Other

China Medical University Hospital

Jigatek Corporation

Chia-Hung Kao

Kuo-Chen Wu

Shang-Wen Chen

Wei-Chih Shen

Chih-Wei Wu

Da-Chuan Cheng

Chia-Chuan Liu

Te-Chun Hsieh

A system of deep learning neural network in prostate cancer bone metastasis identification based on whole body bone scan images includes a pre-processing module for receiving input whole body bone scan images, and a neural network module for detecting whether there is a prostate cancer bone metastasis. The neural network module includes: a chest portion network module for establishing first stage faster R-CNN and segmenting training images of chest portion according to the input whole body bone scan images, and using the training images to train second stage faster R-CNN and categorizing the lesions of cancerous bone metastasis; and a pelvis portion network module for establishing first stage faster R-CNN and segmenting training images of pelvis portion according to the input whole body bone scan images, and using the training images to train the convolutional neural network to categorize whether it is a bone metastasis image.

System of deep learning neural network in prostate cancer bone metastasis identification based on whole body bone scan images

A computer-aided recognition system for treatment response of rectal cancer is provided to predict the probability of a pathological complete response (pCR) of a rectal cancer patient after preoperative neoadjuvant chemoradiotherapy. The system includes a random forest model having several decision trees. Each decision tree has at least a feature node. Each feature node generates two branches according to a feature threshold, wherein each branch connects to another feature node or corresponds to an elementary pCR predicting probability. The random forest model integrates the elementary pCR probability of each decision tree, so as to generate a final pCR probability.

Computer-aided recognition system for treatment response of rectal cancer, and computer program product

A prediction system of tumor image-aided prediction of prognosis for patients with uterine cervical cancer is provided. The prediction system includes a data augmentation module and a deep convolution neural network model. The data augmentation module is used to apply a data expansion process of the image data, so as to generate a plurality of slice sets of the uterine cervical cancer tumor. The deep convolution neural network model is used to apply a feature analysis to the slices, so as to predict the prognosis of a patient after chemoradiotherapy.

Prediction system, method and computer program product thereof

The present invention is a method and apparatus for radio frequency identification, comprising a supporter and a data card which can be connected with the supporter, wherein a user can easily carry and use an RFID data card, and, when co-operated with a supporter, the RFID data card can have wider application.

Method and apparatus for radio frequency identification

A portable multi-function device includes a housing and a cover. The housing includes an interior housing and an exterior housing connecting to each other. The interior housing has at least a hub having audio units. Recess parts are located on the upper side of the interior housing for placing the audio units. The exterior housing has a storage box. Terminal ends on side of the storage box connect correspondingly to each of the audio units for placing a data process device in the storage box. The cover is mounted on a side of the housing. A connector is installed at another side of the housing corresponding to the cover to lock and unlock the housing. The cover has holes corresponding to each of the recess parts on the upper side of the interior housing. Whereby, each of the audio units is portable and easy for storage.

Portable multi-function device

The present invention provides a method and an apparatus for playing multi-function device are offered to enable an data processor to amplify the broadcasting power and perform stereophony by the means of a speaker set. This apparatus for playing multi-function device includes an data processor, a monitor, a modulation circuit, an amplification circuit, a speaker set, an audio output plug, a first universal serial bus socket, a second universal serial bus socket, a control panel, and a housing. The connecting method of this invention is to insert an data processor into a rectangle tank, conjoin a universal serial bus connector and a universal serial bus socket, and then, connect an audio output plug to an audio output socket. A back-to-forth of the forgoing connecting method can remove the data processor.

Method and apparatus for playing multi-function device

A universal serial bus (USB) connector connecting structure for a multi-function device comprises a shell, a memory unit installed in said shell, and a universal serial bus, installed at one side of said shell, electrically contacted to said memory unit. Said universal serial bus (USB) is electrically contacted to and embedded on a sliding mechanism which is settled on a built-in fixed bed at one inner side of said shell, whereby said universal serial bus (USB) can be slide out from and stored in said shell by the means of said sliding mechanism.

Growing community of inventors

Taipei, Taiwan

Chia-Hung Kao