Abstract 551P
Background
PD-1/PD-L1 blockades with chemoradiotherapy as neoadjuvant therapy may promote tumor regression in patients with microsatellite stable (MSS) rectal cancer. However, which patient can benefit from this new treatment remains largely unknown, especially through analysis of magnetic resonance imaging (MRI) images.
Methods
Two phase II, open-labeled, studies evaluated the efficacy of anti-PD-1/PD-L1 to neoadjuvant chemoradiotherapy in MSS rectal cancer. Patients with locally advanced middle and low rectal cancer were recruited. All patients received long-course radiotherapy followed by two or three cycles anti-PD-1/PD-L1 treatment and radical resection surgery. Rectal MRI images were collected from patients prior to the radiotherapy. From each patient's rectal MRI set, three images where the tumor was clearly visible were selected and labeled. A convolutional neural network, named PDNet, was developed to extract features from these selected images and predict whether a pathological complete regression (pCR) is achieved.
Results
61 patients were recruited with 100% R0 resection. Among them, 24 patients achieved pCR (39.3%). A dataset comprising 183 rectal MRI images was utilized, with 147 images employed in the training phase and 36 images in the testing phase. After training, the PDNet model demonstrated strong performance on the test dataset (internal validations): it achieved a classification accuracy of 86.11%, a positive predictive value of 93.33%, a negative predictive value of 80.95%, a sensitivity of 77.78%, and a specificity of 94.44%. The model also recorded a p-value of 0.0000498 and an Area Under the Curve (AUC) of 0.8580, with a 95% Confidence Interval (CI) [0.6982, 0.9805].
Conclusions
The study concludes that features extracted from MRI images are highly correlated with the likelihood of achieving pCR. Using the developed neural network model (PDNet), we can predict the probability of achieving pCR before the treatment of PD-1/PD-L1 blockades with chemoradiotherapy in MSS local advanced rectal cancer. External validation of the model is currently underway.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Jianmin Xu.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
547P - Artificial Intelligence-powered analysis of the tumor immune microenvironment in primary and metastatic colorectal cancer
Presenter: Elio Adib
Session: Poster session 16
548P - Simplified immune score based on CD8+ T-cells at the invasive margin provides comparable prognostic value to immune scores in non-metastatic colorectal cancer
Presenter: Durgesh Wankhede
Session: Poster session 16
549P - Combined morphometric immune signatures define the prognosis of patients with resectable colorectal liver metastases
Presenter: Markus Moehler
Session: Poster session 16
550P - The impact of mismatch repair status on accuracy of clinical staging in upfront resected stage II/III rectal cancer in the Netherlands
Presenter: Renee Lunenberg
Session: Poster session 16
552P - Baseline imaging biomarkers to predict outcomes in locally advanced colon cancer (LACC): Data from the FOxTROT international randomised-controlled trial
Presenter: James Platt
Session: Poster session 16
553P - Association of ctDNA-based MRD detection and MRD clearance with short-term overall survival in patients with resectable colorectal cancer: Updated analysis of CIRCULATE-Japan GALAXY
Presenter: JUN NAGATA
Session: Poster session 16
555P - Association between copy number aberration and ctDNA MRD in colorectal cancer: CIRCULATE-Japan GALAXY
Presenter: TOMOYA HARIMA
Session: Poster session 16
556P - Predicting the efficacy of neoadjuvant chemoradiotherapy in rectal cancer patients based on dynamic tumor-informed ctDNA-MRD
Presenter: Weiwei Xiao
Session: Poster session 16