A Cox Nomogram for Assessing Recurrence Free Survival in Hepatocellular Carcinoma Following Surgical Resection Using Dynamic Contrast-Enhanced MRI Radiomics

BACKGROUND

The prognosis of hepatocellular carcinoma (HCC) is difficult to predict and carries high mortality. This study utilized radiomic techniques with clinical examinations to assess recurrence in HCC.

PURPOSE

To develop a Cox nomogram to assess the risk of postoperative recurrence in HCC using radiomic features of three volumes of interest (VOIs) in preoperative dynamic contrast-enhanced MRI (DCE-MRI), along with clinical findings.

STUDY TYPE

Retrospective.

SUBJECTS

249 patients with pathologically proven HCCs undergoing surgical resection at three institutions were selected.

FIELD STRENGTH/SEQUENCE

Fat saturated T2-weighted, Fat saturated T1-weighted, and DCE-MRI performed at 1.5 T and 3.0 T.

ASSESSMENT

Three VOIs were generated; the tumor VOI corresponds to the area from the tumor core to the outer perimeter of the tumor, the tumor +10 mm VOI represents the area from the tumor perimeter to 10 mm distal to the tumor in all directions, finally, the background liver parenchyma VOI represents the hepatic tissue outside the tumor. Three models were generated. The total radiomic model combined information from the three listed VOI's above. The clinical-radiological model combines physical examination findings with imaging characteristics such as tumor size, margin features, and metastasis. The combined radiomic model includes features from both models listed above and showed the highest reliability for assessing 24-month survival for HCC.

STATISTICAL TESTS

The least absolute shrinkage and selection operator (LASSO) Cox regression, univariable, and multivariable Cox regression, Kmeans clustering, and Kaplan-Meier analysis. The discrimination performance of each model was quantified by the C-index. A P value <0.05 was considered statistically significant.

RESULTS

The combined radiomic model, which included features from the radiomic VOI's and clinical imaging provided the highest performance (C-index: training cohort = 0.893, test cohort = 0.851, external cohort = 0.797) in assessing the survival of HCC.

CONCLUSION

The combined radiomic model provides superior ability to discern the possibility of recurrence-free survival in HCC over the total radiomic and the clinical-radiological models.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 2.

The SMART Framework: Selection of Machine learning Algorithms with ReplicaTions - a Case Study on the Microvascular Complications of Diabetes

Over 34 million people in the US have diabetes, a major cause of blindness, renal failure, and amputations. Machine learning (ML) models can predict high-risk patients to help prevent adverse outcomes. Selecting the 'best' prediction model for a given disease, population, and clinical application is challenging due to the hundreds of health-related ML models in the literature and the increasing availability of ML methodologies. To support this decision process, we developed the Selection of Machine-learning Algorithms with ReplicaTions (SMART) Framework that integrates building and selecting ML models with decision theory. We build ML models and estimate performance for multiple plausible future populations with a replicated nested cross-validation technique. We rank ML models by simulating decision-maker priorities, using a range of accuracy measures (e.g., AUC) and robustness metrics from decision theory (e.g., minimax Regret). We present the SMART Framework through a case study on the microvascular complications of diabetes using data from the ACCORD clinical trial. We compare selections made by risk-averse, -neutral, and -seeking decision-makers, finding agreement in 80% of the risk-averse and risk-neutral selections, with the risk-averse selections showing consistency for a given complication. We also found that the models that best predicted outcomes in the validation set were those with low performance variance on the testing set, indicating a risk-averse approach in model selection is ideal when there is a potential for high population feature variability. The SMART Framework is a powerful, interactive tool that incorporates various ML algorithms and stakeholder preferences, generalizable to new data and technological advancements.

A Robust Multi-Sensor Data Fusion Clustering Algorithm Based on Density Peaks

In this paper, a novel multi-sensor clustering algorithm, based on the density peaks clustering (DPC) algorithm, is proposed to address the multi-sensor data fusion (MSDF) problem. The MSDF problem is raised in the multi-sensor target detection (MSTD) context and corresponds to clustering observations of multiple sensors, without prior information on clutter. During the clustering process, the data points from the same sensor cannot be grouped into the same cluster, which is called the cannot link (CL) constraint; the size of each cluster should be within a certain range; and overlapping clusters (if any) must be divided into multiple clusters to satisfy the CL constraint. The simulation results confirm the validity and reliability of the proposed algorithm.

A Prediction-Based Spatial-Spectral Adaptive Hyperspectral Compressive Sensing Algorithm

In order to improve the performance of storage and transmission of massive hyperspectral data, a prediction-based spatial-spectral adaptive hyperspectral compressive sensing (PSSAHCS) algorithm is proposed. Firstly, the spatial block size of hyperspectral images is adaptively obtained according to the spatial self-correlation coefficient. Secondly, a k-means clustering algorithm is used to group the hyperspectral images. Thirdly, we use a local means and local standard deviations (LMLSD) algorithm to find the optimal image in the group as the key band, and the non-key bands in the group can be smoothed by linear prediction. Fourthly, the random Gaussian measurement matrix is used as the sampling matrix, and the discrete cosine transform (DCT) matrix serves as the sparse basis. Finally, the stagewise orthogonal matching pursuit (StOMP) is used to reconstruct the hyperspectral images. The experimental results show that the proposed PSSAHCS algorithm can achieve better evaluation results-the subjective evaluation, the peak signal-to-noise ratio, and the spatial autocorrelation coefficient in the spatial domain, and spectral curve comparison and correlation between spectra-reconstructed performance in the spectral domain-than those of single spectral compression sensing (SSCS), block hyperspectral compressive sensing (BHCS), and adaptive grouping distributed compressive sensing (AGDCS). PSSAHCS can not only compress and reconstruct hyperspectral images effectively, but also has strong denoise performance.