Development and Validation of a Deep Learning Model for Histopathological Slide Analysis in Lung Cancer Diagnosis
Problem
Lung cancer diagnosis is often delayed and relies on pathologist review of histopathology slides, contributing to cancer-related deaths.
Why it matters
Lung cancer is the leading cause of cancer-related deaths worldwide, so faster and more accurate diagnosis affects survival.
What the AI did
A deep learning model combining CNNs and separable CNNs with residual blocks classified cancerous vs non-cancerous lung cell images from whole-slide images.
Results
Accuracy improved from 96% to 98% with classification in under 10 s; model accuracy 100% vs 79% for active pathologists
Impact
On this dataset the model outperformed active pathologists, suggesting potential diagnostic support.
Record
| Venue | Cancers |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Alhassan Ali Ahmed, M. T. Fawi, Agnieszka Brychcy, Mohamed Abouzid, Martin Witt, Elżbieta Kaczmarek |
| Citations | 29 (OpenAlex, at import time) |
| References | 20 |
| Model or method | CNNs and separable CNNs with residual blocks |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/cancers16081506 |
| Open access | gold |
| Keywords | deep learning, lung cancer, histopathology, whole-slide imaging, CNN, diagnosis |
Importance rating
major — millions of lives, an industry or a field
Abstract states lung cancer is the leading cause of cancer-related deaths worldwide; faster, more accurate detection affects survival for a major disease.