Lung Cancer Classification in Histopathology Images Using Multiresolution Efficient Nets

Abstract

Histopathological images are very effective for investigating the status of various biological structures and diagnosing diseases like cancer. In addition, digital histopathology increases diagnosis precision and provides better image quality and more detail for the pathologist with multiple viewing options and team annotations. As a result of the benefits above, faster treatment is available, increasing therapy success rates and patient recovery and survival chances. However, the present manual examination of these images is tedious and time-consuming for pathologists. Therefore, reliable automated techniques are needed to effectively classify normal and malignant cancer images. This paper applied a deep learning approach, namely, EfficientNet and its variants from B0 to B7. We used different image resolutions for each model, from 224 × 224 pixels to 600 × 600 pixels. We also applied transfer learning and parameter tuning techniques to improve the results and overcome the overfitting problem. We collected the dataset from the Lung and Colon Cancer Histopathological Image LC25000 image dataset. The dataset acquisition consists of 25,000 histopathology images of five classes (lung adenocarcinoma, lung squamous cell carcinoma, benign lung tissue, colon adenocarcinoma, and colon benign tissue). Then, we performed preprocessing on the dataset to remove the noisy images and bring them into a standard format. The model's performance was evaluated in terms of classification accuracy and loss. We have achieved good accuracy results for all variants; however, the results of EfficientNetB2 stand excellent, with an accuracy of 97% for 260 × 260 pixels resolution images.

Figure 1

Image samples from LC25000 dataset image. (a, b) Colon adenocarcinoma. (c, d) Colon benign tissue. (e, f) Lung adenocarcinoma. (g, h) Lung squamous cell carcinomas. (i) Benign lung tissue.

Figure 2

Index representation of the dataset image sample before preprocessing to the model's desired size.

Figure 3

Transfer learning schematic diagram.

Figure 4

Block diagram of the proposed work.

Figure 5

The basic idea of EfficientNet [16] is to carefully balance scale, the network width depth, and resolution if resources are available (https://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html).

Figure 6

EfficientNetB0 training and validation plot of accuracy and loss.

Figure 7

EfficientNetB1 training and validation plot of accuracy and loss.

Figure 8

EfficientNetB2 model training and validation plot of accuracy and loss.

Figure 9

EfficientNetB3 model training and validation plot of accuracy and loss.

Figure 10

EfficientNetB4 model training and validation plot of accuracy and loss.

Figure 11

EfficientNetB5 model training and validation plot of accuracy and loss.

Figure 12

EfficientNetB6 model training and validation plot of accuracy and loss.

Figure 13

EfficientNetB7 model training and validation plot of accuracy and loss.