• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제15권9호
• /
• pp.700-704
• /
• 2009

본 논문은 영상보정 및 다단계 정합을 통한 전립선의 MR 영상과 병리 영상 간의 융합방법을 제안한다. 제안 방법은 영상보정, 강체 정합, 비강체 정합, 영상융합의 네 단계로 이루어진다. 첫째, 영상보정 단계에서 T2 MR 강조 영상의 출혈 부위의 자기값을 T1 MR 강조 영상의 자기값으로 대체시키고, 2, 4장으로 분리된 병리 영상을 한장의 영상으로 만든 후 MR 영상과 동일한 해상도로 줄인다. 둘째, 전립선의 T2 MR 강조 영상과 병리 영상 간에 자기간의 상호정보를 최적화하는 강체변환을 구한다. 셋째, TPS 와핑을 이용하여 병리 영상의 전립선 부위가 T2 MR 강조 영상의 전립선 부위에 정합되는 비강체변환을 구한다. 넷째, MR 영상과 변환을 적용시킨 병리 영상을 융합한다. 실험 결과 영상보정 및 다단계 정합 후의 전립선의 T2 MR 강조 영상과 병리 영상의 간의 평균 거리 오차는 0.8815 mm였고, 두 영상의 융합을 통해 T2 MR 강조 영상에서 전립선 암의 위치를 정확하게 볼 수 있었다.

• Applied Microscopy
• /
• 제51권
• /
• pp.6.1-6.9
• /
• 2021

Histopathology is a well-established standard diagnosis employed for the majority of malignancies, including breast cancer. Nevertheless, despite training and standardization, it is considered operator-dependent and errors are still a concern. Fractal dimension analysis is a computational image processing technique that allows assessing the degree of complexity in patterns. We aimed here at providing a robust and easily attainable method for introducing computer-assisted techniques to histopathology laboratories. Slides from two databases were used: A) Breast Cancer Histopathological; and B) Grand Challenge on Breast Cancer Histology. Set A contained 2480 images from 24 patients with benign alterations, and 5429 images from 58 patients with breast cancer. Set B comprised 100 images of each type: normal tissue, benign alterations, in situ carcinoma, and invasive carcinoma. All images were analyzed with the FracLac algorithm in the ImageJ computational environment to yield the box count fractal dimension (Db) results. Images on set A on 40x magnification were statistically different (p = 0.0003), whereas images on 400x did not present differences in their means. On set B, the mean Db values presented promising statistical differences when comparing. Normal and/or benign images to in situ and/or invasive carcinoma (all p < 0.0001). Interestingly, there was no difference when comparing normal tissue to benign alterations. These data corroborate with previous work in which fractal analysis allowed differentiating malignancies. Computer-aided diagnosis algorithms may beneficiate from using Db data; specific Db cut-off values may yield ~ 99% specificity in diagnosing breast cancer. Furthermore, the fact that it allows assessing tissue complexity, this tool may be used to understand the progression of the histological alterations in cancer.

• 한국멀티미디어학회논문지
• /
• 제24권8호
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• 한국컴퓨터그래픽스학회논문지
• /
• 제29권3호
• /
• pp.127-135
• /
• 2023

조직병리에서 전체 슬라이드 영상의 정확한 분할은 질병 진단과 치료 계획에 매우 중요한 작업이다. 그러나 전체 슬라이드 영상은 크기가 크고 조직의 형태, 염색 및 촬영 조건이 다양하기 때문에 기존의 자동 영상 분할 알고리즘을 항상 적용하는 것은 어렵다. 최근 인간의 전문 지식과 알고리즘을 결합한 대화형 영상 분할 기술의 발전은 전체 슬라이드 영상 분할의 효율 성과 정확성을 개선할 수 있는 가능성을 보여주었다. 그러나 이러한 접근 방식은 동시에 어려운 과제를 제기하기도 했다. 본 논문에서는 다중 해상도 전체 슬라이드 영상을 활용하는 새로운 대화형 분할 방법인 ZoomISEG를 제안한다. 기존의 단일 스케일 방법과의 비교 및 ablation study를 통해 제안된 방법의 효율성과 성능을 입증한다. 실험 결과, 제안된 방법은 사람의 개입을 줄이면서도 최고 해상도 데이터를 사용하는 방식에 필적하는 정확도를 달성함을 확인했다.

• Investigative Magnetic Resonance Imaging
• /
• 제22권3호
• /
• pp.194-199
• /
• 2018

We present image findings, especially rare MRI of a primary breast angiosarcoma with its histopathology, and also analyze the relevant medical literature reports in terms of the MRI findings. As our patient had unique features of a primary breast angiosarcoma, this case could be very helpful for future diagnosis of this rare breast malignancy by MRI.

• Investigative Magnetic Resonance Imaging
• /
• 제20권2호
• /
• pp.136-139
• /
• 2016

Clear cell sarcoma is rare and difficult to diagnose. Herein, we present a case of clear cell sarcoma in the dorsum of the wrist with MRI findings, including diffusion-weighted imaging, and histopathologic correlation, which was initially diagnosed as giant cell tumor of tendon sheath.

• 한국멀티미디어학회논문지
• /
• 제23권4호
• /
• pp.539-548
• /
• 2020

Deep learning technology is currently being used and applied in many different fields. Convolution neural network (CNN) is a method of artificial neural networks in deep learning, which is commonly used for analyzing different types of images through classification. In the conventional classification of histopathology images of prostate carcinomas, the rating of cancer is classified by human subjective observation. However, this approach has produced to some misdiagnosing of cancer grading. To solve this problem, CNN based classification method is proposed in this paper, to train the histological images and classify the prostate cancer grading into two classes of the benign and malignant. The CNN architecture used in this paper is based on the VGG models, which is specialized for image classification. However, color normalization was performed based on the contrast enhancement technique, and the normalized images were used for CNN training, to compare the classification results of both original and normalized images. In all cases, accuracy was over 90%, accuracy of the original was 96%, accuracy of other cases was higher, and loss was the lowest with 9%.

• 동의생리병리학회지
• /
• 제21권4호
• /
• pp.898-906
• /
• 2007

This study was to evaluate the effects of oral administration of Processed Sulphur on Hepatotoxicity. Processed Sulphur was administered orally to rats for 28 days. We measured the body and liver weight index, heamtological and biomedical parameters. We also observed the histopathological changes of liver in rats. No significant differences in body weight, liver weight index, heamtological and biomedical parameters and histopathological changes of hepatocyte between control and Processed Sulphur fed group were found. Our data indicate that hepatotoxicity was not caused by oral medication of Processed Sulphur up to 60mg/200g/day for 28 days in rats. Therefore, Processed Sulphur appears to be safe and non-toxic in these studies and a no-observed adverse effect level (NOAEL) in rats is established at 60mg/200g/day. The data could provide satisfactory preclinical evidence of safety to launch clinical trial on standardized formulation of mineral extracts.

• 대한의용생체공학회:의공학회지
• /
• 제31권3호
• /
• pp.234-239
• /
• 2010

We have developed and reported several micro-spikes for minimally invasive biopsy. This paper presents a diagnosis protocol for micro-spike biopsy using paraffin-based tissue collecting tool. Using the proposed tissue collecting tool, which has a negative micro-spike structure in a porous chamber, the biopsied tissue in a micro-spike is effectively detached. The proposed diagnosis protocol prevents the loss of tissues in a paraffin embedding and sectioning process. Hence, it is compatible with conventional histopathology without additional reagents and processes. The gastro-intestinal tissue of a pig is biopsied in an in vivo environment, and then it is detached from a micro-spike using the paraffin-based tissue collecting tool. A histopathological photomicrograph of the detached tissue is acquired with the proposed diagnosis protocol. The acquired image offers clinical quality. This result shows that the paraffin-based tissue collecting tool is applicable to the medical practice.

• 한국임상수의학회지
• /
• 제22권4호
• /
• pp.431-434
• /
• 2005

A 2-year-old castrated male, Cocker spaniel dog with a history of chronic productive cough for 2 to 3 months and with unsuccessful treatment was referred to Veterinary Medical Teaching Hospital, Seoul National University. On thoracic radiographs, there were alveolar infiltrations at left cranial and right caudal lung fields, and soft-tissue opacity round to oval images at overall lung field. The bronchi were dilated, tortuous and not tapered. Abnormal air was accumulated focally in the caudodorsal lung fields. To scrutinize the soft-tissue opacity image and accumulated air, computed tomography (CT) was done. On CT images, severe cylindrical or tubular bronchiectasis was confirmed. And the soft-tissue opacity images were found in the dilated bilated and thought to complexes of mucous plugs, inflammatory cells, necrotic and fibrotic tissue. The dog was dead next day to the CT scan, so necropsy and histopathologic examination were perfermed. On the histopathology, there were cylindrical bronhiectasis and severe diffuse chronic fibrinous necropurulent bronchitis and bronchopneumonia. In this case, it was difficult to diagnose the bronchiectasis only with radiography due to the concurrent lesions, such as pulmonary infiltrations and mucous plugs, which was identified by computed tomography. Thus, computed tomography is considered as a useful modality to confirm tile bronchiectasis camouflaged by the concurrent lesion.