Selection, Visualization, and Interpretation of Deep Features in Lung Adenocarcinoma and Squamous Cell Carcinoma

Taher Dehkharghanian, Shahryar Rahnamayan, Abtin Riasatian, Azam A. Bidgoli, Shivam Kalra, Manit Zaveri, Morteza Babaie, Mahjabin S. Seyed Sajadi, Ricardo Gonzalelz, Phedias Diamandis, Liron Pantanowitz, Tao Huang, Hamid R. Tizhoosh

Research output: Contribution to journalArticlepeer-review


Although deep learning networks applied to digital images have shown impressive results for many pathology-related tasks, their black-box approach and limitation in terms of interpretability are significant obstacles for their widespread clinical utility. This study investigates the visualization of deep features (DFs) to characterize two lung cancer subtypes, adenocarcinoma and squamous cell carcinoma. It demonstrates that a subset of DFs, called prominent DFs, can accurately distinguish these two cancer subtypes. Visualization of such individual DFs allows for a better understanding of histopathologic patterns at both the whole-slide and patch levels, and discrimination of these cancer types. These DFs were visualized at the whole slide image level through DF-specific heatmaps and at tissue patch level through the generation of activation maps. In addition, these prominent DFs can distinguish carcinomas of organs other than the lung. This framework may serve as a platform for evaluating the interpretability of any deep network for diagnostic decision making.

Original languageEnglish (US)
Pages (from-to)2172-2183
Number of pages12
JournalAmerican Journal of Pathology
Issue number12
StatePublished - Dec 2021

ASJC Scopus subject areas

  • Pathology and Forensic Medicine


Dive into the research topics of 'Selection, Visualization, and Interpretation of Deep Features in Lung Adenocarcinoma and Squamous Cell Carcinoma'. Together they form a unique fingerprint.

Cite this