The self-distillation trained multitask dense-attention network for diagnosing lung cancers based on CT scans

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

1 Scopus Citations
View graph of relations

Related Research Unit(s)


Original languageEnglish
Pages (from-to)1738-1753
Number of pages16
Journal / PublicationMedical Physics
Issue number3
Online published16 Sept 2023
Publication statusPublished - Mar 2024


Background: The latest international multidisciplinary histopathological classification of lung cancer indicates that a deeper study of the lung adenocarcinoma requires a comprehensive multidisciplinary platform. However, in the traditional pathological examination or previous computer-vision-based research, the entire lung is not considered in a comprehensive manner. Purpose: The study aims to develop a deep learning model proposed for diagnosing the lung adenocarcinoma histopathologically based on CT scans. Instead of just classifying the lung adenocarcinoma, the pathological report should be inferred based on both the invasiveness and growth pattern of the tumors. Methods: A self-distillation trained multitask dense-attention network (SD-MdaNet) is proposed and validated based on 2412 labeled CT scans from 476 patients and 845 unlabeled scans. Inferring the pathological report is divided into two tasks, predicting the invasiveness of the lung tumor and inferring growth patterns of tumor cells in a comprehensive histopathological subtyping manner with excellent accuracy. In the proposed method, the dense-attention module is introduced to better extract features from a small dataset in the main branch of the MdaNet. Next, task-specific attention modules are utilized in different branches and finally integrated as a multitask model. The second task is a blend of classification and regression tasks. Thus, a specialized loss function is developed. In the proposed knowledge distillation (KD) process, the MdaNet as well as its main branch trained for solving two single tasks, respectively, are treated as multiple teachers to produce a student model. A novel KD loss function is developed to take the advantage of all the models as well as data with labels and without labels. Results: SD-MdaNet achieves an AUC of 98.7 ± 0.4% on invasiveness prediction, and 91.6 ± 1.0% on predominant growth pattern prediction on our dataset. Moreover, the average mean squared error in inferring growth pattern proportion reaches 0.0217 ± 0.0019, and the AUC for predominant growth pattern proportion reaches 91.6 ± 1.0%. The proposed SD-MdaNet is significantly better than all other benchmarking methods (FDR < 0.05). Conclusions: Experimental results demonstrate that the proposed SD-MdaNet can significantly improve the performance of the lung adenocarcinoma pathological diagnosis using only CT scans. Analyses and discussions are conducted to interpret the advantages of the SD-MdaNet. © 2023 American Association of Physicists in Medicine.

Research Area(s)

  • deep neural networks, lung adenocarcinoma, multitask modeling