A deep-learning radiomics-based lymph node metastasis predictive model for pancreatic cancer: a diagnostic study

Development and validation of a preoperative radiomics-based nomogram to identify patients who can benefit from splenic hilar lymphadenectomy: a pooled analysis of three prospective trials

BACKGROUND

The authors aimed to use preoperative computed tomography images to develop a radiomic nomogram to select patients who would benefit from spleen-preserving splenic hilar (No.10) lymphadenectomy (SPSHL).

METHODS

A pooled analysis of three distinct prospective studies was performed. The splenic hilar lymph node (SHLN) ratio (sLNR) was established as the quotient of the number of metastatic SHLN to the total number of SHLN. Radiomic features reflecting the phenotypes of the primary tumor (RS1) and SHLN region (RS2) were extracted and used as predictive factors for sLNR.

RESULTS

This study included 733 patients: 301 in the D2 group and 432 in the D2+No.10 group. The optimal sLNR cutoff value was set at 0.4, and the D2+No.10 group was divided into three groups: sLNR=0, sLNR ≤0.4, and sLNR >0.4. Patients in the D2+No. 10 group were randomly divided into the training ( n =302) and validation ( n =130) cohorts. The AUCs value of the nomogram, including RS1 and RS2, were 0.952 in the training cohort and 0.888 in the validation cohort. The entire cohort was divided into three groups based on the nomogram scores: low, moderate, and high SHLN metastasis burden groups (LMB, MMB, and HMB, respectively). A similar 5-year OS rate was found between the D2 and D2+No. 10 groups in the LMB and HMB groups. In the MMB group, the 5-year OS of the D2+No. 10 group (73.4%) was significantly higher than that of the D2 group (37.6%) ( P <0.001).

CONCLUSIONS

The nomogram showed good predictive ability for distinguishing patients with various SHLN metastasis burdens. It can accurately identify patients who would benefit from SPSHL.

Noninvasive prediction of lymph node metastasis in pancreatic cancer using an ultrasound-based clinicoradiomics machine learning model

OBJECTIVES

This study was designed to explore and validate the value of different machine learning models based on ultrasound image-omics features in the preoperative diagnosis of lymph node metastasis in pancreatic cancer (PC).

METHODS

This research involved 189 individuals diagnosed with PC confirmed by surgical pathology (training cohort: n = 151; test cohort: n = 38), including 50 cases of lymph node metastasis. Image-omics features were extracted from ultrasound images. After dimensionality reduction and screening, eight machine learning algorithms, including logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), extra trees (ET), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP), were used to establish image-omics models to predict lymph node metastasis in PC. The best omics prediction model was selected through ROC curve analysis. Machine learning models were used to analyze clinical features and determine variables to establish a clinical model. A combined model was constructed by combining ultrasound image-omics and clinical features. Decision curve analysis (DCA) and a nomogram were used to evaluate the clinical application value of the model.

RESULTS

A total of 1561 image-omics features were extracted from ultrasound images. 15 valuable image-omics features were determined by regularization, dimension reduction, and algorithm selection. In the image-omics model, the LR model showed higher prediction efficiency and robustness, with an area under the ROC curve (AUC) of 0.773 in the training set and an AUC of 0.850 in the test set. The clinical model constructed by the boundary of lesions in ultrasound images and the clinical feature CA199 (AUC = 0.875). The combined model had the best prediction performance, with an AUC of 0.872 in the training set and 0.918 in the test set. The combined model showed better clinical benefit according to DCA, and the nomogram score provided clinical prediction solutions.

CONCLUSION

The combined model established with clinical features has good diagnostic ability and can be used to predict lymph node metastasis in patients with PC. It is expected to provide an effective noninvasive method for clinical decision-making, thereby improving the diagnosis and treatment of PC.

Application of radiomics for preoperative prediction of lymph node metastasis in colorectal cancer: a systematic review and meta-analysis

BACKGROUND

Colorectal cancer (CRC) stands as the third most prevalent cancer globally, projecting 3.2 million new cases and 1.6 million deaths by 2040. Accurate lymph node metastasis (LNM) detection is critical for determining optimal surgical approaches, including preoperative neoadjuvant chemoradiotherapy and surgery, which significantly influence CRC prognosis. However, conventional imaging lacks adequate precision, prompting exploration into radiomics, which addresses this shortfall by converting medical images into reproducible, quantitative data.

METHODS

Following PRISMA, Supplemental Digital Content 1 (http://links.lww.com/JS9/C77) and Supplemental Digital Content 2 (http://links.lww.com/JS9/C78), and AMSTAR-2 guidelines, Supplemental Digital Content 3 (http://links.lww.com/JS9/C79), we systematically searched PubMed, Web of Science, Embase, Cochrane Library, and Google Scholar databases until 11 January 2024, to evaluate radiomics models' diagnostic precision in predicting preoperative LNM in CRC patients. The quality and bias risk of the included studies were assessed using the Radiomics Quality Score (RQS) and the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Subsequently, statistical analyses were conducted.

RESULTS

Thirty-six studies encompassing 8039 patients were included, with a significant concentration in 2022-2023 (20/36). Radiomics models predicting LNM demonstrated a pooled area under the curve (AUC) of 0.814 (95% CI: 0.78-0.85), featuring sensitivity and specificity of 0.77 (95% CI: 0.69, 0.84) and 0.73 (95% CI: 0.67, 0.78), respectively. Subgroup analyses revealed similar AUCs for CT and MRI-based models, and rectal cancer models outperformed colon and colorectal cancers. Additionally, studies utilizing cross-validation, 2D segmentation, internal validation, manual segmentation, prospective design, and single-center populations tended to have higher AUCs. However, these differences were not statistically significant. Radiologists collectively achieved a pooled AUC of 0.659 (95% CI: 0.627, 0.691), significantly differing from the performance of radiomics models (P<0.001).

CONCLUSION

Artificial intelligence-based radiomics shows promise in preoperative lymph node staging for CRC, exhibiting significant predictive performance. These findings support the integration of radiomics into clinical practice to enhance preoperative strategies in CRC management.

Deep Learning Applications in Pancreatic Cancer

Pancreatic cancer is one of the most lethal gastrointestinal malignancies. Despite advances in cross-sectional imaging, chemotherapy, radiation therapy, and surgical techniques, the 5-year overall survival is only 12%. With the advent and rapid adoption of AI across all industries, we present a review of applications of DL in the care of patients diagnosed with PC. A review of different DL techniques with applications across diagnosis, management, and monitoring is presented across the different pathological subtypes of pancreatic cancer. This systematic review highlights AI as an emerging technology in the care of patients with pancreatic cancer.

Computed tomography-based radiomics improves non-invasive diagnosis of Pneumocystis jirovecii pneumonia in non-HIV patients: a retrospective study

BACKGROUND

Pneumocystis jirovecii pneumonia (PCP) could be fatal to patients without human immunodeficiency virus (HIV) infection. Current diagnostic methods are either invasive or inaccurate. We aimed to establish an accurate and non-invasive radiomics-based way to identify the risk of PCP infection in non-HIV patients with computed tomography (CT) manifestation of pneumonia.

METHODS

This is a retrospective study including non-HIV patients hospitalized for suspected PCP from January 2010 to December 2022 in one hospital. The patients were randomized in a 7:3 ratio into training and validation cohorts. Computed tomography (CT)-based radiomics features were extracted automatically and used to construct a radiomics model. A diagnostic model with traditional clinical and CT features was also built. The area under the curve (AUC) were calculated and used to evaluate the diagnostic performance of the models. The combination of the radiomics features and serum β-D-glucan levels was also evaluated for PCP diagnosis.

RESULTS

A total of 140 patients (PCP: N = 61, non-PCP: N = 79) were randomized into training (N = 97) and validation (N = 43) cohorts. The radiomics model consisting of nine radiomic features performed significantly better (AUC = 0.954; 95% CI: 0.898-1.000) than the traditional model consisting of serum β-D-glucan levels (AUC = 0.752; 95% CI: 0.597-0.908) in identifying PCP (P = 0.002). The combination of radiomics features and serum β-D-glucan levels showed an accuracy of 95.8% for identifying PCP infection (positive predictive value: 95.7%, negative predictive value: 95.8%).

CONCLUSIONS

Radiomics showed good diagnostic performance in differentiating PCP from other types of pneumonia in non-HIV patients. A combined diagnostic method including radiomics and serum β-D-glucan has the potential to provide an accurate and non-invasive way to identify the risk of PCP infection in non-HIV patients with CT manifestation of pneumonia.

TRIAL REGISTRATION

ClinicalTrials.gov (NCT05701631).