Adversarial convolutional network for esophageal tissue segmentation on OCT images

Gan, Meng; Zhang, Miao; Li, Deyin

doi:10.1364/boe.394715

Cited by 16 publications

(11 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Convolutional neural networks (CNN) has been widely used for classification of medical images 46 , 47 and have been applied for OCT images in macular, retina and esophageal related research for automatic tissue segmentation 48 – 50 . To help improve the efficiency of tissue recognition, herein we proposed to use CNN to classify and recognize different epidural tissue types automatically.…”

Section: Introductionmentioning

confidence: 99%

Epidural anesthesia needle guidance by forward-view endoscopic optical coherence tomography and deep learning

Wang

Calle

Reynolds

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Epidural anesthesia requires injection of anesthetic into the epidural space in the spine. Accurate placement of the epidural needle is a major challenge. To address this, we developed a forward-view endoscopic optical coherence tomography (OCT) system for real-time imaging of the tissue in front of the needle tip during the puncture. We tested this OCT system in porcine backbones and developed a set of deep learning models to automatically process the imaging data for needle localization. A series of binary classification models were developed to recognize the five layers of the backbone, including fat, interspinous ligament, ligamentum flavum, epidural space, and spinal cord. The classification models provided an average classification accuracy of 96.65%. During puncture, it is important to maintain a safe distance between the needle tip and the dura mater. Regression models were developed to estimate that distance based on the OCT imaging data. Based on the Inception architecture, our models achieved a mean absolute percentage error of 3.05% ± 0.55%. Overall, our results validated the technical feasibility of using this novel imaging strategy to automatically recognize different tissue structures and measure the distances ahead of the needle tip during the epidural needle placement.

show abstract

Section: Introductionmentioning

confidence: 99%

Epidural anesthesia needle guidance by forward-view endoscopic optical coherence tomography and deep learning

Wang

Calle

Reynolds

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…17 Wang et al designed a fully convolutional network to correct the topology error of the label mask based on adversarial learning. 19 They also proposed a tissue self-attention network and a wavelet-attention network for esophageal layer segmentation. 13,33 Yang et al designed a connectivity-based CE-Net to reduce topological errors by considering context information and successfully segmenting epithelium in human esophageal OCT images.…”

Section: Esophageal Oct Image Segmentation Using Deep Learningmentioning

confidence: 99%

“…18 Wang et al proposed an adversarial learned network to segment esophageal images from guinea pigs. 19 Yang et al designed a connectivitybased CE-Net to segment epithelium in human esophageal OCT images and achieved state-of-the-art performance. 12 Despite the inspiring segmentation performance, the deep networks often require a large number of annotated samples for training, while expert annotation is timeconsuming and expensive.…”

Section: Introductionmentioning

confidence: 99%

Few‐shot segmentation for esophageal OCT images based on self‐supervised vision transformer

Wang,

Gan

2023

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

Automatic segmentation of layered tissue is the key to optical coherence tomography (OCT) image analysis for esophagus. While deep learning technology offers promising solutions to this problem, the requirement for large numbers of annotated samples often poses a significant obstacle, as it is both expensive and challenging to obtain. With this in mind, we introduced a self‐supervised segmentation framework for esophageal OCT images. In particular, the proposed method employs a masked autoencoder (MAE) for self‐supervised training and constructs the segmentation network by integrating a pretrained vision transformer (ViT) encoder with an attentive transformer decoder. In this case, the segmentation network has the potential to accomplish the few‐shot, or the more aggressive one‐shot segmentation, and achieve high‐quality segmentation performance. Experimental results on both a self‐collected mouse esophageal dataset and a public human esophageal OCT dataset confirm the advantages and practical significance of the proposed method.

show abstract

“…Concatenate digunakan untuk menggabungkan feature maps hasil proses konvolusi setiap blok pada jalur encoder dengan feature maps hasil proses upsampling pada jalur decoder menjadi satu buah matriks input baru dengan ukuran matriks yang baru [25].…”

Section: Concatenateunclassified

Arsitektur U-Net pada Segmentasi Citra Hati sebagai Deteksi Dini Kanker Liver

Naraloka

Kesuma

Sukmawati

et al. 2022

View full text Add to dashboard Cite

Hati adalah salah satu organ tubuh manusia yang bertanggung jawab untuk mencerna, meyerap, dan memproses makanan serta berfungsi untuk menyaring darah dari saluran pencernaan sebelum dibawa kebagian organ tubuh lainnya. Hati sangat rentan terhadap berbagai penyakit, salah satunya yaitu kanker liver. untuk itu perlu dilakukannya deteksi sejak dini atau diagnosa terhadap organ hati. Untuk mengatasi permasalahan tersebut, pada penelitian ini dilakukan segmentasi hati menggunakan metode Convolutional Neural Network (CNN) dengan arsitektur U-Net pada citra hati. Langkah awal pada penelitian ini dilakukan pre-processing data yang menerapkan teknik green channel, histogram equalization (HE), dan contrast limited adaptive histogram equalization (CLAHE). Setelah itu dilakukan proses segmentasi sesuai dengan metode yang diusulkan. Penelitian ini menggunakan dataset hati yang didapatkan dari website Kaggle. Hasil penelitian menggunakan metode CNN arsitektur U-Net pada data mendapatkan nilai akurasi sebesar 97,62%, sensitivitas sebesar 89,84%, spesifisitas sebesar 98,37%, koefisen jaccard sebesar 76,99%, dan dice similarity coefficient (DSC) sebesar 87%. Berdasarkan hasil tersebut, dapat disimpulkan bahwa metode yang diusulkan memiliki hasil yang sangat baik dalam melakukan segmentasi terhadap citra hati.

show abstract

Adversarial convolutional network for esophageal tissue segmentation on OCT images

Cited by 16 publications

References 52 publications

Epidural anesthesia needle guidance by forward-view endoscopic optical coherence tomography and deep learning

Epidural anesthesia needle guidance by forward-view endoscopic optical coherence tomography and deep learning

Few‐shot segmentation for esophageal OCT images based on self‐supervised vision transformer

Arsitektur U-Net pada Segmentasi Citra Hati sebagai Deteksi Dini Kanker Liver

Contact Info

Product

Resources

About