0.56). CONCLUSION: This study represents the first successful prediction of pathological complete response achievement after neoadjuvant chemotherapy for NSCLC, as well as the patients' survival, utilizing intratumoral and peritumoral radiomics features.

A nomogram for predicting liver metastasis in patients with gastric gastrointestinal stromal tumor.

BACKGROUND: Liver metastasis (LIM) is an important factor in the diagnosis, treatment, follow-up, and prognosis of patients with gastric gastrointestinal stromal tumor (GIST). There is no simple tool to assess the risk of LIM in patients with gastric GIST. Our aim was to develop and validate a nomogram to identify patients with gastric GIST at high risk of LIM. METHODS: Patient data diagnosed as having gastric GIST between 2010 and 2019 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided into training cohort and internal validation cohort in a 7:3 ratio. For external validation, retrospective data collection was performed on patients diagnosed as having gastric GIST at Yunnan Cancer Center (YNCC) between January 2015 and May 2023. Univariate and multivariate logistic regression analyses were used to identify independent risk factors associated with LIM in patients with gastric GIST. An individualized LIM nomogram specific for gastric GIST was formulated based on the multivariate logistic model; its discriminative performance, calibration, and clinical utility were evaluated. RESULTS: In the SEER database, a cohort of 2341 patients with gastric GIST was analyzed, of which 173 cases (7.39%) were found to have LIM; 239 patients with gastric GIST from the YNCC database were included, of which 25 (10.46%) had LIM. Multivariate analysis showed tumor size, tumor site, and sex were independent risk factors for LIM (P < .05). The nomogram based on the basic clinical characteristics of tumor size, tumor site, sex, and age demonstrated significant discrimination, with an area under the curve of 0.753 (95% CI, 0.692-0.814) and 0.836 (95% CI, 0.743-0.930) in the internal and external validation cohort, respectively. The Hosmer-Lemeshow test showed that the nomogram was well calibrated, whereas the decision curve analysis and the clinical impact plot demonstrated its clinical utility. CONCLUSION: Tumor size, tumor subsite, and sex were significantly correlated with the risk of LIM in gastric GIST. The nomogram for patients with GIST can effectively predict the individualized risk of LIM and contribute to the planning and decision making related to metastasis management in clinical practice.

Diversity Scaling Analysis of Chinese Gut Microbiomes Across Ethnicities and Lifestyles.

Diversity scaling (changes) of human gut microbiome is important because it measures the inter-individual heterogeneity of diversity and other important parameters of population-level diversity. Understanding the heterogeneity of microbial diversity can be used as a reference for the personalized medicine of microbiome-associated diseases. Similar to diversity per se, diversity scaling may also be influenced by host factors, especially lifestyles and ethnicities. Nevertheless, this important topic regarding Chinese populations has not been addressed, to our best knowledge. Here, we fill the gap by applying a recent extension to the classic species-area relationship (SAR), i.e., diversity-area relationship (DAR), to reanalyze a large dataset of Chinese gut microbiomes covering the seven biggest Chinese ethnic groups (covering > 95% Chinese) living rural and urban lifestyles. Four DAR profiles were constructed to investigate the diversity scaling, diversity overlap, potential maximal diversity, and the ratio of local to global diversity of Chinese gut microbiomes. We discovered the following: (i) The diversity scaling parameters (z) at various taxon levels are little affected by either ethnicity or lifestyles, as exhibited by less than 0.5% differences in pairwise comparisons. (ii) The maximal accrual diversity (potential diversity) exhibited difference in only about 5% of pairwise comparisons, and all of the differences occurred in ethnicity comparisons (i.e., lifestyles had no effects). (iii) Ethnicity seems to have stronger effects than lifestyles across all taxon levels, and this may reflect the reality that China has been experiencing rapid urbanization in the last few decades, while the ethnic-related genetic background may change relatively little during the same period.

Pretreatment Contrast-Enhanced Computed Tomography Radiomics for Prediction of Pathological Regression Following Neoadjuvant Chemotherapy in Locally Advanced Gastric Cancer: A Preliminary Multicenter Study.

BACKGROUND: Sensitivity to neoadjuvant chemotherapy in locally advanced gastric cancer patients varies; however, an effective predictive marker is currently lacking. We aimed to propose and validate a practical treatment efficacy prediction method based on contrast-enhanced computed tomography (CECT) radiomics. METHOD: Data of l24 locally advanced gastric carcinoma patients who underwent neoadjuvant chemotherapy were acquired retrospectively between December 2012 and August 2020 from three different cancer centers. In total, 1216 radiomics features were initially extracted from each lesion's pretreatment portal venous phase computed tomography image. Subsequently, a radiomics predictive model was constructed using machine learning software. Clinicopathological data and radiological parameters of the enrolled patients were collected and analyzed retrospectively. Univariate and multivariate logistic regression analyses were performed to screen for independent predictive indices. Finally, we developed an integrated model combining clinicopathological predictive parameters and radiomics features. RESULT: In the training set, 10 (14.9%) patients achieved a good response (GR) after preoperative neoadjuvant chemotherapy (n = 77), whereas in the testing set, seven (17.5%) patients achieved a GR (n = 47). The radiomics predictive model showed competitive prediction efficacy in both the training and independent external validation sets. The areas under the curve (AUC) values were 0.827 (95% confidence interval [CI]: 0.609-1.000) and 0.854 (95% CI: 0.610-1.000), respectively. Similarly, when only the single hospital data were included as an independent external validation set (testing set 2), AUC values of the models were 0.827 (95% CI: 0.650-0.952) and 0.889 (95% CI: 0.663-1.000) in the training set and testing set 2, respectively. CONCLUSION: Our study is the first to discover that CECT radiomics could provide powerful and consistent predictions of therapeutic sensitivity to neoadjuvant chemotherapy among gastric cancer patients across different hospitals.

Nomogram For The Prediction Of Malignancy In Small (8-20 mm) Indeterminate Solid Solitary Pulmonary Nodules In Chinese Populations.

PURPOSE: This study aimed to develop and validate a nomogram for predicting the malignancy of small (8-20 mm) solid indeterminate solitary pulmonary nodules (SPNs) in a Chinese population by using routine clinical and computed tomography data. METHODS: The prediction model was developed using a retrospective cohort that comprised 493 consecutive patients with small indeterminate SPNs who were treated between December 2012 and December 2016. The model was independently validated using a second retrospective cohort comprising 216 consecutive patients treated between January 2017 and May 2018. The investigated variables included patient characteristics (e.g., age and smoking history), nodule parameters (e.g., marginal spiculation and significant enhancement), and tumor biomarker levels (e.g., carcinoembryonic antigen). A prediction model was developed by using multivariable logistic regression analysis, and the model's performance was presented as a nomogram. The model was evaluated based on its discriminative ability, calibration, and clinical usefulness. RESULTS: The developed nomogram was ultimately based on age, marginal spiculation, significant enhancement, and pleural indentation. The Harrell concordance index values were 0.869 in the training cohort (95% confidence interval: 0.837-0.901) and 0.847 in the validation cohort (95% confidence interval: 0.792-0.902). The Hosmer-Lemeshow test revealed good calibration in each of the training and validation cohorts. Decision curve analysis confirmed that the nomogram was clinically useful (risk threshold from 0.10 to 0.85). CONCLUSION: Patient age, marginal spiculation, significant enhancement, and pleural indentation are independent predictors of malignancy in small indeterminate solid SPNs. The developed nomogram is easy-to-use and may allow the accurate prediction of malignancy in small indeterminate solid SPNs among Chinese patients.

Bladder PEComa: A case report and literature review.

The location of PEComa is rare in bladder, and the misdiagnosis rate is very high before operation.the characteristic of the bladder PEComa is that the CT is a round, elliptical or irregular cystic mass with a large volume, more than 5 cm or more, and the edge is clear. The solid part of the scanning tumor is obviously enhanced, and the rich blood supply artery and the drainage vein can be seen.

Role of CT scan in differentiating the type of colorectal cancer.

OBJECTIVES: Most colorectal cancers are classical adenocarcinomas (AC), and less frequent subtypes include mucinous adenocarcinomas (MAC) and signet-ring cell carcinomas (SC). The purpose of this study was to evaluate the computed tomography (CT) findings that can help to differentiate MAC and SC from AC. METHODS: CT scans of 168 patients with pathologically proven MAC and 67 patients with pathologically proven SC were analyzed, and 220 patients with classical AC were also included as a control group. CT findings of the three groups were compared and contrasted in terms of the bowel involvement patterns, contrast enhancement patterns, and presence or absence of bowel obstruction, intratumoral calcification, pericolic fat infiltration, and local tumor extension to adjacent organs. Statistical analyses were made by using the one-way analysis of variance, least significant difference test, and Pearson's chi-square test. RESULTS: Compared with classical AC, the MAC showed more severe (6.29±2.69 cm vs 4.57±1.74 cm, P<0.001) and higher percentage of occurrence of eccentric bowel-wall thickening (37.2% vs 11.5%, P<0.001). Heterogeneous contrast enhancement was most common in MAC (P<0.01), and MAC showed more areas with hypoattenuation (P<0.001). The presence of intratumoral calcification was most frequent in MAC (17.9% vs 2% vs 6.8%) (P<0.001); the SC also were more severe (5.75±2.28 cm vs 4.57±1.74 cm. P=0.001) than AC, but SC tend to show more cases of concentric even bowel-wall thickening (67.2%); homogeneous contrast enhancement was most common in SC (P<0.01), and it showed a target appearance. The presence of peritoneal seeding was most frequent in SC (35.8% vs 8% vs 2.7%, P<0.001), while the presence of regional lymph node metastasis (P=0.190) and direct invasion of adjacent organs or metastasis (P=0.323) were not significantly different among them. CONCLUSION: Some radiological features by CT can be used to classify different colon tumor types.

[Comparison of CT manifestations of primary colorectal mucinous adenocarcinoma and signet ring cell carcinoma].

OBJECTIVE: To compare the difference in CT manifestations between primary colorectal mucinous adenocarcinoma and signet ring cell carcinoma in order to improve radiologic diagnosis. METHODS: Clinicopathological data and CT findings of 109 patients with colorectal mucinous adenocarcinoma and 46 patients with primary colorectal signet-ring cell carcinoma confirmed by surgery and pathology from March 2008 to February 2015 in the Tumor Hospital of Yunnan Province were retrospectively collected. Differences in age, gender, tumor location, length and thickness of the involved intestinal wall, thickening pattern of the intestinal wall, lesion density, calcification, contrast-enhanced form, peri-intestinal invasion, occurrence of intestinal obstruction and metastasis of other organs were compared between the two groups. RESULTS: Among 109 patients with colorectal mucinous adenocarcinoma, 68 were men and 41 were women with a mean age of (56.8±15.4) years. Among 46 patients with primary colorectal signet-ring cell carcinoma, 26 were men and 20 were women with a mean age of (42.9±15.6) years. Compared with mucinous adenocarcinoma group, signet-ring cell carcinoma group showed more concentric bowel-wall thickening[93.5%(43/46) vs. 81.6%(89/109), χ2=9.19, P=0.030], higher lesion density [(42.0±3.0) Hu vs. (28.5±1.5) Hu, t=37.30, P=0.000], more marked enhancement [54.3%(25/46) vs. 12.8%(14/109), χ2=35.21, P=0.000], less vast-low-density region in enhanced CT imaging[2.2%(1/46) vs. 45.0%(49/109), χ2=73.31, P=0.000] and more severe peri-intestinal invasion [41.3% (19/46) vs. 17.4%(19/109), χ2=10.25, P=0.006]. Calcification was found in 18.3%(20/109) of mucinous adenocarcinoma cases, but was not found in signet-ring cell carcinoma cases (χ2=9.69, P=0.002). Target ring sign in contrast-enhanced scan was observed in 15.2%(7/46) of signet-ring cell carcinoma cases, while in none of mucinous adenocarcinoma cases (χ2=17.37, P=0.000). There were no statistically significant differences in lesion location, length and thickness of the involved intestinal wall, occurrence of intestinal obstruction, lymph node metastasis, liver or peritoneum metastasis between two groups(all P>0.05). CONCLUSIONS: Signet-ring cell carcinoma is often found in younger patients, whose CT manifestation is characterized by the target ring sign in contrast-enhanced scan, while primary colorectal mucinous adenocarcinoma is often in older patients, whose CT manifestation is characterized by calcification in unenhanced scan and low density region in enhanced CT show.

Genome-wide profiling of chemoradiation­induced changes in alternative splicing in colon cancer cells.

Alternative splicing is a key mechanism that regulates protein diversity and has been found to be associated with colon cancer progression and metastasis. However, the function of alternative splicing in chemoradiation­resistant colon cancer remains elusive. In this study, we constructed a chemoradiation­resistant colon cancer cell line. Through RNA-sequencing of normal and chemoradiation­resistant colon cancer cells (HCT116), we found 818 genes that were highly expressed in the normal HCT116 cells, whereas 285 genes were highly expressed in the chemoradiation-resistant HCT116 (RCR-HCT116) cells. Gene ontology (GO) analysis showed that genes that were highly expressed in the HCT116 cells were enriched in GO categories related to cell cycle and cell division, whereas genes that were highly expressed in the RCR-HCT116 cells were associated with regulation of system processes and response to wounding. Analysis of alternative splicing events revealed that exon skipping was significantly increased in the chemoradiation­resistant colon cancer cells. Moreover, we identified 323 alternative splicing events in 293 genes that were significantly different between the two different HCT116 cell types. These alternative splicing­related genes were clustered functionally into several groups related with DNA replication, such as deoxyribonucleotide metabolic/catabolic processes, response to DNA damage stimulus and helicase activity. These findings enriched our knowledge by elucidating the function of alternative splicing in chemoradiation-resistant colon cancer.

The CT and US features of Ewing's sarcoma/primary neuroectodermal tumor of the kidney: two case reports and review of literature.

Ewing's sarcoma/primary neuroectodermal tumor (EWS/PNET) is an extraordinarily rare primary tumor of the kidney with characteristic histology. To date, the imaging features of EWS/PNET have not been clearly described. Here, we report two cases of EWS/PNET confirmed by fine-needle aspiration biopsy and analyze the findings of computed tomography and ultrasound. The radiological features of EWS/PNET are presented along with a brief review of the pertinent literature to have a further understanding of EWS/PNET's imaging features.