Related Experiment Video
Updated: Jun 6, 2025
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
Published on: April 12, 2024
A histopathology-based artificial intelligence system assisting the screening of genetic alteration in intrahepatic
Han Xiao1, Jianping Wang2, Zongpeng Weng3
1Department of Medical Ultrasonics, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
Background:
Targeted therapy for intrahepatic cholangiocarcinoma (ICC) shows superior survival outcomes but patients with certain targetable alterations are no more than 20%. Genetic alteration screening for all ICC patients is of high cost and not routinely performed. This study intends to develop a histopathology-based artificial intelligence (AI)-assisted system for predicting genetic alteration of ICC.
Methods:
We constructed a Genetic Alteration Prediction (GAP) system based on multi-instance learning and self-supervised learning to predict genetic alterations using whole-slide images (WSIs) of H&E-stained slides. A total of 2069 WSIs from 232 ICC patients underwent surgery of the FAH-SYSU dataset were used for model construction and adjustment by five-fold cross-validation. Another 150 patients from three medical centres were used as independent external validations. We also compared the cost-effectiveness of GAP-assisted precise treatment and all-sequencing strategy to non-sequencing strategy.
Results:
The GAP was able to predict actionable genetic alterations of ICC, including FGFR2 and IDH. The area under the receiver operating characteristic curves (AUC) for FGFR2 and IDH were 0.754 and 0.713 in the internal dataset, and 0.724 and 0.656 in the external dataset, respectively. Furthermore, compared to giving chemotherapy without sequencing for every patient, GAP-assisted precise treatment could increase 1 progression-free quality-adjusted life month with a cost of $13871.72, the co-responding figure for all-sequencing strategy is $44538.93. Decision curve analysis showed that AI-assisted strategy provides better clinical benefits.
Conclusions:
We constructed an AI-assisted genetic alteration screening system which is predictable to ICC actionable targets and has potential to assist precise targeted treatment of advanced ICC.
Insights
An AI system predicts genetic alterations in intrahepatic cholangiocarcinoma (ICC) from histopathology slides, aiding targeted therapy. This approach is more cost-effective than routine genetic sequencing for all patients.
Area of Science:
- Oncology
- Artificial Intelligence
- Medical Diagnostics
Background:
- Targeted therapy improves outcomes for intrahepatic cholangiocarcinoma (ICC), but only 20% of patients have targetable alterations.
- Genetic screening for ICC is costly and not standard practice.
- Histopathology-based AI can potentially predict genetic alterations in ICC.
Purpose of the Study:
- To develop an artificial intelligence (AI)-assisted system for predicting genetic alterations in ICC using histopathology images.
- To evaluate the cost-effectiveness of the AI-assisted system compared to traditional genetic sequencing.
Main Methods:
- A Genetic Alteration Prediction (GAP) system was built using multi-instance and self-supervised learning on whole-slide images (WSIs) from 232 ICC patients.
- The model was validated on an independent external dataset of 150 patients.
- Cost-effectiveness analysis compared GAP-assisted treatment, all-sequencing, and non-sequencing strategies.
Main Results:
- The GAP system accurately predicted actionable genetic alterations (FGFR2, IDH) with AUCs of 0.754 and 0.713 (internal) and 0.724 and 0.656 (external).
- GAP-assisted precise treatment increased progression-free quality-adjusted life month by 1 with a cost of $13,871.72, significantly less than the $44,538.93 for all-sequencing.
- Decision curve analysis indicated superior clinical benefits for the AI-assisted strategy.
Conclusions:
- An AI-assisted system for predicting ICC actionable targets was developed.
- This system shows potential for assisting precise targeted treatment in advanced ICC.
- The AI approach offers a cost-effective alternative to comprehensive genetic sequencing.
