《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (5): 1647-1657.DOI: 10.11772/j.issn.1001-9081.2025050568
• 前沿与综合应用 • 上一篇
收稿日期:2025-05-22
修回日期:2025-07-23
接受日期:2025-08-11
发布日期:2025-08-20
出版日期:2026-05-10
通讯作者:
张博凯
作者简介:彭文(1980—),男,内蒙古赤峰人,副教授,博士,CCF会员,主要研究方向:医学影像分析、人工智能
Wen PENG1, Bokai ZHANG1(
), Jinwei LIN2
Received:2025-05-22
Revised:2025-07-23
Accepted:2025-08-11
Online:2025-08-20
Published:2026-05-10
Contact:
Bokai ZHANG
About author:PENG Wen, born in 1980, Ph. D., associate professor. His research interests include medical image analysis, artificial intelligence.摘要:
染色体核型分析在产前筛查和遗传疾病诊断中具有重要意义,但现有染色体分类模型普遍存在特征提取能力不足、图像质量敏感性强以及对局部细节感知不充分等问题,导致染色体整体分类准确率不高,尤其是短小染色体常常被错误识别。因此,提出一种融合图像纹理增强与超分辨率技术的染色体粗粒度-细粒度级联分类框架。首先,基于国际人类细胞遗传命名系统(ISCN)对染色体进行粗分类,将染色体划分为长染色体与短小染色体组,缓解类别不均衡与特征混淆问题;其次,针对长染色体分类任务,增加特征增强模块优化分类模型对长染色体的细节感知能力;随后,针对短小染色体图像的特点引入图像超分辨率技术,提升图像质量与模型感知能力。在私有数据集上的实验结果表明,所提框架的染色体整体分类准确率达到98.91%,整体F1分数达到98.77%,其中长染色体的F1分数为99.01%,短小染色体的F1分数为98.31%。该染色体级联分类框架针对不同分类任务采取差异化分类策略与分类模型,显著提升了染色体分类精度和模型鲁棒性。
中图分类号:
彭文, 张博凯, 林金炜. 融合图像纹理增强与超分辨率的染色体级联分类框架[J]. 计算机应用, 2026, 46(5): 1647-1657.
Wen PENG, Bokai ZHANG, Jinwei LIN. Chromosome cascaded classification framework integrating image texture enhancement and super-resolution[J]. Journal of Computer Applications, 2026, 46(5): 1647-1657.
| 分类任务 | 长染色体数 | 短小染色体数 | 总数 |
|---|---|---|---|
| 染色体粗分类 | 31 773 | 14 590 | 46 363 |
| 长染色体细分类 | 31 773 | 31 773 | |
| 短小染色体细分类 | 45 931 | 45 931 | |
| 染色体分类 | 31 773 | 14 590 | 46 363 |
表1 Dataset1在各个分类任务中的染色体分布
Tab. 1 Chromosome distribution of Dataset1 in various classification tasks
| 分类任务 | 长染色体数 | 短小染色体数 | 总数 |
|---|---|---|---|
| 染色体粗分类 | 31 773 | 14 590 | 46 363 |
| 长染色体细分类 | 31 773 | 31 773 | |
| 短小染色体细分类 | 45 931 | 45 931 | |
| 染色体分类 | 31 773 | 14 590 | 46 363 |
| 方法 | Acc | P | R | F1 |
|---|---|---|---|---|
| SwinTransformer-small | 98.81 | 98.58 | 98.66 | 98.62 |
| ResNet18 | 99.13 | 99.18 | 98.81 | 98.99 |
| Inception-ResNetV2 | 99.24 | 99.45 | 98.80 | 99.12 |
| SIATE-Net | 99.33 | 99.31 | 99.09 | 99.20 |
| ResNet50 | 99.57 | 99.59 | 99.41 | 99.50 |
| EfficientNet-B4 | 100.00 | 100.00 | 100.00 | 100.00 |
表2 不同模型的染色体粗分类性能对比 ( %)
Tab. 2 Performance comparison of different models for coarse chromosome classification
| 方法 | Acc | P | R | F1 |
|---|---|---|---|---|
| SwinTransformer-small | 98.81 | 98.58 | 98.66 | 98.62 |
| ResNet18 | 99.13 | 99.18 | 98.81 | 98.99 |
| Inception-ResNetV2 | 99.24 | 99.45 | 98.80 | 99.12 |
| SIATE-Net | 99.33 | 99.31 | 99.09 | 99.20 |
| ResNet50 | 99.57 | 99.59 | 99.41 | 99.50 |
| EfficientNet-B4 | 100.00 | 100.00 | 100.00 | 100.00 |
| 方法 | Acc | P | R | F1 |
|---|---|---|---|---|
| EfficientNet-B4 | 98.89 | 98.95 | 98.67 | 98.77 |
| FEM-EfficientNet-B4 | 99.05 | 99.03 | 99.00 | 99.01 |
表3 长染色体细分类模型的性能对比 ( %)
Tab. 3 Performance comparison of models for fine classification of long chromosomes
| 方法 | Acc | P | R | F1 |
|---|---|---|---|---|
| EfficientNet-B4 | 98.89 | 98.95 | 98.67 | 98.77 |
| FEM-EfficientNet-B4 | 99.05 | 99.03 | 99.00 | 99.01 |
| 方法 | Acc | P | R | F1 |
|---|---|---|---|---|
| EfficientNet-B4 | 90.72 | 91.75 | 89.09 | 90.05 |
| SIATE-Net | 95.17 | 94.77 | 94.69 | 94.68 |
| CATE-Net | 95.88 | 96.37 | 95.43 | 95.82 |
表4 短小染色体细分类模型性能的对比 ( %)
Tab. 4 Performance comparison of models for fine classification of short chromosomes
| 方法 | Acc | P | R | F1 |
|---|---|---|---|---|
| EfficientNet-B4 | 90.72 | 91.75 | 89.09 | 90.05 |
| SIATE-Net | 95.17 | 94.77 | 94.69 | 94.68 |
| CATE-Net | 95.88 | 96.37 | 95.43 | 95.82 |
| 预处理方法 | PSNR/dB | SSIM | Acc/% | P/% | R/% | F1/% |
|---|---|---|---|---|---|---|
| 原始图像 | 95.88 | 96.37 | 95.43 | 95.82 | ||
| Bicubic | 39.24 | 0.991 43 | 96.18 | 95.59 | 96.56 | 95.98 |
| SRCNN | 53.35 | 0.993 15 | 96.55 | 96.06 | 96.88 | 96.43 |
| SRGAN | 56.74 | 0.993 84 | 97.59 | 97.89 | 95.94 | 96.75 |
| LapSRN | 59.53 | 0.999 95 | 97.92 | 97.34 | 98.12 | 97.68 |
| EDSR | 61.15 | 0.999 96 | 98.28 | 97.52 | 97.50 | 97.50 |
| LBNet | 62.67 | 0.999 85 | 98.62 | 97.95 | 98.75 | 98.31 |
表5 超分辨率方法的性能对比
Tab. 5 Performance comparison of super-resolution methods
| 预处理方法 | PSNR/dB | SSIM | Acc/% | P/% | R/% | F1/% |
|---|---|---|---|---|---|---|
| 原始图像 | 95.88 | 96.37 | 95.43 | 95.82 | ||
| Bicubic | 39.24 | 0.991 43 | 96.18 | 95.59 | 96.56 | 95.98 |
| SRCNN | 53.35 | 0.993 15 | 96.55 | 96.06 | 96.88 | 96.43 |
| SRGAN | 56.74 | 0.993 84 | 97.59 | 97.89 | 95.94 | 96.75 |
| LapSRN | 59.53 | 0.999 95 | 97.92 | 97.34 | 98.12 | 97.68 |
| EDSR | 61.15 | 0.999 96 | 98.28 | 97.52 | 97.50 | 97.50 |
| LBNet | 62.67 | 0.999 85 | 98.62 | 97.95 | 98.75 | 98.31 |
图10 短小染色体样本及Grad-CAM热力图在超分辨率技术处理前后的对比
Fig. 10 Comparison of short chromosome samples and Grad-CAM heatmaps before and after super-resolution processing
| 任务 | 方法 | Acc | P | R | F1 |
|---|---|---|---|---|---|
染色体 粗分类 | EfficientNet-B4 | 100.00 | 100.00 | 100.00 | 100.00 |
长染色体 细分类 | FEM-EfficientNet-B4 | 99.05 | 99.03 | 99.00 | 99.01 |
短小染色体 细分类 | LBNet+CATE-Net | 98.62 | 97.95 | 98.75 | 98.31 |
| 染色体分类 | 本文框架 | 98.91 | 98.67 | 98.92 | 98.77 |
表6 Dataset1上染色体分类子任务的分类性能 ( %)
Tab. 6 Classification performance of subtasks of chromosome classification on Dataset1
| 任务 | 方法 | Acc | P | R | F1 |
|---|---|---|---|---|---|
染色体 粗分类 | EfficientNet-B4 | 100.00 | 100.00 | 100.00 | 100.00 |
长染色体 细分类 | FEM-EfficientNet-B4 | 99.05 | 99.03 | 99.00 | 99.01 |
短小染色体 细分类 | LBNet+CATE-Net | 98.62 | 97.95 | 98.75 | 98.31 |
| 染色体分类 | 本文框架 | 98.91 | 98.67 | 98.92 | 98.77 |
| 模型 | Acc | P | R | F1 | F1_L | F1_S |
|---|---|---|---|---|---|---|
| VGG | 89.99 | 89.96 | 90.11 | 89.95 | 92.60 | 87.11 |
| ResNet | 95.18 | 95.34 | 95.01 | 95.12 | 96.95 | 92.31 |
| DenseNet | 95.94 | 95.88 | 96.13 | 95.99 | 97.18 | 94.11 |
| Vision Transformer | 97.07 | 97.11 | 97.11 | 97.04 | 97.95 | 96.62 |
| VAN | 97.50 | 97.63 | 97.44 | 97.58 | 98.26 | 96.78 |
| CIR-Net | 96.52 | 96.10 | 96.77 | 96.47 | 98.03 | 93.59 |
| SIATE-Net | 98.04 | 98.08 | 97.71 | 97.90 | 98.33 | 97.42 |
| 本文框架 | 98.91 | 98.67 | 98.92 | 98.77 | 99.01 | 98.31 |
表7 Dataset1上不同分类模型的性能对比 ( %)
Tab. 7 Performance comparison of different classification models on Dataset1
| 模型 | Acc | P | R | F1 | F1_L | F1_S |
|---|---|---|---|---|---|---|
| VGG | 89.99 | 89.96 | 90.11 | 89.95 | 92.60 | 87.11 |
| ResNet | 95.18 | 95.34 | 95.01 | 95.12 | 96.95 | 92.31 |
| DenseNet | 95.94 | 95.88 | 96.13 | 95.99 | 97.18 | 94.11 |
| Vision Transformer | 97.07 | 97.11 | 97.11 | 97.04 | 97.95 | 96.62 |
| VAN | 97.50 | 97.63 | 97.44 | 97.58 | 98.26 | 96.78 |
| CIR-Net | 96.52 | 96.10 | 96.77 | 96.47 | 98.03 | 93.59 |
| SIATE-Net | 98.04 | 98.08 | 97.71 | 97.90 | 98.33 | 97.42 |
| 本文框架 | 98.91 | 98.67 | 98.92 | 98.77 | 99.01 | 98.31 |
| 任务 | 方法 | Acc | P | R | F1 |
|---|---|---|---|---|---|
染色体 粗分类 | EfficientNet-B4 | 100.00 | 100.00 | 100.00 | 100.00 |
长染色体 细分类 | FEM-EfficientNet-B4 | 99.51 | 99.54 | 99.45 | 99.48 |
短小染色体 细分类 | LBNet+CATE-Net | 98.94 | 99.11 | 99.04 | 99.05 |
| 染色体分类 | 本文框架 | 99.33 | 99.39 | 99.31 | 99.34 |
表8 Dataset2上染色体分类子任务的分类性能 ( %)
Tab. 8 Classification performance of subtasks of chromosome classification on Dataset2
| 任务 | 方法 | Acc | P | R | F1 |
|---|---|---|---|---|---|
染色体 粗分类 | EfficientNet-B4 | 100.00 | 100.00 | 100.00 | 100.00 |
长染色体 细分类 | FEM-EfficientNet-B4 | 99.51 | 99.54 | 99.45 | 99.48 |
短小染色体 细分类 | LBNet+CATE-Net | 98.94 | 99.11 | 99.04 | 99.05 |
| 染色体分类 | 本文框架 | 99.33 | 99.39 | 99.31 | 99.34 |
| 模型 | Acc | P | R | F1 | F1_L | F1_S |
|---|---|---|---|---|---|---|
| VGG | 92.58 | 91.91 | 92.17 | 92.23 | 93.27 | 91.31 |
| ResNet | 94.77 | 93.95 | 94.62 | 93.70 | 95.69 | 92.97 |
| DenseNet | 95.85 | 95.60 | 94.47 | 94.55 | 96.76 | 93.44 |
| Vision Transformer | 97.96 | 97.84 | 97.36 | 97.97 | 98.63 | 94.93 |
| VAN | 98.55 | 98.71 | 98.54 | 98.60 | 98.96 | 98.27 |
| CIR-Net | 96.12 | 95.87 | 96.15 | 96.03 | 97.25 | 94.08 |
| SIATE-Net | 98.95 | 98.60 | 98.84 | 98.84 | 99.27 | 98.51 |
| 本文框架 | 99.33 | 99.39 | 99.31 | 99.34 | 99.48 | 99.05 |
表9 Dataset2上不同分类模型的性能对比 ( %)
Tab. 9 Performance comparison of different classification models on Dataset2
| 模型 | Acc | P | R | F1 | F1_L | F1_S |
|---|---|---|---|---|---|---|
| VGG | 92.58 | 91.91 | 92.17 | 92.23 | 93.27 | 91.31 |
| ResNet | 94.77 | 93.95 | 94.62 | 93.70 | 95.69 | 92.97 |
| DenseNet | 95.85 | 95.60 | 94.47 | 94.55 | 96.76 | 93.44 |
| Vision Transformer | 97.96 | 97.84 | 97.36 | 97.97 | 98.63 | 94.93 |
| VAN | 98.55 | 98.71 | 98.54 | 98.60 | 98.96 | 98.27 |
| CIR-Net | 96.12 | 95.87 | 96.15 | 96.03 | 97.25 | 94.08 |
| SIATE-Net | 98.95 | 98.60 | 98.84 | 98.84 | 99.27 | 98.51 |
| 本文框架 | 99.33 | 99.39 | 99.31 | 99.34 | 99.48 | 99.05 |
| Class(i) | Dataset1 | Dataset2 | ||||||
|---|---|---|---|---|---|---|---|---|
| Acci | Pi | Ri | F1i | Acci | Pi | Ri | F1i | |
| 1 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 2 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 3 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 4 | 100.00 | 97.56 | 100.00 | 98.77 | 100.00 | 100.00 | 100.00 | 100.00 |
| 5 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 6 | 97.50 | 100.00 | 97.50 | 98.73 | 96.15 | 100.00 | 96.15 | 98.04 |
| 7 | 100.00 | 97.56 | 100.00 | 98.77 | 100.00 | 96.30 | 100.00 | 98.11 |
| 8 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 100.00 | 100.00 | 100.00 |
| 9 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 10 | 100.00 | 95.24 | 100.00 | 97.56 | 100.00 | 100.00 | 100.00 | 100.00 |
| 11 | 97.50 | 97.50 | 97.50 | 97.50 | 100.00 | 100.00 | 100.00 | 100.00 |
| 12 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 13 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 100.00 | 100.00 | 100.00 |
| 14 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 96.30 | 100.00 | 98.11 |
| 15 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 16 | 97.50 | 95.12 | 97.50 | 96.30 | 96.15 | 100.00 | 96.15 | 98.04 |
| 17 | 97.50 | 100.00 | 97.50 | 98.73 | 96.15 | 100.00 | 96.15 | 98.04 |
| 18 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 96.30 | 100.00 | 98.11 |
| 19 | 100.00 | 97.56 | 100.00 | 98.77 | 100.00 | 100.00 | 100.00 | 100.00 |
| 20 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 92.86 | 100.00 | 96.30 |
| 21 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 22 | 100.00 | 100.00 | 100.00 | 100.00 | 96.15 | 100.00 | 96.15 | 98.04 |
| X | 96.55 | 96.55 | 96.55 | 96.55 | 95.00 | 100.00 | 95.00 | 97.44 |
| Y | 100.00 | 90.91 | 100.00 | 95.45 | 100.00 | 100.00 | 100.00 | 100.00 |
表10 Dataset1和Dataset2上染色体分类框架分类性能 ( %)
Tab. 10 Classification performance of chromosome classification framework on Dataset1 and Dataset2
| Class(i) | Dataset1 | Dataset2 | ||||||
|---|---|---|---|---|---|---|---|---|
| Acci | Pi | Ri | F1i | Acci | Pi | Ri | F1i | |
| 1 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 2 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 3 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 4 | 100.00 | 97.56 | 100.00 | 98.77 | 100.00 | 100.00 | 100.00 | 100.00 |
| 5 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 6 | 97.50 | 100.00 | 97.50 | 98.73 | 96.15 | 100.00 | 96.15 | 98.04 |
| 7 | 100.00 | 97.56 | 100.00 | 98.77 | 100.00 | 96.30 | 100.00 | 98.11 |
| 8 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 100.00 | 100.00 | 100.00 |
| 9 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 10 | 100.00 | 95.24 | 100.00 | 97.56 | 100.00 | 100.00 | 100.00 | 100.00 |
| 11 | 97.50 | 97.50 | 97.50 | 97.50 | 100.00 | 100.00 | 100.00 | 100.00 |
| 12 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 13 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 100.00 | 100.00 | 100.00 |
| 14 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 96.30 | 100.00 | 98.11 |
| 15 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 16 | 97.50 | 95.12 | 97.50 | 96.30 | 96.15 | 100.00 | 96.15 | 98.04 |
| 17 | 97.50 | 100.00 | 97.50 | 98.73 | 96.15 | 100.00 | 96.15 | 98.04 |
| 18 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 96.30 | 100.00 | 98.11 |
| 19 | 100.00 | 97.56 | 100.00 | 98.77 | 100.00 | 100.00 | 100.00 | 100.00 |
| 20 | 97.50 | 100.00 | 97.50 | 98.73 | 100.00 | 92.86 | 100.00 | 96.30 |
| 21 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |
| 22 | 100.00 | 100.00 | 100.00 | 100.00 | 96.15 | 100.00 | 96.15 | 98.04 |
| X | 96.55 | 96.55 | 96.55 | 96.55 | 95.00 | 100.00 | 95.00 | 97.44 |
| Y | 100.00 | 90.91 | 100.00 | 95.45 | 100.00 | 100.00 | 100.00 | 100.00 |
| 任务 | 方法 | 参数量/106 | GFLOPs | 推理 时间/s | 平均F1/% |
|---|---|---|---|---|---|
染色体 粗分类 | EfficientNet-B4 | 17.56 | 173.77 | 0.034 6 | 100.00 |
长染色体 细分类 | FEM-EfficientNet-B4 | 17.56 | 173.86 | 0.038 0 | 99.25 |
短小染色体 细分类 | LBNet | 0.73 | 58.54 | 0.039 5 | |
| CATE-Net | 26.09 | 30.20 | 0.012 0 | 98.68 | |
| 染色体分类 | 本文框架 | 61.97 | 323.04 | 0.076 9 | 99.10 |
表11 染色体分类子任务上的模型复杂度
Tab. 11 Model complexity of subtasks of chromosome classification
| 任务 | 方法 | 参数量/106 | GFLOPs | 推理 时间/s | 平均F1/% |
|---|---|---|---|---|---|
染色体 粗分类 | EfficientNet-B4 | 17.56 | 173.77 | 0.034 6 | 100.00 |
长染色体 细分类 | FEM-EfficientNet-B4 | 17.56 | 173.86 | 0.038 0 | 99.25 |
短小染色体 细分类 | LBNet | 0.73 | 58.54 | 0.039 5 | |
| CATE-Net | 26.09 | 30.20 | 0.012 0 | 98.68 | |
| 染色体分类 | 本文框架 | 61.97 | 323.04 | 0.076 9 | 99.10 |
| 模型 | 参数量/106 | GFLOPs | 推理时间/s | 平均F1/% |
|---|---|---|---|---|
| VGG | 138.36 | 11.69 | 0.003 0 | 91.09 |
| ResNet | 44.55 | 33.02 | 0.010 1 | 94.41 |
| DenseNet | 28.68 | 15.50 | 0.030 6 | 95.27 |
| Vision Transformer | 309.52 | 0.92 | 0.010 6 | 97.51 |
| VAN | 44.77 | 419.65 | 0.024 1 | 98.09 |
| CIR-Net | 60.19 | 49.21 | 0.021 0 | 96.25 |
| SIATE-Net | 40.36 | 30.23 | 0.131 8 | 98.37 |
| 本文框架 | 61.97 | 323.04 | 0.076 9 | 99.10 |
表12 不同分类模型的复杂度统计
Tab. 12 Complexity statistics of different classification models
| 模型 | 参数量/106 | GFLOPs | 推理时间/s | 平均F1/% |
|---|---|---|---|---|
| VGG | 138.36 | 11.69 | 0.003 0 | 91.09 |
| ResNet | 44.55 | 33.02 | 0.010 1 | 94.41 |
| DenseNet | 28.68 | 15.50 | 0.030 6 | 95.27 |
| Vision Transformer | 309.52 | 0.92 | 0.010 6 | 97.51 |
| VAN | 44.77 | 419.65 | 0.024 1 | 98.09 |
| CIR-Net | 60.19 | 49.21 | 0.021 0 | 96.25 |
| SIATE-Net | 40.36 | 30.23 | 0.131 8 | 98.37 |
| 本文框架 | 61.97 | 323.04 | 0.076 9 | 99.10 |
| [1] | 冯涛,陈斌,张跃飞. 基于改进的Mask R-CNN的染色体图像分割框架[J]. 计算机应用, 2020, 40(11): 3332-3339. |
| FENG T, CHEN B, ZHANG Y F. Chromosome image segmentation framework based on improved Mask R-CNN[J]. Journal of Computer Applications, 2020, 40(11): 3332-3339. | |
| [2] | LIN C, ZHAO G, YIN A, et al. A multi-stages chromosome segmentation and mixed classification method for chromosome automatic karyotyping[C]// Proceedings of the 2020 International Conference on Web Information Systems and Applications, LNCS 12432. Cham: Springer, 2020: 365-376. |
| [3] | SOMASUNDARAM D, MADIAN N, GOH K M, et al. Chromosome segmentation and classification: an updated review[J]. Knowledge and Information Systems, 2025, 67(2): 977-1011. |
| [4] | ABID F, HAMAMI L. A survey of neural network based automated systems for human chromosome classification[J]. Artificial Intelligence Review, 2018, 49(1): 41-56. |
| [5] | LeCUN Y, BOSER B, DENKER J S, et al. Backpropagation applied to handwritten Zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551. |
| [6] | KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]// Proceedings of the 25th International Conference on Neural Information Processing Systems — Volume 1. Red Hook: Curran Associates Inc., 2012: 1097-1105. |
| [7] | SHARMA M, SAHA O, SRIRAMAN A, et al. Crowdsourcing for chromosome segmentation and deep classification[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2017: 786-793. |
| [8] | ZHANG W, SONG S, BAI T, et al. Chromosome classification with convolutional neural network based deep learning[C]// Proceedings of the 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics. Piscataway: IEEE, 2018: 1-5. |
| [9] | HU X, YI W, JIANG L, et al. Classification of metaphase chromosomes using deep convolutional neural network[J]. Journal of Computational Biology, 2019, 26(5): 473-484. |
| [10] | LIN C, ZHAO G, YIN A, et al. MixNet: a better promising approach for chromosome classification based on aggregated residual architecture[C]// Proceedings of the 2020 International Conference on Computer Vision, Image and Deep Learning. Piscataway: IEEE, 2020: 313-318. |
| [11] | XIE S, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5987-5995. |
| [12] | WANG C, HAN M, WU Y, et al. CNN based chromosome classification architecture for combined dataset[C]// Proceedings of the 6th International Conference on Communication, Image and Signal Processing. Piscataway: IEEE, 2021: 69-74. |
| [13] | HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. |
| [14] | HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. |
| [15] | SHARMA M, SWATI, VIG L. Automatic chromosome classification using deep attention based sequence learning of chromosome bands[C]// Proceedings of the 2018 International Joint Conference on Neural Networks. Piscataway: IEEE, 2018: 1-8. |
| [16] | HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. |
| [17] | LIN C, ZHAO G, YANG Z, et al. CIR-Net: automatic classification of human chromosome based on Inception-ResNet architecture[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022, 19(3): 1285-1293. |
| [18] | SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning[C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2017: 4278-4284. |
| [19] | 罗纯龙,赵屹. 染色体核型分析深度学习方法综述[J]. 中国图象图形学报, 2023, 28(11): 3363-3385. |
| LUO C L, ZHAO Y. Review of deep learning methods for karyotype analysis[J]. Journal of Image and Graphics, 2023, 28(11): 3363-3385. | |
| [20] | 平金如,孙子文. 特征融合的MV2-Transformer肺炎X 光图像分类模型[J]. 计算机应用, 2025, 45(12): 4030-4036. |
| PING J R, SUN Z W. Pneumonia X-ray image classification model by MV2-Transformer with feature fusion[J]. Journal of Computer Applications, 2025, 45(12): 4030-4036. | |
| [21] | QIN Y, WEN J, ZHENG H, et al. Varifocal-Net: a chromosome classification approach using deep convolutional networks[J]. IEEE Transactions on Medical Imaging, 2019, 38(11): 2569-2581. |
| [22] | 彭文,林金伟. 基于空间信息关注和纹理增强的短小染色体分类方法[J]. 图学学报, 2024, 45(5): 1017-1029. |
| PENG W, LIN J W. A short chromosome classification method based on spatial attention and texture enhancement[J]. Journal of Graphics, 2024, 45(5): 1017-1029. | |
| [23] | ZHU L, JI D, ZHU S, et al. Learning statistical texture for semantic segmentation[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 12532-12541. |
| [24] | McGOWAN-JORDAN J, HASTINGS T J, MOORE S. ISCN 2020: an international system for human cytogenomic nomenclature (2020) reprint of ‘cytogenetic and genome research 2020, vol. 160, no. 7-8’[M]. Basel: Karger, 2020. |
| [25] | ZHANG Y, YE M, ZHU G, et al. FFCA-YOLO for small object detection in remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: No.5611215. |
| [26] | GAO G, WANG Z, LI J, et al. Lightweight bimodal network for single-image super-resolution via symmetric CNN and recursive Transformer[C]// Proceedings of the 31st International Joint Conference on Artificial Intelligence. California: ijcai.org, 2022: 913-919. |
| [27] | DING W, CHANG L, GU C, et al. Classification of chromosome karyotype based on Faster-RCNN with the segmentation and enhancement preprocessing model[C]// Proceedings of the 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics. Piscataway: IEEE, 2019: 1-5. |
| [28] | SWATI S, SHARMA M, VIG L. Automatic classification of low resolution chromosomal images[C]// Proceedings of the 2018 European Conference on Computer Vision Workshops, LNCS 11134. Cham: Springer, 2019: 315-325. |
| [29] | LIU X, FU L, LIN C W J, et al. SRAS-net: low-resolution chromosome image classification based on deep learning[J]. IET Systems Biology, 2022, 16(3/4): 85-97. |
| [30] | CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 1800-1807. |
| [31] | TAN M, LE Q V. EfficientNet: rethinking model scaling for convolutional neural networks[C]// Proceedings of the 36th International Conference on Machine Learning. New York: JMLR.org, 2019: 6105-6114. |
| [32] | DONG C, LOY C C, HE K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. |
| [33] | LEDIG C, THEIS L, HUSZÁR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 105-114. |
| [34] | LAI W S, HUANG J B, AHUJA N, et al. Deep Laplacian pyramid networks for fast and accurate super-resolution[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5835-5843. |
| [35] | LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2017: 1132-1140. |
| [36] | SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 618-626. |
| [1] | 徐千惠, 钮可, 朱顺哲, 石林, 李军. 增强型可逆神经网络视频隐写网络GAB3D-SEVSN[J]. 《计算机应用》唯一官方网站, 2026, 46(2): 467-474. |
| [2] | 张嘉祥, 李晓明, 张佳慧. 结合新类特征增强与度量机制的小样本目标检测算法[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2984-2992. |
| [3] | 张伟, 牛家祥, 马继超, 沈琼霞. 深层语义特征增强的ReLM中文拼写纠错模型[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2484-2490. |
| [4] | 刘皓宇, 孔鹏伟, 王耀力, 常青. 基于多视角信息的行人检测算法[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2325-2332. |
| [5] | 党伟超, 范英豪, 高改梅, 刘春霞. 融合时序与全局上下文特征增强的弱监督动作定位[J]. 《计算机应用》唯一官方网站, 2025, 45(3): 963-971. |
| [6] | 谢斌红, 高婉银, 陆望东, 张英俊, 张睿. 小样本相似性匹配特征增强的密集目标计数网络[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 403-410. |
| [7] | 孟海腾, 赵小乐, 李天瑞. 基于非对称信息蒸馏网络的轻量级图像超分辨重建[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 601-609. |
| [8] | 杨本臣, 李浩然, 金海波. 级联融合与增强重建的多聚焦图像融合网络[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 594-600. |
| [9] | 周景, 唐振洋, 董晖, 刘心. 融合特征增强和对比学习的电力客服工单多标签文本分类方法[J]. 《计算机应用》唯一官方网站, 2025, 45(12): 3847-3854. |
| [10] | 刘子涵, 周登文, 刘玉铠. 基于全局依赖Transformer的图像超分辨率网络[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1588-1596. |
| [11] | 郭琳, 刘坤虎, 马晨阳, 来佑雪, 徐映芬. 基于感受野扩展残差注意力网络的图像超分辨率重建[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1579-1587. |
| [12] | 王杰, 孟华. 基于点云整体拓扑结构的图像分类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1107-1113. |
| [13] | 李新叶, 侯晔凝, 孔英会, 燕志旗. 结合特征融合与增强注意力的少样本目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 745-751. |
| [14] | 陈豪, 夏振平, 程成, 林李兴, 张博文. 基于Transformer-CNN的轻量级图像超分辨率重建网络[J]. 《计算机应用》唯一官方网站, 2024, 44(1): 292-299. |
| [15] | 陈佳, 张鸿. 基于特征增强和语义相关性匹配的图像文本检索方法[J]. 《计算机应用》唯一官方网站, 2024, 44(1): 16-23. |
| 阅读次数 | ||||||
|
全文 |
|
|||||
|
摘要 |
|
|||||