Investigation of Appropriate Scaling of Networks and Images for Convolutional Neural Network-Based Nerve Detection in Ultrasound-Guided Nerve Blocks.

Ultrasound imaging is an essential tool in anesthesiology, particularly for ultrasound-guided peripheral nerve blocks (US-PNBs). However, challenges such as speckle noise, acoustic shadows, and variability in nerve appearance complicate the accurate localization of nerve tissues. To address this issue, this study introduces a deep convolutional neural network (DCNN), specifically Scaled-YOLOv4, and investigates an appropriate network model and input image scaling for nerve detection on ultrasound images. Utilizing two datasets, a public dataset and an original dataset, we evaluated the effects of model scale and input image size on detection performance. Our findings reveal that smaller input images and larger model scales significantly improve detection accuracy. The optimal configuration of model size and input image size not only achieved high detection accuracy but also demonstrated real-time processing capabilities.

Improved segmentation of basal ganglia from MR images using convolutional neural network with crossover-typed skip connection.

PURPOSE: Accurate and automatic segmentation of basal ganglia from magnetic resonance (MR) images is important for diagnosis and treatment of various brain disorders. However, the basal ganglia segmentation is a challenging task because of the class imbalance and the unclear boundaries among basal ganglia anatomical structures. Thus, we aim to present an encoder-decoder convolutional neural network (CNN)-based method for improved segmentation of basal ganglia by focusing on skip connections that determine the segmentation performance of encoder-decoder CNNs. We also aim to reveal the effect of skip connections on the segmentation of basal ganglia with unclear boundaries. METHODS: We used the encoder-decoder CNNs with the following five patterns of skip connections: without skip connection, with full-resolution horizontal skip connection, with horizontal skip connections, with vertical skip connections, and with crossover-typed skip connections (the proposed method). We compared and evaluated the performance of the CNNs in the experiment of basal ganglia segmentation using T1-weighted MR brain images of 79 patients. RESULTS: The experimental results showed that the skip connections at each scale level help CNNs to acquire multi-scale image features, the vertical skip connections contribute on acquiring finer image features for segmentation of smaller anatomical structures with more blurred boundaries, and the crossover-typed skip connections, a combination of horizontal and vertical skip connections, provided better segmentation accuracy. CONCLUSION: This paper investigated the effect of skip connections on the basal ganglia segmentation and revealed the crossover-typed skip connections might be effective for improving the segmentation of basal ganglia with the class imbalance and the unclear boundaries.

Detecting the location of lung cancer on thoracoscopic images using deep convolutional neural networks.

OBJECTIVES: The prevalence of minimally invasive surgeries has increased the need for tumor detection using thoracoscopic images during lung cancer surgery. We conducted this study to analyze the efficacy of a deep convolutional neural network (DCNN) for tumor detection using recorded thoracoscopic images of pulmonary surfaces. MATERIALS AND METHODS: We collected 644 intraoperative thoracoscopic images of changes in pulmonary appearance from 427 patients with lung cancer between 2012 and 2021. The lesion areas on the thoracoscopic images were detected by bounding boxes using an advanced version of YOLO, a well-known DCNN for object detection. The DCNN model was trained and evaluated by a 15-fold cross-validation scheme. Each predicted bounding box was considered successful detection when it overlapped more than 50% of the lesion areas annotated by board-certified surgeons. RESULTS AND CONCLUSIONS: Precision, recall, and F1-measured values of 91.9%, 90.5%, and 91.1%, respectively, were obtained. The presence of lymphatic vessel invasion was associated with successful detection (p = 0.045). The presence of pathological pleural invasion also showed a tendency toward successful detection (p = 0.081). The proposed DCNN-based algorithm yielded an accuracy of more than 90% tumor detection. These algorithms will help surgeons detect lung cancer displayed on a screen automatically.

Detecting ossification of the posterior longitudinal ligament on plain radiographs using a deep convolutional neural network: a pilot study.

BACKGROUND CONTEXT: Its rare prevalence and subtle radiological changes often lead to difficulties in diagnosing cervical ossification of the posterior longitudinal ligament (OPLL) on plain radiographs. However, OPLL progression may lead to trauma-induced spinal cord injury, resulting in severe paralysis. To address the difficulties in diagnosis, a deep learning approach using a convolutional neural network (CNN) was applied. PURPOSE: The aim of our research was to evaluate the performance of a CNN model for diagnosing cervical OPLL. STUDY DESIGN AND SETTING: Diagnostic image study. PATIENT SAMPLE: This study included 50 patients with cervical OPLL, and 50 control patients with plain radiographs. OUTCOME MEASURES: For the CNN model performance evaluation, we calculated the area under the receiver operating characteristic curve (AUC). We also compared the sensitivity, specificity, and accuracy of the diagnosis by the CNN with those of general orthopedic surgeons and spine specialists. METHODS: Computed tomography was used as the gold standard for diagnosis. Radiographs of the cervical spine in neutral, flexion, and extension positions were used for training and validation of the CNN model. We used the deep learning PyTorch framework to construct the CNN architecture. RESULTS: The accuracy of the CNN model was 90% (18/20), with a sensitivity and specificity of 80% and 100%, respectively. In contrast, the mean accuracy of orthopedic surgeons was 70%, with a sensitivity and specificity of 73% (SD: 0.12) and 67% (SD: 0.17), respectively. The mean accuracy of the spine surgeons was 75%, with a sensitivity and specificity of 80% (SD: 0.08) and 70% (SD: 0.08), respectively. The AUC of the CNN model based on the radiographs was 0.924. CONCLUSIONS: The CNN model had successful diagnostic accuracy and sufficient specificity in the diagnosis of OPLL.

Development of a Wearable Haptic Glove Presenting Haptic Sensation by Electrical Stimulation.

Most haptic devices generate haptic sensation using mechanical actuators. However, the workload and limited workspace handicap the operator from operating freely. Electrical stimulation is an alternative approach to generate haptic sensations without using mechanical actuators. The light weight of the electrodes adhering to the body brings no limitations to free motion. Because a real haptic sensation consists of feelings from several areas, mounting the electrodes to several different body areas can make the sensations more realistic. However, simultaneously stimulating multiple electrodes may result in "noise" sensations. Moreover, the operators may feel tingling because of unstable stimulus signals when using the dry electrodes to help develop an easily mounted haptic device using electrical stimulation. In this study, we first determine the appropriate stimulation areas and stimulus signals to generate a real touch sensation on the forearm. Then, we propose a circuit design guideline for generating stable electrical stimulus signals using a voltage divider resistor. Finally, based on the aforementioned results, we develop a wearable haptic glove prototype. This haptic glove allows the user to experience the haptic sensations of touching objects with five different degrees of stiffness.

Performance improvement of weakly supervised fully convolutional networks by skip connections for brain structure segmentation.

PURPOSE: For the planning and navigation of neurosurgery, we have developed a fully convolutional network (FCN)-based method for brain structure segmentation on magnetic resonance (MR) images. The capability of an FCN depends on the quality of the training data (i.e., raw data and annotation data) and network architectures. The improvement of annotation quality is a significant concern because it requires much labor for labeling organ regions. To address this problem, we focus on skip connection architectures and reveal which skip connections are effective for training FCNs using sparsely annotated brain images. METHODS: We tested 2D FCN architectures with four different types of skip connections. The first was a U-Net architecture with horizontal skip connections that transfer feature maps at the same scale from the encoder to the decoder. The second was a U-Net++ architecture with dense convolution layers and dense horizontal skip connections. The third was a full-resolution residual network (FRRN) architecture with vertical skip connections that pass feature maps between each downsampled scale path and the full-resolution scale path. The last one was a hybrid architecture with a combination of horizontal and vertical skip connections. We validated the effect of skip connections on medical image segmentation from sparse annotation based on these four FCN architectures, which were trained under the same conditions. RESULTS: For multiclass segmentation of the cerebrum, cerebellum, brainstem, and blood vessels from sparsely annotated MR images, we performed a comparative evaluation of segmentation performance among the above four FCN approaches: U-Net, U-Net++, FRRN, and hybrid architectures. The experimental results show that the horizontal skip connections in the U-Net architectures were effective for the segmentation of larger sized objects, whereas the vertical skip connections in the FRRN architecture improved the segmentation of smaller sized objects. The hybrid architecture with both horizontal and vertical skip connections achieved the best results of the four FCN architectures. We then performed an ablation study to explore which skip connections in the FRRN architecture contributed to the improved segmentation of blood vessels. In the ablation study, we compared the segmentation performance between architectures with a horizontal path (HP), an HP and vertical up paths (HP+VUPs), an HP and vertical down paths (HP+VDPs), and an HP and vertical up and down paths (FRRN). We found that the vertical up paths were effective in improving the segmentation of smaller sized objects. CONCLUSIONS: This paper investigated which skip connection architectures were effective for multiclass brain segmentation from sparse annotation. Consequently, using vertical skip connections with horizontal skip connections allowed FCNs to improve segmentation performance.

Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks.

Brain structure segmentation on magnetic resonance (MR) images is important for various clinical applications. It has been automatically performed by using fully convolutional networks. However, it suffers from the class imbalance problem. To address this problem, we investigated how loss weighting strategies work for brain structure segmentation tasks with different class imbalance situations on MR images. In this study, we adopted segmentation tasks of the cerebrum, cerebellum, brainstem, and blood vessels from MR cisternography and angiography images as the target segmentation tasks. We used a U-net architecture with cross-entropy and Dice loss functions as a baseline and evaluated the effect of the following loss weighting strategies: inverse frequency weighting, median inverse frequency weighting, focal weighting, distance map-based weighting, and distance penalty term-based weighting. In the experiments, the Dice loss function with focal weighting showed the best performance and had a high average Dice score of 92.8% in the binary-class segmentation tasks, while the cross-entropy loss functions with distance map-based weighting achieved the Dice score of up to 93.1% in the multi-class segmentation tasks. The results suggested that the distance map-based and the focal weightings could boost the performance of cross-entropy and Dice loss functions in class imbalanced segmentation tasks, respectively.

Complex-Valued Wavelet Spectrum Analysis of Respiratory Conditions and Its Feasibility in the Detection of Low-Functional Respiration.

Respiratory monitoring is a significant issue to reduce patient risks and medical staff labor in postoperative care and epidemic infection, particularly after the COVID-19 pandemic. Oximetry is widely used for respiration monitoring in the clinic, but it sometimes fails to capture a low-functional respiratory condition even though a patient has breathing difficulty. Another approach is breathing-sound monitoring, but this is unstable due to the indirect measurement of lung volume. Kobayashi in our team is developing a sensor measuring temporal changes in lung volume with a displacement sensor attached across the sixth and eighth ribs. For processing these respiratory signals, we propose the combination of complex-valued wavelet transform and the correlation among spectrum sequences. We present the processing results and discuss its feasibility to detect a low-functional condition in respiration. The result for detecting low-functional respiration showed good performance with a sensitivity of 0.88 and specificity of 0.88 to 1 in its receiver operating characteristic (ROC) curve.

A Small and High-Speed Driving Mechanism for 3D Shape Measurement in Monocular Endoscopy.

Three-dimensional (3D) shape acquisition has been widely introduced to enrich quantitative analysis with the combination of object shape and texture, for example, surface roughness evaluation in industry and gastrointestinal endoscopy in medicine. Shape from focus is a promising technique to measure substance surfaces in 3D space because no occlusion problem appears in principle, as does with stereo shape measurement, which is another commonly used option. We have been developing endoscopic shape measurement devices and shape reconstruction algorithms. In this paper, we propose a mechanism for driving an image sensor reciprocated for the shape from focus of 3D shape measurement in monocular endoscopy. It uses a stepping motor and a planar-end cam, which transforms the motor rotation to imaging sensor reciprocation, to implement the shape from focus of 3D shape measurement in endoscopy. We test and discuss the device in terms of its driving accuracy and application feasibility for endoscopic 3D shape measurement.

Label cleaning and propagation for improved segmentation performance using fully convolutional networks.

PURPOSE: In recent years, fully convolutional networks (FCNs) have been applied to various medical image segmentation tasks. However, it is difficult to generate a large amount of high-quality annotation data to train FCNs for medical image segmentation. Thus, it is desired to achieve high segmentation performances even from incomplete training data. We aim to evaluate performance of FCNs to clean noises and interpolate labels from noisy and sparsely given label images. METHODS: To evaluate the label cleaning and propagation performance of FCNs, we used 2D and 3D FCNs to perform volumetric brain segmentation from magnetic resonance image volumes, based on network training on incomplete training datasets from noisy and sparse annotation. RESULTS: The experimental results using pseudo-incomplete training data showed that both 2D and 3D FCNs could provide improved segmentation results from the incomplete training data, especially by using three orthogonal annotation images for network training. CONCLUSION: This paper presented a validation for label cleaning and propagation based on FCNs. FCNs might have the potential to achieve improved segmentation performances even from sparse annotation data including possible noises by manual annotation, which can be an important clue to more efficient annotation.

Suction-fixing surgical device for assisting liver manipulation with laparoscopic forceps.

PURPOSE: Noninvasiveness and stability are significant issues in laparoscopic liver resection. Inappropriate grasping force can cause damage or serious bleeding to the liver. In addition, instability of grasping can result unsafe operations or wavered cutting. We propose a surgical device to improve stability of liver manipulation. METHODS: A proposed device adheres to the liver surface with suction fixation, then tunes its stiffness to being hard and shapes like as a bulge on the liver surface to be grasped with laparoscopic forceps. It consists of two soft beams, a chamber sponge, membrane covering the device upper, suburb extrusion wing membrane, a vacuuming tube and to-be-grasped bars. The beams are designed as being non-stretchable and easy to bend. The device is connected to a medical vacuuming pump to vacuum air in the device and then gets hard to transfer forceps operation well. This stiffness tuning mechanism by pneumatic control features the device for achieving good liver shape followability and forceps operation propagation less invasively. The proposed device was tested with rubber phantoms and porcine livers on shape followability, stiffness transition, liver invasiveness and operational usability in the experiments. RESULTS: Performance of the proposed device was assessed in experiments. The device showed good object-shape followability. It held the liver with 2.43-N force for vertical lifting and 4.90-N shear force with - 80 kPa vacuuming pressure. Invasiveness was reduced to acceptable level of liver damage. In usability test, the device grasped the liver stably and transferred surgical forceps operations to the liver surface well. CONCLUSION: The proposed device showed effective performance to improve laparoscopic liver manipulation. It held the liver stably and less invasively and transferred forceps operation force to the liver surface well.

A comparison between 2- and 3-dimensional approaches to solid component measurement as radiological criteria for sublobar resection in lung adenocarcinoma ≤ 2 cm in size.

PURPOSE: We compared three-dimensional (3D) and two-dimensional (2D) measurements of the solid component to determine radiological criteria for sublobar resection of lung adenocarcinoma ≤ 2 cm in size. METHODS: We included 233 surgical cases. The maximum size of the solid component for 3D measurement was calculated by delineating the solid component on successive axial images and reconstructing the 3D surface model. RESULTS: The predictive performance for adenocarcinoma in situ (n = 43) and minimally invasive adenocarcinoma (n = 77) were equivalent to areas under the curve of 0.871 and 0.857 for 2D and 3D measurements (p = 0.229), respectively. A solid component of 5 mm had a prognostic impact on both measurements ( ≤ 5 mm versus > 5 mm; p = 0.003 for 2D and p = 0.002 for 3D, log-rank test). Survival rates at 5 years were 94.7-96.9% following lobectomy and sublobar resection among patients with a solid component ≤ 5 mm in size. Sublobar resection resulted in worse survival rates, with declines at 5 years of 15.8% on 2D and 11.5% on 3D measurements, than lobectomy in patients with a solid component > 5 mm in size. CONCLUSIONS: A solid component ≤ 5 mm in size is an appropriate criterion for sublobar resection for both measurements. In addition, 2D measurement is justified because of its simple implementation.

Prediction of IDH and TERT promoter mutations in low-grade glioma from magnetic resonance images using a convolutional neural network.

Identification of genotypes is crucial for treatment of glioma. Here, we developed a method to predict tumor genotypes using a pretrained convolutional neural network (CNN) from magnetic resonance (MR) images and compared the accuracy to that of a diagnosis based on conventional radiomic features and patient age. Multisite preoperative MR images of 164 patients with grade II/III glioma were grouped by IDH and TERT promoter (pTERT) mutations as follows: (1) IDH wild type, (2) IDH and pTERT co-mutations, (3) IDH mutant and pTERT wild type. We applied a CNN (AlexNet) to four types of MR sequence and obtained the CNN texture features to classify the groups with a linear support vector machine. The classification was also performed using conventional radiomic features and/or patient age. Using all features, we succeeded in classifying patients with an accuracy of 63.1%, which was significantly higher than the accuracy obtained from using either the radiomic features or patient age alone. In particular, prediction of the pTERT mutation was significantly improved by the CNN texture features. In conclusion, the pretrained CNN texture features capture the information of IDH and TERT genotypes in grade II/III gliomas better than the conventional radiomic features.

Lesion location implemented magnetic resonance imaging radiomics for predicting IDH and TERT promoter mutations in grade II/III gliomas.

Molecular biological characterization of tumors has become a pivotal procedure for glioma patient care. The aim of this study is to build conventional MRI-based radiomics model to predict genetic alterations within grade II/III gliomas attempting to implement lesion location information in the model to improve diagnostic accuracy. One-hundred and ninety-nine grade II/III gliomas patients were enrolled. Three molecular subtypes were identified: IDH1/2-mutant, IDH1/2-mutant with TERT promoter mutation, and IDH-wild type. A total of 109 radiomics features from 169 MRI datasets and location information from 199 datasets were extracted. Prediction modeling for genetic alteration was trained via LASSO regression for 111 datasets and validated by the remaining 58 datasets. IDH mutation was detected with an accuracy of 0.82 for the training set and 0.83 for the validation set without lesion location information. Diagnostic accuracy improved to 0.85 for the training set and 0.87 for the validation set when lesion location information was implemented. Diagnostic accuracy for predicting 3 molecular subtypes of grade II/III gliomas was 0.74 for the training set and 0.56 for the validation set with lesion location information implemented. Conventional MRI-based radiomics is one of the most promising strategies that may lead to a non-invasive diagnostic technique for molecular characterization of grade II/III gliomas.

Characteristics and outcomes of elderly patients with diffuse gliomas: a multi-institutional cohort study by Kansai Molecular Diagnosis Network for CNS Tumors.

INTRODUCTION: This study investigates the current state of clinical practice and molecular analysis for elderly patients with diffuse gliomas and aims to elucidate treatment outcomes and prognostic factors of patients with glioblastomas. METHODS: We collected elderly cases (≥ 70 years) diagnosed with primary diffuse gliomas and enrolled in Kansai Molecular Diagnosis Network for CNS Tumors. Clinical and pathological characteristics were analyzed retrospectively. Various factors were evaluated in univariate and multivariate models to examine their effects on overall survival. RESULTS: Included in the study were 140 elderly patients (WHO grade II: 7, III: 19, IV: 114), median age was 75 years. Sixty-seven patients (47.9%) had preoperative Karnofsky Performance Status score of ≥ 80. All patients underwent resection (gross-total: 20.0%, subtotal: 14.3%, partial: 39.3%, biopsy: 26.4%). Ninety-six of the patients (68.6%) received adjuvant treatment consisting of radiotherapy (RT) with temozolomide (TMZ). Seventy-eight of the patients (75.0%) received radiation dose of ≥ 50 Gy. MGMT promoter was methylated in 68 tumors (48.6%), IDH1/2 was wild-type in 129 tumors (92.1%), and TERT promoter was mutated in 78 of 128 tumors (60.9%). Median progression-free and overall survival of grade IV cases was 8.2 and 13.6 months, respectively. Higher age (≥ 80 years) and TERT promoter mutated were associated with shorter survival. Resection and adjuvant RT + TMZ were identified as independent factors for good prognosis. CONCLUSIONS: This community-based study reveals characteristics and outcomes of elderly glioma patients in a real-world setting. Elderly patients have several potential factors for poor prognosis, but resection followed by RT + TMZ could lengthen duration of survival.

Marker-less tracking of brain surface deformations by non-rigid registration integrating surface and vessel/sulci features.

PURPOSE: To compensate for brain shift in image-guided neurosurgery, we propose a new non-rigid registration method that integrates surface and vessel/sulci feature to noninvasively track the brain surface. METHOD: Textured brain surfaces were acquired using phase-shift three-dimensional (3D) shape measurement, which offers 2D image pixels and their corresponding 3D points directly. Measured brain surfaces were noninvasively tracked using the proposed method by minimizing a new energy function, which is a weighted combination of 3D point corresponding estimation and surface deformation constraints. Initially, the measured surfaces were divided into featured and non-featured parts using a Frangi filter. The corresponding feature/non-feature points between intraoperative brain surfaces were estimated using the closest point algorithm. Subsequently, smoothness and rigidity constraints were introduced in the energy function for a smooth surface deformation and local surface detail conservation, respectively. Our 3D shape measurement accuracy was evaluated using 20 spheres for bias and precision errors. In addition, the proposed method was evaluated based on root mean square error (RMSE) and target registration error (TRE) with five porcine brains for which deformations were produced by gravity and pushing with different displacements in both the vertical and horizontal directions. RESULTS: The minimum and maximum bias errors were 0.32 and 0.61 mm, respectively. The minimum and maximum precision errors were 0.025 and 0.30 mm, respectively. Quantitative validation with porcine brains showed that the average RMSE and TRE were 0.1 and 0.9 mm, respectively. CONCLUSION: The proposed method appeared to be advantageous in integrating vessels/sulci feature, robust to changes in deformation magnitude and integrated feature numbers, and feasible in compensating for brain shift deformation in surgeries.

Fluoroscopy-based laser guidance system for linear surgical tool insertion depth control.

PURPOSE: In most orthopedic surgeries, knowing how far to insert surgical tools is crucial. The objective of this study was to provide guidance information on depth without tracking surgical tools. A previously developed laser guidance system for linear surgical tool insertion uses two laser beams that display the insertion point and orientation on the skin surface. However, the system only provides 4 degrees of freedom guidance (an entry point on the planned pathway line and the orientation) but do not inform surgeons on the ideal insertion depth. METHOD: A 5-DOF guidance method was developed to provide guidance information by direct projection onto the surgical area using laser beams without tracking markers. A position and orientation guidance performed by two laser beams and depth guidance performed by a single laser beam are appeared on the surgical area in turn. However, depth point appears on the surgical tool side face with some error because of tool radius. Using the actual depth position, insertion path vector and location of the laser sources, the correct depth point on the tool's surface is calculated by the proposed method. So, this system can indicate and navigate the 5-DOF which is planning path and the correct depth point. RESULTS: An evaluation of the accuracy of depth guidance revealed a depth guidance error of 0.55±0.29 mm and results from phantom target insertions revealed overall system accuracies of 1.44 ± 1.09 mm, 0.91° ± 0.82°. In addition, overall system accuracies of application feasibility experiment under the X-ray condition were 1.94 ± 0.98mm, 1.39° ± 1.30°. CONCLUSION: A new surgical tool depth insertion method was developed using a fluorolaser guidance system. This tool informs surgeons of the surgical tool tip depth assuming that the insertion point and orientation are correct. The new method was tested successfully in vitro.

Fully automatic segmentation of the femur from 3D-CT images using primitive shape recognition and statistical shape models.

PURPOSE: Femur segmentation is well established and widely used in computer-assisted orthopedic surgery. However, most of the robust segmentation methods such as statistical shape models (SSM) require human intervention to provide an initial position for the SSM. In this paper, we propose to overcome this problem and provide a fully automatic femur segmentation method for CT images based on primitive shape recognition and SSM. METHOD: Femur segmentation in CT scans was performed using primitive shape recognition based on a robust algorithm such as the Hough transform and RANdom SAmple Consensus. The proposed method is divided into 3 steps: (1) detection of the femoral head as sphere and the femoral shaft as cylinder in the SSM and the CT images, (2) rigid registration between primitives of SSM and CT image to initialize the SSM into the CT image, and (3) fitting of the SSM to the CT image edge using an affine transformation followed by a nonlinear fitting. RESULTS: The automated method provided good results even with a high number of outliers. The difference of segmentation error between the proposed automatic initialization method and a manual initialization method is less than 1 mm. CONCLUSION: The proposed method detects primitive shape position to initialize the SSM into the target image. Based on primitive shapes, this method overcomes the problem of inter-patient variability. Moreover, the results demonstrate that our method of primitive shape recognition can be used for 3D SSM initialization to achieve fully automatic segmentation of the femur.

Miniature objective lens with variable focus for confocal endomicroscopy.

Spectrally encoded confocal microscopy (SECM) is a reflectance confocal microscopy technology that can rapidly image large areas of luminal organs at microscopic resolution. One of the main challenges for large-area SECM imaging in vivo is maintaining the same imaging depth within the tissue when patient motion and tissue surface irregularity are present. In this paper, we report the development of a miniature vari-focal objective lens that can be used in an SECM endoscopic probe to conduct adaptive focusing and to maintain the same imaging depth during in vivo imaging. The vari-focal objective lens is composed of an aspheric singlet with an NA of 0.5, a miniature water chamber, and a thin elastic membrane. The water volume within the chamber was changed to control curvature of the elastic membrane, which subsequently altered the position of the SECM focus. The vari-focal objective lens has a diameter of 5 mm and thickness of 4 mm. A vari-focal range of 240 µm was achieved while maintaining lateral resolution better than 2.6 µm and axial resolution better than 26 µm. Volumetric SECM images of swine esophageal tissues were obtained over the vari-focal range of 260 µm. SECM images clearly visualized cellular features of the swine esophagus at all focal depths, including basal cell nuclei, papillae, and lamina propria.