Abstract Purpose To use artificial intelligence to establish an automatic diagnosis system for corneal endothelium diseases (CEDs). Methods We develop an automatic system for detecting multiple common CEDs involving an enhanced compact convolutional transformer (ECCT). Specifically, we introduce a cross-head relative position encoding scheme into a standard self-attention module to capture contextual information among different regions and employ a token-attention feed-forward network to place greater focus on valuable abnormal regions. Results A total of 2723 images from CED patients are used to train our system. It achieves an accuracy of 89.53%, and the area under the receiver operating characteristic curve (AUC) is 0.958 (95% CI 0.943–0.971) on images from multiple centres. Conclusions Our system is the first artificial intelligence-based system for diagnosing CEDs worldwide. Images can be uploaded to a specified website, and automatic diagnoses can be obtained; this system can be particularly helpful under pandemic conditions, such as those seen during the recent COVID-19 pandemic.

PurposeThe goal was to develop a fully automated grading system for the evaluation of punctate epithelial erosions (PEEs) using deep neural networks.MethodsA fully automated system was developed to detect corneal position and grade staining severity given a corneal fluorescein staining image. The fully automated pipeline consists of the following three steps: a corneal segmentation model extracts corneal area; five image patches are cropped from the staining image based on the five subregions of extracted cornea; a staining grading model predicts a score for each image patch from 0 to 3, and automated grading score for the whole cornea is obtained from 0 to 15. Finally, the clinical grading scores annotated by three ophthalmologists were compared with automated grading scores.ResultsFor corneal segmentation, the segmentation model achieved an intersection over union of 0.937. For punctate staining grading, the grading model achieved a classification accuracy of 76.5% and an area under the receiver operating characteristic curve of 0.940 (95% CI 0.932 to 0.949). For the fully automated pipeline, Pearson’s correlation coefficient between the clinical and automated grading scores was 0.908 (p<0.01). Bland-Altman analysis revealed 95% limits of agreement between the clinical and automated grading scores of between −4.125 and 3.720 (concordance correlation coefficient=0.904). The average time required for processing a single stained image during pipeline was 0.58 s.ConclusionA fully automated grading system was developed to evaluate PEEs. The grading results may serve as a reference for ophthalmologists in clinical trials and residency training procedures.

Background The goal of this study is to develop a fully automated segmentation and morphometric parameter estimation system for assessing abnormal corneal endothelial cells (CECs) from LASER in vivo confocal microscopy (IVCM) images. Methods First, we developed a fully automated deep learning system for assessing abnormal CECs using a previous development set composed of normal images and a newly constructed development set composed of abnormal images. Second, two testing sets, one with 169 normal images and the other with 211 abnormal images, were used to evaluate the clinical validity and effectiveness of the proposed system on LASER IVCM images with different corneal endothelial conditions, particularly on abnormal images. Third, the automatically calculated endothelial cell density (ECD) and the manually calculated ECD were compared using both the previous and proposed systems. Results The automated morphometric parameter estimations of the average number of cells, ECD, coefficient of variation in cell area and percentage of hexagonal cells were 257 cells, 2648 ± 511 cells/mm 2 , 32.18 ± 6.70% and 56.23 ± 8.69% for the normal CEC testing set and 83 cells, 1450 ± 656 cells/mm 2 , 34.87 ± 10.53% and 42.55 ± 20.64% for the abnormal CEC testing set. Furthermore, for the abnormal CEC testing set, Pearson’s correlation coefficient between the automatically and manually calculated ECDs was 0.9447; the 95% limits of agreement between the manually and automatically calculated ECDs were between 329.0 and − 579.5 (concordance correlation coefficient = 0.93). Conclusions This is the first report to count and analyze the morphology of abnormal CECs in LASER IVCM images using deep learning. Deep learning produces highly objective evaluation indicators for LASER IVCM corneal endothelium images and greatly expands the range of applications for LASER IVCM.

Compressed image super-resolution (SR) task is useful in practical scenarios, such as mobile communication and the internet, where images are usually downsampled and compressed due to limited bandwidth and storage capacity. However, a combination of compression and downsampling degradations makes the SR problem more challenging. To restore high-quality and high-resolution images, local context and long-range dependency modeling are both crucial. In this paper, for JPEG compressed image SR, we propose a consecutively-interactive dual-branch network (CIDBNet) to take advantage of both convolution and transformer operations, which are good at extracting local features and global interactions, respectively. To better aggregate the two-branch information, we newly introduce an adaptive cross-branch fusion module (ACFM), which adopts a cross-attention scheme to enhance the two-branch features and then fuses them weighted by a content-adaptive map. Experiments show the effectiveness of CIDBNet, and in particular, CIDBNet achieves higher performance than a larger variant of HAT (HAT-L).

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track~2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.

Manga character recognition is a key technology for manga character retrieval and verification. This task is very challenging since the manga character images have a long-tailed distribution and large quality variations. Training models with cross-entropy softmax loss on such imbalanced data would introduce biases to feature and class weight norms. To handle this problem, we propose a novel dual loss which is the sum of two losses: dual ring loss and dual adaptive re-weighting loss. Dual ring loss combines weight and feature soft normalization and serves as a regularization term to softmax loss. Dual adaptive re-weighting loss re-weights softmax loss according to the norm of both feature and class weight. With the proposed losses, we have achieved encouraging results on the Manga109 benchmark. Specifically, compared with the baseline softmax loss, our method improves the character retrieval mAP from 35.72% to 38.88% and the character verification accuracy from 87.00% to 88.50%.

Tyrosine Kinase Inhibitor (TKI) of Epidermal Growth Factor Receptor (EGFR) is a first-line therapy for non-small cell carcinoma lung cancer patients with EGFR mutations, but patients often develop resistance to such a target therapy. Recently several PD-1 and PD-L1 inhibitors were approved for treating NSCLC, however, it remains unclear whether EGFR mutant NSCLC would benefit from PD-1/PD-L1 treatment. PD-1 response in cancer patients is closely associated with oncogenic mutation status, tumor microenvironment, PD-L1 expression and tumor mutation burden (TMB); however, the lack of pre-clinical models limited the investigation of the checkpoint inhibitors in EGFR mutant tumors. Here we use human PBMC reconstitution system for immune-humanization, and established a series of IO-Xenograft models (IO-CDX and IO-PDX) with cancer cell lines (IO-CDX) or patient-derived tissues (IO-PDX) that contain various EGFR mutations, including EGFR 19 del, L858R, T790M, and EGFR over-expression, amplification and fusion. We treated these models with either EGFR TKI (erlotinib, afatinib or osimertinib) or nivolumab, a PD-1 inhibitor. The predictive biomarkers including PD-L1 expression and TMB were analyzed by whole exom sequencing (WES) and FACS for tumor infiltrating lymphocytes (TILs), respectively. We found that 3 TKI-resistant PDX models bearing EGFR T790M mutation exhibited lower TILs than those bearing EGFR wild type or exon 19del mutation. Of the 8 IO-CDX or IO-PDX humanized models we have examined, those exhibiting higher TILs achieved better responses to nivolumab treatment. The 3 most sensitive models are EGFR amplification (wt), EGFR over-expression (wt) and EGFR exon 19del. In contrast, the EGFR T790M model from H1975 cell line was observed with hyper-progressive disease after nivolumab treatment. We will also discuss the contribution of PD-L1 expression and TMB to nivolumab in other models. In summary, these well-established IO-CDX and IO-PDX models can provide a human-resembling immune system for of immune therapeutics and combination with targeted therapies, and help to facilitate the understanding of relationship among tumor microenvironment, driver oncogenic mutations and drug response. Citation Format: Xuzhen Tang, Li Yang, Hui Qi, Xianzhi Zhai, Fuyang Wang, Xiangnan Qiang, Jie Xu, Xiaoran Qin, Qingyang Gu, Shaoyu Yan, Qunsheng Ji. Evaluation of immune checkpoint inhibitor efficacy in EGFR mutant tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 1055.

Scene text recognition is very challenging due to the complex background, low resolution, perspective distortion and curved placement, etc. Most of the state-of-the-art methods adopt the attention-based encoder-decoder framework, and usually get suboptimal recognition performance for challenging text images due to the misalignment between attention region and target character region. In this paper, a novel module, named Gated Cascade Attention Module (GCAM), is proposed to increase the alignment precision of attention in a cascade way. Moreover, a channel and spatial attention module is introduced into the encoder to extract more discriminative features for text recognition. By assembling these two modules, a novel scene text recognizer is developed, and extensive experiments demonstrate it can achieve state-of-the-art results on multiple benchmarks of regular and irregular text images.

The recognition of manga (Japanese comics) characters is an essential step in industrial applications, such as manga character retrieval, content analysis and copyright protection. However, conventional methods for manga character recognition are mainly based on handcrafted features which are not robust enough for manga of various style. The emergence of deep learning based methods provides representational features, which has a huge demand for labeled data. In this paper, we propose a framework to exploit unlabeled manga data to facilitate the discriminative capability of deep feature representations for manga character recognition (i.e., unsupervised learning on manga images), which does not rely on any manual annotation. Specifically, we first train an initial feature model using an anime character dataset. Then, we adopt a Progressive Main Characters Mining (PMCM) strategy which iterates between two steps: 1) produce selected data with estimated labels from unlabeled data, 2) update the feature model by the selected data. These two steps are mutually promoted in essence. Experimental results on Manga109 dataset, to which we introduce new head annotations, demonstrate the effectiveness of the proposed framework and the usefulness in manga character verification and retrieval.

Geometric objects in educational materials are often illustrated as 2D line drawings, which results in the loss of depth information. To alleviate the problem of fully understanding the 3D structure of geometric objects, we propose a novel method to reconstruct the 3D shape of a geometric object illustrated in a line drawing image. In contrast to most existing methods, ours directly take a single line drawing image as input and generate a valid sketch for reconstruction. Given a single input line drawing image, we first classify the geometric object in the image with convolution neural network (CNN). More specifically, we pre-train the model with simulated images to alleviate the problems of data collection and unbalanced distribution among different classes. Then, we generate the sketch of the geometric object with our proposed bottom-up and top-down scheme. Finally, we finish reconstruction by minimizing an objective function of reconstruction error. Extensive experimental results demonstrate that our method performs significantly better in both accuracy and efficiency compared with the existing methods.

Face detection of comic characters is a necessary step in most applications, such as comic character retrieval, automatic character classification and comic analysis. However, the existing methods were developed for simple cartoon images or small size comic datasets, and detection performance remains to be improved. In this paper, we propose a Faster R-CNN based method for face detection of comic characters. Our contribution is twofold. First, for the binary classification task of face detection, we empirically find that the sigmoid classifier shows a slightly better performance than the softmax classifier. Second, we build two comic datasets, JC2463 and AEC912, consisting of 3375 comic pages in total for characters face detection evaluation. Experimental results have demonstrated that the proposed method not only performs better than existing methods, but also works for comic images with different drawing styles.

Hepatocellular carcinoma (HCC) is a common cancer with poor prognosis worldwide and the molecular mechanism is not well understood. This study aimed to establish a collection of human HCC cell lines from patient-derived xenograft (PDX) models. From the 20 surgical HCC sample collections, 7 tumors were successfully developed in immunodeficient mice and further established 7 novel HCC cell lines (LIXC002, LIXC003, LIXC004, LIXC006, LIXC011, LIXC012 and CPL0903) by primary culture. The characterization of cell lines was defined by morphology, growth kinetics, cell cycle, chromosome analysis, short tandem repeat (STR) analysis, molecular profile, and tumorigenicity. Additionally, response to clinical chemotherapeutics was validated both in vitro and in vivo. STR analysis indicated that all cell lines were unique cells different from known cell lines and free of contamination by bacteria or mycoplasma. The other findings were quite heterogeneous between individual lines. Chromosome aberration could be found in all cell lines. Alpha-fetoprotein was overexpressed only in 3 out of 7 cell lines. 4 cell lines expressed high level of vimentin. Ki67 was strongly stained in all cell lines. mRNA level of retinoic acid induced protein 3 (RAI3) was decreased in all cell lines. The 7 novel cell lines showed variable sensitivity to 8 tested compounds. LIXC011 and CPL0903 possessed multiple drug resistance property. Sorafenib inhibited xenograft tumor growth of LIXC006, but not of LIXC012. Our results indicated that the 7 novel cell lines with low passage maintaining their clinical and pathological characters could be good tools for further exploring the molecular mechanism of HCC and anti-cancer drug screening.

目的 将临床胃癌组织皮下移植于免疫缺陷小鼠,以建立人源性胃癌移植瘤模型,并对建成模型进行初步评价.方法 将98例手术切除的胃癌组织分别皮下移植于SCID小鼠体内,待移植瘤体积长至500～1 000 mm3时,取出肿瘤传代至BALB/c-nu/nu裸小鼠体内,同时进行速冻,石蜡包埋,冻存等样本组织库保藏.对石蜡包埋的组织进行HE染色,观察其病理特征;选取12例生长良好的模型用5-氟尿嘧啶和顺铂进行药效学实验;选取3例模型进行体外药物敏感性实验.结果 25例胃癌模型移植成功并能够稳定传代,成功率为25.52％.各代移植瘤组织形态学特征与患者肿瘤组织一致.体内药效学结果表明,5-氟尿嘧啶(25 mg/kg)对2例模型有一定的抑制作用(TGI＞60％),对10例模型无明显的抑制作用.顺铂(5 mg/kg)对3例模型有明显的抑制作用(TGI＞100％),对4例模型有一定的抑制作用(TGI,60％～90％),对5例模型无明显抑制作用(TGI＜60％).体外药物敏感性实验表明对5-氟尿嘧啶敏感程度依次为GAX001 (IC50:3.187 μm)＞GAX007(IC50:6.886 μmol)＞GAX027(IC50:8.323 μmol),对顺铂敏感程度依次为GAX027(IC50:2.753 μmol)＞GAX001(IC50:3.211 μmol)＞ GAX007(IC50:8.137 μmol).结论 成功建立了25例人源性胃癌小鼠移植瘤模型,移植瘤保留了临床胃癌的病理特征,对其中12例进行的药效学评价表明对相同的化疗药物敏感性不同,能够反映患者的遗传多样性,可用于抗肿瘤药物的筛选和研究.

Multiple drug resistance (MDR) occurring during chemotherapy is a major obstacle for treatment of cancers using chemotherapeutic drugs; thus, the mechanisms underlying MDR have attracted intensive attention. Many studies have shown that tumor-initiating cells exhibit a chemotherapeutic tolerance characteristic. However, whether the MDR cells possess tumor-initiating cells properties and its underlying mechanisms remain to be fully elucidated. In this study, we utilized a well-established MDR cell line K562/A02 enriched by doxorubicin from K562 cells to determine if the K562/A02 cells possess tumor-initiating properties and investigated its potential molecular mechanisms. We observed that the expressions of Oct4, Sox2, and Nanog, all of which are well-characterized stem cell markers, in K562/A02 cells were elevated in comparison to parental K562 cells; in addition, we found that K562/A02 cells exhibited more potent in vitro and in vivo tumor-initiating properties, as revealed by sphere assay, self-renewal assay, soft agar assay, and animal studies. Furthermore, our data suggest that snail and twist1, two well known transcriptional factors for the epithelial-mesenchymal transition (EMT) program, may be potentially involved in the acquisition of tumor-initiating properties of K562/A02 cells. Thus, our study demonstrates that MDR K562/A02 cells possess tumor-initiating properties, most likely due to the elevated expressions of snail and twist1.

Abstract Rodent tumor models with histological and molecular resemblance of human tumors and improved predictive value for clinical drug response are highly desired for oncology drug discovery and development. Patient-derived xenograft (PDX) tumor models are believed to better preserve features of human malignancy than cancer cell line-derived xenograft models. We have established more than 170 PDX models from Asian-prevalent human tumors in SCID or nude mice. Here we report molecular and pharmacological profiling of a panel of pancreatic adenocarcinoma (PAC) and hepatocellular carcinoma (HCC) models. Among 13 PAC models, Sequenom analysis showed KRAS mutation in all models, p53 mutation in 3, p16/CDKN2A deletion in 9 and SMAD4 deletion in 4 models. Comparison of transcriptomes by Affymetrix U133Plus2 between the original tumor and derived xenografts at different passages (P1-P6) in one PAC model revealed a high degree of similarity (R2 =0.92-0.97). Also, the gene mutational status and histological characters remained unchanged across the parental tumor and different passages of the PDX model. Evaluation of response to Gemzar treatment (60 mpk, Q4D x 3) showed significant tumor regression in 6 PAC models and partial tumor growth inhibition in 4 PAC models. Notably, the regression cohort and the partial response cohort displayed differential gene expression patterns. In addition, primary tumor cells derived from PAC models via tissue digestion were tested in vitro with Gemzar. The in vitro sensitivity to Gemzar of derived cells correlated with in vivo response of the parental PAC models. Gene expression analysis in 11 HCC models found aberrant gene expression involving several signaling pathways such as WNT, EGF/IGF and TGF-β, which recapitulate the alteration of these pathways in human HCC. These HCC PDX models exhibited major features of three HCC subclasses defined by the study in human HCC: S1 with activation of WNT and TGF-β pathways, S2 with enriched AKT and MYC activation and S3 with β-catenin activation. The response of these models to Sorafenib was also examined and varying degrees of sensitivity to Sorafenib were observed. Together, we have successfully generated PDX tumor models that preserve the histological and biological properties of the original human tumor and represent a heterogeneous patient population with varying degree of response to current stand of care. These models are a relevant and powerful tool for evaluation of anticancer therapeutics. Whole genome sequencing and gene expression profiling by RNAseq on PDX models are being preformed. Citation Format: Xiaoran Qin, Zhonghua Tang, Gang Hu, Kedong Ouyang, Ke Wang, Fu Li, Fubo Xie, Qiuming Pan, Min Shi, Gang Zhao, Yixin Zhang, Chunchao Zhu, Danyi Wen, Weikang Tao. Establishment and molecular characterization of a panel of Asian patient-derived tumor xenograft models . [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 2779. doi:10.1158/1538-7445.AM2013-2779

We evaluated the influence of DNA aneuploidy on chemotherapy-resistance in human Gastric cancer cell MKN45; we also evaluated the reversal effects of HZ08 on these cells and then preliminary investigated the possible involved pathway. We made use of a pair of human Gastric cancer cell dip-MKN45 (diploid MKN45) and aneu-MKN45 (aneuploid MKN45). Growth inhibition in response to chemotherapeutic drugs was evaluated by CellTiter-Glo Luminescent Cell Viability assay and clone formation assay. Flow cytometry and immuno-assay were applied to evaluate apoptosis and the expression of relative signaling molecules. MKN45 xenograft was generated to evaluate in vivo action. Aneu-MKN45 developed a resistance to cisplatin which could be reversed by HZ08; Flow cytometry and western-blot indicates that HZ08-combination could induce apoptosis and increase the expression of apoptosis-related biomarkers on aneu-MKN45; in vivo study also reflect the same correlation between aneuploidy and cisplatin-resistance, which could be antagonized by HZ08 combination; When investigating the involved pathway, in anue-MKN45, the expression of molecules in p53 pathway was decreased; HZ08 could increase the expression of p53 down-stream molecules as well as elevate the activity of p53, while inhibiting Mdm2, the major negative regulator of p53; p53 inhibitor Pifithrin-α could completely abrogate HZ08's synergism effects, and mimic cisplatin-resistance on dip-MKN45.Lower p53 pathway expression that attenuates cisplatin-induced apoptosis might be at least partly the reason of cisplatin-resistance occurred in aneuploid MKN45 both in vitro and in vivo; Combination of HZ08 could sensitize cisplatin-induced apoptosis through the activation of the p53 pathway, therefore represented a synergism effect on aneuploid MKN45 cells.

AIM:To investigate the value of interleukin-8 (IL-8), a pro-inflammatory chemokine, in predicting the prognosis of pancreatic cancer. METHODS: Expression of IL-8 and its receptor CXCR1was assessed by immunohistochemistry in pancreatic cancer and chronic pancreatitis samples.Enzyme-linked immunosorbent assay was used to detect the serum IL-8 levels in pancreatic cancer patients.Human pancreatic cancer tissues were heterotopically transplanted to the immune-deficiency mice to evaluate the effect of serum IL-8 on the tumorigenesis of the cancer samples.RESULTS: IL-8 and CXCR1 proteins were both overexpressed in pancreatic adenocarcinoma samples (55.6% and 65.4%, respectively) compared with the matched para-cancer tissues (25.9% and 12.3%, P < 0.01), or chronic pancreatitis (0% and 25%, P < 0.05).Serum IL-8 levels in pancreatic cancer patients (271.1 ± 187.7 ng/mL) were higher than in other digestive system tumors, such as gastric cancer (41.77 ± 9.11 ng/mL, P = 0.025), colorectal carcinoma (78.72 ± 80.60 ng/mL, P = 0.032) and hepatocellular carcinoma (59.60 ± 19.80 ng/mL, P = 0.016).In vivo tumorigenesis analysis further proved that tumor tissues from patients with higher serum IL-8 levels grew faster than those with lower IL-8 levels.CONCLUSION: IL-8 can be a fine serum marker for predicting the prognosis pancreatic cancer.