Medical Journal of the Islamic Republic Of Iran
مجله پزشکی جمهوری اسلامی ایران
Med J Islam Repub Iran
Medical Sciences
http://mjiri.iums.ac.ir
2
journal2
1016-1430
2251-6840
8
10.18869/mjiri
14
8888
13
en
jalali
1398
11
1
gregorian
2020
2
1
34
1
online
1
fulltext
en
Artificial intelligence in automatic classification of invasive ductal carcinoma breast cancer in digital pathology images
Medical Physics
Medical Physics
Original Research
Original Research
<div style="text-align: justify;"><strong>Background: </strong>Breast cancer is one of the most causes of death in women. Early diagnosis and detection of Invasive Ductal Carcinoma (IDC) is an important key for the treatment of IDC. Computer-aided approaches have great potential to improve diagnosis accuracy. In this paper, we proposed a deep learning-based method for the automatic classification of IDC in whole slide images (WSI) of breast cancer. Furthermore, different types of deep neural networks training such as training from scratch and transfer learning to classify IDC were evaluated.<br>
<strong>Methods:</strong> In total, 277524 image patches with 50×50-pixel size form original images were used for model training. In the first method, we train a simple convolutional neural network (named it baseline model) on these images. In the second approach, we used the pre-trained VGG-16 CNN model via feature extraction and fine-tuning for the classification of breast pathology images.<br>
<strong>Results:</strong> Our baseline model achieved a better result for the automatic classification of IDC in terms of F-measure and accuracy (83%, 85%) in comparison with original paper on this data set and achieved a comparable result with a new study that introduced accepted- rejected pooling layer. Also, transfer learning via feature extraction yielded better results (81%, 81%) in comparison with handcrafted features. Furthermore, transfer learning via feature extraction yielded better classification results in comparison with the baseline model.<br>
<strong>Conclusion:</strong> The experimental results demonstrate that using deep learning approaches yielded better results in comparison with handcrafted features. Also, using transfer learning in histopathology image analysis yielded significant results in comparison with training from scratch in much less time.</div>
Invasive ductal carcinoma, Breast cancer, Artificial intelligence, Convolutional neural networks, Deep learning, Digital pathology
965
973
http://mjiri.iums.ac.ir/browse.php?a_code=A-10-5503-1&slc_lang=en&sid=1
Mohammad
Abdolahi
m.abdolahi@bpums.ac.ir
200319475328460064476
200319475328460064476
No
Department of Radiation Technology, School of Medicine, Bushehr University of Medical Sciences, Bushehr, Iran
Mohammad
Salehi
salehi.mo@tak.iums.ac.ir
200319475328460064477
200319475328460064477
No
Department of Medical Physics, School of Medicine, & Medical Image and Signal Processing Research Core, & Student Research Committee, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
Iman
Shokatian
iman.shokatian@gmail.com
200319475328460064478
200319475328460064478
No
Department of Medical Physics, School of Medicine, & Medical Image and Signal Processing Research Core, & Student Research Committee, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
Reza
Reiazi
reiazi.r@iums.ac.ir
200319475328460064479
200319475328460064479
Yes
Department of Medical Physics, School of Medicine, & Medical Image and Signal Processing Research Core, Iran University of Medical Sciences, Tehran, Iran