Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer

The application of artificial intelligence in upper gastrointestinal cancers

Upper gastrointestinal cancers, mainly comprising esophageal and gastric cancers, are among the most prevalent cancers worldwide. There are many new cases of upper gastrointestinal cancers annually, and the survival rate tends to be low. Therefore, timely screening, precise diagnosis, appropriate treatment strategies, and effective prognosis are crucial for patients with upper gastrointestinal cancers. In recent years, an increasing number of studies suggest that artificial intelligence (AI) technology can effectively address clinical tasks related to upper gastrointestinal cancers. These studies mainly focus on four aspects: screening, diagnosis, treatment, and prognosis. In this review, we focus on the application of AI technology in clinical tasks related to upper gastrointestinal cancers. Firstly, the basic application pipelines of radiomics and deep learning in medical image analysis were introduced. Furthermore, we separately reviewed the application of AI technology in the aforementioned aspects for both esophageal and gastric cancers. Finally, the current limitations and challenges faced in the field of upper gastrointestinal cancers were summarized, and explorations were conducted on the selection of AI algorithms in various scenarios, the popularization of early screening, the clinical applications of AI, and large multimodal models.

Prediction of esophageal fistula in radiotherapy/chemoradiotherapy for patients with advanced esophageal cancer by a clinical-deep learning radiomics model : Prediction of esophageal fistula in radiotherapy/chemoradiotherapy patients

BACKGROUND

Esophageal fistula (EF), a rare and potentially fatal complication, can be better managed with predictive models for personalized treatment plans in esophageal cancers. We aim to develop a clinical-deep learning radiomics model for effectively predicting the occurrence of EF.

METHODS

The study involved esophageal cancer patients undergoing radiotherapy or chemoradiotherapy. Arterial phase enhanced CT images were used to extract handcrafted and deep learning radiomic features. Along with clinical information, a 3-step feature selection method (statistical tests, Least Absolute Shrinkage and Selection Operator, and Recursive Feature Elimination) was used to identify five feature sets in training cohort for constructing random forest EF prediction models. Model performance was compared and validated in both retrospective and prospective test cohorts.

RESULTS

One hundred seventy five patients (122 in training and 53 in test cohort)were retrospectively collected from April 2018 to June 2022. An additional 27 patients were enrolled as a prospective test cohort from June 2022 to December 2023. Post-selection in the training cohort, five feature sets were used for model construction: clinical, handcrafted radiomic, deep learning radiomic, clinical-handcrafted radiomic, and clinical-deep learning radiomic. The clinical-deep learning radiomic model excelled with AUC of 0.89 (95% Confidence Interval: 0.83-0.95) in the training cohort, 0.81 (0.65-0.94) in the test cohort, and 0.85 (0.71-0.97) in the prospective test cohort. Brier-score and calibration curve analyses validated its predictive ability.

CONCLUSIONS

The clinical-deep learning radiomic model can effectively predict EF in patients with advanced esophageal cancer undergoing radiotherapy or chemoradiotherapy.

Clinical-radiomics nomogram for the risk prediction of esophageal fistula in patients with esophageal squamous cell carcinoma treated with intensity-modulated radiation therapy or volumetric-modulated arc therapy

Background

Esophageal fistula (EF) is a serious adverse event as a result of radiotherapy in patients with esophageal cancer (EC). We aimed to identify the predictive factors and establish a prediction model of EF in patients with esophageal squamous cell carcinoma (ESCC) who underwent intensity-modulated radiation therapy (IMRT) or volumetric-modulated arc therapy (VMAT).

Methods

Patients with ESCC treated with IMRT or VMAT from January 2013 to December 2020 at Xijing Hospital were retrospectively analyzed. Ultimately, 43 patients with EF and 129 patients without EF were included in the analysis and propensity-score matched in a 1:3 ratio. The clinical characteristics and radiomics features were extracted. Univariate and multivariate stepwise logistic regression analyses were used to determine the risk factors associated with EF.

Results

The median follow-up time was 24.0 months (range, 1.3-104.9 months), and the median overall survival (OS) was 13.1 months in patients with EF. A total of 1,158 radiomics features were extracted, and eight radiomics features were selected for inclusion into a model for predicting EF, with an area under the receiver operating characteristic curve (AUC) value of 0.794. Multivariate analysis showed that tumor length, tumor volume, T stage, lymphocyte rate (LR), and grade IV esophagus stenosis were related to EF, and the AUC value of clinical model for predicting EF was 0.849. The clinical-radiomics model had the best performance in predicting EF with an AUC value of 0.896.

Conclusions

The clinical-radiomics nomogram can predict the risk of EF in ESCC patients and is helpful for the individualized treatment of EC.

Multi-omics and Multi-VOIs to predict esophageal fistula in esophageal cancer patients treated with radiotherapy

OBJECTIVE

This study aimed to develop a prediction model for esophageal fistula (EF) in esophageal cancer (EC) patients treated with intensity-modulated radiation therapy (IMRT), by integrating multi-omics features from multiple volumes of interest (VOIs).

METHODS

We retrospectively analyzed pretreatment planning computed tomographic (CT) images, three-dimensional dose distributions, and clinical factors of 287 EC patients. Nine groups of features from different combination of omics [Radiomics (R), Dosiomics (D), and RD (the combination of R and D)], and VOIs [esophagus (ESO), gross tumor volume (GTV), and EG (the combination of ESO and GTV)] were extracted and separately selected by unsupervised (analysis of variance (ANOVA) and Pearson correlation test) and supervised (Student T test) approaches. The final model performance was evaluated using five metrics: average area under the receiver-operator-characteristics curve (AUC), accuracy, precision, recall, and F1 score.

RESULTS

For multi-omics using RD features, the model performance in EG model shows: AUC, 0.817 ± 0.031; 95% CI 0.805, 0.825; p < 0.001, which is better than single VOI (ESO or GTV).

CONCLUSION

Integrating multi-omics features from multi-VOIs enables better prediction of EF in EC patients treated with IMRT. The incorporation of dosiomics features can enhance the model performance of the prediction.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review

Importance

Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.

Highlights

We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma.

Conclusion

AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

Chemoradiation for elderly patients (≥ 65 years) with esophageal cancer: a retrospective single-center analysis

Background

Present studies on the efficacy and safety of curative chemoradiation therapy (CRT) with esophageal cancer reflect heterogenous results especially in elderly patients. The aim of this study was to evaluate the toxicity and efficacy of CRT in patients ≥ 65 years. In a cohort, the focus centered around treatment-related toxicity (CTCAE Grade > 3), overall survival as well as progression free survival, comparing these rates in-between patients older than 70 years to those younger than 70 years.

Methods

A total of 67 patients older than 65 years (34 (50.7%) were older than 70 years) met the inclusion criteria for retrospective analysis (period from January 2013 to October 2017). Treatment consisted of radiotherapy and chemotherapy with carboplatin/paclitaxel or fluorouracil (5-FU)/cisplatin with the intention of neoadjuvant or definite chemoradiation. A sum of 67 patients received CRT (44 (65.6%) patients in neoadjuvant, 23 (34.4%) in definite intent). Of these, 22 and 12 patients were older than 70 years (50% and 52.2% in both treatment groups, respectively). Median age was 71 years and patients had a good physical performance status (ECOG 0: 57.6%, ECOG 1: 27.3%). Median follow-up was 24 months. Most patients had advanced tumour stages (T3 stage: n = 51, 79.7%) and nodal metastasis (N1 stage: n = 54, 88.5%). A subgroup comparison was conducted between patients aged ≤ 70 years and > 70 years.

Results

In severe (CTCAE Grade 3–5) toxicities (acute and late), no significant differences were observed between both patient groups (< 70 years vs. > 70 years). 21% had acute grade 3 events, 4 patients (4%) had grade 4 events, and two patients (3%) had one grade 5 event. Late toxicity after CRT was grade 1 in 13 patients (22%), grade 2 in two (3%), grade 3 in two (3%), grade 4 in four (7%), and grade 5 in one (2%). Median overall survival (OS) of all patients was 30 months and median progression-free survival (PFS) was 16 months. No significant differences were seen for OS (32 months vs. 25 months; p = 0.632) and PFS (16 months vs. 12 months; p = 0.696) between older patients treated with curative intent and younger ones. Trimodal therapy significantly prolonged both OS and PFS (p = 0.005; p = 0.018), regardless of age.

Conclusion

CRT in elderly patients (≥ 65 years) with esophageal cancer is feasible and effective. Numbers for acute and late toxicities can be compared to cohorts of younger patients (< 65 years) with EC who received the same therapies. Age at treatment initiation alone should not be the determining factor. Instead, functional status, risk of treatment-related morbidities, life expectancy and patient´s preferences should factor into the choice of therapy.