Computer‐aided diagnosis system for the detection of bronchiectasis in chest computed tomography images

A computer‐aided diagnosis (CAD) system has been developed for the detection of bronchiectasis from computed tomography (CT) images of chest. A set of CT images of the chest with known diagnosis were collected and these images were first denoised using Wiener filter. The lung tissue was then segmented using optimal thresholding. The Pathology Bearing Regions (PBRs) were then extracted by applying pixel‐based segmentation. For each PBR, a gray level co‐occurrence matrix (GLCM) was constructed. From the GLCM texture features were extracted and feature vectors were constructed. A probabilistic neural network (PNN) was constructed and trained using this set of feature vectors. The images together with the PBRs and the corresponding feature vector and diagnosis were stored in an image database. Rules for diagnosis and for determining the severity of the disease were generated by analyzing the images known to be affected by bronchiectasis. The rules were then validated by a human expert. The validated rules were stored in the Knowledge Base. When a physician gives a CT image to the CAD system, it first transforms the image into a set of feature vectors, one for each PBR in the image. It then performs the diagnosis using two techniques: PNN and mahalanobis distance measure. The final diagnosis and the severity of the disease are determined by correlating the diagnosis determined by both the techniques in consultation with the knowledge base. The system also retrieves similar cases from the database. Thus, this system would aid the physicians in diagnosing bronchiectasis. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 290–298, 2009     

Multi‐modal brain tumor image segmentation based on SDAE

Accurate tumor segmentation has the ability to provide doctors with a basis for surgical planning. Moreover, brain tumor segmentation needs to extract different tumor tissues (Edema, tumor, tumor enhancement, and necrosis) from normal tissues which is a big challenge because tumor structures vary considerably across patients in terms of size, extension, and localization. In this article, we evaluate a fully automated method for segmenting brain tumor images from multi‐modal magnetic resonance imaging volumes based on stacked de‐noising auto‐encoders (SDAEs). Specially, we adopted multi‐modality information from T1, T1c, T2, and Flair images, respectively. We extracted gray level patches from different modalities as the input of the SDAE. After trained by the SDAE, the raw network parameters will be obtained, which are adopted as a parameter of the feed forward neural network for classification. A simple post‐processing is implemented by threshold segmentation method to generate a mask to get the final segmentation result. By evaluating the proposed method on the BRATS 2015, it can be proven that our method obtains the better performance than other state‐of‐the‐art counterpart methods. And a preliminary dice score of 0.86 for whole tumor segmentation has been achieved.     

FHDT: Fuzzy and Hyco-entropy-based Decision Tree Classifier for Tuberculosis Diagnosis from Sputum Images

Tuberculosis (TB) is one of the infectious diseases spread by the infectious agent Mycobacterium tuberculosis. Sputum smear microscopy is the primary tool used for the diagnosis of pulmonary TB, but has its limitations such as low sensitivity and large observation time. Hence, an automated technique is preferred for the diagnosis of TB. This paper develops a technique for TB diagnosis based on the bacilli count by proposing Fuzzy and Hyco-entropy-based Decision Tree (FHDT) classifier using sputum smear microscopic images. The proposed technique involves three steps: segmentation, feature extraction and classification. Initially, the input sputum smear microscopic image is subjected to a colour space transformation, for which a thresholding is applied to obtain the segmented result. Important features such as length, density, area and few histogram features are extracted for FHDT-based classification that classifies the segments into few-bacilli, non-bacilli and overlapping bacilli. An entropy function, called hyco-entropy, is designed for the optimal selection of feature. For further analysis of classification, that is, to count the number in the overlapping bacilli, the fuzzy classifier is adopted. FHDT classifier is evaluated in terms of Segmentation Accuracy (SA), Mean Squared Error (MSE) and Missing Count (MC) using microscopic images taken from ZNSM-iDB, where it can attain maximum mean SA of 0.954 and mean MC of 2.4.     

MRI brain image classification—a hybrid approach

The present article proposes a novel computer‐aided diagnosis (CAD) technique for the classification of the magnetic resonance brain images. The current method adopt color converted hybrid clustering segmentation algorithm with hybrid feature selection approach based on IGSFFS (Information gain and Sequential Forward Floating Search) and Multi‐Class Support Vector Machine (MC‐SVM) classifier technique to segregate the magnetic resonance brain images into three categories namely normal, benign and malignant. The proposed hybrid evolutionary segmentation algorithm which is the combination of WFF(weighted firefly) and K‐means algorithm called WFF‐K‐means and modified cuckoo search (MCS) and K‐means algorithm called MCS‐K‐means, which can find better cluster partition in brain tumor datasets and also overcome local optima problems in K‐means clustering algorithm. The experimental results show that the performance of the proposed algorithm is better than other algorithms such as PSO‐K‐means, color converted K‐means, FCM and other traditional approaches. The multiple feature set comprises color, texture and shape features derived from the segmented image. These features are then fed into a MC‐SVM classifier with hybrid feature selection algorithm, trained with data labeled by experts, enabling the detection of brain images at high accuracy levels. The performance of the method is evaluated using classification accuracy, sensitivity, specificity, and receiver operating characteristic (ROC) curves. The proposed method provides highest classification accuracy of greater than 98% with high sensitivity and specificity rates of greater than 95% for the proposed diagnostic model and this shows the promise of the approach. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 226–244, 2015     

Multifunctional RbxWO3 Nanorods for Simultaneous Combined Chemo‐photothermal Therapy and Photoacoustic/CT Imaging

Light‐triggered drug delivery based on near‐infrared (NIR)‐mediated photothermal nanocarriers has received tremendous attention for the construction of cooperative therapeutic systems in nanomedicine. Herein, a new paradigm of light‐responsive drug carrier that doubles as a photothermal agent is reported based on the NIR light‐absorber, Rb _x WO₃ (rubidium tungsten bronze, Rb‐TB) nanorods. With doxorubicin (DOX) payload, the DOX‐loaded Rb‐TB composite (Rb‐TB‐DOX) simultaneously provides a burst‐like drug release and intense heating effect upon 808‐nm NIR light exposure. MTT assays show the photothermally enhanced antitumor activity of Rb‐TB‐DOX to the MCF‐7 cancer cells. Most remarkably, Rb‐TB‐DOX combined with NIR irradiation also shows dramatically enhanced chemotherapeutic effect to DOX‐resistant MCF‐7 cells compared with free DOX, demonstrating the enhanced efficacy of combinational chemo‐photothermal therapy for potentially overcoming drug resistance in cancer chemotherapy. Furthermore, in vivo study of combined chemo‐photothermal therapy is also conducted and realized on pancreatic (Pance‐1) tumor‐bearing nude mice. Apart from its promise for cancer therapy, the as‐prepared Rb‐TB can also be employed as a new dual‐modal contrast agent for photoacoustic tomography and (PAT) X‐ray computed tomography (CT) imaging because of its high NIR optical absorption capability and strong X‐ray attenuation ability, respectively. The results presented in the current study suggest promise of the multifunctional Rb _x WO₃ nanorods for applications in cancer theranostics.     

Developing a New qPCR‐Based System for Screening Mutation

An accurate genotyping analysis is one of the critical prerequisites for lung cancer targeted therapy. Here, a quantitative polymerase chain reaction (qPCR)‐based mutation detection system, mutation‐selected amplification‐specific system PCR (MASS‐PCR), is developed. The specific primers and probes used in MASS‐PCR exactly match with the mutant sequence that only allows mutant gene to emit the fluorescence peak. To determine the sensitivity of MASS‐PCR, 717 lung cancer specimens, 61 formalin‐fixed paraffin‐embedded (FFPE) tissues, and 656 fresh reaction tissues are collected and undergo mutation detection of lung cancer driver genes (EGFR, KRAS, BRAF, HER2, MET, ALK, and ROS1). These samples are divided into two groups. Mutations in Group I, which has 631 fresh reaction tissues, are analyzed by MASS‐PCR and the amplification refractory mutation system PCR (ARMS‐PCR). While group II samples, 25 fresh reaction tissues and 61 FFPE tissues, are screened through MASS‐PCR and next‐generation sequencing (NGS). All results are verified by direct sequencing. MASS‐PCR shows high consistency with ARMS‐PCR (kappa value > 0.733) and NGS (kappa value = 0.79) (P < 0.001). For the samples with inconsistent MASS‐PCR and ARMS‐PCR results, DS results more likely support the MASS‐PCR results. These data suggest that MASS‐PCR is a convenient, accurate, and economical method for the detection of lung cancer driver gene mutations in clinical practice.     

Sniffing the Unique “Odor Print” of Non‐Small‐Cell Lung Cancer with Gold Nanoparticles

A highly sensitive and fast‐response array of sensors based on gold nanoparticles, in combination with pattern recognition methods, can distinguish between the odor prints of non‐small‐cell lung cancer and negative controls with 100% accuracy, with no need for preconcentration techniques. Additionally, preliminary results indicate that the same array of sensors might serve as a better tool for understanding the biochemical source of volatile organic compounds that might occur in cancer cells and appear in the exhaled breath, as compared to traditional spectrometry techniques. The reported results provide a launching pad to initiate a bedside tool that might be able to screen for early stages of lung cancer and allow higher cure rates. In addition, such a tool might be used for the immediate diagnosis of fresh (frozen) tissues of lung cancer in operating rooms, where a dichotomic diagnosis is crucial to guide surgeons.     

A Radial Flow Microfluidic Device for Ultra‐High‐Throughput Affinity‐Based Isolation of Circulating Tumor Cells

Circulating tumor cells (CTCs) are believed to play an important role in metastasis, a process responsible for the majority of cancer‐related deaths. But their rarity in the bloodstream makes microfluidic isolation complex and time‐consuming. Additionally the low processing speeds can be a hindrance to obtaining higher yields of CTCs, limiting their potential use as biomarkers for early diagnosis. Here, a high throughput microfluidic technology, the OncoBean Chip, is reported. It employs radial flow that introduces a varying shear profile across the device, enabling efficient cell capture by affinity at high flow rates. The recovery from whole blood is validated with cancer cell lines H1650 and MCF7, achieving a mean efficiency >80% at a throughput of 10 mL h^?1 in contrast to a flow rate of 1 mL h^?1 standardly reported with other microfluidic devices. Cells are recovered with a viability rate of 93% at these high speeds, increasing the ability to use captured CTCs for downstream analysis. Broad clinical application is demonstrated using comparable flow rates from blood specimens obtained from breast, pancreatic, and lung cancer patients. Comparable CTC numbers are recovered in all the samples at the two flow rates, demonstrating the ability of the technology to perform at high throughputs.     

Detection of pneumonia in chest X‐ray images by using 2D discrete wavelet feature extraction with random forest

Pneumonia is one of the most common and fatal diseases in the world. Early diagnosis and treatment are important factors in reducing mortality caused by the aforementioned disease. One of the most important and common techniques to diagnose pneumonia disease is the X‐ray images. By evaluating these images, various machine‐learning methods are used for accuracy in diagnosis. The presented study in this article utilizes machine‐learning techniques to evaluate these X‐ray images. The diagnosis of pediatric pneumonia is classified with a proposed machine learning method by using the chest X‐ray images. The proposed system firstly utilizes a two‐dimensional discrete wavelet transform to extract features from images. The features obtained from the wavelet method are labeled as normal and pneumonia and applied to the classifier for classification. Besides, Random Forest algorithm is used for the classification technique of 5856 X‐ray images. A 10‐fold cross‐validation method is used to evaluate the success of the proposed method and to ensure that the system avoided overfitting. By using various machine learning algorithms, simulation results reveal that the Random Forest method is proposed and it gives successful results. Results also show that, at the end of the training and validation process, the proposed method achieves higher success with an accuracy of 97.11%.     

Morphological feature extraction and KNG-CNN classification of CT images for early lung cancer detection

Lung cancer is a dangerous disease causing death to individuals. Currently precise classification and differential diagnosis of lung cancer is essential with the stability and accuracy of cancer identification is challenging. Classification scheme was developed for lung cancer in CT images by Kernel based Non-Gaussian Convolutional Neural Network (KNG-CNN). KNG-CNN comprises of three convolutional, two fully connected and three pooling layers. Kernel based Non-Gaussian computation is used for the diagnosis of false positive or error encountered in the work. Initially Lung Image Database Consortium image collection (LIDC-IDRI) dataset is used for input images and a ROI based segmentation using efficient CLAHE technique is carried as preprocessing steps, enhancing images for better feature extraction. Morphological features are extracted after the segmentation process. Finally, KNG-CNN method is used for effectual classification of tumour > 30mm. An accuracy of 87.3% was obtained using this technique. This method is effectual for classifying the lung cancer from the CT scanned image.     

Classification of Coronavirus (COVID‐19) from X‐ray and CT images using shrunken features

Necessary screenings must be performed to control the spread of the COVID‐19 in daily life and to make a preliminary diagnosis of suspicious cases. The long duration of pathological laboratory tests and the suspicious test results led the researchers to focus on different fields. Fast and accurate diagnoses are essential for effective interventions for COVID‐19. The information obtained by using X‐ray and Computed Tomography (CT) images is vital in making clinical diagnoses. Therefore it is aimed to develop a machine learning method for the detection of viral epidemics by analyzing X‐ray and CT images. In this study, images belonging to six situations, including coronavirus images, are classified using a two‐stage data enhancement approach. Since the number of images in the dataset is deficient and unbalanced, a shallow image augmentation approach was used in the first phase. It is more convenient to analyze these images with hand‐crafted feature extraction methods because the dataset newly created is still insufficient to train a deep architecture. Therefore, the Synthetic minority over‐sampling technique algorithm is the second data enhancement step of this study. Finally, the feature vector is reduced in size by using a stacked auto‐encoder and principal component analysis methods to remove interconnected features in the feature vector. According to the obtained results, it is seen that the proposed method has leveraging performance, especially to make the diagnosis of COVID‐19 in a short time and effectively. Also, it is thought to be a source of inspiration for future studies for deficient and unbalanced datasets.     

Nanoagents Based on Poly(ethylene glycol)‐b‐Poly(l‐thyroxine) Block Copolypeptide for Enhanced Dual‐Modality Imaging and Targeted Tumor Radiotherapy

Future healthcare requires development of novel theranostic agents that are capable of not only enhancing diagnosis and monitoring therapeutic responses but also augmenting therapeutic outcomes. Here, a versatile and stable nanoagent is reported based on poly(ethylene glycol)‐b‐poly(l ‐thyroxine) (PEG‐PThy) block copolypeptide for enhanced single photon emission computed tomography/computed tomography (SPECT/CT) dual‐modality imaging and targeted tumor radiotherapy in vivo. PEG‐PThy acquired by polymerization of l ‐thyroxine‐N‐carboxyanhydride (Thy‐NCA) displays a controlled M_n, high iodine content of ≈49.2 wt%, and can spontaneously form 65 nm‐sized nanoparticles (PThyN). In contrast to clinically used contrast agents like iohexol and iodixanol, PThyN reveals iso‐osmolality, low viscosity, and long circulation time. While PThyN exhibits comparable in vitro CT attenuation efficacy to iohexol, it greatly enhances in vivo CT imaging of vascular systems and soft tissues. PThyN allows for surface decoration with the cRGD peptide achieving enhanced CT imaging of subcutaneous B16F10 melanoma and orthotopic A549 lung tumor. Taking advantages of a facile iodine exchange reaction, ¹²⁵I‐labeled PThyN enables SPECT/CT imaging of tumors and monitoring of PThyN biodistribution in vivo. Besides, ¹³¹I‐labeled and cRGD‐functionalized PThyN displays remarkable growth inhibition of the B16F10 tumor in mice (tumor inhibition rate > 89%). These poly(l ‐thyroxine) nanoparticles provide a unique and versatile theranostic platform for varying diseases.     

An intelligent mining system for diagnosing medical images using combined texture‐histogram features

The aim of this article is to design an expert system for medical image diagnosis. We propose a method based on association rule mining combined with classification technique to enhance the diagnosis of medical images. This system classifies the images into two categories namely benign and malignant. In the proposed work, association rules are extracted for the selected features using an algorithm called AprioriTidImage, which is an improved version of Apriori algorithm. Then, a new associative classifier CLASS_Hiconst ( CL assifier based on ASS ociation rules with Hi gh Con fidence and S uppor t ) is modeled and used to diagnose the medical images. The performance of our approach is compared with two different classifiers Fuzzy‐SVM and multilayer back propagation neural network (MLPNN) in terms of classifier efficiency with sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. The experimental result shows 96% accuracy, 97% sensitivity, and 96% specificity and proves that association rule based classifier is a powerful tool in assisting the diagnosing process. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 194–203, 2013     

CMOS‐Compatible Silicon Nanowire Field‐Effect Transistors for Ultrasensitive and Label‐Free MicroRNAs Sensing

MicroRNAs (miRNAs) have been regarded as promising biomarkers for the diagnosis and prognosis of early‐stage cancer as their expression levels are associated with different types of human cancers. However, it is a challenge to produce low‐cost miRNA sensors, as well as retain a high sensitivity, both of which are essential factors that must be considered in fabricating nanoscale biosensors and in future biomedical applications. To address such challenges, we develop a complementary metal oxide semiconductor (CMOS)‐compatible SiNW‐FET biosensor fabricated by an anisotropic wet etching technology with self‐limitation which provides a much lower manufacturing cost and an ultrahigh sensitivity. This nanosensor shows a rapid (< 1 minute) detection of miR‐21 and miR‐205, with a low limit of detection (LOD) of 1 zeptomole (ca. 600 copies), as well as an excellent discrimination for single‐nucleotide mismatched sequences of tumor‐associated miRNAs. To investigate its applicability in real settings, we have detected miRNAs in total RNA extracted from lung cancer cells as well as human serum samples using the nanosensors, which demonstrates their potential use in identifying clinical samples for early diagnosis of cancer.     

A novel classifier model for mass classification using BI-RADS category in ultrasound images based on Type-2 fuzzy inference system

Ultrasound imaging is an imaging technique for early detection of breast cancer. Breast Imaging Reporting and Data System (BI-RADS) lexicon, developed by The American College of Radiology, provides a standard for expert doctors to interpret the ultrasound images of breast cancer. This standard describes the features to classify the tumour as benign or malignant and it also categorizes the biopsy requirement as a percentage. Biopsy is an invasive method that doctors use for diagnosis of breast cancer. Computer-aided detection (CAD)/diagnosis systems that are designed to include the feature standards used in benign/malignant classification help the doctors in diagnosis but they do not provide enough information about the BI-RADS category of the mass. These systems classify the benign tumours with 90% biopsy possibility (BI-RADS-4) and with 2% biopsy possibility (BI-RADS-2) in the same category. There are some studies in the literature that make category classification via commonly used classifier methods but their success rates are low. In this study, a two-layer, high-success-rate classifier model based on Type-2 fuzzy inference is developed, which classifies the tumour as benign or malignant with its BI-RADS category by incorporating the opinions of the expert doctors. A 99.34% success rate in benign/malignant classification and a 92% success rate in category classification (BI-RADS 2, 3, 4, 5) were obtained in the accuracy tests. These results indicate that the CAD system is valuable as a means of providing a second diagnostic opinion when radiologists carry out mass diagnosis.     

An integrated feature frame work for automated segmentation of COVID‐19 infection from lung CT images

The novel coronavirus disease (SARS‐CoV‐2 or COVID‐19) is spreading across the world and is affecting public health and the world economy. Artificial Intelligence (AI) can play a key role in enhancing COVID‐19 detection. However, lung infection by COVID‐19 is not quantifiable due to a lack of studies and the difficulty involved in the collection of large datasets. Segmentation is a preferred technique to quantify and contour the COVID‐19 region on the lungs using computed tomography (CT) scan images. To address the dataset problem, we propose a deep neural network (DNN) model trained on a limited dataset where features are selected using a region‐specific approach. Specifically, we apply the Zernike moment (ZM) and gray level co‐occurrence matrix (GLCM) to extract the unique shape and texture features. The feature vectors computed from these techniques enable segmentation that illustrates the severity of the COVID‐19 infection. The proposed algorithm was compared with other existing state‐of‐the‐art deep neural networks using the Radiopedia and COVID‐19 CT Segmentation datasets presented specificity, sensitivity, sensitivity, mean absolute error (MAE), enhance‐alignment measure (EM_φ), and structure measure (S_m) of 0.942, 0.701, 0.082, 0.867, and 0.783, respectively. The metrics demonstrate the performance of the model in quantifying the COVID‐19 infection with limited datasets.     

Classification of Fourier transform infrared microscopic imaging data of human breast cells by cluster analysis and artificial neural networks

Cluster analysis and artificial neural networks (ANNs) are applied to the automated assessment of disease state in Fourier transform infrared microscopic imaging measurements of normal and carcinomatous immortalized human breast cell lines. K-means clustering is used to implement an automated algorithm for the assignment of pixels in the image to cell and non-cell categories. Cell pixels are subsequently classified into carcinoma and normal categories through the use of a feed-forward ANN computed with the Broyden-Fletcher-Goldfarb-Shanno training algorithm. Inputs to the ANN consist of principal component scores computed from Fourier filtered absorbance data. A grid search optimization procedure is used to identify the optimal network architecture and filter frequency response. Data from three images corresponding to normal cells, carcinoma cells, and a mixture of normal and carcinoma cells are used to build and test the classification methodology. A successful classifier is developed through this work, although differences in the spectral backgrounds between the three images are observed to complicate the classification problem. The robustness of the final classifier is improved through the use of a rejection threshold procedure to prevent classification of outlying pixels.     

Breast cancer histopathology image classification using kernelized weighted extreme learning machine

Histopathology is considered as the gold standard for diagnosing breast cancer. Traditional machine learning (ML) algorithm provides a promising performance for cancer diagnosis if the training dataset is balanced. Nevertheless, if the training dataset is imbalanced the performance of the ML model is skewed toward the majority class. It may pose a problem for the pathologist because if the benign sample is misclassified as malignant, then a pathologist could make a misjudgment about the diagnosis. A limited investigation has been done in literature for solving the class imbalance problem in computer‐aided diagnosis (CAD) of breast cancer using histopathology. This work proposes a hybrid ML model to solve the class imbalance problem. The proposed model employs pretrained ResNet50 and the kernelized weighted extreme learning machine for CAD of breast cancer using histopathology. The breast cancer histopathological images are obtained from publicly available BreakHis and BisQue datasets. The proposed method achieved a reasonable performance for the classification of the minority as well as the majority class instances. In comparison, the proposed approach outperforms the state‐of‐the‐art ML models implemented in previous studies using the same training‐testing folds of the publicly accessible BreakHis dataset.     

Robust generation of high‐quality unstructured meshes on realistic biomedical geometry

In this paper, we propose efficient and robust unstructured mesh generation methods based on computed tomography (CT) and magnetic resonance imaging (MRI) data, in order to obtain a patient‐specific geometry for high‐fidelity numerical simulations. Surface extraction from medical images is carried out mainly using open source libraries, including the Insight Segmentation and Registration Toolkit and the Visualization Toolkit, into the form of facet surface representation. To create high‐quality surface meshes, we propose two approaches. One is a direct advancing front method, and the other is a modified decimation method. The former emphasizes the controllability of local mesh density, and the latter enables semi‐automated mesh generation from low‐quality discrete surfaces. An advancing‐front‐based volume meshing method is employed. Our approaches are demonstrated with high‐fidelity tetrahedral meshes around medical geometries extracted from CT/MRI data. Copyright © 2005 John Wiley & Sons, Ltd.     

Fluorescent Imaging‐Guided Chemotherapy‐and‐Photodynamic Dual Therapy with Nanoscale Porphyrin Metal–Organic Framework

Imaging‐guided therapy systems (IGTSs) are revolutionary techniques used in cancer treatment due to their safety and efficiency. IGTSs should have tunable compositions for bioimaging, a suitable size and shape for biotransfer, sufficient channels and/or pores for drug loading, and intrinsic biocompatibility. Here, a biocompatible nanoscale zirconium‐porphyrin metal–organic framework (NPMOF)‐based IGTS that is prepared using a microemulsion strategy and carefully tuned reaction conditions is reported. A high content of porphyrin (59.8%) allows the achievement of efficient fluorescent imaging and photodynamic therapy (PDT). The 1D channel of the Kagome topology of NPMOFs provides a 109% doxorubicin loading and pH‐response smart release for chemotherapy. The fluorescence guiding of the chemotherapy‐and‐PDT dual system is confirmed by the concentration of NPMOFs at cancer sites after irradiation with a laser and doxorubicin release, while low toxicity is observed in normal tissues. NPMOFs are established as a promising platform for the early diagnosis of cancer and initial therapy.