Development and validation of the 3D U-Net algorithm for segmentation of pelvic lymph nodes on diffusion-weighted images

Application of Texture and Volume Model Analysis to Dedicated Axillary High-resolution 3D T2-weighted MR Imaging: A Novel Method for Diagnosing Lymph Node Metastasis in Patients with Clinically Node-negative Breast Cancer

PURPOSE

To evaluate the effectiveness of the texture analysis of axillary high-resolution 3D T2-weighted imaging (T2WI) in distinguishing positive and negative lymph node (LN) metastasis in patients with clinically node-negative breast cancer.

METHODS

Between December 2017 and May 2021, 242 consecutive patients underwent high-resolution 3D T2WI and were classified into the training (n = 160) and validation cohorts (n = 82). We performed manual 3D segmentation of all visible LNs in axillary level I to extract the texture features. As the additional parameters, the number of the LNs and the total volume of all LNs for each case were calculated. The least absolute shrinkage and selection operator algorithm and Random Forest were used to construct the models. We constructed the texture model using the features from the LN with the largest least axis length in the training cohort. Furthermore, we constructed the 3 models combining the selected texture features of the LN with the largest least axis length, the number of LNs, and the total volume of all LNs: texture-number model, texture-volume model, and texture-number-volume model. As a conventional method, we manually measured the largest cortical diameter. Moreover, we performed the receiver operating curve analysis in the validation cohort and compared area under the curves (AUCs) of the models.

RESULTS

The AUCs of the texture model, texture-number model, texture-volume model, texture-number-volume model, and conventional method in the validation cohort were 0.7677, 0.7403, 0.8129, 0.7448, and 0.6851, respectively. The AUC of the texture-volume model was higher than those of other models and conventional method. The sensitivity, specificity, positive predictive value, and negative predictive value of the texture-volume model were 90%, 69%, 49%, and 96%, respectively.

CONCLUSION

The texture-volume model of high-resolution 3D T2WI effectively distinguished positive and negative LN metastasis for patients with clinically node-negative breast cancer.

Can Machine Learning Models Detect and Predict Lymph Node Involvement in Prostate Cancer? A Comprehensive Systematic Review

(1) Background: Recently, Artificial Intelligence (AI)-based models have been investigated for lymph node involvement (LNI) detection and prediction in Prostate cancer (PCa) patients, in order to reduce surgical risks and improve patient outcomes. This review aims to gather and analyze the few studies available in the literature to examine their initial findings. (2) Methods: Two reviewers conducted independently a search of MEDLINE databases, identifying articles exploring AI's role in PCa LNI. Sixteen studies were selected, and their methodological quality was appraised using the Radiomics Quality Score. (3) Results: AI models in Magnetic Resonance Imaging (MRI)-based studies exhibited comparable LNI prediction accuracy to standard nomograms. Computed Tomography (CT)-based and Positron Emission Tomography (PET)-CT models demonstrated high diagnostic and prognostic results. (4) Conclusions: AI models showed promising results in LN metastasis prediction and detection in PCa patients. Limitations of the reviewed studies encompass retrospective design, non-standardization, manual segmentation, and limited studies and participants. Further research is crucial to enhance AI tools' effectiveness in this area.

Semiautomated pelvic lymph node treatment response evaluation for patients with advanced prostate cancer: based on MET-RADS-P guidelines

BACKGROUND

The evaluation of treatment response according to METastasis Reporting and Data System for Prostate Cancer (MET-RADS-P) criteria is an important but time-consuming task for patients with advanced prostate cancer (APC). A deep learning-based algorithm has the potential to assist with this assessment.

OBJECTIVE

To develop and evaluate a deep learning-based algorithm for semiautomated treatment response assessment of pelvic lymph nodes.

METHODS

A total of 162 patients who had undergone at least two scans for follow-up assessment after APC metastasis treatment were enrolled. A previously reported deep learning model was used to perform automated segmentation of pelvic lymph nodes. The performance of the deep learning algorithm was evaluated using the Dice similarity coefficient (DSC) and volumetric similarity (VS). The consistency of the short diameter measurement with the radiologist was evaluated using Bland-Altman plotting. Based on the segmentation of lymph nodes, the treatment response was assessed automatically with a rule-based program according to the MET-RADS-P criteria. Kappa statistics were used to assess the accuracy and consistency of the treatment response assessment by the deep learning model and two radiologists [attending radiologist (R1) and fellow radiologist (R2)].

RESULTS

The mean DSC and VS of the pelvic lymph node segmentation were 0.82 ± 0.09 and 0.88 ± 0.12, respectively. Bland-Altman plotting showed that most of the lymph node measurements were within the upper and lower limits of agreement (LOA). The accuracies of automated segmentation-based assessment were 0.92 (95% CI: 0.85-0.96), 0.91 (95% CI: 0.86-0.95) and 75% (95% CI: 0.46-0.92) for target lesions, nontarget lesions and nonpathological lesions, respectively. The consistency of treatment response assessment based on automated segmentation and manual segmentation was excellent for target lesions [K value: 0.92 (0.86-0.98)], good for nontarget lesions [0.82 (0.74-0.90)] and moderate for nonpathological lesions [0.71 (0.50-0.92)].

CONCLUSION

The deep learning-based semiautomated algorithm showed high accuracy for the treatment response assessment of pelvic lymph nodes and demonstrated comparable performance with radiologists.

Utility of diffusion weighted imaging-based radiomics nomogram to predict pelvic lymph nodes metastasis in prostate cancer

Background

Preoperative pelvic lymph node metastasis (PLNM) prediction can help clinicians determine whether to perform pelvic lymph node dissection (PLND). The purpose of this research is to explore the feasibility of diffusion-weighted imaging (DWI)-based radiomics for preoperative PLNM prediction in PCa patients at the nodal level.

Methods

The preoperative MR images of 1116 pathologically confirmed lymph nodes (LNs) from 84 PCa patients were enrolled. The subjects were divided into a primary cohort (67 patients with 192 positive and 716 negative LNs) and a held-out cohort (17 patients with 43 positive and 165 negative LNs) at a 4:1 ratio. Two preoperative pelvic lymph node metastasis (PLNM) prediction models were constructed based on automatic LN segmentation with quantitative radiological LN features alone (Model 1) and combining radiological and radiomics features (Model 2) via multiple logistic regression. The visual assessments of junior (Model 3) and senior (Model 4) radiologists were compared.

Results

No significant difference was found between the area under the curve (AUCs) of Models 1 and 2 (0.89 vs. 0.90; P = 0.573) in the held-out cohort. Model 2 showed the highest AUC (0.83, 95% CI 0.76, 0.89) for PLNM prediction in the LN subgroup with a short diameter ≤ 10 mm compared with Model 1 (0.78, 95% CI 0.70, 0.84), Model 3 (0.66, 95% CI 0.52, 0.77), and Model 4 (0.74, 95% CI 0.66, 0.88). The nomograms of Models 1 and 2 yielded C-index values of 0.804 and 0.910, respectively, in the held-out cohort. The C-index of the nomogram analysis (0.91) and decision curve analysis (DCA) curves confirmed the clinical usefulness and benefit of Model 2.

Conclusions

A DWI-based radiomics nomogram incorporating the LN radiomics signature with quantitative radiological features is promising for PLNM prediction in PCa patients, particularly for normal-sized LNM.