Background Accurate prediction of tumour response to neoadjuvant chemoradiotherapy enables personalised perioperative therapy for locally advanced rectal cancer. We aimed to develop and validate an artificial intelligence radiopathomics integrated model to predict pathological complete response in patients with locally advanced rectal cancer using pretreatment MRI and haematoxylin and eosin (H&E)-stained biopsy slides. MethodsIn this multicentre observational study, eligible participants who had undergone neoadjuvant chemoradiotherapy followed by radical surgery were recruited, with their pretreatment pelvic MRI (T2-weighted imaging, contrast-enhanced T1-weighted imaging, and diffusion-weighted imaging) and whole slide images of H&E-stained biopsy sections collected for annotation and feature extraction. The RAdioPathomics Integrated preDiction System (RAPIDS) was constructed by machine learning on the basis of three feature sets associated with pathological complete response: radiomics MRI features, pathomics nucleus features, and pathomics microenvironment features from a retrospective training cohort. The accuracy of RAPIDS for the prediction of pathological complete response in locally advanced rectal cancer was verified in two retrospective external validation cohorts and further validated in a multicentre, prospective observational study (ClinicalTrials.gov, NCT04271657). Model performances were evaluated using area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

Background The aim of this work is to combine radiological and pathological information of tumor to develop a signature for pretreatment prediction of discrepancies of pathological response at several centers and restage patients with locally advanced rectal cancer (LARC) for individualized treatment planning. Patients and Methods A total of 981 consecutive patients with evaluation of response according to tumor regression grade (TRG) who received nCRT were retrospectively recruited from four hospitals (primary cohort and external validation cohort 1–3); both pretreatment multiparametric MRI (mp-MRI) and whole slide image (WSI) of biopsy specimens were available for each patient. Quantitative image features were extracted from mp-MRI and WSI and used to construct a radiopathomics signature (RPS) powered by an artificial-intelligence model. Models based on mp-MRI or WSI alone were also constructed for comparison. Results The RPS showed overall accuracy of 79.66–87.66% in validation cohorts. The areas under the curve of RPS at specific response grades were 0.98 (TRG0), 0.93 (≤ TRG1), and 0.84 (≤ TRG2). RPS at each grade of pathological response revealed significant improvement compared with both signatures constructed without combining multiscale tumor information (P < 0.01). Moreover, RPS showed relevance to distinct probabilities of overall survival and disease-free survival in patients with LARC who underwent nCRT (P < 0.05). Conclusions The results of this study suggest that radiopathomics, combining both radiological information of the whole tumor and pathological information of local lesions from biopsy, could potentially predict discrepancies of pathological response prior to nCRT for better treatment planning.

No abstract

Neoadjuvant chemoradiotherapy (nCRT) followed by surgery is the standard treatment for locally advanced rectal cancer. Here, we analyzed the impact of local and systemic environments on the tumor response to preoperative chemoradiotherapy in rectal cancer. We recruited 141 patients with rectal cancer treated with nCRT. We evaluated the local tumor environment, including tumor-infiltrating lymphocytes (TILs), intratumor budding (ITB), and the systemic inflammatory environment, including the neutrophil-to-lymphocyte ratio (NLR) and C-reactive protein (CRP) level. Our finding revealed that tumor regression was significantly associated with the density of CD8+ TILs in the intraepithelial, the presence of ITB, the combination of NLR and CRP (NLR-CRP) value, and the combination of CD8+ intraepithelial TIL (iTIL) density and ITB presence. Moreover, multivariate analysis showed that only the combination of CD8+ iTILs and ITB was an independent predictive factor for the pathological response to nCRT in rectal cancer. Our finding demonstrate that the local tumor environment was a better predictor of the tumor response than the systemic environment and thus provided new insight into screening for patients who are more likely to benefit from cancer treatment.

ObjectiveThis study aimed to develop an artificial intelligence model for predicting the pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) of locally advanced rectal cancer (LARC) using digital pathological images.BackgroundnCRT followed by total mesorectal excision (TME) is a standard treatment strategy for patients with LARC. Predicting the PCR to nCRT of LARC remine difficulty.Methods842 LARC patients treated with standard nCRT from three medical centers were retrospectively recruited and subgrouped into the training, testing and external validation sets. Treatment response was classified as pCR and non-pCR based on the pathological diagnosis after surgery as the ground truth. The hematoxylin &amp; eosin (H&amp;E)-stained biopsy slides were manually annotated and used to develop a deep pathological complete response (DeepPCR) prediction model by deep learning.ResultsThe proposed DeepPCR model achieved an AUC-ROC of 0.710 (95% CI: 0.595, 0.808) in the testing cohort. Similarly, in the external validation cohort, the DeepPCR model achieved an AUC-ROC of 0.723 (95% CI: 0.591, 0.844). The sensitivity and specificity of the DeepPCR model were 72.6% and 46.9% in the testing set and 72.5% and 62.7% in the external validation cohort, respectively. Multivariate logistic regression analysis showed that the DeepPCR model was an independent predictive factor of nCRT (P=0.008 and P=0.004 for the testing set and external validation set, respectively).ConclusionsThe DeepPCR model showed high accuracy in predicting pCR and served as an independent predictive factor for pCR. The model can be used to assist in clinical treatment decision making before surgery.