PMID- 36358732 OWN - NLM STAT- PubMed-not-MEDLINE LR - 20230308 IS - 2072-6694 (Print) IS - 2072-6694 (Electronic) IS - 2072-6694 (Linking) VI - 14 IP - 21 DP - 2022 Oct 28 TI - A Soft Label Deep Learning to Assist Breast Cancer Target Therapy and Thyroid Cancer Diagnosis. LID - 10.3390/cancers14215312 [doi] LID - 5312 AB - According to the World Health Organization Report 2022, cancer is the most common cause of death contributing to nearly one out of six deaths worldwide. Early cancer diagnosis and prognosis have become essential in reducing the mortality rate. On the other hand, cancer detection is a challenging task in cancer pathology. Trained pathologists can detect cancer, but their decisions are subjective to high intra- and inter-observer variability, which can lead to poor patient care owing to false-positive and false-negative results. In this study, we present a soft label fully convolutional network (SL-FCN) to assist in breast cancer target therapy and thyroid cancer diagnosis, using four datasets. To aid in breast cancer target therapy, the proposed method automatically segments human epidermal growth factor receptor 2 (HER2) amplification in fluorescence in situ hybridization (FISH) and dual in situ hybridization (DISH) images. To help in thyroid cancer diagnosis, the proposed method automatically segments papillary thyroid carcinoma (PTC) on Papanicolaou-stained fine needle aspiration and thin prep whole slide images (WSIs). In the evaluation of segmentation of HER2 amplification in FISH and DISH images, we compare the proposed method with thirteen deep learning approaches, including U-Net, U-Net with InceptionV5, Ensemble of U-Net with Inception-v4, Inception-Resnet-v2 encoder, and ResNet-34 encoder, SegNet, FCN, modified FCN, YOLOv5, CPN, SOLOv2, BCNet, and DeepLabv3+ with three different backbones, including MobileNet, ResNet, and Xception, on three clinical datasets, including two DISH datasets on two different magnification levels and a FISH dataset. The result on DISH breast dataset 1 shows that the proposed method achieves high accuracy of 87.77 +/- 14.97%, recall of 91.20 +/- 7.72%, and F1-score of 81.67 +/- 17.76%, while, on DISH breast dataset 2, the proposed method achieves high accuracy of 94.64 +/- 2.23%, recall of 83.78 +/- 6.42%, and F1-score of 85.14 +/- 6.61% and, on the FISH breast dataset, the proposed method achieves high accuracy of 93.54 +/- 5.24%, recall of 83.52 +/- 13.15%, and F1-score of 86.98 +/- 9.85%, respectively. Furthermore, the proposed method outperforms most of the benchmark approaches by a significant margin (p <0.001). In evaluation of segmentation of PTC on Papanicolaou-stained WSIs, the proposed method is compared with three deep learning methods, including Modified FCN, U-Net, and SegNet. The experimental result demonstrates that the proposed method achieves high accuracy of 99.99 +/- 0.01%, precision of 92.02 +/- 16.6%, recall of 90.90 +/- 14.25%, and F1-score of 89.82 +/- 14.92% and significantly outperforms the baseline methods, including U-Net and FCN (p <0.001). With the high degree of accuracy, precision, and recall, the results show that the proposed method could be used in assisting breast cancer target therapy and thyroid cancer diagnosis with faster evaluation and minimizing human judgment errors. FAU - Wang, Ching-Wei AU - Wang CW AUID- ORCID: 0000-0001-9992-6863 AD - Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan. AD - Graduate Institute of Applied Science and Technology, National Taiwan University of Science and Technology, Taipei 106335, Taiwan. FAU - Lin, Kuan-Yu AU - Lin KY AD - Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan. FAU - Lin, Yi-Jia AU - Lin YJ AUID- ORCID: 0000-0002-8073-8659 AD - Department of Pathology, Tri-Service General Hospital, Taipei 11490, Taiwan. AD - Institute of Pathology and Parasitology, National Defense Medical Center, Taipei 11490, Taiwan. FAU - Khalil, Muhammad-Adil AU - Khalil MA AD - Graduate Institute of Applied Science and Technology, National Taiwan University of Science and Technology, Taipei 106335, Taiwan. FAU - Chu, Kai-Lin AU - Chu KL AD - Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan. FAU - Chao, Tai-Kuang AU - Chao TK AUID- ORCID: 0000-0001-8219-6382 AD - Department of Pathology, Tri-Service General Hospital, Taipei 11490, Taiwan. AD - Institute of Pathology and Parasitology, National Defense Medical Center, Taipei 11490, Taiwan. LA - eng GR - MOST109-2221-E-011-018-MY3, MOST 111-2320-B-016-009/Ministry of Science and Technology, Taiwan/ GR - NTUST-TSGH-111-05/National Taiwan University of Science and Technology-Tri-Service General Hospital/ GR - TSGH-D-109094, TSGH-D-110036, TSGH-A-111010, TSGH-A-112008/Tri-Service General Hospital, Taipei, Taiwan/ PT - Journal Article DEP - 20221028 PL - Switzerland TA - Cancers (Basel) JT - Cancers JID - 101526829 PMC - PMC9657740 OTO - NOTNLM OT - HER2 overexpression OT - brightfield dual in situ hybridization OT - fine needle aspiration OT - fluorescence in situ hybridization OT - metastatic breast cancer OT - soft label deep learning OT - thin prep OT - thyroid cancer COIS- The authors declare that they have no known competing financial interest or personal relationship that could have appeared to influence the work reported in this paper. EDAT- 2022/11/12 06:00 MHDA- 2022/11/12 06:01 PMCR- 2022/10/28 CRDT- 2022/11/11 01:06 PHST- 2022/08/30 00:00 [received] PHST- 2022/10/20 00:00 [revised] PHST- 2022/10/25 00:00 [accepted] PHST- 2022/11/11 01:06 [entrez] PHST- 2022/11/12 06:00 [pubmed] PHST- 2022/11/12 06:01 [medline] PHST- 2022/10/28 00:00 [pmc-release] AID - cancers14215312 [pii] AID - cancers-14-05312 [pii] AID - 10.3390/cancers14215312 [doi] PST - epublish SO - Cancers (Basel). 2022 Oct 28;14(21):5312. doi: 10.3390/cancers14215312.