Quasi-supervised learning for super-resolution PET.

Low resolution of positron emission tomography (PET) limits its diagnostic performance. Deep learning has been successfully applied to achieve super-resolution PET. However, commonly used supervised learning methods in this context require many pairs of low- and high-resolution (LR and HR) PET images. Although unsupervised learning utilizes unpaired images, the results are not as good as that obtained with supervised deep learning. In this paper, we propose a quasi-supervised learning method, which is a new type of weakly-supervised learning methods, to recover HR PET images from LR counterparts by leveraging similarity between unpaired LR and HR image patches. Specifically, LR image patches are taken from a patient as inputs, while the most similar HR patches from other patients are found as labels. The similarity between the matched HR and LR patches serves as a prior for network construction. Our proposed method can be implemented by designing a new network or modifying an existing network. As an example in this study, we have modified the cycle-consistent generative adversarial network (CycleGAN) for super-resolution PET. Our numerical and experimental results qualitatively and quantitatively show the merits of our method relative to the state-of-the-art methods. The code is publicly available at https://github.com/PigYang-ops/CycleGAN-QSDL.

Multi-modal tumor segmentation methods based on deep learning: a narrative review.

Background and Objective: Automatic tumor segmentation is a critical component in clinical diagnosis and treatment. Although single-modal imaging provides useful information, multi-modal imaging provides a more comprehensive understanding of the tumor. Multi-modal tumor segmentation has been an essential topic in medical image processing. With the remarkable performance of deep learning (DL) methods in medical image analysis, multi-modal tumor segmentation based on DL has attracted significant attention. This study aimed to provide an overview of recent DL-based multi-modal tumor segmentation methods. Methods: In in the PubMed and Google Scholar databases, the keywords "multi-modal", "deep learning", and "tumor segmentation" were used to systematically search English articles in the past 5 years. The date range was from 1 January 2018 to 1 June 2023. A total of 78 English articles were reviewed. Key Content and Findings: We introduce public datasets, evaluation methods, and multi-modal data processing. We also summarize common DL network structures, techniques, and multi-modal image fusion methods used in different tumor segmentation tasks. Finally, we conclude this study by presenting perspectives for future research. Conclusions: In multi-modal tumor segmentation tasks, DL technique is a powerful method. With the fusion methods of different modal data, the DL framework can effectively use the characteristics of different modal data to improve the accuracy of tumor segmentation.

QS-ADN: quasi-supervised artifact disentanglement network for low-dose CT image denoising by local similarity among unpaired data.

Deep learning has been successfully applied to low-dose CT (LDCT) image denoising for reducing potential radiation risk. However, the widely reported supervised LDCT denoising networks require a training set of paired images, which is expensive to obtain and cannot be perfectly simulated. Unsupervised learning utilizes unpaired data and is highly desirable for LDCT denoising. As an example, an artifact disentanglement network (ADN) relies on unpaired images and obviates the need for supervision but the results of artifact reduction are not as good as those through supervised learning. An important observation is that there is often hidden similarity among unpaired data that can be utilized. This paper introduces a new learning mode, called quasi-supervised learning, to empower ADN for LDCT image denoising. For every LDCT image, the best matched image is first found from an unpaired normal-dose CT (NDCT) dataset. Then, the matched pairs and the corresponding matching degree as prior information are used to construct and train our ADN-type network for LDCT denoising. The proposed method is different from (but compatible with) supervised and semi-supervised learning modes and can be easily implemented by modifying existing networks. The experimental results show that the method is competitive with state-of-the-art methods in terms of noise suppression and contextual fidelity. The code and working dataset are publicly available athttps://github.com/ruanyuhui/ADN-QSDL.git.

3D PET/CT tumor segmentation based on nnU-Net with GCN refinement.

Objective. Whole-body positron emission tomography/computed tomography (PET/CT) scans are an important tool for diagnosing various malignancies (e.g. malignant melanoma, lymphoma, or lung cancer), and accurate segmentation of tumors is a key part of subsequent treatment. In recent years, convolutional neural network based segmentation methods have been extensively investigated. However, these methods often give inaccurate segmentation results, such as oversegmentation and undersegmentation. To address these issues, we propose a postprocessing method based on a graph convolutional network (GCN) to refine inaccurate segmentation results and improve the overall segmentation accuracy.Approach. First, nnU-Net is used as an initial segmentation framework, and the uncertainty in the segmentation results is analyzed. Certain and uncertain pixels are used to establish the nodes of a graph. Each node and its 6 neighbors form an edge, and 32 nodes are randomly selected as uncertain nodes to form edges. The highly uncertain nodes are used as the subsequent refinement targets. Second, the nnU-Net results of the certain nodes are used as labels to form a semisupervised graph network problem, and the uncertain part is optimized by training the GCN to improve the segmentation performance. This describes our proposed nnU-Net + GCN segmentation framework.Main results.We perform tumor segmentation experiments with the PET/CT dataset from the MICCIA2022 autoPET challenge. Among these data, 30 cases are randomly selected for testing, and the experimental results show that the false-positive rate is effectively reduced with nnU-Net + GCN refinement. In quantitative analysis, there is an improvement of 2.1% for the average Dice score, 6.4 for the 95% Hausdorff distance (HD95), and 1.7 for the average symmetric surface distance.Significance. The quantitative and qualitative evaluation results show that GCN postprocessing methods can effectively improve the tumor segmentation performance.

Abnormal functional connectivity density involvement in freezing of gait and its application for subtyping Parkinson's disease.

The pathophysiological mechanisms at work in Parkinson's disease (PD) patients with freezing of gait (FOG) remain poorly understood. Functional connectivity density (FCD) could provide an unbiased way to analyse connectivity across the brain. In this study, a total of 23 PD patients with FOG (PD FOG + patients), 26 PD patients without FOG (PD FOG- patients), and 22 healthy controls (HCs) were recruited, and their resting-state functional magnetic resonance imaging (rs-fMRI) images were collected. FCD mapping was first performed to identify differences between groups. Pearson correlation analysis was used to explore relationships between FCD values and the severity of FOG. Then, a machine learning model was employed to classify each pair of groups. PD FOG + patients showed significantly increased short-range FCD in the precuneus, cingulate gyrus, and fusiform gyrus and decreased long-range FCD in the frontal gyrus, temporal gyrus, and cingulate gyrus. Short-range FCD values in the middle temporal gyrus and inferior temporal gyrus were positively correlated with FOG questionnaire (FOGQ) scores, and long-range FCD values in the middle frontal gyrus were negatively correlated with FOGQ scores. Using FCD in abnormal regions as input, a support vector machine (SVM) classifier can achieve classification with good performance. The mean accuracy values were 0.895 (PD FOG + vs. HC), 0.966 (PD FOG- vs. HC), and 0.897 (PD FOG + vs. PD FOG-). This study demonstrates that PD FOG + patients showed altered short- and long-range FCD in several brain regions involved in action planning and control, motion processing, emotion, cognition, and object recognition.

Aberrant degree centrality of functional brain networks in subclinical depression and major depressive disorder.

Background: As one of the most common diseases, major depressive disorder (MDD) has a significant adverse impact on the li of patients. As a mild form of depression, subclinical depression (SD) serves as an indicator of progression to MDD. This study analyzed the degree centrality (DC) for MDD, SD, and healthy control (HC) groups and identified the brain regions with DC alterations. Methods: The experimental data were composed of resting-state functional magnetic resonance imaging (rs-fMRI) from 40 HCs, 40 MDD subjects, and 34 SD subjects. After conducting a one-way analysis of variance, two-sample t-tests were used for further analysis to explore the brain regions with changed DC. Receiver operating characteristic (ROC) curve analysis of single index and composite index features was performed to analyze the distinguishable ability of important brain regions. Results: For the comparison of MDD vs. HC, increased DC was found in the right superior temporal gyrus (STG) and right inferior parietal lobule (IPL) in the MDD group. For SD vs. HC, the SD group showed a higher DC in the right STG and the right middle temporal gyrus (MTG), and a smaller DC in the left IPL. For MDD vs. SD, increased DC in the right middle frontal gyrus (MFG), right IPL, and left IPL, and decreased DC in the right STG and right MTG was found in the MDD group. With an area under the ROC (AUC) of 0.779, the right STG could differentiate MDD patients from HCs and, with an AUC of 0.704, the right MTG could differentiate MDD patients from SD patients. The three composite indexes had good discriminative ability in each pairwise comparison, with AUCs of 0.803, 0.751, and 0.814 for MDD vs. HC, SD vs. HC, and MDD vs. SD, respectively. Conclusion: Altered DC in the STG, MTG, IPL, and MFG were identified in depression groups. The DC values of these altered regions and their combinations presented good discriminative ability between HC, SD, and MDD. These findings could help to find effective biomarkers and reveal the potential mechanisms of depression.

EMDS-7: Environmental microorganism image dataset seventh version for multiple object detection evaluation.

Nowadays, the detection of environmental microorganism indicators is essential for us to assess the degree of pollution, but the traditional detection methods consume a lot of manpower and material resources. Therefore, it is necessary for us to make microbial data sets to be used in artificial intelligence. The Environmental Microorganism Image Dataset Seventh Version (EMDS-7) is a microscopic image data set that is applied in the field of multi-object detection of artificial intelligence. This method reduces the chemicals, manpower and equipment used in the process of detecting microorganisms. EMDS-7 including the original Environmental Microorganism (EM) images and the corresponding object labeling files in ".XML" format file. The EMDS-7 data set consists of 41 types of EMs, which has a total of 2,65 images and 13,216 labeled objects. The EMDS-7 database mainly focuses on the object detection. In order to prove the effectiveness of EMDS-7, we select the most commonly used deep learning methods (Faster-Region Convolutional Neural Network (Faster-RCNN), YOLOv3, YOLOv4, SSD, and RetinaNet) and evaluation indices for testing and evaluation. EMDS-7 is freely published for non-commercial purpose at: https://figshare.com/articles/dataset/EMDS-7_DataSet/16869571.

EBHI-Seg: A novel enteroscope biopsy histopathological hematoxylin and eosin image dataset for image segmentation tasks.

Background and purpose: Colorectal cancer is a common fatal malignancy, the fourth most common cancer in men, and the third most common cancer in women worldwide. Timely detection of cancer in its early stages is essential for treating the disease. Currently, there is a lack of datasets for histopathological image segmentation of colorectal cancer, which often hampers the assessment accuracy when computer technology is used to aid in diagnosis. Methods: This present study provided a new publicly available Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset for Image Segmentation Tasks (EBHI-Seg). To demonstrate the validity and extensiveness of EBHI-Seg, the experimental results for EBHI-Seg are evaluated using classical machine learning methods and deep learning methods. Results: The experimental results showed that deep learning methods had a better image segmentation performance when utilizing EBHI-Seg. The maximum accuracy of the Dice evaluation metric for the classical machine learning method is 0.948, while the Dice evaluation metric for the deep learning method is 0.965. Conclusion: This publicly available dataset contained 4,456 images of six types of tumor differentiation stages and the corresponding ground truth images. The dataset can provide researchers with new segmentation algorithms for medical diagnosis of colorectal cancer, which can be used in the clinical setting to help doctors and patients. EBHI-Seg is publicly available at: https://figshare.com/articles/dataset/EBHI-SEG/21540159/1.

An Entropy Weighted Nonnegative Matrix Factorization Algorithm for Feature Representation.

Nonnegative matrix factorization (NMF) has been widely used to learn low-dimensional representations of data. However, NMF pays the same attention to all attributes of a data point, which inevitably leads to inaccurate representations. For example, in a human-face dataset, if an image contains a hat on a head, the hat should be removed or the importance of its corresponding attributes should be decreased during matrix factorization. This article proposes a new type of NMF called entropy weighted NMF (EWNMF), which uses an optimizable weight for each attribute of each data point to emphasize their importance. This process is achieved by adding an entropy regularizer to the cost function and then using the Lagrange multiplier method to solve the problem. Experimental results with several datasets demonstrate the feasibility and effectiveness of the proposed method. The code developed in this study is available at https://github.com/Poisson-EM/Entropy-weighted-NMF.

Improving the level of autism discrimination with augmented data by GraphRNN.

Datasets are the key to deep learning in autism disease research. However, due to the small quantity and heterogeneity of samples in current public datasets, for example Autism Brain Imaging Data Exchange (ABIDE), the recognition research is not sufficiently effective. Previous studies primarily focused on optimizing feature selection methods and data augmentation to improve recognition accuracy. This research is based on the latter, which learns the edge distribution of a real brain network through the graph recurrent neural network (GraphRNN) and generates synthetic data that have an incentive effect on the discriminant model. Experimental results show that the synthetic data greatly improves the classification ability of the subsequent classifiers, for example, it can improve the classification accuracy of a 50-layer ResNet by up to 30% compared with the case without synthetic data.

Alterations of functional connectivity of the lateral habenula in subclinical depression and major depressive disorder.

BACKGROUND: Major depressive disorder (MDD) is a common cause of disability and morbidity, affecting about 10% of the population worldwide. Subclinical depression (SD) can be understood as a precursor of MDD, and therefore provides an MDD risk indicator. The pathogenesis of MDD and SD in humans is still unclear, and the current diagnosis lacks accurate biomarkers and gold standards. METHODS: A total of 40 MDD, 34 SD, and 40 healthy control (HC) participants matched by age, gender, and education were included in this study. Resting-state functional magnetic resonance images (rs-fMRI) were used to analyze the functional connectivity (FC) of the posterior parietal thalamus (PPtha), which includes the lateral habenula, as the region of interest. Analysis of variance with the post hoc t-test test was performed to find significant differences in FC and clarify the variations in FC among the HC, SD, and MDD groups. RESULTS: Increased FC was observed between PPtha and the left inferior temporal gyrus (ITG) for MDD versus SD, and between PPtha and the right ITG for SD versus HC. Conversely, decreased FC was observed between PPtha and the right middle temporal gyrus (MTG) for MDD versus SD and MDD versus HC. The FC between PPtha and the middle frontal gyrus (MFG) in SD was higher than that in MDD and HC. Compared with the HC group, the FC of PPtha-ITG (left and right) increased in both the SD and MDD groups, PPtha-MTG (right) decreased in both the SD and MDD groups and PPtha-MFG (right) increased in the SD group and decreased in the MDD group. CONCLUSION: Through analysis of FC measured by rs-fMRI, the altered FC between PPtha and several brain regions (right and left ITG, right MTG, and right MFG) has been identified in participants with SD and MDD. Different alterations in FC between PPtha and these regions were identified for patients with depression. These findings might provide insights into the potential pathophysiological mechanisms of SD and MDD, especially related to PPtha and the lateral habenula.

A comprehensive survey on deep learning techniques in CT image quality improvement.

High-quality computed tomography (CT) images are key to clinical diagnosis. However, the current quality of an image is limited by reconstruction algorithms and other factors and still needs to be improved. When using CT, a large quantity of imaging data, including intermediate data and final images, that can reflect important physical processes in a statistical sense are accumulated. However, traditional imaging techniques cannot make full use of them. Recently, deep learning, in which the large quantity of imaging data can be utilized and patterns can be learned by a hierarchical structure, has provided new ideas for CT image quality improvement. Many researchers have proposed a large number of deep learning algorithms to improve CT image quality, especially in the field of image postprocessing. This survey reviews these algorithms and identifies future directions.

Structural Brain Network Abnormalities in Parkinson's Disease With Freezing of Gait.

Objective: Diffusion tensor imaging (DTI) studies have investigated white matter (WM) integrity abnormalities in Parkinson's disease (PD). However, little is known about the topological changes in the brain network. This study aims to reveal these changes by comparing PD without freezing of gait (FOG) (PD FOG-), PD with FOG (PD FOG+), and healthy control (HC). Methods: 21 PD FOG+, 34 PD FOG-, and 23 HC were recruited, and DTI images were acquired. The graph theoretical analysis and network-based statistical method were used to calculate the topological parameters and assess connections. Results: PD FOG+ showed a decreased normalized clustering coefficient, small-worldness, clustering coefficient, and increased local network efficiency compared with HCs. PD FOG+ showed decreased centrality, degree centrality, and nodal efficiency in the striatum, frontal gyrus, and supplementary motor area (SMA). PD FOG+ showed decreased connections in the frontal gyrus, cingulate gyrus, and caudate nucleus (CAU). The between centrality of the left SMA and left CAU was negatively correlated with FOG questionnaire scores. Conclusion: This study demonstrates that PD FOG+ exhibits disruption of global and local topological organization in structural brain networks, and the disrupted topological organization can be potential biomarkers in PD FOG+. These new findings may provide increasing insight into the pathophysiological mechanism of PD FOG+.

Iterator-Net: sinogram-based CT image reconstruction.

Image reconstruction is extremely important for computed tomography (CT) imaging, so it is significant to be continuously improved. The unfolding dynamics method combines a deep learning model with a traditional iterative algorithm. It is interpretable and has a fast reconstruction speed, but the essence of the algorithm is to replace the approximation operator in the optimization objective with a learning operator in the form of a convolutional neural network. In this paper, we firstly design a new iterator network (iNet), which is based on the universal approximation theorem and tries to simulate the functional relationship between the former and the latter in the maximum-likelihood expectation maximization (MLEM) algorithm. To evaluate the effectiveness of the method, we conduct experiments on a CT dataset, and the results show that our iNet method improves the quality of reconstructed images.

Altered Degree Centrality of Brain Networks in Parkinson's Disease With Freezing of Gait: A Resting-State Functional MRI Study.

Freezing of gait (FOG) in Parkinson's disease (PD) leads to devastating consequences; however, little is known about its functional brain network. We explored the differences in degree centrality (DC) of functional networks among PD with FOG (PD FOG+), PD without FOG (PD FOG-), and healthy control (HC) groups. In all, 24 PD FOG+, 37 PD FOG-, and 22 HCs were recruited and their resting-state functional magnetic imaging images were acquired. The whole brain network was analyzed using graph theory analysis. DC was compared among groups using the two-sample t-test. The DC values of disrupted brain regions were correlated with the FOG Questionnaire (FOGQ) scores. Receiver operating characteristic curve analysis was performed. We found significant differences in DC among groups. Compared with HCs, PD FOG+ patients showed decreased DC in the middle frontal gyrus (MFG), superior temporal gyrus (STG), parahippocampal gyrus (PhG), inferior temporal gyrus (ITG), and middle temporal gyrus (MTG). Compared with HC, PD FOG- presented with decreased DC in the MFG, STG, PhG, and ITG. Compared with PD FOG-, PD FOG+ showed decreased DC in the MFG and ITG. A negative correlation existed between the DC of ITG and FOGQ scores; the DC in ITG could distinguish PD FOG+ from PD FOG- and HC. The calculated AUCs were 81.3, 89.5, and 77.7% for PD FOG+ vs. HC, PD FOG- vs. HC, and PD FOG+ vs. PD FOG-, respectively. In conclusion, decreased DC of ITG in PD FOG+ patients compared to PD FOG- patients and HCs may be a unique feature for PD FOG+ and can likely distinguish PD FOG+ from PD FOG- and HC groups.

Integrating Structural and Functional Interhemispheric Brain Connectivity of Gait Freezing in Parkinson's Disease.

Freezing of gait (FOG) has devastating consequences for patients with Parkinson's disease (PD), but the underlying pathophysiological mechanism is unclear. This was investigated in the present study by integrated structural and functional connectivity analyses of PD patients with or without FOG (PD FOG+ and PD FOG-, respectively) and healthy control (HC) subjects. We performed resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging of 24 PD FOG+ patients, 37 PD FOG- patients, and 24 HCs. Tract-based spatial statistics was applied to identify white matter (WM) abnormalities across the whole brain. Fractional anisotropy (FA) and mean diffusivity (MD) of abnormal WM areas were compared among groups, and correlations between these parameters and clinical severity as determined by FOG Questionnaire (FOGQ) score were analyzed. Voxel-mirrored homotopic connectivity (VMHC) was calculated to identify brain regions with abnormal interhemispheric connectivity. Structural and functional measures were integrated by calculating correlations between VMHC and FOGQ score and between FA, MD, and VMHC. The results showed that PD FOG+ and PD FOG- patients had decreased FA in the corpus callosum (CC), cingulum (hippocampus), and superior longitudinal fasciculus and increased MD in the CC, internal capsule, corona radiata, superior longitudinal fasciculus, and thalamus. PD FOG+ patients had more WM abnormalities than PD FOG- patients. FA and MD differed significantly among the splenium, body, and genu of the CC in all three groups (P < 0.05). The decreased FA in the CC was positively correlated with FOGQ score. PD FOG+ patients showed decreased VMHC in the post-central gyrus (PCG), pre-central gyrus, and parietal inferior margin. In PD FOG+ patients, VMHC in the PCG was negatively correlated with FOGQ score but positively correlated with FA in CC. Thus, FOG is associated with impaired interhemispheric brain connectivity measured by FA, MD, and VMHC, which are related to clinical FOG severity. These results demonstrate that integrating structural and functional MRI data can provide new insight into the pathophysiological mechanism of FOG in PD.

LCPR-Net: low-count PET image reconstruction using the domain transform and cycle-consistent generative adversarial networks.

BACKGROUND: Reducing the radiation tracer dose and scanning time during positron emission tomography (PET) imaging can reduce the cost of the tracer, reduce motion artifacts, and increase the efficiency of the scanner. However, the reconstructed images to be noisy. It is very important to reconstruct high-quality images with low-count (LC) data. Therefore, we propose a deep learning method called LCPR-Net, which is used for directly reconstructing full-count (FC) PET images from corresponding LC sinogram data. METHODS: Based on the framework of a generative adversarial network (GAN), we enforce a cyclic consistency constraint on the least-squares loss to establish a nonlinear end-to-end mapping process from LC sinograms to FC images. In this process, we merge a convolutional neural network (CNN) and a residual network for feature extraction and image reconstruction. In addition, the domain transform (DT) operation sends a priori information to the cycle-consistent GAN (CycleGAN) network, avoiding the need for a large amount of computational resources to learn this transformation. RESULTS: The main advantages of this method are as follows. First, the network can use LC sinogram data as input to directly reconstruct an FC PET image. The reconstruction speed is faster than that provided by model-based iterative reconstruction. Second, reconstruction based on the CycleGAN framework improves the quality of the reconstructed image. CONCLUSIONS: Compared with other state-of-the-art methods, the quantitative and qualitative evaluation results show that the proposed method is accurate and effective for FC PET image reconstruction.

Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising.

Due to the widespread use of positron emission tomography (PET) in clinical practice, the potential risk of PET-associated radiation dose to patients needs to be minimized. However, with the reduction in the radiation dose, the resultant images may suffer from noise and artifacts that compromise diagnostic performance. In this paper, we propose a parameter-transferred Wasserstein generative adversarial network (PT-WGAN) for low-dose PET image denoising. The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural details, and ii) a task-specific initialization based on transfer learning is developed to train PT-WGAN using trainable parameters transferred from a pretrained model, which significantly improves the training efficiency of PT-WGAN. The experimental results on clinical data show that the proposed network can suppress image noise more effectively while preserving better image fidelity than recently published state-of-the-art methods. We make our code available at https://github.com/90n9-yu/PT-WGAN.

[Brain functional network reconstruction based on compressed sensing and fast iterative shrinkage-thresholding algorithm].

The construction of brain functional network based on resting-state functional magnetic resonance imaging (fMRI) is an effective method to reveal the mechanism of human brain operation, but the common brain functional network generally contains a lot of noise, which leads to wrong analysis results. In this paper, the least absolute shrinkage and selection operator (LASSO) model in compressed sensing is used to reconstruct the brain functional network. This model uses the sparsity of L1-norm penalty term to avoid over fitting problem. Then, it is solved by the fast iterative shrinkage-thresholding algorithm (FISTA), which updates the variables through a shrinkage threshold operation in each iteration to converge to the global optimal solution. The experimental results show that compared with other methods, this method can improve the accuracy of noise reduction and reconstruction of brain functional network to more than 98%, effectively suppress the noise, and help to better explore the function of human brain in noisy environment.

Predicting Unnecessary Nodule Biopsies from a Small, Unbalanced, and Pathologically Proven Dataset by Transfer Learning.

This study explores an automatic diagnosis method to predict unnecessary nodule biopsy from a small, unbalanced, and pathologically proven database. The automatic diagnosis method is based on a convolutional neural network (CNN) model. Because of the small and unbalanced samples, the presented method aims to improve the transfer learning capability via the VGG16 architecture and optimize the related transfer learning parameters. For comparison purpose, a traditional machine learning method is implemented, which extracts the texture features and classifies the features by support vector machine (SVM). The database includes 68 biopsied nodules, 16 are pathologically proven benign and the remaining 52 are malignant. To consider the volumetric data by the CNN model, each image slice from each nodule volume is selected randomly until all image slices of each nodule are utilized. The leave-one-out and 10-folder cross validations are applied to train and test the randomly selected 68 image slices (one image slice from one nodule) in each experiment, respectively. The averages over all the experimental outcomes are the final results. The experiments revealed that the features from both the medical and the natural images share the similarity of focusing on simpler and less-abstract objects, leading to the conclusion that not the more the transfer convolutional layers, the better the classification results. Transfer learning from other larger datasets can supply additional information to small and unbalanced datasets to improve the classification performance. The presented method has shown the potential to adapt CNN architecture to improve the prediction of unnecessary nodule biopsy from small, unbalanced, and pathologically proven volumetric dataset.