Nengliang Ouyang1, Weijia Wang2, Li Ma3, Yanfang Wang3, Qingwu Chen3, Shanhong Yang2, Jinye Xie2, Shaoshen Su2, Yin Cheng2, Qiong Cheng2, Lei Zheng4, Yong Yuan2. 1. Department of Laboratory Medicine, Zhongshan Hospital, Sun Yat-sen University, Zhongshan, PR China; Department of Laboratory Medicine, Nanfang Hospital, Southern Medical University, GuangZhou, PR China. 2. Department of Laboratory Medicine, Zhongshan Hospital, Sun Yat-sen University, Zhongshan, PR China. 3. Zhongshan Yangshi Technology Co., Ltd, ZhongShan, PR China. 4. Department of Laboratory Medicine, Nanfang Hospital, Southern Medical University, GuangZhou, PR China.
Abstract
PURPOSE: To evaluate the efficacy of diagnosis systems based upon instance segmentation with convolutional neural networks (CNNs) for diagnosing acute promyelocytic leukemia (APL) in bone marrow smear images. MATERIALS AND METHODS: A self-established dataset was used in this study that was exempted from review by the institution review board, which consisted of 13,504 bone marrow smear images. One subset of the dataset with 12,215 labeled images was split into training (80%) and validation (20%), another with 1289 labeled images was used to test, in which each test entry consists of about 130 images. An instance segmentation method named Mask R-CNN was used to detect and classify the nucleated cells. Here, we train a trained neural network from scratch; for comparison, we also use a network pre-trained on MS COCO (common objects in context, a data set provided by Microsoft which can be used for image recognition, the images in MS coco dataset are divided into training, validation and test sets) and fine-tuned with our dataset and both were trained with same data augmentation scheme. Diagnosis systems based on trained models and "FAB Classification" (French-American-British classification systems, a series of diagnostic criteria for acute leukemia, which was first proposed in 1976) were developed for diagnosing the test entry as APL or as not. Average precision (AP) and average recall (AR) were used to evaluate model performance. RESULTS: The best-performing model had an average precision of 62.5%, which was the augmented pre-trained Mask R-CNN with average recall 84.1%. The average precision of the pre-trained model was greater than that of the model trained from scratch (P < 0.05). Augmenting the dataset further increased accuracy (P < 0 0.03). CONCLUSION: Deep learning technology such as instance segmentation with Mask R-CNN may accurately diagnose APL in bone marrow smear images with an average precision of 62.5% when 0.5 as IoU thresholds. A data augmentation and pre-trained approach further improved accuracy.
PURPOSE: To evaluate the efficacy of diagnosis systems based upon instance segmentation with convolutional neural networks (CNNs) for diagnosing acute promyelocytic leukemia (APL) in bone marrow smear images. MATERIALS AND METHODS: A self-established dataset was used in this study that was exempted from review by the institution review board, which consisted of 13,504 bone marrow smear images. One subset of the dataset with 12,215 labeled images was split into training (80%) and validation (20%), another with 1289 labeled images was used to test, in which each test entry consists of about 130 images. An instance segmentation method named Mask R-CNN was used to detect and classify the nucleated cells. Here, we train a trained neural network from scratch; for comparison, we also use a network pre-trained on MS COCO (common objects in context, a data set provided by Microsoft which can be used for image recognition, the images in MS coco dataset are divided into training, validation and test sets) and fine-tuned with our dataset and both were trained with same data augmentation scheme. Diagnosis systems based on trained models and "FAB Classification" (French-American-British classification systems, a series of diagnostic criteria for acute leukemia, which was first proposed in 1976) were developed for diagnosing the test entry as APL or as not. Average precision (AP) and average recall (AR) were used to evaluate model performance. RESULTS: The best-performing model had an average precision of 62.5%, which was the augmented pre-trained Mask R-CNN with average recall 84.1%. The average precision of the pre-trained model was greater than that of the model trained from scratch (P < 0.05). Augmenting the dataset further increased accuracy (P < 0 0.03). CONCLUSION: Deep learning technology such as instance segmentation with Mask R-CNN may accurately diagnose APL in bone marrow smear images with an average precision of 62.5% when 0.5 as IoU thresholds. A data augmentation and pre-trained approach further improved accuracy.
Authors: Karsten Wendt; Jan Moritz Middeke; Jan-Niklas Eckardt; Tim Schmittmann; Sebastian Riechert; Michael Kramer; Anas Shekh Sulaiman; Katja Sockel; Frank Kroschinsky; Johannes Schetelig; Lisa Wagenführ; Ulrich Schuler; Uwe Platzbecker; Christian Thiede; Friedrich Stölzel; Christoph Röllig; Martin Bornhäuser Journal: BMC Cancer Date: 2022-02-22 Impact factor: 4.430