Diagnostic Assessment of Deep Learning Algorithms for Frozen Tissue Section Analysis in Women with Breast Cancer / Journal of the Korean Cancer Association, 대한암학회지

Purpose@#Assessing the metastasis status of the sentinel lymph nodes (SLNs) for hematoxylin and eosin–stained frozen tissue sections by pathologists is an essential but tedious and time-consuming task that contributes to accurate breast cancer staging. This study aimed to review a challenge competition (HeLP 2019) for the development of automated solutions for classifying the metastasis status of breast cancer patients. @*Materials and Methods@#A total of 524 digital slides were obtained from frozen SLN sections: 297 (56.7%) from Asan Medical Center (AMC) and 227 (43.4%) from Seoul National University Bundang Hospital (SNUBH), South Korea. The slides were divided into training, development, and validation sets, where the development set comprised slides from both institutions and training and validation set included slides from only AMC and SNUBH, respectively. The algorithms were assessed for area under the receiver operating characteristic curve (AUC) and measurement of the longest metastatic tumor diameter. The final total scores were calculated as the mean of the two metrics, and the three teams with AUC values greater than 0.500 were selected for review and analysis in this study. @*Results@#The top three teams showed AUC values of 0.891, 0.809, and 0.736 and major axis prediction scores of 0.525, 0.459, and 0.387 for the validation set. The major factor that lowered the diagnostic accuracy was micro-metastasis. @*Conclusion@#In this challenge competition, accurate deep learning algorithms were developed that can be helpful for making a diagnosis on intraoperative SLN biopsy. The clinical utility of this approach was evaluated by including an external validation set from SNUBH.

Accuracy of one-step automated orthodontic diagnosis model using a convolutional neural network and lateral cephalogram images with different qualities obtained from nationwide multi-hospitals / 대한치과교정학회지

Objective@#The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. @*Methods@#Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradientweighted class activation mapping (Grad-CAM). @*Results@#In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. @*Conclusions@#Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

An Open Medical Platform to Share Source Code and Various Pre-Trained Weights for Models to Use in Deep Learning Research

Deep learning-based applications have great potential to enhance the quality of medical services. The power of deep learning depends on open databases and innovation. Radiologists can act as important mediators between deep learning and medicine by simultaneously playing pioneering and gatekeeping roles. The application of deep learning technology in medicine is sometimes restricted by ethical or legal issues, including patient privacy and confidentiality, data ownership, and limitations in patient agreement. In this paper, we present an open platform, MI2RLNet, for sharing source code and various pre-trained weights for models to use in downstream tasks, including education, application, and transfer learning, to encourage deep learning research in radiology. In addition, we describe how to use this open platform in the GitHub environment. Our source code and models may contribute to further deep learning research in radiology, which may facilitate applications in medicine and healthcare, especially in medical imaging, in the near future. All code is available at https://github.com/mi2rl/MI2RLNet.

Challenge for Diagnostic Assessment of Deep Learning Algorithm for Metastases Classification in Sentinel Lymph Nodes on Frozen Tissue Section Digital Slides in Women with Breast Cancer / Journal of the Korean Cancer Association, 대한암학회지

Purpose@#Assessing the status of metastasis in sentinel lymph nodes (SLNs) by pathologists is an essential task for the accurate staging of breast cancer. However, histopathological evaluation of sentinel lymph nodes by a pathologist is not easy and is a tedious and time-consuming task. The purpose of this study is to review a challenge competition (HeLP 2018) to develop automated solutions for the classification of metastases in hematoxylin and eosin–stained frozen tissue sections of SLNs in breast cancer patients. @*Materials and Methods@#A total of 297 digital slides were obtained from frozen SLN sections, which include post–neoadjuvant cases (n = 144, 48.5%) in Asan Medical Center, South Korea. The slides were divided into training, development, and validation sets. All of the imaging datasets have been manually segmented by expert pathologists. A total of 10 participants were allowed to use the Kakao challenge platform for six weeks with two P40 GPUs. The algorithms were assessed in terms of the AUC (area under receiver operating characteristic curve). @*Results@#The top three teams showed 0.986, 0.985, and 0.945 AUCs for the development set and 0.805, 0.776, and 0.765 AUCs for the validation set. Micrometastatic tumors, neoadjuvant systemic therapy, invasive lobular carcinoma, and histologic grade 3 were associated with lower diagnostic accuracy. @*Conclusion@#In a challenge competition, accurate deep learning algorithms have been developed, which can be helpful in making frozen diagnosis of intraoperative sentinel lymph node biopsy. Whether this approach has clinical utility will require evaluation in a clinical setting

The usefulness of fluorodeoxyglucose-PET/CT for preoperative evaluation of ductal carcinoma in situ

PURPOSE: PET/CT is useful in preoperative evaluation of invasive breast cancer (IBC) to predict axillary metastasis and staging workup. The usefulness is unclear in cases of ductal carcinoma in situ (DCIS) diagnosed at biopsy before surgery, which sometimes is upgraded to IBC after definitive surgery. The aim of this study is to find out the usefulness of PET/CT on DCIS as a preoperative evaluation tool. METHODS: We investigated 102 patients preoperatively diagnosed with DCIS who subsequently underwent definitive surgery between 2010 and 2015. The uptake of 18F-fluorodeoxyglucose was graded by visual and semiquantitative methods. We analyzed the maximum standardized uptake value (SUVmax) of each patient with clinicopathologic variables. We determined optimal cutoff values for SUVmax by receiver operating characteristic curve analysis. RESULTS: Fifteen cases out of 102 cases (14.7%) were upgraded to IBC after surgery. The SUVmax was higher in patients upgraded to IBC (mean: 2.56 vs. 1.36) (P = 0.007). The SUVmax was significantly higher in patients who had symptoms, palpable masses, lesions over 2 cm in size and BI-RAD category 5. Both visual and semiquantitative analysis were significant predictors of IBC underestimation. SUVmax of 2.65 was the theoretical cutoff value in ROC curve analysis in predicting the underestimation of IBC. The underestimation rate was significantly higher in patients with SUVmax >2.65 (P < 0.001), over the moderate enhanced uptake on visual analysis (P < 0.001). CONCLUSION: PET/CT can be used as a complementary evaluation tool to predict the underestimation of DCIS combined with the lesion size, palpable mass, symptomatic lesion, and BI-RAD category.

KCHO-1, a novel herbal anti-inflammatory compound, attenuates oxidative stress in an animal model of amyotrophic lateral sclerosis

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease characterized by selective death of motor neurons in the central nervous system. The main cause of the disease remains elusive, but several mutations have been associated with the disease process. In particular, mutant superoxide dismutase 1 (SOD1) protein causes oxidative stress by activating glia cells and contributes to motor neuron degeneration. KCHO-1, a novel herbal combination compound, contains 30% ethanol and the extracts of nine herbs that have been commonly used in traditional medicine to prevent fatigue or inflammation. In this study, we investigated whether KCHO-1 administration could reduce oxidative stress in an ALS model. KCHO-1 administered to ALS model mice improved motor function and delayed disease onset. Furthermore, KCHO-1 administration reduced oxidative stress through gp91(phox) and the MAPK pathway in both classically activated microglia and the spinal cord of hSOD1(G93A) transgenic mice. The results suggest that KCHO-1 can function as an effective therapeutic agent for ALS by reducing oxidative stress.

Effects of High-Intensity-Focused Ultrasound Treatment on Benign Uterine Tumor

In this study, the effects of high-intensity-focused ultrasound (HIFU) treatment on benign uterine tumor patients were examined. A total of 333 patients diagnosed with fibroids or adenomyosis using diagnostic sonography, treated with HIFU between February 4, 2010 and December 29, 2014 at a hospital in Korea, and followed up for three or six months were selected for this study. Their benign uterine tumor volume was measured, and the effects of HIFU treatment on the volume were analyzed according to age, disease, fertility, and treatment duration. The volume of benign tumors of the uterus changed by age in all age groups after conducting HIFU treatment for 3 and 6 months, respectively. The rate of decrease in individuals' in their twenties was the largest, at 64.9%. When the decreasing volume of benign tumors of the uterus was analyzed by type of disease, the treatment efficacy for adenomyosis was the best, with a decrease of 164.83 cm3 after 6 months. Myoma had the fastest decreasing rate, at 68.5%. When evaluated on the basis of fertility, the volume of benign tumors of the uterus continued to decrease until 6 months after completing all procedures. The volume has continued to decrease for 6 months after all procedures. This study showed that HIFU treatments for uterine fibroid and adenomyosis is an effective non-invasive therapy via reducing the benign uterine tumor volume. Therefore, the HIFU method might replace other conventional treatment methods.

Effects of High-Intensity-Focused Ultrasound Treatment on Benign Uterine Tumor

In this study, the effects of high-intensity-focused ultrasound (HIFU) treatment on benign uterine tumor patients were examined. A total of 333 patients diagnosed with fibroids or adenomyosis using diagnostic sonography, treated with HIFU between February 4, 2010 and December 29, 2014 at a hospital in Korea, and followed up for three or six months were selected for this study. Their benign uterine tumor volume was measured, and the effects of HIFU treatment on the volume were analyzed according to age, disease, fertility, and treatment duration. The volume of benign tumors of the uterus changed by age in all age groups after conducting HIFU treatment for 3 and 6 months, respectively. The rate of decrease in individuals' in their twenties was the largest, at 64.9%. When the decreasing volume of benign tumors of the uterus was analyzed by type of disease, the treatment efficacy for adenomyosis was the best, with a decrease of 164.83 cm3 after 6 months. Myoma had the fastest decreasing rate, at 68.5%. When evaluated on the basis of fertility, the volume of benign tumors of the uterus continued to decrease until 6 months after completing all procedures. The volume has continued to decrease for 6 months after all procedures. This study showed that HIFU treatments for uterine fibroid and adenomyosis is an effective non-invasive therapy via reducing the benign uterine tumor volume. Therefore, the HIFU method might replace other conventional treatment methods.