CT radiomics models are unable to predict new liver metastasis after successful thermal ablation of colorectal liver metastases.

BACKGROUND: Patients with colorectal liver metastases (CRLM) who undergo thermal ablation are at risk of developing new CRLM after ablation. Identification of these patients might enable individualized treatment. PURPOSE: To investigate whether an existing machine-learning model with radiomics features based on pre-ablation computed tomography (CT) images of patients with colorectal cancer can predict development of new CRLM. MATERIAL AND METHODS: In total, 94 patients with CRLM who were treated with thermal ablation were analyzed. Radiomics features were extracted from the healthy liver parenchyma of CT images in the portal venous phase, before thermal ablation. First, a previously developed radiomics model (Original model) was applied to the entire cohort to predict new CRLM after 6 and 24 months of follow-up. Next, new machine-learning models were developed (Radiomics, Clinical, and Combined), based on radiomics features, clinical features, or a combination of both. RESULTS: The external validation of the Original model reached an area under the curve (AUC) of 0.57 (95% confidence interval [CI]=0.56-0.58) and 0.52 (95% CI=0.51-0.53) for 6 and 24 months of follow-up. The new predictive radiomics models yielded a higher performance at 6 months compared to 24 months. For the prediction of CRLM at 6 months, the Combined model had slightly better performance (AUC=0.60; 95% CI=0.59-0.61) compared to the Radiomics and Clinical models (AUC=0.55-0.57), while all three models had a low performance for the prediction at 24 months (AUC=0.52-0.53). CONCLUSION: Both the Original and newly developed radiomics models were unable to predict new CLRM based on healthy liver parenchyma in patients who will undergo ablation for CRLM.

CT-based radiomics to distinguish progressive from stable neuroendocrine liver metastases treated with somatostatin analogues: an explorative study.

BACKGROUND: Accurate response evaluation in patients with neuroendocrine liver metastases (NELM) remains a challenge. Radiomics has shown promising results regarding response assessment. PURPOSE: To differentiate progressive (PD) from stable disease (SD) with radiomics in patients with NELM undergoing somatostatin analogue (SSA) treatment. MATERIAL AND METHODS: A total of 46 patients with histologically confirmed gastroenteropancreatic neuroendocrine tumors (GEP-NET) with ≥1 NELM and ≥2 computed tomography (CT) scans were included. Response was assessed with Response Evaluation Criteria in Solid Tumors (RECIST1.1). Hepatic target lesions were manually delineated and analyzed with radiomics. Radiomics features were extracted from each NELM on both arterial-phase (AP) and portal-venous-phase (PVP) CT. Multiple instance learning with regularized logistic regression via LASSO penalization (with threefold cross-validation) was used to classify response. Three models were computed: (i) AP model; (ii) PVP model; and (iii) AP + PVP model for a lesion-based and patient-based outcome. Next, clinical features were added to each model. RESULTS: In total, 19 (40%) patients had PD. Median follow-up was 13 months (range 1-50 months). Radiomics models could not accurately classify response (area under the curve 0.44-0.60). Adding clinical variables to the radiomics models did not significantly improve the performance of any model. CONCLUSION: Radiomics features were not able to accurately classify response of NELM on surveillance CT scans during SSA treatment.

Plasmacytoid transitional cell carcinoma of urinary bladder: a clinicopathologic study of 9 cases.

In this report, we summarized the clinicopathologic features of 9 cases of plasmacytoid transitional cell carcinoma (TCC) of the urinary bladder, a rare variant of TCC. All 9 patients were men with a mean of age 64.3 years (range, 46 to 81 y). All but 1 patient presented with gross hematuria; the remaining patient had urgency and microscopic hematuria. Cystoscopic findings revealed a dominant solid mass with surrounding multiple papillary lesions in 6 cases and multiple masslike lesions in 3 other cases. The initial diagnosis of plasmacytoid TCC was made on transurethral resection in 8 cases and cystoscopic biopsy in 1. One patient had TNM stage I disease, 2 had stage II disease, 3 had stage III disease, and 3 had stage IV disease. Four patients were treated by radical cystectomy with chemotherapy, 2 by radical cystectomy alone, 1 each by chemotherapy or intravesical bacillus Calmette-Guerin infusion alone, and 1 did not receive any further therapy. Microscopically, all tumors contained plasmacytoid cells, which composed 30% to 100% of the entire tumor. Eight of 9 cases were associated with high-grade TCC, and transitional cell carcinoma in situ was present in 4 cases. The plasmacytoid tumor cells were characterized by eccentrically located nuclei and abundant eosinophilic cytoplasm. Interestingly, plasmacytoid transitional cell carcinoma in situ was noted in 1 case. Immunohistochemical staining demonstrated that both plasmacytoid and conventional TCC components were positive for cytokeratins 7 and 20. The mean Ki-67 labeling index was 30% (range, 10% to 50%), and p53 expression in the majority of cases was low (5% to 10%), except for in 2 cases (70% and 80%). The mean follow-up in 8 patients was 24.5 months (range, 5 to 47 mo); the other patient was lost to follow-up. Five patients died of disease from 5 to 36 months, 2 patients were alive with disease at 30 and 47 months, and 1 patient was alive and well at 36 months with no evidence of disease. In summary, plasmacytoid TCC tends to present at an advanced stage and to have a poor prognosis. Morphologic recognition and distinction from other plasmacytoid malignant neoplasms is critical for its clinical management and immunohistochemical studies may be required for differential diagnosis.