Development of multi-class computer-aided diagnostic systems using the NICE/JNET classifications for colorectal lesions.

BACKGROUND AND AIM: Diagnostic support using artificial intelligence may contribute to the equalization of endoscopic diagnosis of colorectal lesions. We developed computer-aided diagnosis (CADx) support system for diagnosing colorectal lesions using the NBI International Colorectal Endoscopic (NICE) classification and the Japan NBI Expert Team (JNET) classification. METHODS: Using Residual Network as the classifier and NBI images as training images, we developed a CADx based on the NICE classification (CADx-N) and a CADx based on the JNET classification (CADx-J). For validation, 480 non-magnifying and magnifying NBI images were used for the CADx-N and 320 magnifying NBI images were used for the CADx-J. The diagnostic performance of the CADx-N was evaluated using the magnification rate. RESULTS: The accuracy of the CADx-N for Types 1, 2, and 3 was 97.5%, 91.2%, and 93.8%, respectively. The diagnostic performance for each magnification level was good (no statistically significant difference). The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the CADx-J were 100%, 96.3%, 82.8%, 100%, and 96.9% for Type 1; 80.3%, 93.7%, 94.1%, 79.2%, and 86.3% for Type 2A; 80.4%, 84.7%, 46.8%, 96.3%, and 84.1% for Type 2B; and 62.5%, 99.6%, 96.8%, 93.8%, and 94.1% for Type 3, respectively. CONCLUSIONS: The multi-class CADx systems had good diagnostic performance with both the NICE and JNET classifications and may aid in educating non-expert endoscopists and assist in diagnosing colorectal lesions.

A needle-type micro-sampling device for collecting nanoliter sap sample from plants.

In plant research, measuring the physiological parameters of plants is vital for understanding the behavior and response of plants to changes in the external environment. Plant sap analysis provides an approach for elucidating the physiological condition of plants. However, to facilitate accurate sap analysis, a sampling device capable of collecting sap samples from plants is required. In this paper, a minimally invasive, needle-type micro-sampling device capable of collecting nanoliter (~ 91 nL) quantities of sap from plants is described. The developed micro-sampling system showed great reproducibility (3%) in experiments designed to assess sampling performance. As a proof of concept, sap samples were collected continuously from target plants with the micro-sampling system, and the dynamic changes in potassium ions, plant hormones and sugar levels inside plants were analyzed. The results demonstrated the feasibility of the micro-sampling device and its potential for developing a measurement system for plant research in the future.

A computer system to be used with laser-based endoscopy for quantitative diagnosis of early gastric cancer.

GOALS: To evaluate the usefulness of a newly devised computer system for use with laser-based endoscopy in differentiating between early gastric cancer, reddened lesions, and surrounding tissue. BACKGROUND: Narrow-band imaging based on laser light illumination has come into recent use. We devised a support vector machine (SVM)-based analysis system to be used with the newly devised endoscopy system to quantitatively identify gastric cancer on images obtained by magnifying endoscopy with blue-laser imaging (BLI). We evaluated the usefulness of the computer system in combination with the new endoscopy system. STUDY: We evaluated the system as applied to 100 consecutive early gastric cancers in 95 patients examined by BLI magnification at Hiroshima University Hospital. We produced a set of images from the 100 early gastric cancers; 40 flat or slightly depressed, small, reddened lesions; and surrounding tissues, and we attempted to identify gastric cancer, reddened lesions, and surrounding tissue quantitatively. RESULTS: The average SVM output value was 0.846 ± 0.220 for cancerous lesions, 0.381 ± 0.349 for reddened lesions, and 0.219 ± 0.277 for surrounding tissue, with the SVM output value for cancerous lesions being significantly greater than that for reddened lesions or surrounding tissue. The average SVM output value for differentiated-type cancer was 0.840 ± 0.207 and for undifferentiated-type cancer was 0.865 ± 0.259. CONCLUSIONS: Although further development is needed, we conclude that our computer-based analysis system used with BLI will identify gastric cancers quantitatively.

Quantitative identification of mucosal gastric cancer under magnifying endoscopy with flexible spectral imaging color enhancement.

BACKGROUND AND AIM: Magnifying endoscopy with flexible spectral imaging color enhancement (FICE) is clinically useful in diagnosing gastric cancer and determining treatment options; however, there is a learning curve. Accurate FICE-based diagnosis requires training and experience. In addition, objectivity is necessary. Thus, a software program that can identify gastric cancer quantitatively was developed. METHODS: A bag-of-features framework with densely sampled scale-invariant feature transform descriptors to magnifying endoscopy images of 46 mucosal gastric cancers was applied. Computer-based findings were compared with histologic findings. The probability of gastric cancer was calculated by means of logistic regression, and sensitivity and specificity of the system were determined. RESULTS: The average probability was 0.78 ± 0.25 for the images of cancer and 0.31 ± 0.25 for the images of noncancer tissue, with a significant difference between the two groups. An optimal cut-off point of 0.59 was determined on the basis of the receiver operating characteristic curves. The computer-aided diagnosis system yielded a detection accuracy of 85.9% (79/92), sensitivity for a diagnosis of cancer of 84.8% (39/46), and specificity of 87.0% (40/46). CONCLUSION: Further development of this system will allow for quantitative evaluation of mucosal gastric cancers on magnifying gastrointestinal endoscopy images obtained with FICE.

Defocus-aware Dirichlet particle filter for stable endoscopic video frame recognition.

BACKGROUND AND OBJECTIVE: A computer-aided system for colorectal endoscopy could provide endoscopists with important helpful diagnostic support during examinations. A straightforward means of providing an objective diagnosis in real time might be for using classifiers to identify individual parts of every endoscopic video frame, but the results could be highly unstable due to out-of-focus frames. To address this problem, we propose a defocus-aware Dirichlet particle filter (D-DPF) that combines a particle filter with a Dirichlet distribution and defocus information. METHODS: We develop a particle filter with a Dirichlet distribution that represents the state transition and likelihood of each video frame. We also incorporate additional defocus information by using isolated pixel ratios to sample from a Rayleigh distribution. RESULTS: We tested the performance of the proposed method using synthetic and real endoscopic videos with a frame-wise classifier trained on 1671 images of colorectal endoscopy. Two synthetic videos comprising 600 frames were used for comparisons with a Kalman filter and D-DPF without defocus information, and D-DPF was shown to be more robust against the instability of frame-wise classification results. Computation time was approximately 88ms/frame, which is sufficient for real-time applications. We applied our method to 33 endoscopic videos and showed that the proposed method can effectively smoothen highly unstable probability curves under actual defocus of the endoscopic videos. CONCLUSION: The proposed D-DPF is a useful tool for smoothing unstable results of frame-wise classification of endoscopic videos to support real-time diagnosis during endoscopic examinations.

Image segmentation of pyramid style identifier based on Support Vector Machine for colorectal endoscopic images.

With the increase of colorectal cancer patients in recent years, the needs of quantitative evaluation of colorectal cancer are increased, and the computer-aided diagnosis (CAD) system which supports doctor's diagnosis is essential. In this paper, a hardware design of type identification module in CAD system for colorectal endoscopic images with narrow band imaging (NBI) magnification is proposed for real-time processing of full high definition image (1920 × 1080 pixel). A pyramid style image segmentation with SVMs for multi-size scan windows, which can be implemented on an FPGA with small circuit area and achieve high accuracy, is proposed for actual complex colorectal endoscopic images.

Transfer learning for Bag-of-Visual words approach to NBI endoscopic image classification.

We address a problem of endoscopic image classification taken by different (e.g., old and new) endoscopies. Our proposed method formulates the problem as a constraint optimization that estimates a linear transformation between feature vectors (or Bag-of-Visual words histograms) in a framework of transfer learning. Experimental results show that the proposed method works much better than the case without feature transformation.

SVM-MRF segmentation of colorectal NBI endoscopic images.

In this paper we investigate a method for segmentation of colorectal Narrow Band Imaging (NBI) endoscopic images with Support Vector Machine (SVM) and Markov Random Field (MRF). SVM classifiers recognize each square patch of an NBI image and output posterior probabilities that represent how likely the given patch falls into a certain label. To prevent the spatial inconsistency between adjacent patches and encourage segmented regions to have smoother shapes, MRF is introduced by using the posterior outputs of SVMs as a unary term of MRF energy function. Segmentation results of 1191 NBI images are evaluated in experiments in which SVMs were trained with 480 trimmed NBI images and the MRF energy was minimized by an α - ß swap Graph Cut.

Labeling colorectal NBI zoom-videoendoscope image sequences with MRF and SVM.

In this paper, we propose a sequence labeling method by using SVM posterior probabilities with a Markov Random Field (MRF) model for colorectal Narrow Band Imaging (NBI) zoom-videoendoscope. Classifying each frame of a video sequence by SVM classifiers independently leads to an output sequence which is unstable and hard to understand by endoscopists. To make it more stable and readable, we use an MRF model to label the sequence of posterior probabilities. In addition, we introduce class asymmetry for the NBI images in order to keep and enhance frames where there is a possibility that cancers might have been detected. Experimental results with NBI video sequences demonstrate that the proposed MRF model with class asymmetry performs much better than a model without asymmetry.