Chi-Chung Chen

Chi-Chung Chen

Auto-generated profile, based on publicly available information

Chi-Chung Chen

AetherAI Co., Ltd., Taipei, Taiwan

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 February 2021 in Nature Communications
Verified
Journal Article
Open access
PDF file
Chi-Long ChenChi-Long Chen
Chi-Long Chen
CCChi-Chung Chen
Chi-Chung Chen
WYWei-Hsiang Yu
Wei-Hsiang Yu
SCSzu-Hua Chen
Szu-Hua Chen
Yu-Chan ChangYu-Chan Chang
Yu-Chan Chang
CCCheng-Yu Chen
Cheng-Yu Chen
Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole-slide images (WSIs). Most studies have employed patch-based methods, which often require detailed annotation of image patches. This typically involves laborious free-hand contouring on WSIs. To alleviate the burden of such contouring and obtain benefits from scaling up training with numerous WSIs, we develop a method for training neural networks on entire WSIs using only slide-level diagnoses. Our method leverages the unified memory mechanism to overcome the memory constraint of compute accelerators. Experiments conducted on a data set of 9662 lung cancer WSIs reveal that the proposed method achieves areas under the receiver operating characteristic curve of 0.9594 and 0.9414 for adenocarcinoma and squamous cell carcinoma classification on the testing set, respectively. Furthermore, the method demonstrates higher classification performance than multiple-instance learning as well as strong localization results for small lesions through class activation mapping.

10 June 2022 in Nature Communications
Verified
Journal Article
Open access
PDF file
SHShih-Chiang Huang
Shih-Chiang Huang
CCChi-Chung Chen
Chi-Chung Chen
JLJui Lan
Jui Lan
THTsan-Yu Hsieh
Tsan-Yu Hsieh
HCHuei-Chieh Chuang
Huei-Chieh Chuang
TCTse-Ching Chen
Tse-Ching Chen
The pathological identification of lymph node (LN) metastasis is demanding and tedious. Although convolutional neural networks (CNNs) possess considerable potential in improving the process, the ultrahigh-resolution of whole slide images hinders the development of a clinically applicable solution. We design an artificial-intelligence-assisted LN assessment workflow to facilitate the routine counting of metastatic LNs. Unlike previous patch-based approaches, our proposed method trains CNNs by using 5-gigapixel images, obviating the need for lesion-level annotations. Trained on 5907 LN images, our algorithm identifies metastatic LNs in gastric cancer with a slide-level area under the receiver operating characteristic curve (AUC) of 0.9936. Clinical experiments reveal that the workflow significantly improves the sensitivity of micrometastasis identification (81.94% to 95.83%, P < .001) and isolated tumor cells (67.95% to 96.15%, P < .001) in a significantly shorter review time (−31.5%, P < .001). Cross-site evaluation indicates that the algorithm is highly robust (AUC = 0.9829).

8 June 2021 in Laboratory Investigation
Verified
Journal Article
Open access
WCWen-Yu Chuang
Wen-Yu Chuang
CCChi-Chung Chen
Chi-Chung Chen
WYWei-Hsiang Yu
Wei-Hsiang Yu
CYChi-Ju Yeh
Chi-Ju Yeh
SCShang-Hung Chang
Shang-Hung Chang
CYChao-Yuan Yeh
Chao-Yuan Yeh
Detection of nodal micrometastasis (tumor size: 0.2-2.0 mm) is challenging for pathologists due to the small size of metastatic foci. Since lymph nodes with micrometastasis are counted as positive nodes, detecting micrometastasis is crucial for accurate pathologic staging of colorectal cancer. Previously, deep learning algorithms developed with manually annotated images performed well in identifying micrometastasis of breast cancer in sentinel lymph nodes. However, the process of manual annotation is labor intensive and time consuming. Multiple instance learning was later used to identify metastatic breast cancer without manual annotation, but its performance appears worse in detecting micrometastasis. Here, we developed a deep learning model using whole-slide images of regional lymph nodes of colorectal cancer with only a slide-level label (either a positive or negative slide). The training, validation, and testing sets included 1963, 219, and 1000 slides, respectively. A supercomputer TAIWANIA 2 was used to train a deep learning model to identify metastasis. At slide level, our algorithm performed well in identifying both macrometastasis (tumor size > 2.0 mm) and micrometastasis with an area under the receiver operating characteristics curve (AUC) of 0.9993 and 0.9956, respectively. Since most of our slides had more than one lymph node, we then tested the performance of our algorithm on 538 single-lymph node images randomly cropped from the testing set. At single-lymph node level, our algorithm maintained good performance in identifying macrometastasis and micrometastasis with an AUC of 0.9944 and 0.9476, respectively. Visualization using class activation mapping confirmed that our model identified nodal metastasis based on areas of tumor cells. Our results demonstrate for the first time that micrometastasis could be detected by deep learning on whole-slide images without manual annotation.

31 July 2023 in Histopathology
Verified
Journal Article
Closed access
YLYi‐Jyun Lin
Yi‐Jyun Lin
CCChi‐Chung Chen
Chi‐Chung Chen
CLChia‐Hsiang Lee
Chia‐Hsiang Lee
CYChao-Yuan Yeh
Chao-Yuan Yeh
YJYung-Ming Jeng
Yung-Ming Jeng

4 October 2024 in bioRxiv
Verified
Preprint
Open access
PDF file
CCChi-Chung Chen
Chi-Chung Chen
YYYi-Chen Yeh
Yi-Chen Yeh
MLMatthew My Lin
Matthew My Lin
CYChao-Yuan Yeh
Chao-Yuan Yeh
A robust artificial intelligence-assisted workflow for tumor assessment in pathology requires not only accurate classification but also precise lesion localization. While current weakly supervised learning methods significantly reduce the need for extensive annotations and leverage large quantities of annotation-free whole-slide images (WSIs) to enhance classification robustness, they often fall short in segmentation accuracy. We attribute this limitation to the optimization goals in classification, which tend to focus solely on the most representative features—an approach that is particularly inefficient for WSIs with gigapixel resolution. To address this challenge, we introduce a novel approach based on streaming convolution, an end-to-end method for WSI training. Our contributions include the Rectified LogSumExp (ReLSE) pooling method and adaptive pseudo annotation generation for self-training, both designed to encourage models to learn from sub-representative features. Using only slide-level annotations from the CAMELYON16 dataset, our method achieves a significant improvement in metastasis localization, with a patch-level recall from 53.88% to 79.18% at a precision of 80%. This conclusion also holds for a dataset collected from Taipei Veterans General Hospital (TVGH), used in the assessment of lung cancer lymph node metastasis with a recall improved from 42.98% to 72.27%. The proposed method can also be integrated with additional manual annotations. Experiment results showed the semi-supervised model (recall: 91.12%) could even outperform the strongly supervised model (recall: 81.80%) on the TVGH dataset.

13 July 2026 in Research Square
Verified
Preprint
Open access
CCChi-Chung Chen
Chi-Chung Chen
SHShih-Chiang Huang
Shih-Chiang Huang
TCTu-Yung Chang
Tu-Yung Chang
CCChen-Lin Chi
Chen-Lin Chi
HCHuei-Chieh Chuang
Huei-Chieh Chuang
TCTse-Ching Chen
Tse-Ching Chen
Gastric biopsy interpretation requires simultaneous assessment of malignancies, precancerous lesions, infections, and benign conditions, yet existing artificial intelligence models address only two to three diagnostic categories and have been evaluated under a single mode of clinical integration. Here we develop a deep learning model that classifies gastric biopsies into 29 pathological categories spanning malignancy subtypes, dysplasia, metaplasia, Helicobacter pylori , and benign findings. The model leverages a vision foundation model pre-trained on 70,618 whole slide images and fine-tuned end-to-end on 10,462 gastric biopsies without pixel-level annotations. On internal validation ( n = 2,957), the model achieves an area under the curve of 0.9945 for malignancy detection. We evaluate two paradigms for clinical integration: a post-read alert system and a concurrent assistance system. In retrospective simulation across four independent hospital cohorts ( n = 4,679), the post-read system identifies 17 malignancies that were missed or miscoded in routine diagnostic records. In a prospective reader study with six pathologists, concurrent AI assistance significantly improves sensitivity for malignancy (92.2% to 94.8%, P = .034) and metaplasia (94.2% to 97.4%, P = .013). Furthermore, the foundation model fine-tuned on only 400 slides outperforms a conventional model trained on over 10,000 slides, demonstrating extreme data efficiency. In addition, the model produces pixel-resolution lesion localization across all 29 categories without any pixel-level annotations, providing the heatmaps used in the concurrent assistance system. These results establish a framework for dual-mode AI deployment in gastric biopsy pathology—concurrent assistance for real-time diagnostic support and post-read alerts for retrospective quality assurance.