Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging

By Yiwen Xu, Ahmed Hosny, R. Zeleznik, Chintan Parmar, T. Coroller, I. Franco, R. Mak, Hugo J. W. L. Aerts. Clinical Cancer Research, 2019

505 citations recorded by the source corpus.

Purpose: Tumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non–small cell lung cancer (NSCLC). Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans). Results: Deep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17–17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016). Conclusions: We demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.

Subfields: Artificial Intelligence, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/43b1d2bc7fdb875b22d768d6435b14258581041e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Pulmonary and Respiratory Medicine

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Artificial Intelligence in Cancer Research and Precision Medicine (2021, unknown): “109).”
Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing (2023, methodology): “Existing models typically employ either late fusion of global image representations [58,64,68,74], which can miss fine-grained localised changes [32], or explicit spatial correspondence of features, using fixed spatial grids [48] or object detection [37].”
Deep learning with noisy labels: exploring techniques and remedies in medical image analysis (2019, background): “level image processing tasks such as denoising, enhancement, and reconstruction [6], to more high-level image analysis tasks such as segmentation, detection, classification, and registration [7], [8], and even more challenging tasks such as discovering links between the content of medical images and”
Artificial Intelligence for Clinical Oncology (2021, background): “In one example, AI has demonstrated the ability to synthesize serial CT follow-up imaging for lung cancer patients post chemoradiation and to predict later recurrence (Xu et al., 2019).”
From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. (2023, background): “54 Response to treatment Predicting response to treatment, either prior to or during the early stages of treatment, can aid physicians in selecting the optimal treatment for a patient.”
Artificial intelligence and machine learning for medical imaging: A technology review. (2021, unknown): “In the example of radiomics, embedded feature selection can be implemented with deep neural networks [120] and regularization, hence allowing for end-to-end learning instead of combining manually engineered features with shallow predictive models.”
Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19 (2020, methodology): “learning-based methodology could inspire the follow-up study of COVID-19 [88]–[91].”
Predicting cancer outcomes with radiomics and artificial intelligence in radiology (2021, methodology): “Regarding DL approaches, Xu et al. 115 combined a pretrained CNN with a RNN to analyse longitudinal CT scans of patients with stage III NSCLC before and after treatment.”