Intraoperative detection of parathyroid glands using artificial intelligence: optimizing medical image training with data augmentation methods.

BACKGROUND: Postoperative hypoparathyroidism is a major complication of thyroidectomy, occurring when the parathyroid glands are inadvertently damaged during surgery. Although intraoperative images are rarely used to train artificial intelligence (AI) because of its complex nature, AI may be trained to intraoperatively detect parathyroid glands using various augmentation methods. The purpose of this study was to train an effective AI model to detect parathyroid glands during thyroidectomy. METHODS: Video clips of the parathyroid gland were collected during thyroid lobectomy procedures. Confirmed parathyroid images were used to train three types of datasets according to augmentation status: baseline, geometric transformation, and generative adversarial network-based image inpainting. The primary outcome was the average precision of the performance of AI in detecting parathyroid glands. RESULTS: 152 Fine-needle aspiration-confirmed parathyroid gland images were acquired from 150 patients who underwent unilateral lobectomy. The average precision of the AI model in detecting parathyroid glands based on baseline data was 77%. This performance was enhanced by applying both geometric transformation and image inpainting augmentation methods, with the geometric transformation data augmentation dataset showing a higher average precision (79%) than the image inpainting model (78.6%). When this model was subjected to external validation using a completely different thyroidectomy approach, the image inpainting method was more effective (46%) than both the geometric transformation (37%) and baseline (33%) methods. CONCLUSION: This AI model was found to be an effective and generalizable tool in the intraoperative identification of parathyroid glands during thyroidectomy, especially when aided by appropriate augmentation methods. Additional studies comparing model performance and surgeon identification, however, are needed to assess the true clinical relevance of this AI model.

Predictors of Medical and Dental Clinic Closure by Machine Learning Methods: Cross-Sectional Study Using Empirical Data.

BACKGROUND: Small clinics are important in providing health care in local communities. Accurately predicting their closure would help manage health care resource allocation. There have been few studies on the prediction of clinic closure using machine learning techniques. OBJECTIVE: This study aims to test the feasibility of predicting the closure of medical and dental clinics (MCs and DCs, respectively) and investigate important factors associated with their closure using machine running techniques. METHODS: The units of analysis were MCs and DCs. This study used health insurance administrative data. The participants of this study ran and closed clinics between January 1, 2020, and December 31, 2021. Using all closed clinics, closed and run clinics were selected at a ratio of 1:2 based on the locality of study participants using the propensity matching score of logistic regression. This study used 23 and 19 variables to predict the closure of MCs and DCs, respectively. Key variables were extracted using permutation importance and the sequential feature selection technique. Finally, this study used 5 and 6 variables of MCs and DCs, respectively, for model learning. Furthermore, four machine learning techniques were used: (1) logistic regression, (2) support vector machine, (3) random forest (RF), and (4) Extreme Gradient Boost. This study evaluated the modeling accuracy using the area under curve (AUC) method and presented important factors critically affecting closures. This study used SAS (version 9.4; SAS Institute Inc) and Python (version 3.7.9; Python Software Foundation). RESULTS: The best-fit model for the closure of MCs with cross-validation was the support vector machine (AUC 0.762, 95% CI 0.746-0.777; P<.001) followed by RF (AUC 0.736, 95% CI 0.720-0.752; P<.001). The best-fit model for DCs was Extreme Gradient Boost (AUC 0.700, 95% CI 0.675-0.725; P<.001) followed by RF (AUC 0.687, 95% CI 0.661-0.712; P<.001). The most significant factor associated with the closure of MCs was years of operation, followed by population growth, population, and percentage of medical specialties. In contrast, the main factor affecting the closure of DCs was the number of patients, followed by annual variation in the number of patients, year of operation, and percentage of dental specialists. CONCLUSIONS: This study showed that machine running methods are useful tools for predicting the closure of small medical facilities with a moderate level of accuracy. Essential factors affecting medical facility closure also differed between MCs and DCs. Developing good models would prevent unnecessary medical facility closures at the national level.

Comparative Sensing and Judgment Control System for Temperature Maintenance for Optimal Treatment in Hyperthermic Intraperitoneal Chemotherapy Surgery.

For tumors wherein cancer cells remain in the tissue after colorectal cancer surgery, a hyperthermic anticancer agent is injected into the abdominal cavity to necrotize the remaining cancer cells with heat using a hyperthermic intraperitoneal chemotherapy system. However, during circulation, the processing temperature is out of range and the processing result is deteriorated. This paper proposes a look-up table (LUT) module design method that can stably maintain the processing temperature range during circulation via feedback. If the temperature decreases or increases, the LUT transmits a command signal to the heat exchanger to reduce or increase heat input, thereby maintaining the treatment temperature range. The command signal for increasing and decreasing heat input is Tp and Ta, respectively. The command signal for the treatment temperature range is Ts. If drug temperatures below 41 and above 43 °C are input to the LUT, it sends a Tp or Ta signal to the heat exchanger to increase or decrease the input heat, respectively. If the drug's temperature is 41-43 °C, the LUT generates a Ts signal and proceeds with the treatment. The proposed system can automatically control drug temperature using temperature feedback to ensure rapid, accurate, and safe treatment.

Deep Learning-Based Multi-Class Segmentation of the Paranasal Sinuses of Sinusitis Patients Based on Computed Tomographic Images.

Accurate paranasal sinus segmentation is essential for reducing surgical complications through surgical guidance systems. This study introduces a multiclass Convolutional Neural Network (CNN) segmentation model by comparing four 3D U-Net variations-normal, residual, dense, and residual-dense. Data normalization and training were conducted on a 40-patient test set (20 normal, 20 abnormal) using 5-fold cross-validation. The normal 3D U-Net demonstrated superior performance with an F1 score of 84.29% on the normal test set and 79.32% on the abnormal set, exhibiting higher true positive rates for the sphenoid and maxillary sinus in both sets. Despite effective segmentation in clear sinuses, limitations were observed in mucosal inflammation. Nevertheless, the algorithm's enhanced segmentation of abnormal sinuses suggests potential clinical applications, with ongoing refinements expected for broader utility.

Increasing the Beam Width and Intensity with Refraction Power Effect Using a Combination of Beam Mirrors and Concave Mirrors for Surgical-Fluorescence-Emission-Guided Cancer Monitoring Method.

The primary goal during cancer removal surgery is to completely excise the malignant tumor. Because the color of the tumor and surrounding tissues is very similar, it is difficult to observe with the naked eye, posing a risk of damaging surrounding blood vessels during the tumor removal process. Therefore, fluorescence emission is induced using a fluorescent contrast agent, and color classification is monitored through camera imaging. LEDs must be irradiated to generate the fluorescent emission electromotive force. However, the power and beam width of the LED are insufficient to generate this force effectively, so the beam width and intensity must be increased to irradiate the entire lesion. Additionally, there should be no shaded areas in the beam irradiation range. This paper proposes a method to enhance the beam width and intensity while eliminating shadow areas. A total reflection beam mirror was used to increase beam width and intensity. However, when the beam width increased, a shadow area appeared at the edge, limiting irradiation of the entire lesion. To compensate for this shadow area, a concave lens was combined with the beam mirror, resulting in an increase in beam width and intensity by more than 1.42 times and 18.6 times, respectively. Consequently, the beam width reached 111.8°, and the beam power was 13.6 mW. The proposed method is expected to be useful for observing tumors through the induction of fluorescence emission during cancer removal surgery or for pathological examination in the pathology department.

Deep Learning-Based Nystagmus Detection for BPPV Diagnosis.

In this study, we propose a deep learning-based nystagmus detection algorithm using video oculography (VOG) data to diagnose benign paroxysmal positional vertigo (BPPV). Various deep learning architectures were utilized to develop and evaluate nystagmus detection models. Among the four deep learning architectures used in this study, the CNN1D model proposed as a nystagmus detection model demonstrated the best performance, exhibiting a sensitivity of 94.06 ± 0.78%, specificity of 86.39 ± 1.31%, precision of 91.34 ± 0.84%, accuracy of 91.02 ± 0.66%, and an F1-score of 92.68 ± 0.55%. These results indicate the high accuracy and generalizability of the proposed nystagmus diagnosis algorithm. In conclusion, this study validates the practicality of deep learning in diagnosing BPPV and offers avenues for numerous potential applications of deep learning in the medical diagnostic sector. The findings of this research underscore its importance in enhancing diagnostic accuracy and efficiency in healthcare.

Adjustment of the Length Variation With Wire-driven Using the Stand Looper Tension Technique for Surgical Robot Applications.

MOTIVATION: The wire-driven method used in the field of surgical robots has the advantage of light weight. However, in the process of pull and push for the operation of forceps, the length of the wire is not match, causing malfunction. To solve this problem, the application of looper-tension technology would be suitable. This paper contributes to adjusting the length of the wire by inserting a stand between the wire-driven joints and adding a looper-tension between the stands to adjust the rotation radius of the roll. METHODS: The method consisting of three rolls and loopers for connection between the stands minimizes errors by adjusting the length of the loop in a balanced state due to the rotation change of the roll during the pull and push of the robot arm. The angle and tension applied to the looper are 25° and 8.6 MPa, respectively. RESULTS: An output response can be obtained when the reference operating point fluctuates by ± 50% of the input angle and tension, and if the reference operating point fluctuates by ± 30% while the input angle and tension are fixed, the output response occurs oppositely. When a .15 kg object is loaded up/down with 1.5 newton using forceps, the change in length of pull and push coincides. CONCLUSION: The advantage is that the error of wire pull, and push operation can be reduced, and accurate operation can be expected. Since the proposed technology is applied between joints, the integration process is not complicated, and the weight is light.

A Method to Reduce Tension Differences in Pull/Push Manipulation for a Robot in Fluorescence Emission-Guided Surgical Microscopy.

MOTIVATION: A fluorescence emission-guided microscope used to monitor the outcome of cancer removal surgery is highly effective when employing a manipulator to motorize and switch the observation direction. It is necessary to minimize the alignment of looper tension between the stands for pull/push to change the direction of the manipulator and reduce the error rate caused by tension differences. This paper presents a method to minimize the error rate of looper tension between the stands. METHODS: \The looper is inserted between the stands of the manipulator to minimize the difference in tension and make the stress on the pull and push of the looper constant. The constant stress allows the manipulator to move stably in left/right, up/down, and left/right movements, which will be effective for full-camera observation and close-up shots of the end effector. RESULTS: Reducing the tolerance for differences in the manipulator's looper tension (angle and tension) is crucial. When the input value of the looper tension angle is 50°, the output should closely match 50°. Consequently, the measured response has a tolerance of ±49.98%, resulting in an error rate of .02% (1/50th level). CONCLUSION: A method is proposed to minimize the error rate of the manipulator's looper tension in a robot-based fluorescence emission-guided microscope used to observe the status of cancer surgery. As a result, a stable manipulator with a minimal error rate can achieve a 3.986x magnification for close-up observation by switching between high and low orientations.

Deep learning-based prediction of indication for cracked tooth extraction using panoramic radiography.

BACKGROUND: We aimed to determine the feasibility of utilizing deep learning-based predictions of the indications for cracked tooth extraction using panoramic radiography. METHODS: Panoramic radiographs of 418 teeth (group 1: 209 normal teeth; group 2: 209 cracked teeth) were evaluated for the training and testing of a deep learning model. We evaluated the performance of the cracked diagnosis model for individual teeth using InceptionV3, ResNet50, and EfficientNetB0. The cracked tooth diagnosis model underwent fivefold cross-validation with 418 data instances divided into training, validation, and test sets at a ratio of 3:1:1. RESULTS: To evaluate the feasibility, the sensitivity, specificity, accuracy, and F1 score of the deep learning models were calculated, with values of 90.43-94.26%, 52.63-60.77%, 72.01-75.84%, and 76.36-79.00%, respectively. CONCLUSION: We found that the indications for cracked tooth extraction can be predicted to a certain extent through a deep learning model using panoramic radiography.

The Design of an Automatic Temperature Compensation System through Smart Heat Comparison/Judgment and Control for Stable Thermal Treatment in Hyperthermic Intraperitoneal Chemotherapy (HIPEC) Surgery.

After surgery for ovarian cancer or colorectal cancer, residual tumors are left around. A practical way to treat residual tumors is to destroy them with heat by injecting high-temperature drugs into the abdominal cavity. The injected medicinal substances are induced to flow out of the abdominal cavity; then, the spilled drug flows back into the abdominal cavity through feedback. During this process, the heat starts to decrease; thus, the treatment performance reduces. To overcome this problem, this study compares and assesses the temperature needed to maintain the heat for treatment and transmits a command signal to the heat exchanger through a look-up table (LUT). When the temperature decreases during the circulation of medications leaking out of the abdominal cavity, the LUT transmits a control signal (Tp) to the heat exchanger, which increases or vice versa. However, if the temperature (To) is within the treatment range, the LUT sends a Ts signal to the heat exchanger. This principle generates a pulse signal for the temperature difference (Tdif) in TC by comparing and determining the temperature (To) of the substance flowing out of the abdominal cavity with the reference temperature (Tref) through the temperature comparator (TC). At this time, if the signal is 41 °C or less, the LUT generates (heats) a Tp signal so that the temperature of the heat exchanger can be maintained in the range of 41 °C to 43 °C. If the Tdif is 44 °C or higher, the LUT generates (cools) the Ta signal and maintains the temperature of the heat exchanger at 41-43 °C. If the Tdif is maintained at 41-43 °C, the LUT generates a Tx signal to stop the system performance. At this time, the TC operation performance and Tdif generation process for comparing and determining the signal of To and Tref for drugs leaking out of the abdominal cavity is very important. It was observed that the faster the response signal, the lower the comparison and judgment error was; therefore, the response signal was confirmed to be 0.209 µs. The proposed method can guarantee rapid/accurate/safe treatment and automatically induce temperature adjustment; thus, it could be applied to the field of surgery.

Automatic Spine Segmentation and Parameter Measurement for Radiological Analysis of Whole-Spine Lateral Radiographs Using Deep Learning and Computer Vision.

Radiographic examination is essential for diagnosing spinal disorders, and the measurement of spino-pelvic parameters provides important information for the diagnosis and treatment planning of spinal sagittal deformities. While manual measurement methods are the golden standard for measuring parameters, they can be time consuming, inefficient, and rater dependent. Previous studies that have used automatic measurement methods to alleviate the downsides of manual measurements showed low accuracy or could not be applied to general films. We propose a pipeline for automated measurement of spinal parameters by combining a Mask R-CNN model for spine segmentation with computer vision algorithms. This pipeline can be incorporated into clinical workflows to provide clinical utility in diagnosis and treatment planning. A total of 1807 lateral radiographs were used for the training (n = 1607) and validation (n = 200) of the spine segmentation model. An additional 200 radiographs, which were also used for validation, were examined by three surgeons to evaluate the performance of the pipeline. Parameters automatically measured by the algorithm in the test set were statistically compared to parameters measured manually by the three surgeons. The Mask R-CNN model achieved an average precision at 50% intersection over union (AP50) of 96.2% and a Dice score of 92.6% for the spine segmentation task in the test set. The mean absolute error values of the spino-pelvic parameters measurement results were within the range of 0.4° (pelvic tilt) to 3.0° (lumbar lordosis, pelvic incidence), and the standard error of estimate was within the range of 0.5° (pelvic tilt) to 4.0° (pelvic incidence). The intraclass correlation coefficient values ranged from 0.86 (sacral slope) to 0.99 (pelvic tilt, sagittal vertical axis).

Semi-Permanent Use of Indocyanine Green Latex Phantom for Fluorescence Emission.

INTRODUCTION: Testing the fluorescence emission of the vascular circulation status of the indocyanine green (ICG) fluorescence contrast agent to validate the system performance is crucial. Hence, the development of an ICG phantom is imperative, and this study proposes a method for manufacturing an ICG phantom. METHOD: The ICG with an initial concentration was subjected to 0.2 cc sampling through syringe(x), and an ICG (0.2 cc) is diluted with silicon (Si) latex lubber (10 mL) during the manufactured the phantom. The brightest fluorescence expression state is 30 µM, and if it exceeded 50 µM, fluorescence fading occurred and changed to a dark color. RESULTS: The liquid (ICG) of the concentration range is 0.003 mM to 0.24 mM, and the maximum fluorescence expression range is 0.005 to 0.006 mM when the phantom is irradiated using a 780-nm (800 mW) LED. In addition, the fluorescence emission is reduced to 0.24 mM, and the fluorescence expression concentration is 10 µM, 30 µM, and 50 µM, respectively. The decreasing of the fluorescence emission is beginning to 50 µM. CONCLUSIONS: In this study, the proposed phantom with ICG fluorescence emission using latex lubber is proposed. In this works, the proposed phantom is improved the performance for ICG fluorescence emission. In the manufactured phantom, the phantom is used for gelatin, and the advance of phantom has easy manufacturing and long-life fluorescence emission (semipermanent) due to incorrodible material (latex lubber). To experimental results of a phantom, the ICG fluorescent contrast medium (0.055 mM) is same to 30 µM. Then, the 0.055 mM and 30 µM have high resolution and fluorescence emission status. Thus, the results are in good agreement.

Design of a Miniature Observation Robot for Light Emitting Diode Irradiation and Indocyanine Green Fluorescence-emission Guided Lymph Node Monitoring in Operating Rooms.

MOTIVATION: Typical surgical microscopes used for fluorescence-based lymph node detection experience limitations such as weight and restricted adjustability of the integrated light emitting diode (LED) and camera. This restricts the capture of detailed images of specific regions within the lesion. RESEARCH GOAL: This study proposes a miniature observation robot design that offers adjustable working distance (WD) and rotational radius, along with zoom-in/zoom-out functionality. METHODS: A five-degree-of-freedom manipulator was designed, with the end effector incorporating an LED and concave lens to widen the beam width for comprehensive lesion illumination. Additionally, a long-pass filter was integrated into the camera system to enhance image resolution. EXPERIMENTAL RESULTS: Experiments were conducted using a fluorescence-expressing phantom to evaluate the performance of the robot. Results demonstrated a captured image resolution of 9600 × 3240 pixels and a zoom-in/zoom-out capacity of up to 3.68 times. CONCLUSION: The proposed robot design is cost-effective and highly adjustable, enabling suitability for rapid and accurate detection of fresh lymph nodes during surgeries. The robot's capability to detect small lesions (<1 cm), as validated by phantom tests, holds promise for the detection of minute lymph nodes.

Design of a Compact Hologram System Capable of 3D Lesion Diagnosis in Clinic.

MOTIVATION: This paper proposes a small-sized hologram system for the 3D imaging of lesions in a clinical environment. In a general hologram system, the distance between the beam-generating device and the screen (400 mm) and the size of the screen must be increased proportionally to obtain excellent image quality. However, in a clinical environment, the beam spread distance and screen size must be reduced. This paper proposes a method for reducing the beam divergence distance and screen size for clinical applications. METHODS: To reduce the beam spread distance and screen size, a beam prism with a 45° refractive index is used to reduce the beam spread distance by 1/3. The direction of the bent light must be adjusted such that it can reach the screen accurately. However, because the reflected light may be refracted owing to the material properties of the mirror and cause loss, this problem can be solved by using a full reflection mirror. RESULTS: The beam spread distance of the designed hologram system is 200 mm. The types of lesions obtained from the 3D images of the hologram include the lung, liver, and colon. The image resolution is 300 × 145. CONCLUSION: If the proposed method is used in a clinical environment, doctors can improve their understanding of the patient quickly and efficiently; thereby, shortening the treatment time. The proposed hologram system is expected to be useful in treatment rooms, operating rooms, and educational programs in medical schools.

Design of an Automatic Jackson-Pratt Drain Auxiliary System for Postoperative Management Applications.

Background: After surgery, the exudation at a surgical site can cause complications and infections. The exudation is periodically removed through a Jackson-Pratt (JP) drain while maintaining a negative pressure in the JP bulb. However, the JP drainage tube may be clogged due to blood clotting. Thus, the periodic management of the JP drain is essential. In particular, the postoperative management of the JP drain includes squeezing and stripping it. In this study, we proposed a JP drain auxiliary system that can perform automatic stripping to assist specialists and nurses. Methodology: The proposed system was designed based on pre-experimental measurements and operated as a gripping and rolling device. Experimental Results: Twenty experiments were performed, and an average stripping efficiency of 93.8% was obtained. Conclusions: Consequently, we think that the proposed auxiliary system can automatically contribute to increase working efficiency for specialists and nurses.

Remote Monitoring System for Condition Management of Patients in Free Flap Surgery.

INTRODUCTION: Free flap surgery is inconvenient because an attending physician must observe a patient's condition every day to ensure that normal tissue is restored within 72 h after the surgery. To address this problem, this paper proposes a remote monitoring technology to observe a patient's condition in real time. METHODS: To design a monitoring system, the camera consists of MCU board, DC-DC converter, alarm performance, Wi-fil module, and server, and the camera and MCU part is connected to the server through the wi-fi network. A camera obtains the images of the surgical site once every 2 s, and the images are transmitted to the attending physician or nurse via Wi-Fi communication. The working distance between camera and surgical site is 56 cm, and the viewing angle of a camera is 60° (radius). RESULTS: A video shooting test is also performed, in which the images are obtained once per hour between 17:00 and 08:00 the next day; the results show that high-quality images are obtained in the video shooting test. The imaging error is zero (0 GB) in the video shooting test results. DISCUSSION AND CONCLUSION: The imaging of the surgical site can be obtained by camera system, and the proposed method is that there no storage error occurs during the shooting process. In addition, the shooting performance has high velocity. It is possible to control the WD according to a patient's body via a holding manipulator used for the camera. The new method is expected to be used for remote patient management, for a wide range of procedures, in the medical field.

Deep learning-based prediction of osseointegration for dental implant using plain radiography.

BACKGROUND: In this study, we investigated whether deep learning-based prediction of osseointegration of dental implants using plain radiography is possible. METHODS: Panoramic and periapical radiographs of 580 patients (1,206 dental implants) were used to train and test a deep learning model. Group 1 (338 patients, 591 dental implants) included implants that were radiographed immediately after implant placement, that is, when osseointegration had not yet occurred. Group 2 (242 patients, 615 dental implants) included implants radiographed after confirming successful osseointegration. A dataset was extracted using random sampling and was composed of training, validation, and test sets. For osseointegration prediction, we employed seven different deep learning models. Each deep-learning model was built by performing the experiment 10 times. For each experiment, the dataset was randomly separated in a 60:20:20 ratio. For model evaluation, the specificity, sensitivity, accuracy, and AUROC (Area under the receiver operating characteristic curve) of the models was calculated. RESULTS: The mean specificity, sensitivity, and accuracy of the deep learning models were 0.780-0.857, 0.811-0.833, and 0.799-0.836, respectively. Furthermore, the mean AUROC values ranged from to 0.890-0.922. The best model yields an accuracy of 0.896, and the worst model yields an accuracy of 0.702. CONCLUSION: This study found that osseointegration of dental implants can be predicted to some extent through deep learning using plain radiography. This is expected to complement the evaluation methods of dental implant osseointegration that are currently widely used.

Miniaturized Bandpass Filter Using a Combination of T-Shaped Folded SIR Short Loaded Stubs.

The consumption of multimedia content is ubiquitous in modern society. This is made possible by wireless local area networks (W-LAN) or wire service systems. Bandpass filters (BPF) have become very popular as they solve certain data transmission limitations allowing users to obtain reliable access to their multimedia content. The BPFs with quarter-wavelength short stubs can achieve performance; however, these BPFs are bulky. In this article, we propose a compact BPF with a T-shaped stepped impedance resonator (SIR) transmission line and a folded SIR structure. The proposed BPF uses a T-shaped SIR connected to a J-inverter structure (transmission line); this T-shaped SIR structure is used to replace the λg/4 transmission line seen in conventional stub BPFs. In addition, a folded SIR is added to the short stubs seen in conventional stub BPFs. This approach allows us to significantly reduce the size of the BPF. The advantage of a BPF is its very small size, low insertion loss, and wide bandwidth. The overall size of the new BPF is 2.44 mm × 1.49 mm (0.068λg × 0.059λg). The proposed BPF can be mass produced using semiconductors due to its planar structure. This design has the potential to be widely used in various areas including military, medical, and industrial systems.

Segmentation Performance Comparison Considering Regional Characteristics in Chest X-ray Using Deep Learning.

Chest radiography is one of the most widely used diagnostic methods in hospitals, but it is difficult to read clearly because several human organ tissues and bones overlap. Therefore, various image processing and rib segmentation methods have been proposed to focus on the desired target. However, it is challenging to segment ribs elaborately using deep learning because they cannot reflect the characteristics of each region. Identifying which region has specific characteristics vulnerable to deep learning is an essential indicator of developing segmentation methods in medical imaging. Therefore, it is necessary to compare the deep learning performance differences based on regional characteristics. This study compares the differences in deep learning performance based on the rib region to verify whether deep learning reflects the characteristics of each part and to demonstrate why this regional performance difference has occurred. We utilized 195 normal chest X-ray datasets with data augmentation for learning and 5-fold cross-validation. To compare segmentation performance, the rib image was divided vertically and horizontally based on the spine, clavicle, heart, and lower organs, which are characteristic indicators of the baseline chest X-ray. Resultingly, we found that the deep learning model showed a 6-7% difference in the segmentation performance depending on the regional characteristics of the rib. We verified that the performance differences in each region cannot be ignored. This study will enable a more precise segmentation of the ribs and the development of practical deep learning algorithms.

Clip-Detector Using a Neodymium Magnet to Locate Malignant Tumors during Laparoscopic Surgery.

During laparoscopic surgery for colorectal or gastric cancers, locating the tumor for excision is difficult owing to it being obscured by mucous membranes. Therefore, a clip can be installed around the tumor, which can be located using a sensor. Most of the clip-detectors developed thus far can only detect tumors in either the colon or stomach and require a wire to connect the clip and detector. This study designs a clip and detector that can locate a tumor in the stomach and colon. The clip contains a neodymium magnet that generates a magnetic field, and the detector includes a Colpitts oscillator that allows magnetic coupling of the clip and detector. After installing the prepared clip at the tumor location, the detector is used to locate the clip. To test the clip and detector, we conducted animal experiments, during which four clips were installed in the colon and stomach of a mini pig. We succeeded in locating the clips within 2.17 and 3.14 s in the stomach and colon, respectively, which were shorter than the detection times reported in previous studies. The demand for laparoscopic surgery and endoscopes is predicted to increase owing to this method.