ABSTRACT
Image segmentation of the liver is an important step in several treatments for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a deep learning model to segment the liver on T1w MR images. We sought to determine the best architecture by training, validating, and testing three different deep learning architectures using a total of 819 T1w MR images gathered from six different datasets, both publicly and internally available. Our experiments compared each architecture's testing performance when trained on data from the same dataset via 5-fold cross validation to its testing performance when trained on all other datasets. Models trained using nnUNet achieved mean Dice-Sorensen similarity coefficients > 90% when tested on each of the six datasets individually. The performance of these models suggests that an nnUNet liver segmentation model trained on a large and diverse collection of T1w MR images would be robust to potential changes in contrast protocol and disease etiology.
ABSTRACT
Background and Aims: Limited methods exist to accurately characterize the risk of malignant progression of liver lesions. Enhancement pattern mapping (EPM) measures voxel-based root mean square deviation (RMSD) of parenchyma and the contrast-to-noise (CNR) ratio enhances in malignant lesions. This study investigates the utilization of EPM to differentiate between HCC versus cirrhotic parenchyma with and without benign lesions. Methods: Patients with cirrhosis undergoing MRI surveillance were studied prospectively. Cases (n=48) were defined as patients with LI-RADS 3 and 4 lesions who developed HCC during surveillance. Controls (n=99) were patients with and without LI-RADS 3 and 4 lesions who did not develop HCC. Manual and automated EPM signals of liver parenchyma between cases and controls were quantitatively validated on an independent patient set using cross validation with manual methods avoiding parenchyma with artifacts or blood vessels. Results: With manual EPM, RMSD of 0.37 was identified as a cutoff for distinguishing lesions that progress to HCC from background parenchyma with and without lesions on pre-diagnostic scans (median time interval 6.8 months) with an area under the curve (AUC) of 0.83 (CI: 0.73-0.94) and a sensitivity, specificity, and accuracy of 0.65, 0.97, and 0.89, respectively. At the time of diagnostic scans, a sensitivity, specificity, and accuracy of 0.79, 0.93, and 0.88 were achieved with manual EPM with an AUC of 0.89 (CI: 0.82-0.96). EPM RMSD signals of background parenchyma that did not progress to HCC in cases and controls were similar (case EPM: 0.22 ± 0.08, control EPM: 0.22 ± 0.09, p=0.8). Automated EPM produced similar quantitative results and performance. Conclusion: With manual EPM, a cutoff of 0.37 identifies quantifiable differences between HCC cases and controls approximately six months prior to diagnosis of HCC with an accuracy of 89%.
Current surveillance and diagnostic methods in hepatocellular carcinoma are suboptimal. Enhancement pattern mapping is an imaging technique that quantifies lesion signals and may be useful in diagnostic and surveillance methods. Enhancement pattern mapping describes quantifiable differences between malignant and benign liver tissue on contrast-enhanced MRI. It amplifies lesion signal and distinguishes malignancy in a surveillance population. The novel imaging technique was investigated at single institution and analyzed lesions compared to cirrhotic parenchyma. Future efforts will include further risk stratification across LI-RADS group categories. The results provide evidence that enhancement pattern mapping uses available imaging data to distinguish hepatocellular carcinoma from non-cancerous parenchyma with and without benign lesions on scans six months prior to diagnosis with standard MRI. The technique introduces a prospective modality to improve diagnostic accuracy and early detection with the goal of improving clinical outcomes.
ABSTRACT
BACKGROUND: Outcomes after definitive chemoradiation for squamous cell carcinoma are generally favorable. However, biomarkers to further yield prognostic information are desired. Treatment-related lymphopenia as well as an elevated baseline neutrophil-lymphocyte ratio have been associated with worse survival in several cancer types. We evaluated absolute lymphocyte count and neutrophil-lymphocyte ratio at baseline and at treatment-related nadir in patients with anal cancer for associations with oncologic endpoints. METHODS: We conducted a retrospective analysis of 428 consecutive patients with non-metastatic anal cancer treated with definitive, intensity-modulated radiation therapy-based chemoradiation. We analyzed absolute neutrophil and lymphocyte counts at several timepoints: pretreatment, weekly during treatment, and in the six weeks following treatment completion. Neutrophil-lymphocyte ratio was calculated at baseline and treatment-related nadir. We estimated oncologic endpoints using life tables and compared them using the log-rank test. We conducted univariate and multivariable time-to-event analyses using Cox proportional hazards. RESULTS: Median absolute lymphocyte count at baseline and nadir were 1.80 [interquartile range (IQR), 1.45-2.32] k/µL and 0.26 (IQR, 0.18-0.36) k/µL, respectively, and 31% developed treatment-related grade 4 lymphopenia. Median neutrophil-lymphocyte ratio at baseline and nadir were 2.34 (IQR, 1.68-3.30) and 8.80 (IQR, 5.86-12.68), respectively. Estimates of overall survival, local failure-free survival, distant metastasis-free survival (DMFS), and freedom from colostomy at 5 years were 87%, 86%, 82%, and 88%, respectively. Baseline and nadir absolute lymphocyte count were not associated with selected outcomes on univariate analysis. On multivariable analysis, factors independently associated with death included T3-T4 disease, HIV-positive status, treatment break, and baseline neutrophil-lymphocyte ratio >3. Baseline neutrophil-lymphocyte ratio showed a trend toward association with distant progression or death (P=0.07). The 5-year overall survival estimates for patients with baseline neutrophil-lymphocyte ratios ≤3 and >3 were 92.3% and 80.6%, respectively. CONCLUSIONS: Lymphopenia during and after chemoradiation for anal cancer is common but does not appear to be associated with worse survival, recurrence, or metastases. However, elevated baseline neutrophil-lymphocyte ratio was independently associated with overall survival, local recurrence-free survival, and DMFS. Further studies are needed to determine the clinical utility of baseline neutrophil-lymphocyte ratio to guide treatment and follow-up.