scholarly journals Evaluation of Computer-Aided Nodule Assessment and Risk Yield (CANARY) in Korean patients for prediction of invasiveness of ground-glass opacity nodule

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253204
Author(s):  
Juyoung Lee ◽  
Brian Bartholmai ◽  
Tobias Peikert ◽  
Jaehee Chun ◽  
Hojin Kim ◽  
...  

Differentiating the invasiveness of ground-glass nodules (GGN) is clinically important, and several institutions have attempted to develop their own solutions by using computed tomography images. The purpose of this study is to evaluate Computer-Aided Analysis of Risk Yield (CANARY), a validated virtual biopsy and risk-stratification machine-learning tool for lung adenocarcinomas, in a Korean patient population. To this end, a total of 380 GGNs from 360 patients who underwent pulmonary resection in a single institution were reviewed. Based on the Score Indicative of Lung Cancer Aggression (SILA), a quantitative indicator of CANARY analysis results, all of the GGNs were classified as “indolent” (atypical adenomatous hyperplasia, adenocarcinomas in situ, or minimally invasive adenocarcinoma) or “invasive” (invasive adenocarcinoma) and compared with the pathology reports. By considering the possibility of uneven class distribution, statistical analysis was performed on the 1) entire cohort and 2) randomly extracted six sets of class-balanced samples. For each trial, the optimal cutoff SILA was obtained from the receiver operating characteristic curve. The classification results were evaluated using several binary classification metrics. Of a total of 380 GGNs, the mean SILA for 65 (17.1%) indolent and 315 (82.9%) invasive lesions were 0.195±0.124 and 0.391±0.208 (p < 0.0001). The area under the curve (AUC) of each trial was 0.814 and 0.809, with an optimal threshold SILA of 0.229 for both. The macro F1-score and geometric mean were found to be 0.675 and 0.745 for the entire cohort, while both scored 0.741 in the class-equalized dataset. From these results, CANARY could be confirmed acceptable in classifying GGN for Korean patients after the cutoff SILA was calibrated. We found that adjusting the cutoff SILA is needed to use CANARY in other countries or races, and geometric mean could be more objective than F1-score or AUC in the binary classification of imbalanced data.

Lung Cancer ◽  
2008 ◽  
Vol 60 (2) ◽  
pp. 298-301 ◽  
Author(s):  
Hiroshi Soda ◽  
Yoichi Nakamura ◽  
Katsumi Nakatomi ◽  
Nanae Tomonaga ◽  
Hiroyuki Yamaguchi ◽  
...  

2018 ◽  
Vol 27 (1) ◽  
pp. 45-48
Author(s):  
Shinsuke Uchida ◽  
Koji Tsuta ◽  
Masahiko Kusumoto ◽  
Kouya Shiraishi ◽  
Takashi Kohno ◽  
...  

Pulmonary collision tumors have been described as a special entity of synchronous multiple lung cancer. There have been no reports detailing the chronological changes in primary collision lung cancers on chest computed tomography. We report a case of ground-glass lung nodules gradually colliding with each other. The collision tumors of the lung were composed of minimally invasive adenocarcinoma and adenocarcinoma in situ with epidermal growth factor mutations. Immunohistochemically, the Ki-67 labeling indices were different in the 2 components. Ki-67 staining was useful to distinguish the 2 components. The 2 dominant ground-glass tumors grew slowly with radiologic and pathologic heterogeneity.


2016 ◽  
Vol 8 (7) ◽  
pp. 1561-1570 ◽  
Author(s):  
Youngkyu Moon ◽  
Sook Whan Sung ◽  
Kyo Young Lee ◽  
Sung Bo Sim ◽  
Jae Kil Park

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 506
Author(s):  
Yu-Jin Seol ◽  
Young-Jae Kim ◽  
Yoon-Sang Kim ◽  
Young-Woo Cheon ◽  
Kwang-Gi Kim

This paper reported a study on the 3-dimensional deep-learning-based automatic diagnosis of nasal fractures. (1) Background: The nasal bone is the most protuberant feature of the face; therefore, it is highly vulnerable to facial trauma and its fractures are known as the most common facial fractures worldwide. In addition, its adhesion causes rapid deformation, so a clear diagnosis is needed early after fracture onset. (2) Methods: The collected computed tomography images were reconstructed to isotropic voxel data including the whole region of the nasal bone, which are represented in a fixed cubic volume. The configured 3-dimensional input data were then automatically classified by the deep learning of residual neural networks (3D-ResNet34 and ResNet50) with the spatial context information using a single network, whose performance was evaluated by 5-fold cross-validation. (3) Results: The classification of nasal fractures with simple 3D-ResNet34 and ResNet50 networks achieved areas under the receiver operating characteristic curve of 94.5% and 93.4% for binary classification, respectively, both indicating unprecedented high performance in the task. (4) Conclusions: In this paper, it is presented the possibility of automatic nasal bone fracture diagnosis using a 3-dimensional Resnet-based single classification network and it will improve the diagnostic environment with future research.


2020 ◽  
Author(s):  
Zhiqiang Li ◽  
Hongwei Zheng ◽  
Shanshan Liu ◽  
Xinhua Wang ◽  
Lei Xiao ◽  
...  

Abstract Background: To investigate whether thin-section computed tomography (TSCT) features may efficiently guide the invasiveness basedclassification of lung adenocarcinoma. Methods: Totally, 316 lung adenocarcinoma patients (from 2011-2015) were divided into three groups: 56 adenocarcinoma in situ (AIS), 98 minimally invasive adenocarcinoma (MIA), and 162 invasive adenocarcinoma (IAC) according their pathological results. Their TSCT features, including nodule pattern, shape, pleural invasion, solid proportion, border, margin, vascular convergence, air bronchograms, vacuole sign, pleural indentation, diameter, solid diameter, and CT values of ground-glass nodules (GGN) were analyzed. Pearson’s chi-square test, Fisher’s exact test and One-way ANOVA were adopted tocomparebetweengroups. Receiver operating characteristic (ROC) analysis wereperformedto assess its value for prediction and diagnosis. Results: Patients with IAC were significantly elder than those in AIS or MIA group,and more MIA patients had a smoking history than AIS and IAC. No recurrence happened in the AIS and MIA groups, while 4.3% recurrences were confirmed in the IAC group. As for TSCT variables, we found AIS group showed dominantly higher 91.07%PGGN pattern and 87.50% round/oval nodules than that in MIA and IAC group. In contrast, MIA group showed more cases with undefined border and vascular convergence than AIS and IAC group. Importantly, IAC group uniquely showed higher frequency of pleural invasion compared with MIA and AIS group. The majority of patients (82.1%) in IAC group showed ≥ 50% solid proportion. We found diameter and solid diameter of the lesions were notably larger in the IAC group compared with AIS and MIA groupin quantitative aspect. In addition, for MGGNs, the CT values of ground-glass opacity (GGO) and ground-glass opacity solid portion (GGO-solid) were both higher in the IAC group than AIS and MIA. Finally, we also observed that smooth margin took a dominant proportion in the AIS group while most cases in the IAC group had a lobulate margin. Patients in MIA and IAC group shared higher level of air bronchograms and vacuole signs than AIS group. Conclusions: The unique features in different groups identified by TSCT had diagnosis value for lung adenocarcinoma.


2017 ◽  
Vol 78 (3) ◽  
pp. 279-288 ◽  
Author(s):  
Sang-Kwon Lee ◽  
Seungjo Park ◽  
Byunggyu Cheon ◽  
Sohyeon Moon ◽  
Sunghwa Hong ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document