General Electric Healthcare, Buc, France; LITIS - EA4108 - Quantif, University of Rouen, Rouen, France.
LITIS - EA4108 - Quantif, University of Rouen, Rouen, France; Nuclear Medicine Department, Henri Becquerel Center, Rouen, France.
Comput Biol Med. 2022 Dec;151(Pt A):106208. doi: 10.1016/j.compbiomed.2022.106208. Epub 2022 Oct 18.
Predicting patient response to treatment and survival in oncology is a prominent way towards precision medicine. To this end, radiomics has been proposed as a field of study where images are used instead of invasive methods. The first step in radiomic analysis in oncology is lesion segmentation. However, this task is time consuming and can be physician subjective. Automated tools based on supervised deep learning have made great progress in helping physicians. However, they are data hungry, and annotated data remains a major issue in the medical field where only a small subset of annotated images are available.
In this work, we propose a multi-task, multi-scale learning framework to predict patient's survival and response. We show that the encoder can leverage multiple tasks to extract meaningful and powerful features that improve radiomic performance. We also show that subsidiary tasks serve as an inductive bias so that the model can better generalize.
Our model was tested and validated for treatment response and survival in esophageal and lung cancers, with an area under the ROC curve of 77% and 71% respectively, outperforming single-task learning methods.
Multi-task multi-scale learning enables higher performance of radiomic analysis by extracting rich information from intratumoral and peritumoral regions.
预测肿瘤患者的治疗反应和生存情况是精准医学的一个主要方向。为此，放射组学已被提议作为一个研究领域，其中使用图像而不是侵入性方法。放射组学分析的第一步是病变分割。然而，这项任务既耗时又可能带有医生的主观性。基于监督深度学习的自动化工具在帮助医生方面取得了重大进展。然而，它们需要大量的数据，而在医学领域，注释数据仍然是一个主要问题，因为只有一小部分注释图像可用。
在这项工作中，我们提出了一个多任务、多尺度学习框架来预测患者的生存和反应。我们表明，编码器可以利用多个任务来提取有意义和强大的特征，从而提高放射组学的性能。我们还表明，辅助任务可以作为一种归纳偏差，使模型能够更好地泛化。
我们的模型在食管癌和肺癌的治疗反应和生存方面进行了测试和验证，其 ROC 曲线下面积分别为 77%和 71%，优于单任务学习方法。
多任务多尺度学习通过从肿瘤内和肿瘤周围区域提取丰富的信息，实现了更高的放射组学分析性能。
